Big Data Operation Supervision Platform Based on Smart Government Affairs

Abstract

The present application provides a big data operation supervision platform based on intelligent government affairs, which relates to the field of data processing technology and is used to improve the accuracy and efficiency of government affairs supervision. The operation supervision platform includes: a plurality of business processing modules, a data processing module, a data security module, and a data storage module divided according to geographical administrative regions; the business processing module is used to receive a government affairs processing request initiated by a user client, and the government affairs processing request includes user data and business request data; the data security module is used to perform security detection on the user data and the business request data; the data processing module is used to verify the user data and the business request data and extract key information; the business processing module is used to perform government affairs processing according to the key information; the data storage module is used to store the processing result and transmit the address of the stored processing result to the user client, so that the user client can view the processing result according to the address.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly to a big data operation supervision platform based on smart government affairs. Background Art

[0002] The government service platform is built and operated by government departments, aiming to provide convenient online government services for enterprises and individuals. These platforms usually cover various government services, such as marriage registration, transportation, education examinations, tax payment, social security, certificate handling, professional qualifications, public security, judicial notarization, medical and health care, education and research, and employment and entrepreneurship. For example, the National Government Service Platform provides local government service windows to facilitate the public to query and use government services in various places. Through these platforms, the public can obtain various services and information provided by the government more conveniently, greatly improving the handling efficiency and satisfaction.

[0003] Due to reasons such as different data sources and collection methods, there are problems such as inaccurate, incomplete, and duplicate government data, which need to be cleaned and optimized. Currently, it is difficult to effectively clean the corresponding government data, and it is impossible to conduct supervision and analysis of data cleaning and early warning reminders for cleaning timeliness. It is difficult for the corresponding management personnel to clean the data of the corresponding government service system in a timely and efficient manner, resulting in the accuracy and efficiency of government supervision. Summary of the Invention

[0004] The embodiment of this application provides a big data operation supervision platform based on smart government affairs, which is used to improve the accuracy and efficiency of government supervision.

[0005] The embodiment of the present invention provides a big data operation supervision platform based on smart government affairs. The supervision platform includes: a plurality of business processing modules, a data processing module, a data security module, and a data storage module divided according to the territorial administrative region; the data processing module, the data security module, and the data storage module are communicatively connected to the business processing module;

[0006] The business processing module is used to receive a government affairs processing request initiated by a user client. The government affairs processing request includes user data and business request data, and transmits the government affairs processing request to the data security module;

[0007] The data security module is used to perform security detection on the user data and the business request data, and transmit the user data and the business request data that pass the detection to the data processing module;

[0008] The data processing module is used to verify the user data and the business request data and extract key information, and transmit the extracted key information to the business processing module;

[0009] The business processing module is used to perform government affairs processing according to the key information and transmit the processing result to the data storage module;

[0010] The data storage module is used to store the processing result and transmit the address where the processing result is stored to the user client, so that the user client can view the processing result according to the address.

[0011] In an optional embodiment provided by the present invention, the data security module includes:

[0012] A matching unit that matches the user data and the service request data through the data rules in the normal data rule library and the abnormal data rule library;

[0013] A determining unit, if the user data and the service request data match the data in the normal data rule library, it is determined that the security detection of the user data and the service request data passes; if the user data or the service request data matches the data in the abnormal data rule library, it is determined that the security detection of the user data and the service request data fails;

[0014] A prediction unit is used to obtain user data and service request data that do not match both the normal data rule library and the abnormal data rule library, and input the obtained user data and service request data into a security recognition model to obtain a security detection prediction result.

[0015] In an optional embodiment provided by the present invention, the prediction unit is specifically used for:

[0016] Convert user data and service request data that do not match both the normal data rule library and the abnormal data rule library into target feature vectors;

[0017] Obtain the top N feature vectors with the highest similarity to the target feature vector within a predetermined time period from the feature vector library, and the feature vector library stores feature vectors corresponding to multiple historical government affairs processing requests;

[0018] Combine the target feature vector and the N feature vectors to obtain a feature vector matrix;

[0019] Input the feature vector matrix into the security recognition model to obtain a security detection prediction result.

[0020] In an optional embodiment provided by the present invention, the data security module further includes a training unit, and the training unit is specifically used for:

[0021] Obtain N + 1 sample feature vectors with similarity exceeding a preset value, form a feature sample vector matrix with the obtained N + 1 sample feature vectors, and determine the sample labels corresponding to the sample feature vector matrix;

[0022] Input the sample feature vector matrix into the security recognition model to obtain a security detection prediction result;

[0023] Calculate a loss value according to the security detection prediction result and the sample labels;

[0024] When the loss value is less than the target loss value, complete the training of the security recognition model.

[0025] In an optional embodiment provided by the present invention, the data processing module includes:

[0026] A verification unit for performing rule matching on the user data and the service request data to determine whether the user data and the service request data pass the verification;

[0027] An information extraction unit for, if the user data and the service request data pass the verification, filtering abnormal data from the user data and the service request data and extracting key information through information extraction.

[0028] In an optional embodiment provided by the present invention, the information extraction unit is specifically configured to:

[0029] Segment the filtered user data and service request data;

[0030] Perform first keyword extraction on the segmentation result through a conventional thesaurus and second keyword extraction on the segmentation result through a government affairs thesaurus, and generate a summary of the extracted keywords in combination with context analysis to obtain the key information.

[0031] In an optional embodiment provided by the present invention, the information extraction unit is specifically configured to:

[0032] Segment the filtered user data and service request data, perform first keyword extraction on the segmentation result through a conventional thesaurus and second keyword extraction on the segmentation result through a government affairs thesaurus;

[0033] Generate a keyword feature vector according to the order and quantity of the extracted keywords in the original text;

[0034] Input the keyword feature vector into a summary generation model to obtain the key information.

[0035] In an optional embodiment provided by the present invention, the data storage module includes:

[0036] A storage location determination unit determines a storage location according to the regional administrative area corresponding to the government affairs processing request;

[0037] An encryption unit is used to encrypt the processing result according to the encryption method corresponding to the regional administrative area;

[0038] A storage unit stores the encrypted processing result according to the storage node corresponding to the storage location.

[0039] In an optional embodiment provided by the present invention, the encryption unit is specifically configured to:

[0040] Obtain the region - unique code of the regional administrative area corresponding to the government affairs processing request;

[0041] Encrypt the processing result through the region - unique code and the government - affairs - unique number corresponding to the government affairs processing request.

[0042] The present invention provides a big - data operation supervision platform based on intelligent government affairs. The supervision platform includes: a plurality of business processing modules, data processing modules, data security modules, and data storage modules divided according to regional administrative areas; the data processing module, the data security module, and the data storage module are communicatively connected to the business processing module. The business processing module is used to receive a government affairs processing request initiated by a user client. The government affairs processing request includes user data and business request data, and transmits the government affairs processing request to the data security module; the data security module is used to perform security detection on the user data and business request data, and transmit the user data and business request data that pass the detection to the data processing module; the data processing module is used to verify the user data and business request data and extract key information, and transmit the extracted key information to the business processing module; the business processing module is used to perform government affairs processing according to the key information and transmit the processing result to the data storage module; the data storage module is used to store the processing result and transmit the address of the stored processing result to the user client, so that the user client can view the processing result according to the address. Compared with the existing situation where it is difficult for managers to clean up the data of the corresponding government service system in a timely and efficient manner, after receiving the government affairs processing request, this application first performs security verification and data processing on the data included in the government affairs processing request through the data security module and the data processing module, and then performs business processing on the processed data through the business processing module. Thus, this application can improve the processing efficiency and security of government affairs data, and further improve the accuracy and efficiency of government affairs supervision. Description of the Drawings

[0043] Figure 1Structural block diagram of the big data operation supervision platform based on smart government affairs provided by this application;

[0044] Figure 2 Flowchart of the big data operation supervision platform based on smart government affairs provided by this application;

[0045] Figure 3 Training flowchart of a security recognition model provided by this application. Detailed implementation manners

[0046] To better understand the above technical solutions, the technical solutions of the embodiments of this application will be described in detail below through the accompanying drawings and specific embodiments. It should be understood that the specific features in the embodiments of this application and the embodiments are detailed descriptions of the technical solutions of the embodiments of this application, rather than limitations on the technical solutions of this application. Without conflict, the technical features in the embodiments of this application and the embodiments can be combined with each other.

[0047] As Figure 1 shown, this embodiment provides a big data operation supervision platform based on smart government affairs. The supervision platform includes: multiple business processing modules, a data processing module, a data security module, and a data storage module divided according to the administrative regions by region; the data processing module, the data security module, and the data storage module are communicatively connected to the business processing module.

[0048] The big data operation supervision platform based on smart government affairs in this embodiment aims to improve the work efficiency and service level of the government and facilitate the life and handling of affairs of enterprises and the public. This operation supervision platform realizes information sharing and business collaboration across departments, levels, and regions by integrating multiple government functions and services, thereby effectively improving the convenience and response speed of government services.

[0049] Among them, the business processing module mainly processes various non-emergency demands of enterprises and the public, such as consultations, requests for help, complaints, reports, and suggestions for opinions in the fields of economic regulation, market supervision, social management, public services, ecological environment protection, etc. For example, in this embodiment, according to the types of processing services of the business processing module, the business processing module can be divided into three categories, namely, consultation and request for help: the government service platform provides round-the-clock services, answers questions of enterprises and citizens in aspects such as economy, law, and administration, and provides necessary support and guidance when asking for help; complaints and reports: the public can file complaints and reports about the improper behaviors of government departments or enterprises through this platform, and the platform will handle them according to regulations and feedback the results; opinions and suggestions: the public is encouraged to put forward opinions and suggestions on government policies and service projects to improve and perfect the content and methods of government services.

[0050] The data processing module can be used for: purifying the original data, removing incorrect and inconsistent data to ensure data quality. This step includes removing duplicate records, correcting incorrect data, and filling in missing data, etc.; verifying the accuracy and integrity of the data through association and comparison to ensure higher credibility when the data is further analyzed and applied; merging data from different departments and sources to form a unified data resource pool, which usually requires solving problems such as inconsistent data formats and ambiguous semantics; for the convenience of data sharing and use, it is necessary to standardize the data, including formulating unified coding rules, data formats, and interface standards, etc.

[0051] The data security module is used to detect sensitive words and abnormal words contained in the data, and determine whether the data aggregation contains network security risks such as cyber attacks, network threats, malicious code injection, distributed denial of service attacks, phishing websites, etc.

[0052] Combined with Figure 1 For the publicly available big data operation supervision platform based on smart government affairs, this embodiment provides a big data operation supervision method based on smart government affairs. As Figure 2 shown, this method includes steps S101 - S106, and the detailed content of each step is as follows:

[0053] S101, The business processing module receives the government affairs processing request initiated by the user client. The government affairs processing request includes user data and business request data, and transmits the government affairs processing request to the data security module.

[0054] Among them, the user data includes name, identity identification, contact address, contact phone number, etc., and the business request data includes descriptive data input by the user, business data requested to be processed, etc. This embodiment does not make specific limitations on this.

[0055] The government affairs processing request in this embodiment can be services such as administrative approval, public services, electronic licenses, and performance supervision, which cover the coordinated online handling of 5 - level upper - line linkage departments including autonomous regions, cities, counties (districts), townships (sub - districts), and villages (communities).

[0056] S102, The data security module performs security detection on the user data and business request data, and transmits the user data and business request data that pass the detection to the data processing module.

[0057] In this embodiment, the data security module mainly performs security detection on the government affairs processing request initiated by the user client, such as cyber attacks, network threats, malicious code injection, etc. This embodiment does not make specific limitations on this.

[0058] In an alternative embodiment provided by the present application, the data security module includes: a matching unit, a determining unit, and a predicting unit. The description of each unit is as follows:

[0059] The matching unit is configured to match the user data and the service request data through the data rules in the normal data rule library and the abnormal data rule library. Among them, the normal data rule library stores the data rules corresponding to various types of data. If the user data and the service request data match the data rules in the normal data rule library successfully, it indicates that the user data and the service request data are normal. The abnormal data rule library stores abnormal data rules or abnormal keywords, sensitive words, etc. If the user data and the service request data match the rules or keywords in the abnormal data rule library, it indicates that the user data and the service request data are abnormal.

[0060] The determining unit, if the user data and the service request data match the data in the normal data rule library, determines that the security detection of the user data and the service request data passes; if the user data or the service request data matches the data in the abnormal data rule library, determines that the security detection of the user data and the service request data fails.

[0061] The predicting unit is configured to obtain user data and service request data that do not match both the normal data rule library and the abnormal data rule library, and input the obtained user data and service request data into the security recognition model to obtain a security detection prediction result.

[0062] Specifically, the predicting unit is configured to: convert the user data and the service request data that do not match both the normal data rule library and the abnormal data rule library into target feature vectors; obtain the top N feature vectors with the highest similarity to the target feature vector within a predetermined time period from the feature vector library, where the feature vector library stores the feature vectors corresponding to multiple historical government affairs processing requests; combine the target feature vector and the N feature vectors to obtain a feature vector matrix; input the feature vector matrix into the security recognition model to obtain a security detection prediction result.

[0063] It should be noted that for the initiated network attacks (such as distributed denial of service), the network data or service request data corresponding to most of the attack targets are similar. Therefore, in this embodiment, the N feature vectors with the highest similarity rankings to the target feature vector within a predetermined time period can be obtained, and then whether there is a network security risk is jointly confirmed based on the obtained N feature vectors and the target feature vector. That is, the target feature vector and the N feature vectors are combined to obtain a feature vector matrix; the feature vector matrix is input into the security recognition model to obtain a security detection prediction result. Since the security recognition model is trained through a large number of sample data, inputting the obtained feature vector matrix into this security recognition model can obtain a security detection prediction result.

[0064] In this embodiment, the data security module further includes a training unit, such as Figure 2 The training unit shown is used to train the security recognition model, and the training process of this security recognition model is specifically used to perform the following steps:

[0065] S201, Obtain N + 1 sample feature vectors whose similarity exceeds a preset value, and form a feature sample vector matrix with the obtained N + 1 sample feature vectors, and determine the sample label corresponding to the sample feature vector matrix.

[0066] Among them, the preset value is a value set according to actual needs. The sample label includes the sample label corresponding to the (N + 1)-th sample feature vector, and this sample label includes safe and unsafe.

[0067] In this embodiment, to solve the problem of less sample data, in this embodiment, the feature sample vector matrix is determined by different combinations of sample feature vectors. The combined feature sample vector matrix only needs to ensure that the similarity between each sample feature vector within the combination exceeds the preset value. Therefore, through this embodiment, multiple sample feature vectors can be obtained based on different combinations of sample feature vectors, thereby expanding the quantity of sample data and further improving the training accuracy of the security recognition model.

[0068] S202, Input the sample feature vector matrix into the security recognition model to obtain a security detection prediction result.

[0069] S203, Calculate the loss value according to the security detection prediction result and the sample label.

[0070] The loss value is calculated through the following formula:

[0071] ;

[0072] Among them, is the similarity between the target feature vector and the i-th feature vector, is the security detection prediction result of the target feature vector, is the sample label of the target feature vector, is a constant coefficient.

[0073] S204. When the loss value is less than the target loss value, the training of the security recognition model is completed.

[0074] Among them, the target loss value is a set target value. By comparing the relationship between the loss value and the target loss value, it is determined whether to stop the training task of the security recognition model.

[0075] For the training of a security recognition model provided in this embodiment, first, the obtained N + 1 sample feature vectors are formed into a feature sample vector matrix, and then the sample feature vector matrix is input into the security recognition model to obtain the security detection prediction result. The loss value is calculated according to the security detection prediction result and the sample label. When the loss value is less than the target loss value, the training of the security recognition model is completed. Since in this embodiment, the feature sample vector matrix is determined by different combinations of sample feature vectors, and the combined feature sample vector matrix only needs to ensure that the similarity between each sample feature vector within the combination exceeds a preset value. Therefore, through this embodiment, multiple sample feature vectors can be obtained based on different combinations of sample feature vectors, thereby expanding the quantity of sample data.

[0076] S103. The data processing module verifies the user data and the service request data and extracts key information, and transmits the extracted key information to the service processing module.

[0077] In this embodiment, the data processing module includes: a verification unit and an information extraction unit. Among them, the verification unit is used to perform rule matching on the user data and the service request data to determine whether the user data and the service request data pass the verification. For example, for the identity identification field, it is determined whether the number of digits of the identity identification in the user data meets the requirements, and whether they are all numbers or whether the last digit is a letter that meets the rules. The information extraction unit is used to, if the user data and the service request data pass the verification, filter out abnormal data from the user data and the service request data, and perform information extraction to obtain key information.

[0078] In an optional embodiment provided in this application, the information extraction unit is specifically used to perform word segmentation on the filtered user data and service request data; perform first keyword extraction on the word segmentation result through a conventional thesaurus and perform second keyword extraction on the word segmentation result through a government affairs thesaurus, and generate a summary of the extracted keywords by combining context analysis to obtain the key information.

[0079] Further, the information extraction unit is specifically configured to segment the filtered user data and the service request data, perform first keyword extraction on the segmentation result through a general vocabulary and perform second keyword extraction on the segmentation result through a government affairs vocabulary; generate a keyword feature vector according to the order and quantity of the extracted keywords in the original text; and input the keyword feature vector into a summary generation model to obtain the key information.

[0080] Among them, common keywords are stored in the general vocabulary, and the words matching the keywords in the general vocabulary are first keywords. Keywords related to government affairs-related services are stored in the government affairs vocabulary, and the words matching the keywords in the government affairs vocabulary are second keywords. After the first keyword and the second keyword are extracted in this embodiment, the word frequencies of the first keyword and the second keyword are respectively determined, and the weight value of each keyword is determined based on the word frequency. The greater the word frequency, the greater the corresponding weight value.

[0081] The keyword feature vector corresponding to the first keyword is ;

[0082] The keyword feature vector corresponding to the second keyword is .

[0083] Among them, n is the quantity of the first keywords, m is the total quantity of the second keywords, is the vector of the nth first keyword, is the position of the nth first keyword, is the weight or word frequency of the nth first keyword; is the vector of the mth second keyword, is the position of the mth second keyword, is the weight or word frequency of the mth second keyword.

[0084] After the keyword feature vectors of the first keyword and the second keyword are obtained in this embodiment, the keyword feature vectors are input into a summary generation model to obtain the key information. Among them, the summary generation model is trained according to sample data (a piece of text description data, which includes user data and service request data) and sample labels. The sample data is the keyword feature vectors of the first keyword and the second keyword determined by the above method, and the sample label is the text summary corresponding to the sample data.

[0085] S104. The service processing module performs government affairs processing according to the key information and transmits the processing result to the data storage module.

[0086] The business processing module is a module for processing business. This module can use a human-computer interaction interface, that is, obtain the processing results of the government approval personnel or government affairs processing personnel for the key information through the human-computer interaction interface; or directly perform government affairs processing on the key information based on preset approval rules to obtain the processing results.

[0087] S105, the data storage module stores the processing results and transmits the address where the processing results are stored to the user client, so that the user client can view the processing results according to the address.

[0088] In this embodiment, the data storage module includes: a storage location determination unit, an encryption unit, and a storage unit. The functions of each unit are as follows: The storage location determination unit is used to determine the storage location according to the regional administrative area corresponding to the government affairs processing request; the encryption unit is used to encrypt the processing results according to the encryption method corresponding to the regional administrative area; the storage unit is used to store the encrypted processing results according to the storage node corresponding to the storage location.

[0089] In an optional embodiment provided by this application, the encryption unit is specifically used to obtain the unique regional code of the regional administrative area corresponding to the government affairs processing request; encrypt the processing results through the unique regional code and the unique government affairs number corresponding to the government affairs processing request.

[0090] Furthermore, after transmitting the address where the processing results are stored to the user client in this embodiment, the encrypted secret key is sent to the user client, such as sent to the user client by means of text message or email, etc. After receiving the secret key, the user client decrypts the encrypted processing results with the secret key to view the processing results corresponding to the government affairs processing request initiated by it.

[0091] The big data operation supervision platform based on intelligent government affairs provided by the embodiments of the present application includes: a plurality of business processing modules, a data processing module, a data security module, and a data storage module divided according to regional administrative regions; the data processing module, the data security module, and the data storage module are communicatively connected to the business processing module. The business processing module is used to receive a government affairs processing request initiated by a user client, where the government affairs processing request includes user data and business request data, and transmit the government affairs processing request to the data security module; the data security module is used to perform security detection on the user data and business request data, and transmit the user data and business request data that pass the detection to the data processing module; the data processing module is used to verify the user data and business request data and extract key information, and transmit the extracted key information to the business processing module; the business processing module is used to perform government affairs processing according to the key information and transmit the processing result to the data storage module; the data storage module is used to store the processing result and transmit the address where the processing result is stored to the user client, so that the user client can view the processing result according to the address. Compared with the existing situation where it is difficult for managers to clean up the data of the corresponding government affairs service system in a timely and efficient manner, after receiving the government affairs processing request, the present application first performs security verification and data processing on the data included in the government affairs processing request through the data security module and the data processing module, and then performs business processing on the processed data through the business processing module. Therefore, the present application can improve the processing efficiency and security of government affairs data, and further improve the accuracy and efficiency of government affairs supervision.

[0092] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0093] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A big data operation and supervision platform based on smart government affairs, characterized by: The supervision platform includes: multiple business processing modules, data processing modules, data security modules and data storage modules divided according to geographical administrative regions; the data processing modules, data security modules and data storage modules are connected in communication with the business processing modules; The business processing module is used to receive the government affairs processing request initiated by the user client, the government affairs processing request includes user data and business request data, and transmit the government affairs processing request to the data security module; The data security module is used to perform security checks on user data and service request data, and transmit the user data and service request data that have passed the check to the data processing module; The data processing module is used to verify the user data and business request data and extract key information, and transmit the extracted key information to the business processing module; The business processing module is used to process government affairs according to key information and transmit the processing results to the data storage module; A data storage module is used to store the processing results and transmit the address where the processing results are stored to the user client so that the user client can view the processing results according to the address; The data security module includes: A matching unit matches user data and business request data using data rules in a normal data rule base and an abnormal data rule base; A determination unit, if the user data or the service request data matches the data in the abnormal data rule base, determines that the user data and the service request data fail the security detection; A prediction unit, used to obtain user data and service request data that do not match the normal data rule base and the abnormal data rule base, and input the obtained user data and service request data into the security identification model to obtain a security detection prediction result; The prediction unit is specifically used for: Converting user data and business request data that do not match both the normal data rule base and the abnormal data rule base into a target feature vector; Obtaining N feature vectors with the highest similarity ranking with the target feature vector within a predetermined time period from a feature vector library, wherein the feature vector library stores feature vectors corresponding to multiple historical government affairs processing requests; Combine the target eigenvector and N eigenvectors to obtain an eigenvector matrix; Input the feature vector matrix into the security identification model to obtain the security detection prediction result; The data security module also includes a training unit, which is used to: Obtain N+1 sample feature vectors whose similarity exceeds a preset value, and form a feature sample vector matrix with the obtained N+1 sample feature vectors, and determine the sample label corresponding to the sample feature vector matrix; Input the sample feature vector matrix into the security identification model to obtain the security detection prediction result; Calculate the loss value based on the safety test prediction results and sample labels; When the loss value is less than the target loss value, the training of the security recognition model is completed.

2. The supervision platform according to claim 1, characterized in that: Data processing module, including: A verification unit, used to match the user data and the service request data with rules to determine whether the user data and the service request data have been verified; The information extraction unit is used to filter abnormal data of the user data and the service request data and extract key information if the user data and the service request data are verified.

3. The supervision platform according to claim 2, characterized in that: The information extraction unit is specifically used for: Segment the filtered user data and business request data; The first keyword is extracted from the word segmentation result through the conventional vocabulary, and the second keyword is extracted from the word segmentation result through the government vocabulary, and the extracted keywords are summarized and generated in combination with context analysis to obtain key information.

4. The supervision platform according to claim 3, characterized in that: The information extraction unit is specifically used for: Segmenting the filtered user data and business request data, extracting first keywords from the segmentation results through a conventional word library, and extracting second keywords from the segmentation results through a government word library; Generate a keyword feature vector according to the order and quantity of the extracted keywords in the original text; Input the keyword feature vector into the summary generation model to obtain key information.

5. The supervision platform according to claim 1, characterized in that: Data storage module, including: A storage location determination unit, which determines a storage location according to a geographical administrative region corresponding to the government affairs processing request; An encryption unit, used to encrypt the processing result according to an encryption method corresponding to the regional administrative area; The storage unit stores the encrypted processing result according to the storage node corresponding to the storage location.

6. The supervision platform according to claim 5, characterized in that: The encryption unit is specifically used for: Get the unique regional code of the geographical administrative area corresponding to the government affairs processing request; The processing result is encrypted using the unique regional code and the unique government number corresponding to the government processing request.

Images