A method and system for identifying grassroots governance event types

Abstract

The present invention provides a method and system for identifying the type of grassroots governance events, comprising: determining a new grassroots event to be analyzed; inputting the new grassroots event to be analyzed into a trained event analysis model to obtain an event type identification result; wherein the event analysis model is obtained by constructing a dynamically updated event classification vocabulary, an event processing unit correspondence library, and an event handling measure library based on grassroots historical event data. The present invention establishes an analysis model by integrating event content, an event classification vocabulary, an event handling unit correspondence library, and an event type handling measure library. The model is applied to grassroots streets and communities to handle grassroots governance issues, realizes intelligent identification of event types, analyzes event handling departments, recommends handling measures, effectively supports the rapid handling and resolution of grassroots events, promotes the improvement of grassroots governance efficiency, provides scientific and effective new ideas and means for grassroots governance, can effectively reduce event handling time, and improve event handling efficiency.

Description

Technical Field

[0001] The present invention relates to the field of big data application technology, and in particular to a method and system for identifying grassroots governance event types. Background Art

[0002] Grassroots governance is prevalent in many public affairs and is an important part of building the governance system and governance capacity.

[0003] Due to the complexity and diversity of grassroots incidents, the insufficient governance level of grassroots staff, and the dispersion of grassroots governance functions among different levels and different management departments, two separate management models have been formed: territorial management based on "blocks" and departmental management based on "lines". This makes it difficult for grassroots workers to quickly identify incident problems, clearly identify solution units, and take disposal measures, exposing the shortcomings of grassroots governance capabilities.

[0004] Therefore, it is necessary to propose a new method for identifying grassroots governance event types that can solve the above problems. Summary of the Invention

[0005] The present invention provides a method and system for identifying grassroots governance event types to address the defects in the prior art.

[0006] In a first aspect, the present invention provides a method for identifying grassroots governance event types, comprising:

[0007] Identify new grassroots events to be analyzed;

[0008] The new grassroots event to be analyzed is input into the trained event analysis model to obtain the event type recognition result; wherein, the event analysis model is obtained by constructing a dynamically updated event classification vocabulary library, event processing unit correspondence library and event handling measures library based on grassroots historical event data.

[0009] In one embodiment, the event analysis model is obtained by the following steps:

[0010] Obtaining the grassroots historical event data;

[0011] Extract any historical event from the grassroots historical event data, and use a preset prediction analysis algorithm to fit the event type, event classification word, and actual risk result of the any historical event to obtain a first probability set of the occurrence of the event classification word;

[0012] Constructing the event classification vocabulary, the event processing unit correspondence library, and the event handling measures library based on the first probability set;

[0013] Extracting any other historical event other than the any historical event from the grassroots historical event data, and fitting the any other historical event based on the preset prediction analysis algorithm to obtain a second probability set;

[0014] Processing the first probability set based on the second probability set to obtain an initial event analysis model;

[0015] Acquire grassroots new event data, and continuously update the initial event analysis model based on the grassroots new event data to obtain the event analysis model.

[0016] In one embodiment, the extracting of any historical event from the grassroots historical event data uses a preset prediction analysis algorithm to fit the event type, event classification word, and actual risk result of the any historical event to obtain a first probability set of occurrence of the event classification word, including:

[0017] Obtaining the event type of any of the historical events, wherein the event type includes the event time, event content, and event reporter;

[0018] Using a nonlinear artificial intelligence prediction analysis algorithm, the event type, the event classification word and the actual situation are analyzed to obtain a first sub-probability;

[0019] Analyze the event type, event handling unit, and actual situation to obtain a second sub-probability;

[0020] The event type, event handling measures, and the actual situation are analyzed to obtain a third sub-probability.

[0021] In one embodiment, constructing the event classification vocabulary, the event processing unit correspondence library, and the event handling measures library based on the first probability set includes:

[0022] Extracting event classification words corresponding to the first sub-probability being greater than a preset probability threshold, and constructing the event classification word library;

[0023] Extracting event handling units corresponding to the second sub-probability being greater than the preset probability threshold, and constructing a corresponding relationship database of the event handling units;

[0024] Event handling measures corresponding to the third sub-probability being greater than the preset probability threshold are extracted to construct the event handling measure library.

[0025] In one embodiment, extracting any other historical event from the grassroots historical event data except the any historical event, and fitting the any other historical event based on the preset prediction analysis algorithm to obtain a second probability set includes:

[0026] Obtaining the event type of any other historical event, wherein the event type includes the event time, event content, and event reporter;

[0027] Using the nonlinear artificial intelligence prediction analysis algorithm, the event type, the event classification word and the actual situation are analyzed to obtain a fourth sub-probability;

[0028] Analyze the event type, event handling unit, and actual situation to obtain a fifth sub-probability;

[0029] The event type, event handling measures, and the actual situation are analyzed to obtain a sixth sub-probability.

[0030] In one embodiment, the processing the first probability set based on the second probability set to obtain an initial event analysis model includes:

[0031] Correcting and verifying the first probability set by the second probability set to obtain an optimal probability calculation algorithm;

[0032] Based on the optimal probability calculation algorithm, the initial event analysis model is established.

[0033] In one embodiment, the acquiring of the base-level newly added event data and the continuously updating of the initial event analysis model based on the base-level newly added event data to obtain the event analysis model include:

[0034] Extracting the first keyword from the grassroots newly added event data;

[0035] Based on the first keyword, searching the event classification thesaurus, the event processing unit correspondence library, and the event handling measure library respectively to obtain a matching first event type, a first event handling unit, and a first event handling measure;

[0036] For content without matching events, exclude the first keyword and extract the second keyword;

[0037] Based on the second keyword, searching the event classification thesaurus, the event processing unit correspondence library, and the event handling measure library respectively to obtain a matching second event type, a second event handling unit, and a second event handling measure;

[0038] If no matching result corresponding to the first keyword and the second keyword is obtained, the grassroots newly added event data is used as sample training data and added to the event classification vocabulary library, the event processing unit correspondence library and the event handling measures library.

[0039] In a second aspect, the present invention further provides a grassroots governance event type identification system, comprising:

[0040] A determination module, used to determine new grassroots events to be analyzed;

[0041] The processing module is used to input the new grassroots event to be analyzed into the trained event analysis model to obtain the event type recognition result; wherein, the event analysis model is obtained by constructing a dynamically updated event classification vocabulary library, event processing unit correspondence library and event handling measures library based on grassroots historical event data.

[0042] In a third aspect, the present invention also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the program, the steps of the grassroots governance event type identification method as described in any one of the above are implemented.

[0043] In a fourth aspect, the present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the grassroots governance event type identification method as described in any one of the above are implemented.

[0044] The grassroots governance event type identification method and system provided by the present invention establish an analysis model by integrating event content, event classification vocabulary, event handling unit correspondence library, and event type handling measure library. The model is applied to grassroots streets and communities to handle grassroots governance issues, and can intelligently distinguish event types, analyze event handling departments, and recommend handling measures. It effectively supports the rapid handling and resolution of grassroots events, promotes the improvement of grassroots governance efficiency, provides scientific and effective new ideas and means for grassroots governance, and can effectively reduce event handling time and improve event handling efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 This is a flow chart of the method for identifying grassroots governance event types provided by the present invention;

[0047] Figure 2 This is a schematic diagram of the structure of the grassroots governance event type identification system provided by the present invention;

[0048] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0049] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0050] In response to the problems of the existing technology, the present invention proposes a method for identifying the type of grassroots governance events, which focuses on the intelligent classification and disposal after the event is reported. Relying on cloud computing and big data technology, it can realize intelligent analysis of various problems reported by the grassroots, analyze keywords, identify event classification types, recommend disposal units and disposal measures, and solve the problem of numerous grassroots events that are difficult to handle efficiently.

[0051] Figure 1 This is a flow chart of the method for identifying grassroots governance event types provided by the present invention. Figure 1 As shown, including:

[0052] S1, determine the new grassroots events to be analyzed;

[0053] S2, input the new grassroots event to be analyzed into the trained event analysis model to obtain the event type recognition result; wherein, the event analysis model is obtained by constructing a dynamically updated event classification vocabulary library, event processing unit correspondence library and event handling measures library based on grassroots historical event data.

[0054] Specifically, the grassroots governance event type identification method proposed in the present invention includes three aspects: establishing an analysis model, model verification, new event analysis and measure recommendation. The constructed event analysis model is established by integrating event content, event classification vocabulary, event handling unit correspondence library and event handling measure library.

[0055] Once there is a new grassroots event that needs to be analyzed and predicted, it can be input into the above-established event analysis model to obtain the event type identification result.

[0056] The present invention uses an intelligent event type identification method for grassroots governance to determine the content of problems reported by grassroots people, intelligently judge the event type, and intelligently recommend processing units and measures. It is applied to the construction of grassroots governance systems, reducing event analysis and handling time and improving grassroots governance work efficiency.

[0057] Based on the above embodiment, the event analysis model in the method is implemented by the following steps:

[0058] Obtaining the grassroots historical event data;

[0059] Extract any historical event from the grassroots historical event data, and use a preset prediction analysis algorithm to fit the event type, event classification word, and actual risk result of the any historical event to obtain a first probability set of the occurrence of the event classification word;

[0060] Constructing the event classification vocabulary, the event processing unit correspondence library, and the event handling measures library based on the first probability set;

[0061] Extracting any other historical event other than the any historical event from the grassroots historical event data, and fitting the any other historical event based on the preset prediction analysis algorithm to obtain a second probability set;

[0062] Processing the first probability set based on the second probability set to obtain an initial event analysis model;

[0063] Acquire grassroots new event data, and continuously update the initial event analysis model based on the grassroots new event data to obtain the event analysis model.

[0064] The step of extracting any historical event from the grassroots historical event data and fitting the event type, event classification word, and actual risk result of any historical event using a preset prediction analysis algorithm to obtain a first probability set of occurrence of the event classification word includes:

[0065] Obtaining the event type of any of the historical events, wherein the event type includes the event time, event content, and event reporter;

[0066] Using a nonlinear artificial intelligence prediction analysis algorithm, the event type, the event classification word and the actual situation are analyzed to obtain a first sub-probability;

[0067] Analyze the event type, event handling unit, and actual situation to obtain a second sub-probability;

[0068] The event type, event handling measures, and the actual situation are analyzed to obtain a third sub-probability.

[0069] The step of constructing the event classification vocabulary, the event processing unit correspondence library, and the event handling measures library based on the first probability set includes:

[0070] Extracting event classification words corresponding to the first sub-probability being greater than a preset probability threshold, and constructing the event classification word library;

[0071] Extracting event handling units corresponding to the second sub-probability being greater than the preset probability threshold, and constructing a corresponding relationship database of the event handling units;

[0072] Event handling measures corresponding to the third sub-probability being greater than the preset probability threshold are extracted to construct the event handling measure library.

[0073] The extracting any other historical event other than the any historical event from the grassroots historical event data, and fitting the any other historical event based on the preset prediction analysis algorithm to obtain a second probability set includes:

[0074] Obtaining the event type of any other historical event, wherein the event type includes the event time, event content, and event reporter;

[0075] Using the nonlinear artificial intelligence prediction analysis algorithm, the event type, the event classification word and the actual situation are analyzed to obtain a fourth sub-probability;

[0076] Analyze the event type, event handling unit, and actual situation to obtain a fifth sub-probability;

[0077] The event type, event handling measures, and the actual situation are analyzed to obtain a sixth sub-probability.

[0078] The processing of the first probability set based on the second probability set to obtain an initial event analysis model includes:

[0079] Correcting and verifying the first probability set by the second probability set to obtain an optimal probability calculation algorithm;

[0080] Based on the optimal probability calculation algorithm, the initial event analysis model is established.

[0081] The step of acquiring the newly added event data at the grassroots level and continuously updating the initial event analysis model based on the newly added event data at the grassroots level to obtain the event analysis model includes:

[0082] Extracting the first keyword from the grassroots newly added event data;

[0083] Based on the first keyword, searching the event classification thesaurus, the event processing unit correspondence library, and the event handling measure library respectively to obtain a matching first event type, a first event handling unit, and a first event handling measure;

[0084] For content without matching events, exclude the first keyword and extract the second keyword;

[0085] Based on the second keyword, searching the event classification thesaurus, the event processing unit correspondence library, and the event handling measure library respectively to obtain a matching second event type, a second event handling unit, and a second event handling measure;

[0086] If no matching result corresponding to the first keyword and the second keyword is obtained, the grassroots newly added event data is used as sample training data and added to the event classification vocabulary library, the event processing unit correspondence library and the event handling measures library.

[0087] Specifically, determine the event type, including: event time, event content, and event reporter; the event classification vocabulary includes classification number, event type, and event type description; the event handling unit correspondence library includes event type and handling department; the event handling measure library includes event type, handling department, measure number, measure type, and measure content.

[0088] Based on the above historical event data, a nonlinear artificial intelligence prediction analysis algorithm is used to calculate the probability values ​​of the following three dimensions for any event A1:

[0089] 1) Extract relevant data of A1, analyze event type B1, event classification word R1 and actual situation, and obtain probability value K1;

[0090] 2) Extract the relevant data of A1, analyze the event type B1, event handling unit D1 and the actual situation, and obtain the probability value K2. The algorithm is the same as above.

[0091] 3) Extract the relevant data of A1, analyze the event type B1, event handling measure V1 and the actual situation, and obtain the probability value K3. The algorithm is the same as above.

[0092] 4) The cases where K1, K2, and K3 are greater than or equal to 0.8 are used as the event classification vocabulary, the event handling unit correspondence database, and the event handling measures database.

[0093] It should be noted that the nonlinear artificial intelligence prediction analysis algorithm is described in detail as follows:

[0094] The hyperbolic function Y=a+b(1 / X) is used to calculate massive historical data and confirm the probability value K.

[0095] Furthermore, another event A2 is selected for model verification, as follows:

[0096] 1) For business A2, obtain event type B2 and event classification term R2, and calculate probability K11 using the above analysis model;

[0097] 2) For business A2, obtain event type B2 and event handling unit D2, and calculate probability K12 using the above analysis model;

[0098] 3) Take business A2, obtain event type B2, event handling measure V2, and calculate probability K13 through the above analysis model

[0099] Then, the algorithm model is corrected according to the subsequent actual investigation results to obtain the best probability calculation method.

[0100] Furthermore, based on the new event content, keywords are extracted as R3, and R3 is used as the search term to search in the event classification vocabulary, event handling unit correspondence database, and event handling measure database to find matching event type B3, event handling unit D3, and event handling measure V3;

[0101] For event content that does not match, after excluding keyword R3, extract keyword R31 again and use R31 as the search term to search in the event classification thesaurus, event handling unit correspondence database, and event handling measure database to find matching event type B31, event handling unit D31, and event handling measure V31.

[0102] If no matching items are found through the above operations, they will be added to the analysis database table as sample data for training the model, and added to the event classification vocabulary database, event handling unit correspondence database, and event handling measures database.

[0103] The present invention implements a method for identifying grassroots governance event types based on big data. This method establishes an analysis model by integrating event content, an event classification vocabulary, a database of correspondences between event handling units, and a database of event type handling measures. This model is then applied to grassroots subdistricts and communities in handling grassroots governance issues. This method intelligently identifies event types, analyzes event handling departments, and recommends handling measures. This method effectively supports the rapid handling and resolution of grassroots incidents and promotes improved grassroots governance efficiency. This invention provides scientifically effective new ideas and methods for grassroots governance, effectively reducing event handling time and improving event handling efficiency.

[0104] The following describes the grassroots governance event type identification system provided by the present invention. The grassroots governance event type identification system described below and the grassroots governance event type identification method described above can be referenced to each other.

[0105] Figure 2 This is a schematic diagram of the structure of the grassroots governance event type identification system provided by the present invention. Figure 2 As shown, it includes: a determination module 21 and a processing module 22, wherein:

[0106] The determination module 21 is used to determine the new grassroots events to be analyzed; the processing module 22 is used to input the new grassroots events to be analyzed into the trained event analysis model to obtain the event type recognition result; wherein, the event analysis model is based on grassroots historical event data, and is obtained by constructing a dynamically updated event classification vocabulary library, event processing unit correspondence library and event handling measures library.

[0107] The present invention uses an intelligent event type recognition system for grassroots governance to identify the content of problems reported by grassroots people, intelligently judge the event type, and intelligently recommend processing units and measures. It is applied to the construction of grassroots governance systems, reducing event analysis and handling time and improving grassroots governance work efficiency.

[0108] Figure 3 An example of a physical structure diagram of an electronic device is shown below. Figure 3 As shown, the electronic device may include: a processor (processor) 310, a communication interface (CommunicationsInterface) 320, a memory (memory) 330 and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other via the communication bus 340. The processor 310 can call the logic instructions in the memory 830 to execute the grassroots governance event type identification method, which includes: determining a new grassroots event to be analyzed; inputting the new grassroots event to be analyzed into a trained event analysis model to obtain an event type identification result; wherein the event analysis model is obtained by constructing a dynamically updated event classification vocabulary, an event processing unit correspondence library, and an event handling measure library based on grassroots historical event data.

[0109] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0110] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the grassroots governance event type identification method provided by the above methods, which includes: determining new grassroots events to be analyzed; inputting the new grassroots events to be analyzed into a trained event analysis model to obtain event type identification results; wherein the event analysis model is based on grassroots historical event data, and is obtained by constructing a dynamically updated event classification vocabulary library, event processing unit correspondence library, and event handling measures library.

[0111] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the above-mentioned grassroots governance event type identification method provided, the method comprising: determining a new grassroots event to be analyzed; inputting the new grassroots event to be analyzed into a trained event analysis model to obtain an event type identification result; wherein the event analysis model is based on grassroots historical event data, and is obtained by constructing a dynamically updated event classification vocabulary library, an event processing unit correspondence library, and an event handling measures library.

[0112] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0113] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0114] Finally, it should be noted that 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for identifying grassroots governance event types, characterized by: include: Identify new grassroots events to be analyzed; Input the new grassroots event to be analyzed into a trained event analysis model to obtain an event type recognition result; wherein the event analysis model is obtained by constructing a dynamically updated event classification vocabulary, event processing unit correspondence library, and event handling measure library based on grassroots historical event data; the event analysis model extracts keywords as search based on the content description of the new grassroots event to be analyzed, searches the event classification vocabulary, the event processing unit correspondence library, and the event handling measure library to find matching event types, event handling units, and event handling measures; The event analysis model is obtained by the following steps: Obtaining the grassroots historical event data; Extract any historical event from the grassroots historical event data, and use a preset prediction analysis algorithm to fit the event type, event classification word, and actual risk result of the any historical event to obtain a first probability set of the occurrence of the event classification word; Constructing the event classification vocabulary, the event processing unit correspondence library, and the event handling measures library based on the first probability set; Extracting any other historical event other than the any historical event from the grassroots historical event data, and fitting the any other historical event based on the preset prediction analysis algorithm to obtain a second probability set; Processing the first probability set based on the second probability set to obtain an initial event analysis model; Acquire new event data at the grassroots level, and continuously update the initial event analysis model based on the new event data at the grassroots level to obtain the event analysis model; The preset prediction analysis algorithm includes a hyperbolic function algorithm.

2. The method for identifying grassroots governance event types according to claim 1 is characterized in that: The extracting of any historical event from the grassroots historical event data, using a preset prediction analysis algorithm, fitting the event type, event classification word, and actual risk result of the any historical event to obtain a first probability set of the occurrence of the event classification word, including: Obtaining the event type of any of the historical events, wherein the event type includes the event time, event content, and event reporter; Using a nonlinear artificial intelligence prediction analysis algorithm, the event type, the event classification word and the actual situation are analyzed to obtain a first sub-probability; Analyze the event type, event handling unit, and actual situation to obtain a second sub-probability; The event type, event handling measures, and the actual situation are analyzed to obtain a third sub-probability.

3. The method for identifying grassroots governance event types according to claim 2 is characterized in that: The constructing of the event classification vocabulary, the event processing unit correspondence library, and the event handling measures library based on the first probability set includes: Extracting event classification words corresponding to the first sub-probability being greater than a preset probability threshold, and constructing the event classification word library; Extracting event handling units corresponding to the second sub-probability being greater than the preset probability threshold, and constructing a corresponding relationship database of the event handling units; Event handling measures corresponding to the third sub-probability being greater than the preset probability threshold are extracted to construct the event handling measure library.

4. The method for identifying grassroots governance event types according to claim 2 is characterized in that: The extracting any other historical event other than the any historical event from the grassroots historical event data, and fitting the any other historical event based on the preset prediction analysis algorithm to obtain a second probability set includes: Obtaining the event type of any other historical event, wherein the event type includes the event time, event content, and event reporter; Using the nonlinear artificial intelligence prediction analysis algorithm, the event type, the event classification word and the actual situation are analyzed to obtain a fourth sub-probability; Analyze the event type, event handling unit, and actual situation to obtain a fifth sub-probability; The event type, event handling measures, and the actual situation are analyzed to obtain a sixth sub-probability.

5. The method for identifying grassroots governance event types according to claim 1 is characterized in that: The processing of the first probability set based on the second probability set to obtain an initial event analysis model includes: Correcting and verifying the first probability set by the second probability set to obtain an optimal probability calculation algorithm; Based on the optimal probability calculation algorithm, the initial event analysis model is established.

6. The method for identifying grassroots governance event types according to claim 1 is characterized in that: The step of obtaining the newly added event data at the grassroots level and continuously updating the initial event analysis model based on the newly added event data at the grassroots level to obtain the event analysis model includes: Extracting the first keyword from the grassroots newly added event data; Based on the first keyword, searching the event classification thesaurus, the event processing unit correspondence library, and the event handling measure library respectively to obtain a matching first event type, a first event handling unit, and a first event handling measure; For content without matching events, exclude the first keyword and extract the second keyword; Based on the second keyword, searching the event classification thesaurus, the event processing unit correspondence library, and the event handling measure library respectively to obtain a matching second event type, a second event handling unit, and a second event handling measure; If no matching result corresponding to the first keyword and the second keyword is obtained, the grassroots newly added event data is used as sample training data and added to the event classification vocabulary library, the event processing unit correspondence library and the event handling measures library.

7. A grassroots governance event type identification system, characterized by: include: A determination module, used to determine new grassroots events to be analyzed; A processing module is configured to input the new grassroots event to be analyzed into a trained event analysis model to obtain an event type recognition result; wherein the event analysis model is obtained by constructing a dynamically updated event classification vocabulary, an event processing unit correspondence library, and an event handling measure library based on grassroots historical event data; the event analysis model extracts keywords as search keywords based on the content description of the new grassroots event to be analyzed, searches the event classification vocabulary, the event processing unit correspondence library, and the event handling measure library to find matching event types, event handling units, and event handling measures; The processing module is also used to obtain the grassroots historical event data; extract any historical event from the grassroots historical event data, use a preset prediction analysis algorithm to fit the event type, event classification words and actual risk results of any historical event, and obtain a first probability set of the occurrence of the event classification words; construct the event classification word library, the event processing unit correspondence library and the event handling measures library based on the first probability set; extract any other historical event except the any historical event from the grassroots historical event data, fit the any other historical event based on the preset prediction analysis algorithm, and obtain a second probability set; process the first probability set based on the second probability set to obtain an initial event analysis model; obtain grassroots new event data, and continuously update the initial event analysis model based on the grassroots new event data to obtain the event analysis model; the preset prediction analysis algorithm includes a hyperbolic function algorithm.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the grassroots governance event type identification method as described in any one of claims 1 to 6 are implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the grassroots governance event type identification method as described in any one of claims 1 to 6 are implemented.

Images