WO2018137104A1

WO2018137104A1 - User behavior analysis method and system based on big data mining

Info

Publication number: WO2018137104A1
Application number: PCT/CN2017/072375
Authority: WO
Inventors: 熊益冲
Original assignee: 深圳企管加企业服务有限公司
Priority date: 2017-01-24
Filing date: 2017-01-24
Publication date: 2018-08-02

Abstract

Disclosed in embodiments of the present invention are a user behavior analysis method and system based on big data mining. The method comprises: collecting user behavior data; preprocessing and aggregating the user behavior data by using a parallel computing model; and establishing a user behavior data ontology model according to the aggregated user behavior data, and storing the user behavior data ontology model into a database. Accordingly, by executing the embodiments of the present invention, the powerful processing capability of a cloud computing technology is combined with a large-scale data storage capability, an ontology and analysis thereof and a knowledge discovery method, in this way, mass user behavior data is analyzed in real time, and interest of a user is found in time, thereby implementing effective and precise pushing to the user.

Description

User behavior analysis method and system based on big data mining

Technical field

The present invention relates to the field of Internet technologies, and in particular, to a user behavior analysis method and system based on big data mining.

Background technique

In the field of Internet applications, user behavior analysis refers to the statistical and analysis of real-time and historical user behavior generated by users accessing network services (including accessing and browsing web pages, performing interactive operations, using APP, etc.). information. In the process of users accessing network services, there is a lot of valuable information. According to estimates, users should pay attention to 3-4 items on average during an online shopping process, visit 5-7 websites, and browse more than 40 pages. User behavior information includes but is not limited to the following: network service access times, access frequency, access time, active time, user input keywords, user click links, user interaction operations (such as adding attention, canceling attention, scoring) , save as a bookmark, add to the shopping cart, take out the shopping cart, form an order, cancel an order, pay, refund, etc.). Through the research on user behavior information, we can find out the regular distribution of users when accessing network services, and provide scientific and accurate objective basis for improving user experience, efficient information push and promotion of target marketing. For the research and application of user behavior, the most effective means is to record all user behavior information brought by all actions of users, and to analyze and analyze all user behavior information.

Big data technology is an information processing technology that targets all data resources of any system and discovers the correlation between data representation. It has been widely used in Internet process optimization, targeted message and advertisement push, and user personalized service. And improvement, etc., has become a strong back-office support behind network services. Based on the big data platform, the analysis and utilization of all user behavior information is realized, which adapts to the characteristics of large user behavior information, complex and diversified data formats, and high computing speed requirements, which can meet the actual needs of various types of network services.

For the analysis of user behavior, there have been many studies at home and abroad, but there are some problems: First, most of them focus on mining WEB logs, but these logs are not enough to describe the situation when users visit the website in time; secondly, large websites generally have huge Online users, real-time behavior and contextual information generated The amount is huge, so the storage capacity and calculation speed of the system are stronger, and the analysis results can be fed back to the user in time. At present, most user behavior analysis systems use relational database technology and traditional data processing methods, which can not meet the efficient analysis of massive data.

Summary of the invention

The embodiment of the invention provides a non-intelligent air conditioning monitoring method and system based on the Internet of Things, which can monitor various parameter information of the non-intelligent air conditioner, and adjust the non-intelligent air conditioner according to the parameter information, and can check whether the temperature and humidity setting of the air conditioner is reasonable. Or automatically control the air conditioner switch according to the time period to avoid unnecessary waste of cold source.

The first aspect of the embodiments of the present invention discloses a user behavior analysis method based on big data mining, including:

Collect user behavior data;

Preprocessing and aggregation of user behavior data using a parallel computing model;

Based on the aggregated user behavior data, a user behavior data ontology model is established and stored in the database.

As an optional implementation manner, the method further includes

The user behavior data ontology model is analyzed to find out the user's latest interest data.

As an optional implementation manner, the user behavior data includes a user behavior main body, an occurrence time, a generated page, a scrolling page up and down, a moving or clicking mouse, a page staying time, collecting, printing, saving, accessing the same page, Copy and paste text operations, current user search criteria, and search keyword-related titles.

As an optional implementation manner, the pre-processing includes: removing incomplete data, deleting duplicate data, pictures, and page animation; printing, collecting, saving, and downloading operations on the page, and after converting, converting the The corresponding data format is saved in the database;

The data aggregation includes: filtering and integrating the correct and invalid user behavior information by using a rule-based user behavior aggregation algorithm.

As an optional implementation manner, the establishing a user behavior data ontology model specifically includes:

The OWL-DL description language is used to build the user behavior data ontology model, and the ontology model is decomposed. The database uses an open source non-relational distributed database.

The second aspect of the embodiment of the present invention discloses a user behavior analysis system based on big data mining, including:

An acquisition unit for collecting user behavior data;

a pre-processing unit for performing pre-processing and aggregation on user behavior data using a parallel computing model;

The modeling unit is configured to establish a user behavior data ontology model according to the aggregated user behavior data, and store the data in the database.

As an optional implementation manner, the system further includes:

The analysis unit is configured to analyze the user behavior data ontology model to find out the latest interest data of the user.

As an optional implementation manner, the modeling unit is specifically configured to: establish an ontology model of the user behavior data by using an OWL-DL description language, and decompose the ontology model, where the database adopts an open source non-relational distributed database. .

It can be seen from the above technical solutions that the embodiments of the present invention have the following advantages:

In the embodiment of the present invention, the user behavior data is collected; the user behavior data is preprocessed and aggregated by using a parallel computing model; and the user behavior data ontology model is established according to the aggregated user behavior data, and stored in the database. It can be seen that the implementation of the embodiments of the present invention combines the powerful processing capability of the cloud computing technology with the large-scale data storage capability, the ontology and its analysis, and the knowledge discovery method, analyzes the massive user behavior data in real time, and timely acquires the user interest, thereby realizing Effective and accurate user push.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following description will be made on the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are incorporated in the drawings These figures take additional drawings.

1 is a schematic flowchart of a user behavior analysis method based on big data mining according to a first embodiment of the present invention;

[Correct according to Rule 26 21.03.2017]
2 is a schematic structural diagram of a user behavior analysis system based on big data mining according to a second embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a terminal device according to a third embodiment of the present invention.

detailed description

The present invention will be further described in detail with reference to the accompanying drawings, in which . All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

The terms "first", "second" and the like in the specification and claims of the present invention and the above drawings are used to distinguish different objects, and are not intended to describe a specific order. Furthermore, the terms "comprises" and "comprising" and "comprising" are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or device that comprises a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units not listed, or alternatively Other steps or units inherent to these processes, methods or devices.

The reference to an embodiment herein means that a particular feature, structure, or characteristic described in connection with the embodiments can be included in at least one embodiment of the invention. The appearances of the phrases in various places in the specification are not necessarily referring to the same embodiments, and are not exclusive or alternative embodiments that are mutually exclusive. Those skilled in the art will understand and implicitly understand that the embodiments described herein can be combined with other embodiments.

The embodiment of the invention provides a user behavior analysis method based on big data mining, which combines the powerful processing capability of cloud computing technology with large-scale data storage capability, ontology and its analysis, and knowledge discovery method to analyze massive user behavior data in real time. Get user interest in a timely manner to achieve effective and accurate user push.

Please refer to FIG. 1. FIG. 1 is a user based on big data mining disclosed in the first embodiment of the present invention. Schematic diagram of the behavior analysis method. The method for analyzing user behavior based on big data mining shown in FIG. 1 may include the following steps:

101. Collect user behavior data;

In the embodiment of the present invention, the user behavior data includes a user behavior main body, an occurrence time, a generated page, a scrolling page up and down, a moving or clicking mouse, a page staying time, collecting, printing, saving, accessing the same page number, copying and pasting text. The operation, the search criteria of the current user, and the title corresponding to the search keyword.

102. Perform parallel processing model on user behavior data for pre-processing and aggregation;

In the embodiment of the present invention, the pre-processing includes: removing incomplete data, deleting duplicate data, pictures, and page animation; printing, collecting, saving, and downloading operations on the page, and converting the data into corresponding data after obtaining The format is saved in the database.

103. Establish an ontology model of the user behavior data according to the aggregated user behavior data, and store the data in the database.

In the embodiment of the present invention, the user behavior data ontology model is established by using the OWL-DL description language, and the ontology model is decomposed, and the database adopts an open source non-relational distributed database.

104. Analyze the ontology model of the user behavior data to find out the latest interest data of the user.

In the embodiment of the present invention, the aggregated user behavior data is added to the user behavior data ontology model, and the user behavior data ontology model data stored in the database is analyzed to find the user's latest interest data.

In the method described in FIG. 1, the user behavior data is collected; the user behavior data is preprocessed and aggregated by using a parallel operation model; and the user behavior data ontology model is established according to the aggregated user behavior data, and stored in the database. It can be seen that the implementation of the embodiments of the present invention combines the powerful processing capability of the cloud computing technology with the large-scale data storage capability, the ontology and its analysis, and the knowledge discovery method, analyzes the massive user behavior data in real time, and timely acquires the user interest, thereby realizing Effective and accurate user push.

The following is a system embodiment of the present invention. The system embodiment of the present invention is used to perform the method for implementing the first embodiment of the method of the present invention. For the convenience of description, only the method related to the embodiment of the present invention is shown, and specific calculation details are not disclosed. Please refer to Embodiments 1 to 2 of the present invention.

Please refer to FIG. 2. FIG. 2 is a structural diagram of a user behavior analysis system based on big data mining disclosed in a second embodiment of the present invention. As shown in Figure 2, the system can include:

The collecting unit 201 is configured to collect user behavior data.

The user behavior data includes a user behavior main body, an occurrence time, a generated page, a scrolling page up and down, a moving or clicking mouse, a page staying time, a favorite, a print, a save, a visit to the same page number, a copy and paste text operation, and a current user search. Conditions, search for the title of the keyword.

The pre-processing unit 202 is configured to perform pre-processing and aggregation on the user behavior data by using a parallel computing model.

The pre-processing includes: removing incomplete data, deleting duplicate data, pictures, page animation; printing, collecting, saving, and downloading operations on the page, and after converting, converting the data into a corresponding data format and saving the same in a database;

The modeling unit 203 is configured to establish a user behavior data ontology model according to the aggregated user behavior data, and store the data in the database.

The analyzing unit 204 is configured to analyze the user behavior data ontology model to find the latest interest data of the user.

In the system described in FIG. 2, the acquisition unit collects user behavior data; the pre-processing unit uses a parallel operation model to perform pre-processing and aggregation on the user behavior data; the modeling unit establishes a user behavior data ontology model according to the aggregated user behavior data. And stored in the database. This shows that the implementation of this In the embodiment of the invention, the powerful processing capability of the cloud computing technology and the large-scale data storage capability, the ontology and its analysis, and the knowledge discovery method are combined to analyze the massive user behavior data in real time, and timely acquire the user interest, thereby realizing effective and accurate user push. .

Referring to FIG. 3, FIG. 3 is a schematic structural diagram of a terminal device according to an embodiment of the present invention. As shown in FIG. 3, for the convenience of description, only the parts related to the embodiments of the present invention are shown. For the specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The terminal may include a processor 301, a memory 302, a collector 303, the processor 301, a memory 302, and a transmitter 303 connected by a communication bus 304.

In the foregoing embodiment, each step method flow may be implemented based on the structure of the terminal device. Both the application layer and the operating system kernel can be considered as part of the abstraction structure of the processor 301.

In the embodiment of the present invention, the processor 301 performs the following operations by calling program code stored in the memory 302:

Collect user behavior data;

In the terminal device described in FIG. 3, the collector 303 collects user behavior data; the processor 301 performs preprocessing and aggregation on the user behavior data by using a parallel computing model; and establishes a user behavior data ontology model according to the aggregated user behavior data. And stored in the database. It can be seen that implementing the embodiments of the present invention, the powerful processing capability of the cloud computing technology and the large-scale data storage capability, the ontology and its points The combination of analysis and knowledge discovery methods analyzes massive user behavior data in real time and acquires user interest in time to achieve effective and accurate user push.

As an optional implementation manner, the processor 301 is further configured to perform the following operations by calling program code stored in the memory 302:

The embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium can store a program, and the program includes a part or all steps of a monitoring method of any one of the foregoing method embodiments.

It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should understand that the present invention is not limited by the described action sequence. Because certain steps may be performed in other sequences or concurrently in accordance with the present invention. In the following, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and units involved are not necessarily required by the present invention.

The insufficiency of the method of the embodiment of the present invention may be adjusted, merged, or deleted according to actual needs. The unit of the terminal in the embodiment of the present invention may be integrated, further divided or deleted according to actual needs.

In the above embodiments, the descriptions of the various embodiments are different, and the parts that are not detailed in a certain embodiment can participate in the related description of other embodiments.

In the several embodiments provided by the present application, it should be understood that the disclosed system may be implemented in other manners, for example, the system embodiment described above is illustrative, for example, the division of the unit is A logical function partitioning may be implemented in an actual manner. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an inductive or communication connection through some interface, device or unit, and may be electrical or otherwise.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. . Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional unit in various embodiments of the present invention may be integrated in one processing unit. It is also possible that each unit physically exists alone, or two or more units may be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

It should be noted that, in the foregoing embodiment of the multi-point thermometer reporting system and the terminal device based on the Internet of Things, each unit included is only divided according to functional logic, but is not limited to the above division, as long as the corresponding The functions of the functional units are only for the purpose of facilitating mutual differentiation and are not intended to limit the scope of the present invention.

In addition, those skilled in the art can understand that all or part of the steps of the foregoing embodiments may be completed by a program to instruct related hardware, and the program may be stored in a computer readable storage medium, where the storage medium includes Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read Only Memory (Erasable Programmable Read Only Memory) , EPROM), One-time Programmable Read-Only Memory (OTPROM), Electronically-Erasable Programmable Read-Only Memory (EEPROM), Read-Only Disc (Compact) Disc Read-Only Memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other medium readable by a computer that can be used to carry or store data.

The above is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the embodiments of the present invention. All should be covered by the scope of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

A user behavior analysis method based on big data mining, which is characterized in that it comprises:

Collect user behavior data;

Preprocessing and aggregation of user behavior data using a parallel computing model;

Based on the aggregated user behavior data, a user behavior data ontology model is established and stored in the database.
The method of claim 1 wherein said method further comprises

The user behavior data ontology model is analyzed to find out the user's latest interest data.
The method of claim 1 wherein

The user behavior data includes a user behavior main body, an occurrence time, a generated page, a scrolling page up and down, a moving or clicking mouse, a page staying time, a favorite, a print, a save, a visit to the same page number, a copy and paste text operation, and a current user search. Conditions, search for the title of the keyword.
The method of claim 1 wherein

The pre-processing includes: removing incomplete data, deleting duplicate data, pictures, page animation; printing, collecting, saving, and downloading operations on the page, and after converting, converting the data into a corresponding data format and saving the same in a database;

The data aggregation includes: filtering and integrating the correct and invalid user behavior information by using a rule-based user behavior aggregation algorithm.
The method according to claim 4, wherein the establishing a user behavior data ontology model comprises:

The OWL-DL description language is used to build the user behavior data ontology model, and the ontology model is decomposed. The database uses an open source non-relational distributed database.
A user behavior analysis system based on big data mining, characterized in that

An acquisition unit for collecting user behavior data;

a pre-processing unit for performing pre-processing and aggregation on user behavior data using a parallel computing model;

The modeling unit is configured to establish a user behavior data ontology model according to the aggregated user behavior data, and store the data in the database.
The system of claim 6 wherein the system further comprises:

An analysis unit for analyzing the ontology model of the user behavior data to find out the latest interest of the user according to.
The system according to claim 7, wherein the user behavior data comprises a user behavior subject, an occurrence time, a generated page, a scrolling page up and down, a move or click mouse, a page time, a favorite, a print, a save, and a visit. The same page number, copy and paste text operation, current user's search condition, search title corresponding to the keyword.
The system of claim 7 wherein:

The pre-processing includes: removing incomplete data, deleting duplicate data, pictures, page animation; printing, collecting, saving, and downloading operations on the page, and after converting, converting the data into a corresponding data format and saving the same in a database;

The data aggregation includes: filtering and integrating the correct and invalid user behavior information by using a rule-based user behavior aggregation algorithm.
The system of claim 6 wherein:

The modeling unit is specifically configured to: establish an ontology model of the user behavior data by using an OWL-DL description language, and decompose the ontology model, wherein the database adopts an open source non-relational distributed database.