CN113421014A - Target enterprise determination method, device, equipment and storage medium - Google Patents
Target enterprise determination method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113421014A CN113421014A CN202110773080.4A CN202110773080A CN113421014A CN 113421014 A CN113421014 A CN 113421014A CN 202110773080 A CN202110773080 A CN 202110773080A CN 113421014 A CN113421014 A CN 113421014A
- Authority
- CN
- China
- Prior art keywords
- industry
- data
- enterprise
- popularity
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a method, a device, equipment and a storage medium for determining a target enterprise. The method comprises the following steps: determining industry driving associated data and industry popularity data of each initial industry in at least one historical statistical period; determining industry popularity prediction data of a future statistical period according to the industry drive associated data and the industry popularity data; selecting at least one target industry from each initial industry according to the industry popularity estimation data; determining enterprise co-purchasing power values and enterprise co-purchasing capacity values of the candidate enterprises of the target industries; and selecting a target enterprise from the candidate enterprises according to the enterprise co-purchasing power value and the enterprise co-purchasing capacity value. The embodiment of the invention solves the problems that the co-purchasing prediction of the target enterprise is inaccurate and the active mining of the target enterprise cannot be realized.
Description
Technical Field
The embodiment of the invention relates to a big data analysis and mining technology, in particular to a target enterprise determination method, a device, equipment and a storage medium.
Background
The enterprise co-purchasing is an asset behavior aiming at obtaining the enterprise control right, and is helpful for helping difficult enterprises to get rid of the predicament, helping dominant enterprises to expand rapidly and realizing the operation transformation and upgrading of the enterprises. The power generated by enterprise merger mainly results from pursuit of the maximum increase of capital and enterprise competitive pressure. At present, when most domestic enterprises carry out the business of buying together, a client needs to complete a series of processes such as industry analysis, strategic decision, transaction negotiation, scheme design and the like, and finally the client participates as a fund party and provides loan buying together.
In general, in a technical scheme for realizing enterprise co-purchasing, data indexes such as enterprise financial reports are often used as factors influencing enterprise co-purchasing, screening of the data indexes generally depends on more expert experiences, and target mining is performed on enterprises with co-purchasing requirements passively. In the prior art, the enterprise co-purchasing scheme considers less influence factors of macroscopicity and industry, so that the prediction result of the target co-purchasing enterprise is inaccurate, and active mining of the target co-purchasing enterprise cannot be realized.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for determining a target enterprise, which can realize active mining and accurate prediction of the target co-purchasing enterprise.
In a first aspect, an embodiment of the present invention provides a target enterprise determining method, including:
determining industry driving associated data and industry popularity data of each initial industry in at least one historical statistical period;
determining industry popularity prediction data of a future statistical period according to the industry drive associated data and the industry popularity data;
selecting at least one target industry from each initial industry according to the industry popularity estimation data;
determining enterprise co-purchasing power values and enterprise co-purchasing capacity values of the candidate enterprises of the target industries;
and selecting a target enterprise from the candidate enterprises according to the enterprise co-purchasing power value and the enterprise co-purchasing capacity value.
In a second aspect, an embodiment of the present invention further provides a target enterprise determining apparatus, where the apparatus includes:
the data determination module is used for determining industry driving associated data and industry popularity data of each initial industry in at least one historical statistical period;
the estimated data determining module is used for determining the industry popularity estimated data of a future statistical period according to the industry drive associated data and the industry popularity data;
the target industry determining module is used for selecting at least one target industry from each initial industry according to the industry popularity estimation data;
the numerical value determining module is used for determining enterprise co-purchasing power values and enterprise co-purchasing capacity values of the candidate enterprises of the target industries;
and the target enterprise determining module is used for selecting a target enterprise from the candidate enterprises according to the enterprise co-purchasing power value and the enterprise co-purchasing capacity value.
In a third aspect, an embodiment of the present invention further provides a target enterprise determining apparatus, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the target enterprise determining method according to any one of the embodiments of the present invention.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the program, when executed by a processor, implements the target enterprise determining method according to any one of the embodiments of the present invention.
According to the scheme, the macroscopic industry driving related data is introduced from the consideration of macroscopic factors, and the future industry popularity is estimated. And considering from the microscopic factors, determining the target enterprises in a mode of analyzing the enterprises in each target industry and purchasing power and capacity. The industry driving associated data can be used as an index for reflecting the landscape degree of each industry on a macroscopic level, and the enterprise co-purchasing power and capacity can be used as important influence factors for measuring the development trend of the enterprise. The target enterprise is determined by the aid of the multiple layers, the problems that macroscopic influence factors are less considered in industry analysis and the enterprise analysis is incomplete in the past are solved, the target enterprise is judged from the multidimensional influence factors, and therefore the purpose of more accurate prediction of the target enterprise is achieved.
Drawings
Fig. 1 is a flowchart of a target enterprise determination method according to a first embodiment of the present invention;
fig. 2 is a flowchart of a target enterprise determination method according to a second embodiment of the present invention;
fig. 3 is a flowchart of a target enterprise determination method according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a target enterprise determining apparatus according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of a computer device in the fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a target enterprise determining method according to an embodiment of the present invention, where this embodiment is applicable to a situation where enterprise mining with co-purchase demand is performed automatically, and the method may be executed by a target enterprise determining apparatus, and the apparatus may be implemented in a software and/or hardware manner. As shown in fig. 1, the method specifically includes the following steps:
and S110, determining industry driving related data and industry popularity data of each initial industry in at least one historical statistical period.
The historical statistical period is a period for counting data in a historical period, and may be set by a technician according to actual needs, for example, the historical statistical period may be a monthly or quarterly period. The industry driving associated data is data which directly or indirectly affects the industry popularity and can be updated according to the time frequency corresponding to the historical statistical period. The industry popularity is a comprehensive index reflecting the industry change trend, and can reflect the economic state trend of a certain industry. High business prospect indicates the integration and expansion of the upstream and downstream industries, and low business prospect indicates the need of integrating resources to form a scale effect and save cost.
Specifically, the industry driving data and the industry scene degree data of each initial industry are data updated in at least one historical statistical period, and specifically, the industry driving data and the industry scene degree data can be obtained through official statistical data or domestic business open data of a financial institution information base. If the industry popularity data can not be directly obtained through market public data, the industry popularity data can be obtained through the mode of calculating the existing data, and specifically, the industry popularity data can be obtained through calculating the synchronous index data reflecting the industry popularity through the existing data.
In an optional embodiment, the determining industry popularity data for each initial industry over at least one historical statistical period comprises: determining industry profit data of each initial industry under each historical statistical period; and respectively determining the industry scene degree data of each initial industry in the historical statistical period according to the industry profit data of each initial industry.
Specifically, when industry popularity data of a month cannot be directly obtained through market public data, industry profit data of an initial industry under a historical statistical period can be obtained according to the historical statistical period, wherein the industry profit data at least comprises industry profit data and industry profit data. And calculating the industry popularity data according to the acquired industry profits and industry revenue data in the historical statistical period, and determining the industry popularity data of each initial industry in the historical statistical period.
For example, the industry goodness data may be calculated using the following formula as follows:
wherein JSIiIndustry landscape data, LR, representing industry iiIndicating industry profit data, YS, of industry iiIndustry revenue data representing industry i. The synchronous index can support different industries to compare in the transverse direction and is matched with the actual performance of each industry after being verified. Meanwhile, the synchronous index can also calculate to obtain data representing the industry popularity by obtaining the existing industry profit and industry revenue data, and the problem that the existing market public data may be missing or the industry popularity data cannot be obtained in the historical statistics period is solved.
In an optional embodiment, the determining industry driven associated data of each initial industry for at least one historical statistical period comprises: and acquiring initial industry driving associated data with the updating frequency greater than the length of the statistical period under each historical statistical period. Filling missing data in the initial industry driving associated data to update the initial industry driving associated data. And generating the industry driving associated data under the historical statistical period according to the updated initial industry driving associated data.
In an optional embodiment, the initial industry driving related data may include at least one of macro environment data, upstream and downstream industry driving data, industry self data, and the like.
Illustratively, the macro-environment data may include at least one of national economic data, currency policy data, currency inflation associated data, and financial policy data. Optionally, the macro environment data may include at least one of Gross Domestic Product (GDP), industry added value (e.g., industry added value), and Purchasing Manager Index (PMI); the currency policy data may include at least one of narrow currency (Money1, M1), generalized currency (M2, Money2), and financial institution loan balance parity data; the inflation correlation data may include at least one of Consumer Price Index (CPI), Producer Price Index (PPI), and retail Price Index of goods; the financial policy data may include at least one of financial income, national tax income, and interest rate exchange rate data.
Exemplary, the upstream and downstream business driver data may include: at least one of data of product yield, product price and the like of the upstream industry; at least one of downstream industry product yield, product inventory, and the like; and at least one of import amount, import quantity, export amount, export quantity and the like of the upstream and downstream industries.
Illustratively, the industry-by-industry data may include: at least one of data of electricity consumption in industry, sales volume and output of industrial products and the like; at least one of staff compensation level in industry, working number change, industry patent work quantity and other data.
Specifically, the drive associated data of each initial industry in the historical statistical period is obtained, the data with the update frequency of the drive associated data of each initial industry larger than the length of the statistical period is reserved, the missing value analysis is performed on the data with the missing value in the reserved drive associated data of the initial industries, and the data with the missing rate larger than the preset percentage is removed, wherein the preset percentage can be set according to human experience, and for example, can be 10%. And retaining the industry driving associated data with the deletion rate less than the preset percentage, filling the missing data through an interpolation algorithm, and updating each initial industry driving associated data. Specifically, the filling may be performed by a Linear Interpolation (Linear Interpolation), which is not limited in this embodiment. The non-accumulative values are directly filled by using an interpolation algorithm, and the accumulative values are filled by using the interpolation algorithm and taking years as units. And generating the industry driving associated data in the historical statistical period according to the updated initial industry driving associated data and the historical statistical period.
By means of obtaining the initial industry drive associated data with the updating frequency larger than the statistical period length in the historical statistical period, the initial industry drive associated data can be obtained in each historical statistical period, and the obtained data is guaranteed to have complete periodicity. The industry drive associated data is updated in a mode of filling missing data in the initial industry drive associated data, and the integrity of the data acquired in the statistical period is ensured.
And S120, determining industry popularity estimation data of a future statistical period according to the industry driving correlation data and the industry popularity data.
The industry driving associated data can be used as an index for reflecting the business popularity degree of each industry on a macroscopic level, and the industry popularity degree estimation data of a future statistical period can reflect the future development trend of the industry. Through the corresponding relation between the industry driving associated data and the industry popularity data in the historical statistical period, the industry popularity prediction data of the future statistical period can be predicted.
S130, selecting at least one target industry from each initial industry according to the industry popularity estimation data.
Specifically, according to the prediction of the future statistical period industry popularity estimation data in S120, the estimated industry popularity of each initial industry is compared, and at least one target industry with a better development trend is screened out. The screening of the industry can be manually screened according to experience based on the forecast data of the popularity of each industry, or can be automatically screened by designing a network model according to a screening standard, which is not limited in this embodiment.
And S140, determining the enterprise co-purchasing power value and the enterprise co-purchasing capacity value of the candidate enterprises of each target industry.
Wherein the candidate enterprises are enterprises with co-purchase demands. The enterprise co-purchasing power value is obtained through a co-purchasing power scoring model, and the co-purchasing power scoring model is constructed by enterprise co-purchasing power portrait of candidate enterprises. The enterprise co-purchasing ability value is obtained through a co-purchasing ability scoring model, and the co-purchasing ability scoring model is constructed by enterprise co-purchasing ability portrait of the candidate enterprise.
Specifically, the candidate enterprise is screened and obtained from the target industry, and specifically, the data mining is performed on the obtained public data of each enterprise in each target industry by means of obtaining annual newspaper data, market data and the like published by each enterprise in each target industry and by using a text data mining technology, such as natural language processing, so as to screen and obtain the candidate enterprise from each target industry. The enterprise power portrait and the enterprise capacity portrait of the candidate enterprise are obtained, an enterprise co-purchasing power and enterprise co-purchasing capacity model is built according to the enterprise co-purchasing power portrait and the enterprise co-purchasing capacity portrait, and the enterprise co-purchasing power value and the enterprise co-purchasing capacity value are obtained through the enterprise co-purchasing power model and the enterprise co-purchasing capacity model.
S150, selecting target enterprises from the candidate enterprises according to the enterprise parallel purchasing power value and the enterprise parallel purchasing capacity value.
The target enterprise can be determined by screening candidate target enterprises from the candidate enterprises through the enterprise joint buying power value and screening the target enterprises from the candidate target enterprises through the enterprise joint buying capacity value. Candidate target enterprises can be screened out from the candidate enterprises through the enterprise co-purchasing ability value, and then the target enterprises are screened out from the candidate target enterprises through the enterprise co-purchasing ability value.
Specifically, the enterprise co-purchasing power value and the enterprise co-purchasing ability value are sorted from high to low, candidate enterprises in each industry are selectively screened, specifically, selective screening is performed according to industry related data such as characteristics and industry development trends of each industry and the ranking condition of the enterprise co-purchasing power value and the enterprise co-purchasing ability value, and finally a target enterprise is determined.
According to the scheme, the driving relevant data of the macro industry is introduced from the consideration of macro-level factors, the future industry popularity is estimated, and the target enterprises are determined by analyzing the enterprises in all the target industries and purchasing power and capacity from the consideration of micro-level factors. The industry driving associated data can be used as an index for reflecting the landscape degree of each industry on a macroscopic level, and the enterprise co-purchasing power and capacity can be used as important influence factors for measuring the development trend of the enterprise. The target enterprise is determined by the aid of the multiple layers, the problems that macroscopic influence factors are less considered in industry analysis and the enterprise analysis is incomplete in the past are solved, the target enterprise is judged from the multidimensional influence factors, and therefore the purpose of more accurate prediction of the target enterprise is achieved.
Example two
Fig. 2 is a flowchart of a target enterprise determining method according to a second embodiment of the present invention, which is detailed based on the second embodiment, and as shown in fig. 2, the method includes the following specific steps:
s210, determining industry driving related data and industry popularity data of each initial industry in at least one historical statistical period.
And S220, determining industry popularity estimation data of a future statistical period according to the industry driving correlation data and the industry popularity data.
And S230, selecting at least one target industry from each initial industry according to the industry popularity estimation data.
S240, determining the enterprise co-purchasing power value of the candidate enterprise according to at least one of stockholder background data, business investment data, enterprise competition data and business expansion data of the candidate enterprise.
The shareholder background data can comprise at least one of basic information of the enterprise shareholder, market profitability, initial investment participation, other investment duties of the shareholder and the like; the business investment data can comprise at least one of the data of the external investment situation, the external guarantee situation and the invested situation of the enterprise; the enterprise competition data can comprise at least one of market occupation of the enterprise, status of the enterprise on an industrial chain and the like; the business expansion data may include at least one of staff change, wage issue change, electricity usage, and loan deposit change data of the enterprise.
Specifically, enterprises which are historically purchased and purchased in the industry and relevant data of the enterprises are obtained and used as sample data to construct an enterprise purchasing power model, the sample data is divided into a training set and a test set, the model is trained through the training set, and the model is verified through the test set. And acquiring shareholder background data, business investment data, enterprise competition data and business expansion data of the candidate enterprises. And inputting at least one of the data as a characteristic parameter of the model into the model, and determining the enterprise co-purchasing power value of each candidate enterprise.
In a specific example, the enterprise co-purchasing power model may be a scoring card model, the scoring card model is constructed and scored according to stockholder background data, business investment data, enterprise competition data and business expansion data of the candidate enterprises, and scoring results of the candidate enterprises are used as co-purchasing power values of the candidate enterprises.
And S250, determining the enterprise merging and purchasing ability value of the candidate enterprise according to at least one of enterprise financial data, enterprise capital structure, enterprise operation data and enterprise public opinion data of the candidate enterprise.
The enterprise financial data may include at least one of the data of the enterprise such as liability size, short-term bond proportion, commercial cash flow, gross profit rate, and net asset profit Rate (ROE); the enterprise capital structure may include at least one of enterprise stock price data, share right pledge, etc.; the enterprise business data may include production and marketing data for an enterprise; the enterprise public opinion data may include at least one of enterprise high management changes, significant asset reorganization, enterprise court judicial litigation, and the like.
The enterprise public opinion data is unstructured data of text categories, and can be processed by adopting a natural language processing technology, so that the influence coefficient of the enterprise public opinion data is identified. The method specifically includes the steps of segmenting the text data of the obtained enterprise public opinion data, analyzing the text data through a natural language processing technology, identifying the influence degree of the public opinion, judging whether the public opinion belongs to positive influence or negative influence, classifying the public opinion data according to the positive influence or the negative influence, and obtaining the influence coefficient of the public opinion.
Specifically, enterprises which are historically purchased and purchased in the industry and relevant data of the enterprises are obtained and used as sample data to construct an enterprise purchasing ability model, the sample data is divided into a training set and a test set, the model is trained through the training set, and the model is verified through the test set. And acquiring enterprise financial data, enterprise capital structure, enterprise operation data and enterprise public opinion data of the candidate enterprise. And inputting at least one of the data as a characteristic parameter of the model into the model, and determining the enterprise and purchasing ability value of each candidate enterprise. In a specific example, the enterprise co-purchasing ability network model may be constructed through an Extreme Gradient Boosting (XGBoost) algorithm, enterprise financial data, enterprise capital structure, enterprise business data, and enterprise public opinion data influence factors of candidate enterprises are used as model parameters for input, probability statistics is performed on the candidate enterprises through the model, and a probability result of the candidate enterprises is used as the co-purchasing ability value of each candidate enterprise.
And S260, selecting a target enterprise from the candidate enterprises according to the enterprise parallel purchasing power value and the enterprise parallel purchasing capacity value.
In an optional embodiment, after the target enterprise is selected from the candidate enterprises according to the enterprise joint buying power value and the enterprise joint buying capacity value, the joint buying conditions of the target enterprise are classified and integrated, and a joint buying report is generated. Wherein the merger report may include: the current macroscopic economic trend, the situation of the popularity of each industry, the self-operation situation of the target enterprise, the direction of the enterprise co-purchasing and the like. Wherein, enterprise's self operation condition can also include: financial and newspaper data of enterprises, patent and writing data of enterprises and other related data.
According to the scheme, the enterprise analysis method and the enterprise analysis system have the advantages that the enterprise relevant data are introduced, the enterprise is analyzed from the angle of enterprise co-purchasing power and enterprise co-purchasing capacity, the target enterprise is screened according to the enterprise co-purchasing power value and the capacity value, the problem that the analysis of the enterprise level is not accurate enough is solved, and the effect of improving the enterprise analysis accuracy is achieved.
EXAMPLE III
Fig. 3 is a flowchart of a target enterprise determining method according to a third embodiment of the present invention, which is detailed based on the third embodiment, and as shown in fig. 3, the method includes the following specific steps:
s310, determining industry driving related data and industry popularity data of each initial industry in at least one historical statistical period.
And S320, determining the lead period number between the industry driving relevant data and the industry popularity data in different historical statistic periods.
And the lead period number is a lag period number corresponding to the time when the correlation between the industry scene degree data and the industry driving correlation data is highest in the historical statistical period. Wherein the number of lag periods may be in a period of one month. The lead period number can be used as an important index for predicting the prospect degree estimation index of the future industry. Specifically, the lead period number corresponding to each industry popularity data and the industry driving related data can be obtained through market public data or judged through human experience, or can be determined by calculating the lag correlation between the industry popularity data and the industry driving related data in a historical statistical period.
In an optional embodiment, the determining the number of lead periods between the industry driven associated data and the industry popularity data for different historical statistics periods comprises: constructing initial corresponding relations between the industry driving associated data and the industry scene degree data in different historical statistical periods according to at least one lag period number; and selecting a lead period number from the at least one lag period number according to the correlation between the industry driving correlation data with the initial corresponding relation and the industry scene degree data.
Specifically, taking the unit of month as the lag period number and the historical statistical period as an example, the drive associated data of each industry is lagged by 1 to 12 periods, and the lag result of the drive associated data of each industry lagging by 1 period in the historical statistical period and the perspective data of the industry is taken as the initial corresponding relation. And selecting a leading period number from at least one lagging period number according to the correlation between the industry driving correlation data with the initial corresponding relation and the industry scene degree data. Specifically, the industry driving related data and the industry popularity data of each lag period 1 may be subjected to hypothesis testing, such as P testing or T testing or other testing methods. Taking the P-test method as an example, when each lag period 1 is calculated, the correlation between the industry drive related data and the industry popularity data is calculated, and candidate industry drive related data and candidate industry popularity data, of which the P value is smaller than the set threshold and the correlation is greater than the set threshold, are screened out, wherein the set threshold can be set or adjusted by a technician according to needs or experience values, for example, the set threshold for the P value can be 0.01, and the set threshold for the correlation can be 0.5. And selecting the period number corresponding to the candidate industry driving related data from the at least one lag period number as a lead period number, and determining the industry driving related data with the highest correlation and the lead period number corresponding to the industry driving related data.
In the scheme of the optional embodiment, correlation judgment is performed between the industry driving correlation data and the industry popularity data in the historical statistical period, and the lag period number corresponding to the data with the highest correlation is screened, so that the industry driving correlation data with the highest correlation and the lead period number corresponding to the industry driving correlation data are determined. The scheme of the alternative embodiment determines the number of lead periods in a calculation mode, and is more accurate and persuasive than the determination mode relying on human experience.
S330, determining the mapping relation between the industry driving associated data and the industry scene degree data with different historical statistical periods according to the lead period number.
Specifically, according to the number of lead periods, the mapping relation between industry driving associated data with different historical statistical periods and the industry popularity data is determined. For example, when the lead period number corresponding to the industry driving related data with the highest correlation is 5 periods in a certain period in the historical statistical period, the industry popularity data lagging by 5 periods is determined and a mapping relation with the industry driving related data is established.
S340, establishing an industry popularity estimation model according to the industry driving associated data and the industry popularity data with the mapping relation.
Specifically, the industry driving associated data and the industry popularity data with the mapping relation are fitted according to a fitting algorithm, and an industry popularity estimation model is constructed. The fitting algorithm may be a least square fitting algorithm, which is not limited in this embodiment.
In an optional embodiment, the constructing an industry popularity prediction model according to each industry driving associated data with the mapping relationship and the industry popularity data includes: screening the industry driving associated data according to the co-linearity condition of different dimension data in the industry driving associated data; and constructing an industry popularity estimation model according to the screened industry driving associated data with the mapping relation and the industry popularity data.
Specifically, the industry driving associated data is screened according to the co-linearity condition of different dimensionality data in the industry driving associated data. The collinearity can be measured by a coefficient of Variance (VIF). Industry driven associated data is retained with a VIF value less than a set threshold, where the set threshold may be set or adjusted by a technician as needed or empirically, such as 10. And selectively removing the industry driving related data with the VIF larger than the set threshold value, specifically, selectively removing the industry driving related data according to human experience by combining the deviation degree of the index service of the industry driving related data and the corresponding VIF. And constructing an industry popularity estimation model according to the screened industry driving associated data and the industry popularity data with the mapping relation. The linear relation between industry driving related data is determined according to the value of the variance expansion coefficient, so that the condition that the analysis result of the model is inaccurate due to the fact that multiple collinearity behaviors exist in the industry driving related data is prevented.
In an optional embodiment, the constructing an industry popularity prediction model according to each industry driving associated data with the mapping relationship and the industry popularity data includes: carrying out numerical transformation on the industry popularity data and/or the industry driving correlation data; and constructing an industry popularity estimation model according to the industry driving associated data with the mapping relation and the numerical transformation result of the industry popularity data.
Specifically, the industry popularity data is subjected to numerical transformation. The numerical transformation may be, for example, Box-Cox (Box-Cox transformation) transformation performed on the industry popularity data, and the Box-Cox transformation may reduce an unobservable error in the industry popularity data to some extent. And B-spline curve (B-spline Curves) transformation is carried out on the industry driving correlation data.
Illustratively, the industry landscape data may be numerically transformed using the following formula:
wherein y (lambda) is the transformed industry popularity data, y is the original industry popularity data, and lambda is the transformation parameter.
And constructing an industry popularity estimation model according to the numerical transformation results of the industry driving associated data and the industry popularity data with the mapping relation. Through the numerical transformation of the industry drive associated data and the industry popularity data, the accuracy and the stability of the industry popularity prediction model are improved.
And S350, determining the industry popularity prediction data of the future statistical period according to the industry popularity prediction model.
Specifically, the fitting effect of the constructed industry popularity estimation model is evaluated in a data return measurement mode, and when the error of the industry popularity estimation model is larger than the preset error, industry driving related data and industry popularity data are re-screened through S340. Wherein, the preset error can be set according to human experience. And when the error of the industry popularity prediction model is smaller than the preset error, determining industry popularity prediction data of a future statistical period according to the industry popularity model. In order to more visually display the industry popularity prediction data, the value of the industry popularity prediction data at a certain time point in a future statistical period is used as a base number, and the industry popularity prediction data at other time points in the future statistical period is correspondingly converted. The base number can be set by a technician according to actual needs or empirical values, and for example, the base number can be 100.
And S360, selecting at least one target industry from each initial industry according to the industry popularity estimation data.
And S370, determining the enterprise co-purchasing power value and the enterprise co-purchasing capacity value of the candidate enterprises of each target industry.
And S380, selecting target enterprises from the candidate enterprises according to the enterprise parallel purchasing power value and the enterprise parallel purchasing capacity value.
According to the scheme, the lead period number between the industry drive associated data and the industry popularity data in the historical statistical period is obtained, so that the mapping relation between the data is determined; and constructing an industry popularity model according to the mapping relation, and determining industry popularity prediction data in a future statistical period through the model. The lead time between the industry driving correlation data and the industry popularity data can be used as an important index for predicting future industry popularity prediction data. The problem of inaccurate prediction of the future industry popularity is solved, and accurate prediction of the future industry popularity and accurate judgment of the future industry development trend are realized.
Example four
Fig. 4 is a schematic structural diagram of a target enterprise determining apparatus according to a fourth embodiment of the present invention. The target enterprise determining device provided by the embodiment of the invention can execute the target enterprise determining method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the executing method. The apparatus may be implemented in software and/or hardware, and as shown in fig. 4, the target enterprise determining apparatus specifically includes: the system comprises a data determination module 410, a forecast data determination module 420, a target industry determination module 430, a numerical determination module 440 and a target enterprise determination module 450.
The data determining module 410 is configured to determine industry driving associated data and industry popularity data of each initial industry in at least one historical statistics period;
the estimated data determining module 420 is configured to determine industry popularity estimated data of a future statistical period according to the industry drive associated data and the industry popularity data;
a target industry determining module 430, configured to select at least one target industry from each of the initial industries according to the industry popularity prediction data;
the numerical value determining module 440 is configured to determine an enterprise merger power value and an enterprise merger capacity value of the candidate enterprises of each target industry;
and the target enterprise determining module 450 is configured to select a target enterprise from the candidate enterprises according to the enterprise merger power value and the enterprise merger capacity value.
According to the scheme, the driving relevant data of the macro industry is introduced from the consideration of macro-level factors, the future industry popularity is estimated, and the target enterprises are determined by analyzing the enterprises in all the target industries and purchasing power and capacity from the consideration of micro-level factors. The industry driving associated data can be used as an index for reflecting the landscape degree of each industry on a macroscopic level, and the enterprise co-purchasing power and capacity can be used as important influence factors for measuring the development trend of the enterprise. The target enterprise is determined by the aid of the multiple layers, the problems that macroscopic influence factors are less considered in industry analysis and the enterprise analysis is incomplete in the past are solved, the target enterprise is judged from the multidimensional influence factors, and therefore the purpose of more accurate prediction of the target enterprise is achieved.
Optionally, the estimated data determining module 420 includes:
the lead period number determining unit is used for determining the lead period number between the industry driving related data and the industry scene degree data with different historical statistical periods;
the mapping relation determining unit is used for determining the mapping relation between the industry driving associated data and the industry popularity data in different historical statistical periods according to the lead period number;
the estimation model construction unit is used for constructing an industry popularity estimation model according to the industry driving associated data and the industry popularity data with the mapping relation;
and the estimated data determining unit is used for determining the industry popularity estimated data of the future statistical period according to the industry popularity estimation model.
Optionally, the lead number determining unit is specifically configured to:
constructing initial corresponding relations between the industry driving associated data and the industry scene degree data in different historical statistical periods according to at least one lag period number;
and selecting a lead period number from the at least one lag period number according to the correlation between the industry driving correlation data with the initial corresponding relation and the industry scene degree data.
Optionally, the pre-estimation model building unit is specifically configured to:
screening the industry driving associated data according to the co-linearity condition of different dimension data in the industry driving associated data;
and constructing an industry popularity estimation model according to the screened industry driving associated data with the mapping relation and the industry popularity data.
Optionally, the pre-estimation model building unit is specifically configured to:
carrying out numerical transformation on the industry popularity data and/or the industry driving correlation data;
and constructing an industry popularity estimation model according to the industry driving associated data with the mapping relation and the numerical transformation result of the industry popularity data.
Optionally, the data determining module 410 includes:
the profit data determining unit is used for determining the industry profit data of each initial industry in each historical statistical period;
and the popularity data determining unit is used for respectively determining the industry popularity data of each initial industry in the historical statistical period according to the industry profit data of each initial industry.
Optionally, the data determining module 410 includes:
the updating frequency acquiring unit is used for acquiring initial industry driving associated data of which the updating frequency is greater than the length of a statistical period in each historical statistical period;
the missing data filling unit is used for filling missing data in the initial industry drive associated data so as to update the initial industry drive associated data;
and generating the industry driving associated data under the historical statistical period according to the updated initial industry driving associated data.
Optionally, the value determining module 440 includes:
the parallel purchasing power value determining unit is used for determining the enterprise parallel purchasing power value of the candidate enterprise according to at least one of stockholder background data, business investment data, enterprise competition data and business expansion data of the candidate enterprise;
and the merging and purchasing ability value determining unit is used for determining the enterprise merging and purchasing ability value of the candidate enterprise according to at least one of enterprise financial data, enterprise capital structure, enterprise operation data and enterprise public opinion data of the candidate enterprise.
The target enterprise determining device can execute the target enterprise determining method provided by any embodiment of the application, and has the corresponding functional modules and beneficial effects of executing each target enterprise determining method.
EXAMPLE five
Fig. 5 is a schematic structural diagram of a computer apparatus according to a fifth embodiment of the present invention, as shown in fig. 5, the computer apparatus includes a processor 510, a memory 520, an input device 530, and an output device 540; the number of the processors 510 in the device may be one or more, and one processor 510 is taken as an example in fig. 5; the processor 510, the memory 520, the input device 530 and the output device 540 of the apparatus may be connected by a bus or other means, as exemplified by the bus connection in fig. 5.
The memory 520 may be used as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as program instructions/modules (the data determination module 410, the forecast data determination module 420, the target industry determination module 430, the value determination module 440, and the target enterprise determination module 450) corresponding to the target enterprise determination method in the embodiments of the present invention. The processor 510 executes various functional applications of the device and data processing by executing software programs, instructions and modules stored in the memory 520, i.e., implements the above-described target enterprise-specific method.
The memory 520 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal (such as industry driving related data, industry popularity prediction data, target industry, enterprise merger power value, enterprise merger capacity value, target enterprise, and the like related to the foregoing embodiment), and the like. Further, the memory 520 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 520 may further include memory located remotely from processor 510, which may be connected to devices through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 530 may be used to receive input numeric or character information and generate signal inputs related to user settings and function control of the apparatus. The output device 540 may include a display device such as a display screen.
EXAMPLE six
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a target enterprise determination method, the method including:
determining industry driving associated data and industry popularity data of each initial industry in at least one historical statistical period;
determining industry popularity prediction data of a future statistical period according to the industry drive associated data and the industry popularity data;
selecting at least one target industry from each initial industry according to the industry popularity estimation data;
determining enterprise co-purchasing power values and enterprise co-purchasing capacity values of the candidate enterprises of the target industries;
and selecting a target enterprise from the candidate enterprises according to the enterprise co-purchasing power value and the enterprise co-purchasing capacity value.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the method operations described above, and may also perform related operations in the target enterprise determination method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the embodiments of the present invention can be implemented by software and necessary general hardware, and certainly can be implemented by hardware, but the former is a better implementation in many cases. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions to make a computer device (which may be a personal computer, a server, or a network device) perform the methods described in the embodiments of the present invention.
It should be noted that, in the embodiment of the target enterprise determining apparatus, the included units and modules are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the embodiment of the invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (11)
1. A method for target enterprise determination, comprising:
determining industry driving associated data and industry popularity data of each initial industry in at least one historical statistical period;
determining industry popularity prediction data of a future statistical period according to the industry drive associated data and the industry popularity data;
selecting at least one target industry from each initial industry according to the industry popularity estimation data;
determining enterprise co-purchasing power values and enterprise co-purchasing capacity values of the candidate enterprises of the target industries;
and selecting a target enterprise from the candidate enterprises according to the enterprise co-purchasing power value and the enterprise co-purchasing capacity value.
2. The method of claim 1, wherein determining industry popularity prediction data for a future statistical period based on each of the industry-driven correlation data and the industry popularity data comprises:
determining lead periods between the industry driving correlation data and the industry popularity data of different historical statistical periods;
determining the mapping relation between the industry driving associated data and the industry popularity data in different historical statistical periods according to the lead period number;
constructing an industry popularity estimation model according to the industry driving associated data and the industry popularity data with the mapping relation;
and determining the industry popularity prediction data of a future statistical period according to the industry popularity prediction model.
3. The method of claim 2, wherein the determining a number of lead periods between the industry driven correlation data and the industry popularity data for different historical statistics periods comprises:
constructing initial corresponding relations between the industry driving associated data and the industry scene degree data in different historical statistical periods according to at least one lag period number;
and selecting a lead period number from the at least one lag period number according to the correlation between the industry driving correlation data with the initial corresponding relation and the industry scene degree data.
4. The method of claim 2, wherein constructing an industry popularity prediction model based on the industry-driven associated data and the industry popularity data with the mapping relationship comprises:
screening the industry driving associated data according to the co-linearity condition of different dimension data in the industry driving associated data;
and constructing an industry popularity estimation model according to the screened industry driving associated data with the mapping relation and the industry popularity data.
5. The method of claim 2, wherein constructing an industry popularity prediction model based on the industry-driven associated data and the industry popularity data with the mapping relationship comprises:
carrying out numerical transformation on the industry popularity data and/or the industry driving correlation data;
and constructing an industry popularity estimation model according to the industry driving associated data with the mapping relation and the numerical transformation result of the industry popularity data.
6. The method of any one of claims 1-5, wherein determining industry goodness data for each initial industry over at least one historical statistical period comprises:
determining industry profit data of each initial industry under each historical statistical period;
and respectively determining the industry scene degree data of each initial industry in the historical statistical period according to the industry profit data of each initial industry.
7. The method according to any one of claims 1-5, wherein the determining industry driven associated data for each initial industry over at least one historical statistical period comprises:
aiming at each historical statistical period, acquiring initial industry drive associated data of which the updating frequency is greater than the length of the statistical period under the historical statistical period;
filling missing data in the initial industry driving associated data to update the initial industry driving associated data;
and generating the industry driving associated data under the historical statistical period according to the updated initial industry driving associated data.
8. The method according to any one of claims 1 to 5, wherein the determining of the business merger power value and the business merger capacity value of the candidate businesses of each of the target industries comprises:
determining an enterprise co-purchasing power value of the candidate enterprise according to at least one of stockholder background data, operating investment data, enterprise competition data and operating expansion data of the candidate enterprise;
and determining the enterprise merging and purchasing ability value of the candidate enterprise according to at least one of enterprise financial data, enterprise capital structure, enterprise operation data and enterprise public opinion data of the candidate enterprise.
9. A target enterprise determination apparatus, comprising:
the data determination module is used for determining industry driving associated data and industry popularity data of each initial industry in at least one historical statistical period;
the estimated data determining module is used for determining the industry popularity estimated data of a future statistical period according to the industry drive associated data and the industry popularity data;
the target industry determining module is used for selecting at least one target industry from each initial industry according to the industry popularity estimation data;
the numerical value determining module is used for determining enterprise co-purchasing power values and enterprise co-purchasing capacity values of the candidate enterprises of the target industries;
and the target enterprise determining module is used for selecting a target enterprise from the candidate enterprises according to the enterprise merging purchase power value and the enterprise merging purchase capacity value.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the target enterprise determination method as claimed in any one of claims 1-8.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the target enterprise determination method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110773080.4A CN113421014A (en) | 2021-07-08 | 2021-07-08 | Target enterprise determination method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110773080.4A CN113421014A (en) | 2021-07-08 | 2021-07-08 | Target enterprise determination method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113421014A true CN113421014A (en) | 2021-09-21 |
Family
ID=77720467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110773080.4A Pending CN113421014A (en) | 2021-07-08 | 2021-07-08 | Target enterprise determination method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113421014A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113935626A (en) * | 2021-10-15 | 2022-01-14 | 中国工商银行股份有限公司 | Parallel purchasing technology cooperation platform and technology cooperation method |
| CN114511181A (en) * | 2021-12-31 | 2022-05-17 | 中国环境科学研究院 | Water pollution environmental protection verification method and device based on grid and tax data fusion |
-
2021
- 2021-07-08 CN CN202110773080.4A patent/CN113421014A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113935626A (en) * | 2021-10-15 | 2022-01-14 | 中国工商银行股份有限公司 | Parallel purchasing technology cooperation platform and technology cooperation method |
| CN114511181A (en) * | 2021-12-31 | 2022-05-17 | 中国环境科学研究院 | Water pollution environmental protection verification method and device based on grid and tax data fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Şener et al. | Ranking the predictive performances of value-at-risk estimation methods | |
| US20160342922A1 (en) | Performance analytics based on high performance indices | |
| US8577791B2 (en) | System and computer program for modeling and pricing loan products | |
| CN110880051A (en) | Enterprise value evaluation cloud service system | |
| CN111754116B (en) | Credit evaluation method and device based on label portrait technology | |
| US11593305B2 (en) | Data conversion and distribution systems | |
| CN114048436A (en) | Construction method and construction device for forecasting enterprise financial data model | |
| CN118799058B (en) | A loan risk assessment method and system based on artificial intelligence | |
| US11995667B2 (en) | Systems and methods for business analytics model scoring and selection | |
| KR102628559B1 (en) | Method and device for providing real estate mortgage loan automatic screening platform | |
| KR102620000B1 (en) | Method and device for providing investment valuation service based on financial indicator analysis | |
| Amin et al. | Application of optimistic and pessimistic OWA and DEA methods in stock selection | |
| CN117333025A (en) | Enterprise risk assessment methods, devices, equipment and media based on multi-dimensional data | |
| CN113421014A (en) | Target enterprise determination method, device, equipment and storage medium | |
| CN116596674A (en) | External trade risk assessment method based on big data analysis | |
| Wei | [Retracted] A Machine Learning Algorithm for Supplier Credit Risk Assessment Based on Supply Chain Management | |
| Antunes et al. | Analyzing Chinese banking performance with a trigonometric envelopment analysis for ideal solutions model | |
| CN119250915A (en) | Financial product recommendation method, device, computer equipment and storage medium | |
| Fagbore et al. | Predictive Analytics for Portfolio Risk Using Historical Fund Data and ETL-Driven Processing Models | |
| CN113870007A (en) | A product recommendation method, device, equipment and medium | |
| Yalçın et al. | Evaluating Financial Performance of Companies in the Borsa Istanbul Sustainability Index Using the CRITIC-MABAC Method | |
| TWI634498B (en) | Business operations analysis system and method | |
| KR102662354B1 (en) | Method and device for analyzing investment value based on deep learning | |
| Srairi | The impact of risk and Fintech on ESG performance: evidence from gulf cooperation council (GCC) banks | |
| AU2016200314A1 (en) | Performance analytics based on high performance indices |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210921 |