A social governance-related data processing method based on event text classification

Abstract

The present invention discloses a method for processing social governance-related data based on event text classification. The method provided by the present invention obtains corresponding segmentation results by performing word segmentation processing on event text data to be classified, and inputs the segmentation results corresponding to the event text data to be classified into a trained event text data classification model to obtain classification labels for the event text data to be classified, thereby realizing automatic classification of event text data and solving the problems of low efficiency and waste of human resources in traditional methods of classifying event text data by manpower.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and in particular to a method for processing social governance-related data based on event text classification. Background Art

[0002] Traditional data classification methods mostly use a single classification rule for classification and extraction, and the use of SQL (Structured Query Language) queries often cannot meet the needs of in-depth analysis of data; and the existing classification management of data such as conflict investigation and reporting and social governance-related data such as public security mostly adopts manual management, which has the disadvantages of low work efficiency and the need for a large amount of human resources. Summary of the Invention

[0003] Therefore, the technical problem to be solved by the present invention is to overcome the defects of low efficiency and waste of resources in the existing manual data management, thereby providing a social governance related data processing method based on event text classification.

[0004] According to a first aspect, an embodiment of the present invention discloses a method for constructing an event text data classification model, including: obtaining an event text data set; performing word segmentation processing on the event text data in the event text data set to obtain a word segmentation result corresponding to each event text data; pre-classifying the word segmentation corresponding to each event text data according to the word segmentation result corresponding to each event text data; based on the pre-classification result of the word segmentation corresponding to each event text data, using a corresponding preset label system to label the word segmentation combination formed by the word segmentation corresponding to each event text data, to obtain labeled word segmentation combination data, wherein labels of different word segmentation combinations represent different types of events; using the labeled word segmentation combination data to train a preset model until the target training conditions are met, to obtain an event text data classification model.

[0005] Optionally, the word segmentation processing of the event text data in the event text data set to obtain the word segmentation results corresponding to each event text data includes: performing word segmentation processing on the event text data to obtain word segmentation data; performing dimensionality reduction processing on the word segmentation data to obtain the word segmentation results corresponding to each event text data.

[0006] Optionally, the word segmentation processing of the event text data to obtain word segmentation data includes: desensitizing the event text data to obtain desensitized data; preprocessing the desensitized data; and word segmentation processing of the preprocessed desensitized data to obtain word segmentation data.

[0007] Optionally, the event text data includes people's livelihood and public security text data.

[0008] Optionally, the preset label system includes a multi-level label system formulated for the people's livelihood and public security text data.

[0009] According to the second aspect, an embodiment of the present invention also discloses a method for processing social governance-related data based on event text classification, including: obtaining event text data to be classified; performing word segmentation processing on the event text data to be classified to obtain corresponding word segmentation result data; inputting the word segmentation result data into an event text data classification model for classification, and the event text data classification model is obtained by the event text data classification model construction method as described in the first aspect or any optional implementation method of the first aspect; determining the classification label of the event text data to be classified based on the classification result of the word segmentation result data.

[0010] According to the third aspect, an embodiment of the present invention also discloses a device for constructing an event text data classification model, including: a first acquisition module for acquiring an event text data set; a first word segmentation module for performing word segmentation processing on the event text data in the event text data set to obtain a word segmentation result corresponding to each event text data; a pre-classification module for pre-classifying the word segmentation corresponding to each event text data according to the word segmentation result corresponding to each event text data; a labeling module for labeling the word segmentation combination formed by the word segmentation corresponding to each event text data using a corresponding preset label system according to the pre-classification result of the word segmentation corresponding to each event text data, to obtain labeled word segmentation combination data, wherein labels of different word segmentation combinations represent different types of events; a training module for training a preset model using the labeled word segmentation combination data until the target training conditions are met, thereby obtaining an event text data classification model.

[0011] According to the fourth aspect, an embodiment of the present invention also discloses a social governance-related data processing device based on event text classification, including: a second acquisition module, used to obtain event text data to be classified; a second word segmentation module, used to perform word segmentation processing on the event text data to be classified to obtain corresponding word segmentation result data; a classification module, used to input the word segmentation result data into an event text data classification model for classification, and the event text data classification model is obtained by the event text data classification model construction method as described in the first aspect or any optional implementation method of the first aspect; a determination module, used to determine the classification label of the event text data to be classified based on the classification result of the word segmentation result data.

[0012] According to the fifth aspect, an embodiment of the present invention also discloses an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the steps of the method for constructing an event text data classification model as described in the first aspect or any optional embodiment of the first aspect, or to execute the steps of the method for processing social governance-related data based on event text classification as described in the second aspect.

[0013] According to the sixth aspect, an embodiment of the present invention further discloses a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it implements the steps of the method for constructing an event text data classification model as described in the first aspect or any optional embodiment of the first aspect, or implements the steps of the method for processing social governance-related data based on event text classification as described in the second aspect.

[0014] The technical solution of the present invention has the following advantages:

[0015] The method / device for constructing an event text data classification model provided by the present invention includes: obtaining an event text data set; performing word segmentation processing on the event text data in the event text data set to obtain a word segmentation result corresponding to each event text data; pre-classifying the word segmentation corresponding to each event text data according to the word segmentation result corresponding to each event text data; labeling the word segmentation combination formed by the word segmentation corresponding to each event text data using a corresponding preset label system according to the pre-classification result of the word segmentation corresponding to each event text data, to obtain word segmentation combination data with labels, wherein labels of different word segmentation combinations represent different types of events; and training a preset model using the word segmentation combination data with labels until target training conditions are met, to obtain an event text data classification model. The method of the present invention performs word segmentation processing on event text data to obtain a word segmentation result corresponding to each event text data; pre-classifies the word segmentation result corresponding to each event text data; based on the pre-classification result, labels the word segmentation combination formed by the word segmentation corresponding to each event text data using a corresponding preset label system to obtain labeled word segmentation combination data; uses the labeled word segmentation combination data to train a preset model to obtain an event text data classification model, and subsequently uses the model to classify the event text data, thereby realizing automatic classification and management of the event text data. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific 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.

[0017] Figure 1 This is a flowchart of a specific example of a method for constructing an event text data classification model in an embodiment of the present invention;

[0018] Figure 2 This is a flowchart of a specific example of a method for processing social governance-related data based on event text classification in an embodiment of the present invention;

[0019] Figure 3 This is a principle block diagram of a specific example of an apparatus for constructing an event text data classification model according to an embodiment of the present invention;

[0020] Figure 4 This is a principle block diagram of a specific example of a social governance-related data processing device based on event text classification in an embodiment of the present invention;

[0021] Figure 5 FIG. 4 is a diagram showing a specific example of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0023] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0024] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "installed," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; internal connections between two components; wireless connections or wired connections. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0025] In addition, the technical features involved in different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0026] The embodiment of the present invention discloses a method for constructing an event text data classification model. Figure 1 As shown, the method includes the following steps:

[0027] Step 101: Acquire an event text dataset.

[0028] Exemplarily, an event text data set may be a collection of multiple event text data corresponding to the event to be classified. In an embodiment of the present application, the types of event text data contained in the event text data set may include but are not limited to various people's livelihood and public security text data. People's livelihood and public security text data can be obtained from a database containing information such as a conflict and dispute investigation information table, a community public opinion information table, and a grid reporting clue information table.

[0029] Step 102: Segment the event text data in the event text dataset to obtain a segmentation result corresponding to each event text data. For example, in an embodiment of the present application, WMSEG (Chinese Segmentation Memory Network) can be used to segment the event text data to obtain a segmentation result corresponding to each event text data.

[0030] Step 103 : pre-classify the segmented words corresponding to each event text data according to the segmented word results corresponding to each event text data.

[0031] For example, in an embodiment of the present application, a linear kernel SVM algorithm can be used to pre-classify the word segmentation corresponding to each event text data. SVM, or support vector machine, is a classification algorithm. SVM is suitable for small and medium-sized data samples, nonlinear, and high-dimensional classification problems. Using this method, the corresponding classification can be determined based on the part of speech and meaning of each word in the word segmentation result corresponding to each event text data. For example, when the word segmentation is a word such as dog or snake, the word will be classified as an animal; when the word segmentation is a word such as arrangement, procurement, purchase, purchase, purchase on behalf of, order, order, and order, the word will be classified as a purchase.

[0032] Step 104: Based on the pre-classification results of the segmentation words corresponding to each event text data, the segmentation word combinations formed by the segmentation words corresponding to each event text data are labeled using the corresponding preset label system to obtain segmentation word combination data with labels, wherein the labels of different segmentation word combinations represent different types of events.

[0033] Exemplarily, the segmentation combination can be one or more combinations of multiple segmentations in the segmentation results corresponding to each event text data; the preset label system can be a label system determined for the segmentation combination corresponding to the event text data, and the preset label system includes labels corresponding to the segmentation combination. In an embodiment of the present application, when the segmentation combination corresponding to the event text data is "child + child + support", it can be determined according to the pre-classification result that the classification of "child" and "child" is "minor", and the classification of "support" is "guardianship", and the label corresponding to the segmentation combination classified as "minor" and "guardianship" in the preset label system is "youth support and guardianship", then the label corresponding to the segmentation combination "child + child + support" is also "youth support and guardianship".

[0034] Step 105, use the labeled word segmentation combination data to train the preset model until the target training conditions are met, and obtain the event text data classification model. Exemplarily, the preset model can be any model. In the embodiment of the present application, the preset model can include but is not limited to a deep learning model, which can automatically learn features from the data, avoiding the huge manpower and time costs of manually extracting features using traditional methods. The embodiment of the present application uses a model based on a key-value memory neural network, which uses the word formation information carried by n-tuples to help the model identify word boundaries. The deep learning model in the embodiment of the present application is based on a pre-trained model, which effectively utilizes the information of large-scale unlabeled text, so that the model can achieve excellent performance with very little training data. The F value of the model on the standard data set can reach more than 97%; and the model is based on a Transformer architecture that can be run in high parallelization, avoiding the linear calculation method of traditional HMM and RNN models, greatly increasing the speed of model prediction.

[0035] The event text data classification model construction method provided by the present invention performs word segmentation processing on event text data to obtain a word segmentation result corresponding to each event text data; pre-classifies the word segmentation result corresponding to each event text data; based on the pre-classification result, the word segmentation combination formed by the word segmentation corresponding to each event text data using a corresponding preset label system is labeled to obtain labeled word segmentation combination data; the preset model is trained using the labeled word segmentation combination data to obtain an event text data classification model, which is convenient for subsequent use of the model to classify the event text data, thereby realizing automatic classification and management of the event text data.

[0036] As an optional implementation of the present invention, the above step 102 includes: performing word segmentation processing on the event text data to obtain word segmentation data; performing dimensionality reduction processing on the word segmentation data to obtain a word segmentation result corresponding to each event text data.

[0037] For example, in an embodiment of the present application, the event text data can be segmented using WMSEG (Chinese Word Segmentation Memory Network) to obtain segmented data, which can then be subjected to dimensionality reduction to obtain the segmentation results corresponding to each event text data. Dimensionality reduction can, on the one hand, resolve the curse of dimensionality, alleviate the current situation of "information-rich, knowledge-poor," and reduce complexity; on the other hand, it can provide a better understanding of the data.

[0038] As an optional embodiment of the present invention, the word segmentation processing of the event text data to obtain word segmentation data includes: desensitizing the event text data to obtain desensitized data; preprocessing the desensitized data; and word segmentation processing of the preprocessed desensitized data to obtain word segmentation data.

[0039] Illustratively, in an embodiment of the present application, the method for preprocessing desensitized data may include but is not limited to any of data cleaning, data integration, data transformation, and data induction; data cleaning is to "clean" data by filling in missing values, smoothing noisy data, identifying or deleting outliers, and resolving inconsistencies; data integration is the process of combining data from multiple data sources and storing them in a unified manner to establish a data warehouse.

[0040] As an optional implementation manner of the present invention, the event text data includes text data related to people's livelihood and public security.

[0041] For example, livelihood data can be text data related to people's lives, and public safety data can be text data related to people's safety. For example, public safety data can be "A service recipient called to report that on February 23, 2021, he spent 160 yuan to buy an electric remote control car at V Luggage Store on the first floor of S Square, diagonally opposite J Community, Y Town, T County. After taking it home, the wheels fell off after using it for one hour, which is a quality problem. He reported the problem to the store but to no avail and expressed his disagreement."

[0042] As an optional embodiment of the present invention, the preset label system includes a multi-level label system formulated for the people's livelihood and public security text data.

[0043] For example, in the embodiments of the present application, a multi-level labeling system refers to a word combination corresponding to the same event text data, which can correspond to multiple labels, each label having a corresponding priority. For example, if the word combination corresponding to the event text is "son, daughter + support + divorce", then the labels corresponding to this word combination in the multi-level labeling system may include a first-level label "marriage and family disputes", a second-level label "support, maintenance and guardianship", and a third-level label "youth support and guardianship". The embodiments of the present application do not limit the label type and label level.

[0044] The embodiment of the present invention discloses a method for processing social governance related data based on event text classification, such as Figure 2 As shown, the method includes the following steps:

[0045] Step 201: Acquire event text data to be classified. Exemplarily, the event text data to be classified may be any event text data. In the embodiment of the present application, the event text data to be classified may include but is not limited to text data related to people's livelihood and public security.

[0046] Step 202: Segment the event text data to be classified to obtain corresponding segmentation result data. For example, in an embodiment of the present application, the event text data to be classified may be desensitized, the desensitized data may be preprocessed, and then the preprocessed data may be segmented to obtain corresponding segmentation result data.

[0047] In step 203, the word segmentation result data is input into the event text data classification model for classification. The event text data classification model is obtained by the event text data classification model construction method described in the above embodiment. For example, in the embodiment of the present application, the word segmentation result data is input into the event text data classification model, and a classification label corresponding to the word segmentation result data is output.

[0048] Step 204: Determine the classification label of the event text data to be classified based on the classification result of the word segmentation result data. For example, in this embodiment of the present application, the classification label corresponding to the word segmentation result data output by the event text data classification model can be the classification label of the event text data to be classified.

[0049] The social governance-related data processing method based on event text classification provided by the present invention obtains corresponding segmentation results by performing word segmentation processing on the event text data to be classified, and inputs the word segmentation results corresponding to the event text data to be classified into the event text data classification model to obtain classification labels for the event text data to be classified, thereby realizing automatic classification of event text data and solving the problems of low efficiency and waste of human resources in the traditional method of using manpower to classify event text data.

[0050] The embodiment of the present invention also discloses a device for constructing an event text data classification model. Figure 3 As shown, the device includes: a first acquisition module 301, which is used to acquire an event text data set; a first word segmentation module 302, which is used to perform word segmentation processing on the event text data in the event text data set to obtain a word segmentation result corresponding to each event text data; a pre-classification module 303, which is used to pre-classify the word segmentation corresponding to each event text data according to the word segmentation result corresponding to each event text data; a labeling module 304, which is used to label the word segmentation combination formed by the word segmentation corresponding to each event text data using a corresponding preset label system according to the pre-classification result of the word segmentation corresponding to each event text data, to obtain labeled word segmentation combination data, wherein the labels of different word segmentation combinations represent different types of events; a training module 305, which is used to train a preset model using the labeled word segmentation combination data until the target training conditions are met, thereby obtaining an event text data classification model.

[0051] The event text data classification model construction device provided by the present invention obtains the word segmentation result corresponding to each event text data by performing word segmentation processing on the event text data; pre-classifies the word segmentation result corresponding to each event text data; based on the pre-classification result, the word segmentation combination formed by the word segmentation corresponding to each event text data using the corresponding preset label system is labeled to obtain the word segmentation combination data with labels; the word segmentation combination data with labels is used to train the preset model to obtain the event text data classification model, which is convenient for subsequent use of the model to classify the event text data, thereby realizing the automated management of the event text data.

[0052] As an optional embodiment of the present invention, the first word segmentation module includes: a first word segmentation sub-module, which is used to perform word segmentation processing on the event text data to obtain word segmentation data; and a dimensionality reduction sub-module, which is used to perform dimensionality reduction processing on the word segmentation data to obtain a word segmentation result corresponding to each event text data.

[0053] As an optional embodiment of the present invention, the first word segmentation submodule includes: a desensitization submodule, which is used to desensitize the event text data to obtain desensitized data; preprocess the desensitized data; and a second word segmentation submodule, which is used to segment the preprocessed desensitized data to obtain word segmentation data.

[0054] As an optional implementation manner of the present invention, the event text data includes text data related to people's livelihood and public security.

[0055] As an optional embodiment of the present invention, the preset label system includes a multi-level label system formulated for the people's livelihood and public security text data.

[0056] The embodiment of the present invention also discloses a social governance related data processing device based on event text classification, such as Figure 4 As shown, the device includes: a second acquisition module 501, used to obtain event text data to be classified; a second word segmentation module 502, used to perform word segmentation processing on the event text data to be classified to obtain corresponding word segmentation result data; a classification module 503, used to input the word segmentation result data into an event text data classification model for classification, and the event text data classification model is obtained by the event text data classification model construction method as described in the above embodiment; a determination module 504, used to determine the classification label of the event text data to be classified according to the classification result of the word segmentation result data.

[0057] The embodiment of the present invention further provides an electronic device, such as Figure 5 As shown, the electronic device may include a processor 401 and a memory 402, wherein the processor 401 and the memory 402 may be connected via a bus or other means. Figure 5 The bus connection is taken as an example.

[0058] The processor 401 may be a central processing unit (CPU). The processor 401 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0059] The memory 402 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs, and modules, such as the event text data classification model construction method or the event text data classification method in the embodiment of the present invention. The processor 401 executes various functional applications and data processing of the processor by running the non-transient software programs, instructions, and modules stored in the memory 402, that is, implementing the event text data classification model construction method or the social governance-related data processing method based on event text classification in the above method embodiment.

[0060] The memory 402 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created by the processor 401, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 402 may optionally include a memory remotely located relative to the processor 401, and these remote memories may be connected to the processor 401 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0061] The one or more modules are stored in the memory 402 and when executed by the processor 401, perform the following steps: Figure 1 The event text data classification model construction method in the embodiment shown, or executing the following Figure 2 The social governance-related data processing method based on event text classification in the illustrated embodiment.

[0062] For details of the above electronic equipment, please refer to Figure 1 or Figure 2 The corresponding descriptions and effects in the embodiments shown can be understood and will not be repeated here.

[0063] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD). The storage medium can also include a combination of the above-mentioned types of memory.

[0064] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for constructing an event text data classification model, characterized in that: include: Get the event text dataset; Performing word segmentation processing on the event text data in the event text data set to obtain a word segmentation result corresponding to each event text data; Pre-classifying the segmentation results corresponding to each event text data according to the segmentation results corresponding to each event text data; Based on the pre-classification results of the segmentation words corresponding to each event text data, the segmentation word combinations formed by the segmentation words corresponding to each event text data are labeled using a corresponding preset label system to obtain segmentation word combination data with labels, wherein the labels of different segmentation word combinations represent different types of events; The preset model is trained using the labeled word segmentation combination data until the target training conditions are met, thereby obtaining an event text data classification model.

2. The method according to claim 1, characterized in that The word segmentation processing of the event text data in the event text data set to obtain a word segmentation result corresponding to each event text data includes: Performing word segmentation processing on the event text data to obtain word segmentation data; The word segmentation data is subjected to dimensionality reduction processing to obtain a word segmentation result corresponding to each event text data.

3. The method according to claim 2, characterized in that The performing word segmentation processing on the event text data to obtain word segmentation data includes: Performing desensitization processing on the event text data to obtain desensitized data; Preprocessing the desensitized data; The pre-processed desensitized data is segmented to obtain segmented data.

4. The method according to claim 1, wherein The event text data includes text data related to people's livelihood and public security.

5. The method according to claim 4, characterized in that The preset label system includes a multi-level label system formulated for the people's livelihood and public security text data.

6. A method for processing social governance-related data based on event text classification, characterized in that: include: Obtain the text data of the event to be classified; Performing word segmentation processing on the event text data to be classified to obtain corresponding word segmentation result data; Inputting the word segmentation result data into an event text data classification model for classification, wherein the event text data classification model is obtained by the event text data classification model construction method according to any one of claims 1 to 5; The classification label of the event text data to be classified is determined according to the classification result of the word segmentation result data.

7. A device for constructing an event text data classification model, characterized in that: include: The first acquisition module is used to acquire the event text dataset; A first word segmentation module is used to perform word segmentation processing on the event text data in the event text data set to obtain a word segmentation result corresponding to each event text data; A pre-classification module, configured to pre-classify the segmentation corresponding to each event text data according to the segmentation result corresponding to each event text data; a labeling module for labeling, based on the pre-classification results of the segmentation corresponding to each event text data, the segmentation combinations formed by the segmentation corresponding to each event text data using a corresponding preset labeling system to obtain labeled segmentation combination data, wherein the labels of different segmentation combinations represent different types of events; The training module is used to train the preset model using the labeled word segmentation combination data until the target training conditions are met to obtain an event text data classification model.

8. A social governance-related data processing device based on event text classification, characterized in that: include: The second acquisition module is used to obtain the text data of the event to be classified; The second word segmentation module is used to perform word segmentation processing on the event text data to be classified to obtain corresponding word segmentation result data; a classification module, configured to input the word segmentation result data into an event text data classification model for classification, wherein the event text data classification model is obtained by the event text data classification model construction method according to any one of claims 1 to 5; The determination module is used to determine the classification label of the event text data to be classified according to the classification result of the word segmentation result data.

9. An electronic device, characterized in that: include: at least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the steps of the event text data classification model construction method as described in any one of claims 1 to 5, or to execute the steps of the social governance-related data processing method based on event text classification as described in claim 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the steps of the method for constructing an event text data classification model as described in any one of claims 1 to 5, or implements the steps of the method for processing social governance-related data based on event text classification as described in claim 6.

Images