CN116932842A - Data sharing method, device, terminal equipment and storage medium - Google Patents

Abstract

The invention discloses a data sharing method, a device, terminal equipment and a storage medium, wherein the method comprises the following steps: receiving a shared data acquisition request; acquiring initial shared data through a blockchain network according to the shared data acquisition request; and screening the initial sharing data through a preset risk assessment model, obtaining data to be shared and sharing the data to be shared. The method solves the problems that a plurality of data with different versions easily occur in the process of acquiring the data, the data needs to be selected again and the workload is increased, and improves the data sharing efficiency.

Description

Data sharing method, device, terminal device and storage medium

Technical Field

The present invention relates to the technical field of data sharing, and in particular to a data sharing method, apparatus, terminal equipment and storage medium.

Background Art

With the rapid development of information technology and the rapid popularization of the Internet, global data is growing rapidly and gathering in large quantities, which has had a significant impact on economic development, social governance, national management, life and entertainment. At this stage, data development faces challenges such as difficulties in data openness, sharing and circulation, and difficulties in data security and privacy protection. In such a huge Internet network, in order to achieve resource sharing, distributed computing and storage among users, it is necessary to introduce blockchain technology, realize unified decentralized application management, and realize peer-to-peer networks, so that users can enjoy the advantages of blockchain technology. Therefore, data management methods based on blockchain have been widely used.

However, the traditional blockchain data statistical analysis capabilities are relatively weak, and there are still many problems in the collaborative sharing of data. For example, in actual applications, the data saved by the enterprise often needs to be reviewed, modified or added by different departments before storage. For the same data, since the data needs to be continuously circulated and processed between multiple departments, there are multiple different versions of the same data stored in the blockchain network, that is, several versions modified or added by different departments. As a result, it is easy for users to encounter multiple different versions of data in the process of obtaining data, requiring users to make a selection again, which increases the user's workload and cannot meet the user's usage needs well.

The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art.

Summary of the invention

The main purpose of the present invention is to provide a data sharing method, apparatus, terminal device and storage medium, aiming to solve the technical problem that multiple different versions of data are likely to appear in the process of acquiring data, which requires re-selection and increases the workload.

To achieve the above object, the present invention provides a data sharing method, which comprises:

Receiving a request for obtaining shared data;

According to the shared data acquisition request, initial shared data is acquired through the blockchain network;

The initial sharing data is screened through a preset risk assessment model to obtain the data to be shared and share the data to be shared.

Optionally, the step of obtaining initial shared data through the blockchain network according to the shared data acquisition request includes:

According to the shared data acquisition request, the user's operation authority is verified through a preset contract to obtain a verification result;

According to the verification result, matching is performed through the blockchain network to obtain the initial sharing data.

Optionally, the step of screening the initial shared data by using a preset risk assessment model, obtaining the data to be shared and sharing the data to be shared includes:

Performing risk assessment on the initial shared data using a preset risk assessment model to obtain an assessment result;

According to the evaluation result, the data to be shared is screened to obtain the data to be shared;

The data to be shared is used for data sharing.

Optionally, the step of matching through a blockchain network according to the verification result to obtain initial sharing data includes:

According to the verification result, obtaining a first keyword and a data acquisition condition;

Matching the first keyword through the blockchain network to obtain data candidate areas;

According to the data candidate area, matching is performed through the data acquisition condition to acquire initial sharing data.

Optionally, before the step of performing risk assessment on the initial shared data using a preset risk assessment model and obtaining the assessment result, the step further includes:

Use the historical normal data in the preset database to construct the data set and obtain the training set and test set;

Inputting the training set into a preset initial risk assessment model for training to obtain a trained initial risk assessment model;

The test set is input into the trained initial risk assessment model for model prediction to obtain a risk assessment model.

Optionally, the step of using the data to be shared to perform data sharing includes:

Construct association rules based on several normal user access records and access data in the preset database;

According to the association rule, data sharing is performed using the data to be shared.

Optionally, the step of performing data sharing through the data to be shared according to the association rule includes:

According to the association rule, construct an association relationship between the plurality of normal user access records;

According to the association relationship, a number of initial users to be shared are screened to obtain sharing users;

Data is shared with the sharing users through the data to be shared.

The embodiment of the present invention further provides a data sharing device, the data sharing device comprising:

A receiving module, used for receiving a request for obtaining shared data;

An acquisition module, used to acquire initial shared data through a blockchain network according to the shared data acquisition request;

The sharing module is used to screen the initial sharing data through a preset risk assessment model, obtain the data to be shared and share the data to be shared.

An embodiment of the present invention further proposes a terminal device comprising a memory, a processor, and a data sharing program stored in the memory and executable on the processor. When the data sharing program is executed by the processor, the steps of the data sharing method described above are implemented.

The embodiment of the present invention further proposes a computer-readable storage medium, on which a data sharing program is stored. When the data sharing program is executed by a processor, the steps of the data sharing method described above are implemented.

The data sharing method, device, terminal device and storage medium proposed in the embodiment of the present invention receive a request for obtaining shared data; obtain initial shared data through a blockchain network according to the request for obtaining shared data; screen the initial shared data through a preset risk assessment model, obtain the data to be shared and share the data to be shared. In this way, data sharing is achieved, the problem of multiple different versions of data being prone to appearing in the process of obtaining data, which requires reselection and increases the workload is solved, and the efficiency of data sharing is improved.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic diagram of functional modules of a terminal device to which a data sharing device of the present invention belongs;

FIG2 is a flow chart of an exemplary embodiment of a data sharing method of the present invention;

FIG3 is a schematic diagram of the data sharing method of the present invention involving blockchain characteristics;

FIG4 is a schematic diagram of the overall flow of the data sharing method of the present invention;

FIG5 is a flow chart of another exemplary embodiment of a data sharing method of the present invention;

FIG6 is a schematic diagram of the data sharing method of the present invention involving obtaining initial shared data;

FIG7 is a flow chart of another exemplary embodiment of a data sharing method of the present invention;

FIG8 is a schematic diagram of a flow chart of matching through a blockchain network in a data sharing method of the present invention;

FIG9 is a schematic diagram of a flow chart of the data sharing method of the present invention involving obtaining evaluation results;

FIG10 is a flow chart of another exemplary embodiment of a data sharing method of the present invention;

FIG. 11 is a schematic diagram of a flow chart of data sharing in the data sharing method of the present invention.

The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings.

DETAILED DESCRIPTION

It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

The main solution of the embodiment of the present invention is: according to the shared data acquisition request, the user's operation authority is verified through a preset contract to obtain a verification result; according to the verification result, the initial shared data is matched through the blockchain network. The initial shared data is risk assessed through a preset risk assessment model to obtain an assessment result; according to the assessment result, the data to be shared is screened to obtain the data to be shared; and the data to be shared is used for data sharing. According to the verification result, a first keyword and a data acquisition condition are obtained; through the blockchain network, the first keyword is matched to obtain a data candidate area; according to the data candidate area, the data acquisition condition is matched to obtain the initial shared data. The data set is constructed through the historical normal data in the preset database to obtain a training set and a test set; the training set is input into the preset initial risk assessment model for training to obtain the trained initial risk assessment model; the test set is input into the trained initial risk assessment model for model prediction to obtain a risk assessment model. According to a number of normal user access records and access data in the preset database, an association rule is constructed; according to the association rule, data sharing is performed through the data to be shared. According to the association rules, an association relationship is constructed between the several normal user access records; according to the association relationship, several initial users to be shared are screened to obtain shared users; and data is shared with the shared users through the data to be shared. This solves the problem that multiple different versions of data are prone to appear in the process of acquiring data, which requires reselection and increases the workload, realizes data sharing, and improves the efficiency of data sharing. Based on the scheme of the present invention, starting from the problem that multiple different versions of data are prone to appear in the process of acquiring data in reality, which requires reselection and increases the workload, a data sharing method is designed, and the effectiveness of the data sharing method of the present invention is verified in actual data sharing. Finally, the efficiency of data sharing is significantly improved through the method of the present invention.

The technical terms involved in the present invention are:

Blockchain: Blockchain is a decentralized distributed ledger technology. It is based on cryptographic principles and consensus algorithms. It links data together in the form of blocks and uses encryption technology to ensure the security and integrity of data. Blockchain technology has a wide range of applications, the most famous of which is the implementation of cryptocurrency (such as Bitcoin). In addition, blockchain can also be applied to financial services, supply chain management, the Internet of Things, medical health, intellectual property protection, bill exchange and other fields to achieve decentralized, reliable and efficient data exchange and management.

Simulated annealing genetic algorithm: The simulated annealing algorithm is a heuristic optimization algorithm inspired by the annealing process of solid materials. Its basic idea is to find the global optimal solution by simulating the annealing cooling process of solids at high temperatures.

Collaborative Recommendation Algorithm: Collaborative Filtering Recommendation Algorithm is a commonly used recommendation algorithm. It predicts the user's preference for certain items (such as goods, movies, music, etc.) by analyzing the behavior and interests between users, and gives recommendation results. The advantage of collaborative filtering algorithm is that it can make recommendations based on the user's actual behavior without collecting the user's personal information in advance. It performs well in solving the cold start problem (new users or new items) and is suitable for large-scale recommendation systems. However, collaborative filtering algorithm also has some challenges, such as data sparsity problem, gray group problem (user preferences are difficult to capture), high computational complexity, etc. Therefore, in practical applications, it is also necessary to comprehensively consider other recommendation algorithms and technologies, such as content filtering, deep learning, etc., to improve the recommendation effect and system performance.

The embodiments of the present invention take into account that when the related technologies are performing data sharing, since the data needs to be continuously circulated and processed between multiple departments, there are multiple different versions of the same data stored in the blockchain network, that is, several versions modified or added by different departments. Therefore, this method requires the user to make a selection again, which increases the user's workload.

Therefore, based on the problem that multiple different versions of data are likely to appear in the process of acquiring data in reality, and selection needs to be made again, which increases the workload, a data sharing method is designed, and the effectiveness of the data sharing method of the present invention is verified in actual data sharing. Finally, the efficiency of data sharing is significantly improved through the method of the present invention.

Specifically, referring to FIG. 1, FIG. 1 is a schematic diagram of the functional blocks of the terminal device to which the data sharing device of the present invention belongs. The data sharing device can be a device that is independent of the terminal device and can perform data sharing, and it can be carried on the terminal device in the form of hardware or software. The terminal device can be a smart mobile device with data processing function such as a mobile phone or a tablet computer, and can also be a fixed terminal device or server with data processing function.

In this embodiment, the terminal device to which the data sharing apparatus belongs at least includes an output module 110 , a processor 120 , a memory 130 and a communication module 140 .

The memory 130 stores an operating system and a data sharing program. The data sharing device can receive a request for obtaining shared data; according to the request for obtaining shared data, obtain initial shared data through the blockchain network; screen the initial shared data through a preset risk assessment model, obtain the data to be shared, and share the data to be shared. Data sharing is performed through the data sharing program, and information such as the data sharing results is stored in the memory 130; the output module 110 can be a display screen, etc. The communication module 140 can include a WIFI module, a mobile communication module, a Bluetooth module, etc., and communicates with an external device or server through the communication module 140.

When the data sharing program in the memory 130 is executed by the processor, the following steps are implemented:

Receiving a request for obtaining shared data;

According to the shared data acquisition request, initial shared data is acquired through the blockchain network;

The initial sharing data is screened through a preset risk assessment model to obtain the data to be shared and share the data to be shared.

Furthermore, when the data sharing program in the memory 130 is executed by the processor, the following steps are also implemented:

According to the shared data acquisition request, the user's operation authority is verified through a preset contract to obtain a verification result;

According to the verification result, matching is performed through the blockchain network to obtain the initial sharing data.

Furthermore, when the data sharing program in the memory 130 is executed by the processor, the following steps are also implemented:

Performing risk assessment on the initial shared data using a preset risk assessment model to obtain an assessment result;

According to the evaluation result, the data to be shared is screened to obtain the data to be shared;

The data to be shared is used for data sharing.

Furthermore, when the data sharing program in the memory 130 is executed by the processor, the following steps are also implemented:

According to the verification result, obtaining a first keyword and a data acquisition condition;

Matching the first keyword through the blockchain network to obtain data candidate areas;

According to the data candidate area, matching is performed through the data acquisition condition to acquire initial sharing data.

Furthermore, when the data sharing program in the memory 130 is executed by the processor, the following steps are also implemented:

Use the historical normal data in the preset database to construct the data set and obtain the training set and test set;

Inputting the training set into a preset initial risk assessment model for training to obtain a trained initial risk assessment model;

The test set is input into the trained initial risk assessment model for model prediction to obtain a risk assessment model.

Furthermore, when the data sharing program in the memory 130 is executed by the processor, the following steps are also implemented:

Construct association rules based on several normal user access records and access data in the preset database;

According to the association rule, data sharing is performed using the data to be shared.

Furthermore, when the data sharing program in the memory 130 is executed by the processor, the following steps are also implemented:

According to the association rule, construct an association relationship between the plurality of normal user access records;

According to the association relationship, a number of initial users to be shared are screened to obtain sharing users;

Data is shared with the sharing users through the data to be shared.

This embodiment adopts the above scheme, specifically by receiving a request for obtaining shared data; according to the request for obtaining shared data, obtaining initial shared data through the blockchain network; screening the initial shared data through a preset risk assessment model, obtaining the data to be shared and sharing the data to be shared. A data sharing method is designed based on a blockchain network, and data sharing is performed using the data sharing method, which can solve the problem that multiple different versions of data are prone to appear in the process of obtaining data, and it is necessary to select again, which increases the workload. Based on the scheme of the present invention, a data sharing method is designed based on the problem that multiple different versions of data are prone to appear in the process of obtaining data in reality, and it is necessary to select again, which increases the workload. The effectiveness of the data sharing method of the present invention is verified in actual data sharing, and finally the efficiency of data processing by the method of the present invention is significantly improved.

Based on the above terminal device architecture but not limited to the above framework, an embodiment of the method of the present invention is proposed.

Referring to Figure 2, Figure 2 is a flow chart of an exemplary embodiment of a data sharing method of the present invention. The data sharing method comprises:

Step S01, receiving a request for obtaining shared data;

The execution subject of the method of this embodiment can be a data sharing device, or a data sharing terminal device or server. This embodiment takes a data sharing device as an example, and the data sharing device can be integrated in a terminal device with data processing function.

In order to achieve data sharing, the following steps are taken:

First, the present invention is implemented based on blockchain, as shown in FIG3 , which is a schematic diagram of the data sharing method of the present invention involving the characteristics of blockchain. Blockchain is a decentralized distributed ledger technology. It is based on cryptographic principles and consensus algorithms, by linking data together in the form of blocks, and using encryption technology to ensure the security and integrity of data. Blockchain technology has a wide range of applications, the most famous of which is the implementation of cryptocurrency (such as Bitcoin). In addition, blockchain can also be applied to financial services, supply chain management, the Internet of Things, medical health, intellectual property protection, bill exchange and other fields to achieve decentralized, reliable and efficient data exchange and management;

Finally, when the user needs to share data, a data acquisition request is issued. The data acquisition request is an initiated process, which contains information such as corresponding permissions. Through the data acquisition request, the corresponding shared data can be obtained;

Step S02, obtaining initial shared data through the blockchain network according to the shared data acquisition request;

After receiving the data acquisition request, in order to obtain the initial shared data, take the following steps:

First, each data acquisition request issued by a different user has different permissions, and different permissions can obtain different permissions;

Then, based on the data acquisition request issued by the corresponding user, the authority of the data acquisition request is verified through the smart contract;

Finally, based on the verification results, the data corresponding to the permissions is obtained as the initial sharing data.

Step S03, screening the initial sharing data through a preset risk assessment model, obtaining the data to be shared and sharing the data to be shared;

After obtaining the initial sharing data, you need to verify whether it can be shared. This can be achieved through the following steps:

First, the initial shared data is input into the risk assessment model for classification, wherein the risk assessment model is pre-built and has the function of identifying abnormal data and normal data. Specifically, when classifying, the risk assessment model compares the deviation between the data acquired at the current moment and the normal data at the current moment (i.e., the predicted data at the current moment output by the risk assessment model based on the normal data at the previous moment). If the deviation exceeds a preset threshold, the data is abnormal data or maliciously modified/tampered data; if the deviation does not exceed the preset threshold, the data is normal data;

Then, based on the detection results of abnormal data, the initial shared data is screened in real time to obtain the data to be shared, and the detection results of abnormal data are reported;

Then, the access records and access data of all users are obtained in the historical database;

Then, the obtained access records and access data are screened to obtain normal data;

Then, a user-data matrix is established using the screened user access records and access data;

Then, the association rules in the user-data matrix are used to find the association relationship between the access records of known users, and the similarity between the user to be shared and the known users is calculated;

Finally, select target users with high similarity for data push and send the data to be shared to the target users.

More specifically, as shown in FIG. 4 , FIG. 4 is a flow chart of the overall solution involved in the data sharing method of the present invention.

First, the data acquisition request is received, and the operation authority of the user who issued the data acquisition request is verified using the smart contract to obtain the verification result;

Then, based on the verification result, the block matching the data acquisition request is queried in the blockchain network, and the data to be shared is obtained in the matching block;

Then, the data to be shared is input into the pre-built risk assessment model to screen out the data to be shared that can be shared;

Finally, based on user access records, an improved collaborative filtering recommendation algorithm is used to recommend data to be shared for users.

This embodiment adopts the above scheme, specifically by receiving a request for obtaining shared data; according to the request for obtaining shared data, obtaining initial shared data through the blockchain network; screening the initial shared data through a preset risk assessment model, obtaining the data to be shared and sharing the data to be shared. The risk assessment and sharing of data are realized, and the problem of multiple different versions of data being prone to appearing in the process of obtaining data, which requires reselection and increases the workload, is solved, and the efficiency of data sharing is improved.

Referring to FIG. 5 , FIG. 5 is a flow chart of another exemplary embodiment of the data sharing method of the present invention.

Based on the embodiment shown in FIG. 2 above, the step S02, according to the data acquisition request, the step of acquiring the initial shared data through the blockchain network includes:

Step S021, according to the shared data acquisition request, verify the user's operation authority through a preset contract to obtain a verification result;

Step S022: According to the verification result, matching is performed through the blockchain network to obtain initial sharing data.

Specifically, in order to obtain the initial shared data, the following steps are performed:

First, when sharing data, the data obtained may be different due to the deviations between different departments or systems;

Then, based on the data acquisition request initiated by the user, the user's operation authority is verified through the smart contract to obtain the verification result, where the verification result includes but is not limited to the user's system, department, data classification, etc.;

Finally, according to the user's verification results, the blockchain network is used for matching to obtain the corresponding block, and the data in the block is used as the initial sharing data.

Specifically, as shown in FIG. 6 , FIG. 6 is a schematic diagram of obtaining initial shared data in the data sharing method of the present invention.

M data refers to the data stored in the entire blockchain. For example, the "people" block contains data such as expert talents, data analysis, and employee information. The "finance" block contains data such as reimbursement data, financial statements, procurement, comprehensive budgets, and projects. The "things" block contains data such as procurement, warehouses, and suppliers. The "work" block contains data such as engineering project management, planning and scheduling, survey and design. The "control" block contains data such as contract management, information security, supervision and discipline. The "OA" block contains data such as agency data, bus work orders, and official document data. The "strategy" block contains data such as strategic performance and system management. The "foundation" block contains data such as office software, application monitoring, and user management. Among them, the corresponding blocks should be understood to include but are not limited to, and the corresponding blocks should be adjusted according to actual business needs.

This embodiment uses the above solution to verify the user's operation authority through a preset contract according to the shared data acquisition request to obtain a verification result; and matches through the blockchain network according to the verification result to obtain the initial shared data. The acquisition of initial data is achieved, the problem of no corresponding classification when sharing data is solved, and the efficiency of data sharing is improved.

Referring to FIG. 7 , FIG. 7 is a flow chart of another exemplary embodiment of the data sharing method of the present invention.

Based on the embodiment shown in FIG. 2 , the step S03 of screening the initial shared data by using a preset risk assessment model to obtain the data to be shared includes:

Step S034, performing risk assessment on the initial shared data using a preset risk assessment model to obtain an assessment result;

Step S035: Screen the data to be shared according to the evaluation result to obtain the data to be shared.

Step S036: Use the data to be shared to perform data sharing.

Specifically, in order to realize the transformation of the initial shared data into the data to be shared, the following steps are taken:

First, the initial shared data is input into the risk assessment model for evaluation to obtain the evaluation results. The risk assessment model is constructed in advance and its function is to distinguish between normal data and abnormal data.

Then, according to the evaluation results, the abnormal data in the data to be shared is removed, and the remaining normal data is used as the data to be shared;

Finally, a user-data matrix is constructed through several normal access records and access data in the database, and then the association relationship between normal users is obtained based on the user-data matrix, and the data is shared with users who meet the association relationship through the association relationship.

Through the above scheme, this embodiment specifically uses a preset risk assessment model to conduct a risk assessment on the initial shared data to obtain an assessment result; based on the assessment result, the data to be shared is screened to obtain the data to be shared; and the data to be shared is used for data sharing. In this way, the removal of abnormal data is achieved, the problem of the impact of shared data on the security of the operating system is solved, and the security of data sharing is improved.

Referring to FIG. 8 , FIG. 8 is a schematic diagram of a flow chart of matching through a blockchain network in the data sharing method of the present invention.

Based on the embodiment shown in FIG. 5 , the step S022, according to the verification result, matching through the blockchain network to obtain the initial sharing data includes:

Step S0221, obtaining a first keyword and a data acquisition condition according to the verification result;

Step S0222: Match the first keyword through the blockchain network to obtain a data candidate area;

Step S0223: matching the data candidate area with the data acquisition condition to acquire initial sharing data.

Specifically, in order to obtain the initial shared data, the following steps are taken:

First, the data acquisition request is verified through the smart contract to obtain the verification result;

Then, the first keyword of the data to be obtained and the conditions for data acquisition can be obtained through the verification result, wherein the first keyword can be understood as the data most commonly used by the current user, and the acquisition condition should be understood as whether the user has the authority to obtain the data;

Then, the first keyword is matched through the blockchain network to obtain the data candidate area;

Finally, the data acquisition conditions are matched with the data candidate areas to obtain the initial sharing data.

This embodiment adopts the above scheme, specifically, by obtaining the first keyword and data acquisition conditions according to the verification result; matching the first keyword through the blockchain network to obtain the data candidate area; matching the data acquisition conditions according to the data candidate area to obtain the initial shared data. In this way, the acquisition of the initial shared data is achieved, and the problem of multiple different versions of data that are prone to appear in the process of acquiring data, which requires re-selection and increases the workload, is solved, and the efficiency of data sharing is improved.

9 , which is a schematic diagram of a flow chart of obtaining evaluation results in the data sharing method of the present invention.

Based on the embodiment shown in FIG. 7 , in this embodiment, before the step of performing risk assessment on the initial shared data using a preset risk assessment model to obtain an assessment result, the data sharing method further includes:

Step S031, constructing a data set through historical normal data in a preset database to obtain a training set and a test set;

Step S032, inputting the training set into a preset initial risk assessment model for training to obtain a trained initial risk assessment model;

Step S033: input the test set into the trained initial risk assessment model for model prediction to obtain a risk assessment model.

Specifically, in order to distinguish normal data from abnormal data, the following steps are taken:

First, obtain the historical data in the database and mark the abnormal data and normal data in the historical data. After obtaining the historical data, it also includes extracting, cleaning and sorting the historical data. Cleaning the data includes checking and eliminating invalid data in the historical data;

Then, a data set is constructed using normal data in historical data, and the data set is divided into a training set and a test set. The training set is used for model training, and the test set is used for testing the results of the model.

Finally, the improved BP neural network prediction model is trained based on the constructed training set, and the model is tested using the test set to obtain the risk assessment model;

Furthermore, the specific scheme for obtaining the risk assessment model in this embodiment includes:

First, determine the number of nodes in the input layer, hidden layer, and output layer, and build a three-layer network model;

Then, the historical data in the training set is normalized;

Then, the normal data at the previous moment is used as the input parameter, and the predicted data at the current moment is used as the output parameter;

Then, determine the number of output layer nodes, initialize the learning accuracy, determine the maximum number of training times and the learning rate of the training parameters;

Then, the simulated annealing genetic algorithm is used to iteratively obtain the optimized connection weights and neuron thresholds of the BP neural network and bring them into the neural network model;

Finally, retraining is performed based on the BP neural network algorithm, and the error or training times are judged. If the error is less than the learning accuracy or the training times exceed the preset value, the training is terminated to obtain an improved BP neural network model. Otherwise, return to the previous step and continue learning.

Furthermore, the steps of iteratively obtaining the optimized connection weights and neuron thresholds of the BP neural network using the simulated annealing genetic algorithm and introducing them into the neural network model include:

First, select the fitness function. The simulated annealing genetic algorithm describes how to use this function to determine the fitness of individuals in the population and determine whether the individual is selected.

Then, initialize the network parameters and give the training parameters;

Then, the fitness and total fitness of the individuals in the population are calculated, and it is determined whether they have reached the predetermined value. If so, the BP network is used for iterative calculation, and it is determined whether the global error requirement is met. If not, the simulated annealing genetic algorithm is used to evolve the population, and the corresponding selection, crossover and mutation operations are performed on the individuals in the population. The optimal individual retention strategy is used to select excellent individuals to form an excellent group during the reproduction process until the fitness of the group tends to be stable. After completion, the fitness and total fitness of the individuals in the population are recalculated, and it is determined whether they have reached the predetermined value.

Then, after reaching the predetermined value, the BP network is used for iterative calculation to determine whether the global error requirement is met. If so, the population at this time is output to obtain the optimized connection weights and neuron thresholds of the BP neural network. If not, the simulated annealing genetic algorithm is used to evolve the population.

This embodiment uses the above scheme to construct a data set through historical normal data in a preset database to obtain a training set and a test set; the training set is input into a preset initial risk assessment model for training to obtain a trained initial risk assessment model; the test set is input into the trained initial risk assessment model for model prediction to obtain a risk assessment model. Thus, the acquisition of the risk assessment model is realized, the problem of unsafe data in shared data is solved, and the security of data sharing is improved.

Referring to FIG. 10 , FIG. 10 is a flow chart of another exemplary embodiment of a data sharing method of the present invention.

Based on the embodiment shown in FIG. 2 , the step S04 of sharing data using the data to be shared includes:

Step S0361, constructing association rules based on a number of normal user access records and access data in a preset database;

Step S0362: Sharing data using the data to be shared according to the association rule.

Specifically, in order to achieve data sharing, the following steps are taken:

First, in this embodiment, the data sharing method is to share by constructing association rules;

Then, obtain normal user access records and access data in the database. Normal users should be understood as resigned or new employees in a company system. At this time, employee information data exists in the database, but the specific data may not be clear. Normal users refer to normal employees who are currently working and have corresponding data.

Then, association rules are constructed based on the access records and access data of normal users;

Finally, the data to be shared is shared according to the association rules.

This embodiment uses the above solution to build association rules based on normal user access records and access data in a preset database; and uses the data to be shared to share data based on the association rules. This achieves data sharing, solves the problem of multiple different versions of data that are prone to appear in the process of acquiring data, and requires reselection, which increases the workload, and improves the efficiency of data sharing.

Referring to FIG. 11 , FIG. 11 is a schematic diagram of a flow chart of data sharing in the data sharing method of the present invention.

Based on the embodiment shown in FIG. 10 , the step S042 of sharing data through the data to be shared according to the association rule includes:

Step S03621, constructing association relationships between the normal user access records according to the association rule;

Step S03622, screening a number of initial users to be shared according to the association relationship to obtain sharing users;

Step S03623, sharing data with the sharing user through the data to be shared.

Specifically, in order to screen the initial users to be shared, the following steps are adopted:

First, query all normal user access records through association rules to obtain association relationships. There are multiple normal user records. The association relationships can be used to filter the users to be shared and achieve accurate push.

Then, according to the association relationship, a number of users to be shared are screened to obtain the screened users to be shared;

Finally, the data to be shared is pushed through the improved collaborative recommendation algorithm. The collaborative filtering recommendation algorithm is a commonly used recommendation algorithm. It predicts the user's preference for certain items (such as goods, movies, music, etc.) by analyzing the behavior and interests between users, and gives recommendation results. The advantage of the collaborative filtering algorithm is that it can make recommendations based on the user's actual behavior without collecting the user's personal information in advance. It performs well in solving the cold start problem (new users or new items) and is suitable for large-scale recommendation systems. However, the collaborative filtering algorithm also has some challenges, such as data sparsity, gray group problems (user preferences are difficult to capture), and high computational complexity. Therefore, in practical applications, it is also necessary to comprehensively consider other recommendation algorithms and technologies, such as content filtering and deep learning, to improve the recommendation effect and system performance.

Further, the push process is as follows:

First, all data in the data set in the historical database are set as data set I = {Item1, Item2...Itemm), the association rule is X->Y, X, Y are respectively sets of data in data set I, X is the antecedent of the association rule, Y is the consequent of the association rule, and in this embodiment, it is stipulated that the consequent Y contains only one data, and the entire data set is scanned from beginning to end, and each frequent 1-number set, frequent 2-number set, frequent 3-number set, frequent 4-number set and frequent 5-number set and their corresponding consequent data are determined in turn (in order to simplify the calculation, only the 5-number set is considered here), so as to determine the association relationship between the data and determine its support and confidence;

Then, according to the determined association relationship, the target user's target data is the consequence of the association relationship, and the association relationship existing in the target user's data is analyzed. The existing 5-number sets, 4-number sets, and 3-number sets and the corresponding association relationships are searched in turn, and finally all the found number sets are placed in the user's candidate set. In order to simplify the calculation, 2-number sets, 1-number sets and the corresponding association relationships will no longer be considered. If the target user does not have a 5-number set, 4-number set, or 3-number set with an association relationship, the association relationship will not be considered, and the similarity between the user in the matrix and the target user will be directly calculated;

Then, if the support of the association rule in the candidate set is greater than 20% and the confidence is greater than 20%, the users corresponding to the qualified association relationship are determined as similar users of the target user (repeated similar users are used only once). The similarity between these similar users and the target user is calculated, and the similarity is sorted in descending order. The similarity calculation formula is as follows:

In the formula, Sia and Sja represent the number of times user i and user j visit data a, n represents the total number of users, d represents a preset integer value, in this embodiment d=2, m represents the total number of data, where it should be noted that the existing collaborative recommendation algorithm is often used for product recommendation, and the collaborative recommendation algorithm based on user access situation mines according to the user's access records when recommending products, however, a large number of users may not necessarily purchase products when they visit them, and the user's access to some products is accidental, so the mined user preferences are not completely true and reliable, and the accuracy of the recommendation results cannot be guaranteed. Therefore, when using the collaborative recommendation algorithm to recommend the required data for users, the application adopts the method of screening the normal data of the access records and access data to construct the user-data matrix, uses the improved similarity calculation method to calculate the similarity between users, and combines the correlation between the user access data to predict and recommend the required data of the target user;

Finally, select the N users with the greatest similarity as the nearest neighbors, calculate the results of TOP-N recommendations for the target user based on their corresponding similarities and the number of visits by the user, and complete the recommendation in combination with the required data after screening. The calculation formula is as follows:

In the formula, Nc represents the user set of the nearest neighbors of user C (target user), the predicted number of visits of user C to data h is Sch, Snh represents the known number of visits of the nearest neighbor N to data h, Represents the average number of visits by user C and user N.

This embodiment uses the above scheme to build associations between the normal user access records according to the association rules; screens the initial users to be shared according to the associations to obtain shared users; and shares data with the shared users through the data to be shared. This achieves data sharing, solves the problem of multiple different versions of data that are prone to appear in the process of acquiring data, and requires reselection, which increases the workload, and improves the efficiency of data sharing.

In addition, an embodiment of the present invention further provides a data sharing device, the data sharing device comprising:

A receiving module, used for receiving a request for obtaining shared data;

An acquisition module, used to acquire initial shared data through a blockchain network according to the shared data acquisition request;

The sharing module is used to screen the initial sharing data through a preset risk assessment model, obtain the data to be shared and share the data to be shared.

In addition, an embodiment of the present invention also proposes a terminal device, which includes a memory, a processor, and a data sharing program stored in the memory and executable on the processor, and the data sharing program implements the steps of the data sharing method described above when executed by the processor.

Since all the technical solutions of all the aforementioned embodiments are adopted when the data sharing program is executed by the processor, it has at least all the beneficial effects brought by all the technical solutions of all the aforementioned embodiments, which will not be described one by one here.

In addition, an embodiment of the present invention further proposes a computer-readable storage medium, on which a data sharing program is stored. When the data sharing program is executed by a processor, the steps of the data sharing method described above are implemented.

Since all the technical solutions of all the aforementioned embodiments are adopted when the data sharing program is executed by the processor, it has at least all the beneficial effects brought by all the technical solutions of all the aforementioned embodiments, which will not be described one by one here.

Compared with the prior art, the data sharing method, device, terminal device and storage medium proposed in the embodiment of the present invention receive a request for obtaining shared data; according to the request for obtaining shared data, obtain initial shared data through the blockchain network; screen the initial shared data through a preset risk assessment model, obtain the data to be shared and share the data to be shared. This solves the problem that multiple different versions of data are prone to appear in the process of obtaining data, which requires selection again and increases the workload, realizes data sharing, and improves the efficiency of data sharing. Based on the scheme of the present invention, starting from the problem that multiple different versions of data are prone to appear in the process of obtaining data in reality, which requires selection again and increases the workload, a data sharing method is designed, and the effectiveness of the data sharing method of the present invention is verified in actual data sharing. Finally, the efficiency of data sharing through the method of the present invention is significantly improved.

Compared with the existing technology, the embodiment of the present invention has the following advantages:

1. This application receives the user's data acquisition request and verifies the user's operation authority, obtains the required data using the block that matches the data acquisition request, and uses the pre-built risk assessment model to conduct risk assessment on the required data to determine the credibility of the data;

2. The improved collaborative filtering recommendation algorithm based on user access records is used to recommend the required data to users and realize data sharing. Compared with the traditional blockchain data sharing method, the present invention can not only perform risk assessment on the required data and filter out abnormal data, but also recommend the corresponding required data to the target users based on the user's access records, thereby better meeting the data sharing needs of multiple parties.

It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) as above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, a controlled terminal, or a network device, etc.) to execute the method of each embodiment of the present invention.

The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims (10)

1. A data sharing method, characterized in that the data sharing method includes the following steps: Receive shared data acquisition requests; According to the shared data acquisition request, obtain initial shared data through the blockchain network; The initial shared data is screened through a preset risk assessment model, the data to be shared is obtained, and the data to be shared is shared. 2. The data sharing method according to claim 1, wherein the step of obtaining initial shared data through a blockchain network according to the shared data acquisition request includes: According to the shared data acquisition request, verify the user's operating authority through the preset contract and obtain the verification result; According to the verification results, matching is performed through the blockchain network to obtain initial sharing data. 3. The data sharing method according to claim 1, wherein the steps of screening the initial shared data through a preset risk assessment model, obtaining the data to be shared and sharing the data to be shared include: Conduct a risk assessment on the initial shared data through a preset risk assessment model and obtain the assessment results; According to the evaluation results, filter the data to be shared and obtain the data to be shared; Use the data to be shared for data sharing. 4. The data sharing method according to claim 2, characterized in that the step of matching through the blockchain network according to the verification result and obtaining the initial shared data includes: According to the verification result, obtain the first keyword and data acquisition conditions; Through the blockchain network, match the first keyword and obtain the data candidate area; According to the data candidate area, matching is performed through the data acquisition conditions to obtain initial shared data. 5. The data sharing method according to claim 3, wherein the step of performing a risk assessment on the initial shared data through a preset risk assessment model, and obtaining the assessment result further includes: Through the historical normal data in the preset database, construct the data set and obtain the training set and test set; Input the training set into the preset initial risk assessment model for training, and obtain the trained initial risk assessment model; The test set is input into the trained initial risk assessment model for model prediction to obtain a risk assessment model. 6. The data sharing method according to claim 3, wherein the step of using the data to be shared for data sharing includes: Build association rules based on several normal user access records and access data in the preset database; According to the association rules, data sharing is performed through the data to be shared. 7. The data sharing method according to claim 6, wherein the step of sharing data through the data to be shared according to the association rules includes: According to the association rules, construct an association relationship between the several normal user access records; According to the association relationship, screen a number of initial users to be shared to obtain shared users; Data sharing is performed with the sharing users through the data to be shared. 8. A data sharing device, characterized in that the data sharing device includes: The receiving module is used to receive shared data acquisition requests; An acquisition module, configured to acquire initial shared data through the blockchain network according to the shared data acquisition request; A sharing module is used to filter the initial sharing data through a preset risk assessment model, obtain the data to be shared, and share the data to be shared. 9. A terminal device, characterized in that the terminal device includes a memory, a processor, and a data sharing program stored on the memory and executable on the processor, and the data sharing program is processed by the When the server is executed, the steps of the data sharing method according to any one of claims 1-7 are implemented. 10. A computer-readable storage medium, characterized in that a data sharing program is stored on the computer-readable storage medium, and when the data sharing program is executed by a processor, the data sharing program implements any one of claims 1-7 The steps of the data sharing method.