Dynamic multi-task situation assessment method, system and device for urban social governance and storage medium

Abstract

The invention provides a dynamic multi-task situation assessment method, system and device for urban social governance, and a storage medium, so as to realize dynamic multi-task situation assessment for urban social governance. The method comprises the steps that a social governance dynamic multi-task situation assessment index system is constructed, first-level indexes of risk factors are constructed from the four dimensions of event severity, social influence degree, countermeasures and public participation assessment, the first-level indexes are subdivided, and corresponding second-level indexes are set; the method comprises the following steps: acquiring index data of a social event, and preprocessing the index data, the index data comprising first-level index data and / or second-level index data; obtaining conditional probability calculation between the first-level indexes and the second-level indexes, and constructing a Bayesian network model; training and testing the Bayesian network model based on the index data to obtain a trained Bayesian network; and judging the situation of any social event according to the trained Bayesian model.

Description

Technical Field

[0001] The present application relates to the technical field of public opinion analysis, and specifically to a situation assessment method, system, device and storage medium for dynamic multi-task urban social governance. Background Art

[0002] With the rapid development of Internet technology, the number of Internet users in my country has exceeded 900 million, and the penetration rate has exceeded 65%. The popularity of the Internet has greatly enriched the channels for obtaining information, allowing the public to access and discuss social events anytime and anywhere. However, this also means that negative information and extreme views on the Internet may spread rapidly, forming an online public opinion crisis. If these negative information becomes mainstream, it may have an adverse impact on social development. Strengthening the monitoring and management of online public opinion and timely guiding and responding to it are of great significance to maintaining social stability and promoting healthy development.

[0003] However, traditional online public opinion analysis mainly relies on the perspective of social science, focusing on macro qualitative analysis such as the construction of indicator systems, trend development and governance methods. Faced with the explosive growth of network data, these macro analysis methods can no longer meet the researchers' in-depth research needs on online public opinion situation perception, dissemination mechanism and situation prediction.

[0004] In view of the above problems, how to evaluate the situation of online public opinion is an issue that needs to be solved urgently. Summary of the invention

[0005] The embodiments of the present application provide a situation assessment method, system, device and storage medium for dynamic multi-task social governance in urban areas, so as to realize situation assessment for dynamic multi-task social governance in urban areas.

[0006] In order to achieve the above objectives, this application adopts the following technical solutions:

[0007] On the first aspect, the present application provides a situation assessment method for dynamic multi-task social governance in an urban area, the method comprising: constructing a situation assessment index system for dynamic multi-task social governance, constructing a first-level indicator for risk factors from four dimensions: event severity, social impact, response measures, and public participation assessment, and subdividing the first-level indicator to set corresponding second-level indicators; collecting indicator data of social events and preprocessing the indicator data, the indicator data including first-level indicator data and / or second-level indicator data; obtaining conditional probability inference between first-level indicators and second-level indicators, and constructing a Bayesian network model; training and testing the Bayesian network model based on the indicator data to obtain a trained Bayesian network; judging the situation of any social event based on the trained Bayesian model.

[0008] A possible design scheme, the first aspect of the method also includes constructing a first-level indicator of risk factors from four dimensions: incident severity, social impact, response measures, and public participation assessment, and subdividing the first-level indicator to set corresponding second-level indicators, including: incident severity includes three second-level indicators: incident category attributes, casualties caused by the incident, and property losses caused by the incident; social impact includes three second-level indicators: economic impact, social stability impact, and political impact; response measures include three second-level indicators: response speed, resource allocation, and departmental collaboration; public participation assessment includes three second-level indicators: public attention, public participation, and public satisfaction.

[0009] In a possible design solution, the method of the first aspect further includes preprocessing the indicator data, including at least one of the following processing methods:

[0010] 1) Data deduplication, removing duplicate records in the indicator data set;

[0011] 2) For missing values ​​with a low proportion, delete them directly;

[0012] 3) For important missing values, interpolation, mean, median, and mode can be used to fill them;

[0013] 4) For abnormal values, directly delete them or replace them with reasonable values;

[0014] 5) Convert data into unified formats and standards;

[0015] 6) Automatically check and verify data by setting data validation rules.

[0016] A possible design scheme, the method of the first aspect also includes obtaining the conditional probability between the primary indicator and the secondary indicator, and constructing a Bayesian network model, including:

[0017] The first-level index and the second-level index are nodes of the Bayesian network; according to the EM algorithm, the conditional probability between each node is calculated to determine the conditional probability between each node;

[0018] Alternatively, conditional probabilities between nodes are determined based on expert opinions and instance data.

[0019] A possible design scheme, the method of the first aspect also includes, based on the indicator data, training and testing the Bayesian network model to obtain a trained Bayesian network, including: using a 12-fold cross-validation method to divide the preprocessed indicator data into 12 parts, 1 of which is used as a test set and the other 11 are used as training sets, to train and test the Bayesian network model to obtain a trained Bayesian network.

[0020] A possible design scheme, the method of the first aspect also includes, based on the indicator data, before training and testing the Bayesian network model, further including:

[0021] Perform Z-score standardization on the indicator data and scale the data to the interval of [-1, 1].

[0022] The standardization formula is:

[0023] in, X is the original indicator data, μ is the mean of the indicator data, and σ is the standard deviation of the indicator data;

[0024] According to the standardized indicator data, the corresponding intervals are divided, and different levels are divided according to the intervals.

[0025] A possible design scheme, the method of the first aspect also includes a human-computer interaction interface, through which the indicator data of any social event is input, the situation of any social event is determined based on the trained Bayesian model, and the results are displayed to the user.

[0026] In the second aspect, a situation assessment system for dynamic multi-task social governance in the city is provided, and the situation assessment system for dynamic multi-task social governance in the city includes:

[0027] The system construction module is used to build a dynamic and multi-task situation assessment indicator system for social governance. It constructs the first-level indicators of risk factors from four dimensions: severity of incidents, degree of social impact, response measures, and public participation assessment. It also subdivides the first-level indicators and sets corresponding second-level indicators.

[0028] A collection and processing module, used to collect indicator data of a social event and pre-process the indicator data, the indicator data includes primary indicator data and / or secondary indicator data;

[0029] The acquisition module is used to obtain the conditional probability inference between the primary index and the secondary index and build a Bayesian network model;

[0030] The training and testing module is used to train and test the Bayesian network model based on the indicator data to obtain the trained Bayesian network;

[0031] The judgment module is used to judge the situation of any social event based on the trained Bayesian model.

[0032] According to a third aspect, a situation assessment device for dynamic multi-tasks of urban social governance is provided, and the situation assessment device for dynamic multi-tasks of urban social governance includes a module for executing the method of the first aspect.

[0033] In a possible design scheme, the situation assessment device for dynamic multi-task of urban social governance of the third aspect may also include a transceiver. The transceiver may be a transceiver circuit or an interface circuit. The transceiver may be used for the situation assessment device for dynamic multi-task of urban social governance of the third aspect to communicate with other devices.

[0034] In a possible design scheme, the situation assessment device for dynamic multi-task of urban social governance of the second aspect may also include a memory. The memory may be integrated with the processor or provided separately. The memory may be used to store instructions involved in the method of the first aspect.

[0035] In a fourth aspect, a computer-readable storage medium is provided, which includes a computer program or instruction stored therein. When the computer program or instruction is executed, the situation assessment method for dynamic multi-task urban social governance described in the first aspect is executed.

[0036] In an embodiment of the present application, a dynamic multi-task situation assessment index system for social governance is constructed, and a first-level indicator of risk factors is constructed from four dimensions: event severity, social impact, response measures, and public participation assessment. The first-level indicator is subdivided and corresponding second-level indicators are set; indicator data of social events are collected and pre-processed, and the indicator data includes first-level indicator data and / or second-level indicator data; conditional probability inference between first-level indicators and second-level indicators is obtained, and a Bayesian network model is constructed; based on the indicator data, the Bayesian network model is trained and tested to obtain a trained Bayesian network; based on the trained Bayesian model, the situation of any social event is determined, thereby realizing situation assessment for dynamic multi-task social governance in the urban area.

[0037] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 A flow chart of a situation assessment method for dynamic multi-task urban social governance provided in an embodiment of the present application;

[0040] Figure 2 A schematic diagram of the structure of a situation assessment device for dynamic multi-task urban social governance provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application. At the same time, in the description of the embodiments of the present application, the terms "first", "second", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0042] Figure 1 A flow chart of a situation assessment method for dynamic multi-task social governance in a city provided in an embodiment of the present application. The situation assessment method for dynamic multi-task social governance in a city is applicable to situation level assessment of sudden network events, or other possible methods, which are not limited here.

[0043] The process of the situation assessment method for dynamic multi-task urban social governance is as follows:

[0044] Step S101, construct a dynamic multi-task situation assessment indicator system for social governance, construct the first-level indicators of risk factors from four dimensions: severity of incidents, degree of social impact, response measures, and public participation assessment, and subdivide the first-level indicators and set corresponding second-level indicators.

[0045] Taking into account the specific attributes of social governance situation assessment and the availability of data, the social governance situation evaluation index system is constructed into three parts, namely: target variables, primary indicators and secondary indicators.

[0046] (1) Target variable: the situation assessment level. The incident is divided into four levels: extremely serious, serious, relatively serious, and general, based on factors such as the size of the loss caused by the incident and the size of the social impact. The target variable is the situation assessment level finally determined in this application.

[0047] (2) Primary indicators: mainly include four aspects: severity of the incident, degree of social impact, response measures, and public participation assessment.

[0048] (3) Secondary indicators: This is a subdivision of the primary indicators. There are 12 indicators in total, which are quantified through the captured data. At the same time, this indicator is also the evidence variable in the Bayesian network model.

[0049] The severity of the event in the first-level index represents the impact caused by the event, which includes three indicators: the event category attribute, casualties caused by the event, and property losses caused by the event.

[0050] The degree of social impact refers to the social impact caused by the event, including economic impact, social stability impact and political impact.

[0051] The response measures refer to the government's response after the incident, including response speed, resource allocation, and departmental collaboration.

[0052] The public participation assessment refers to the public's participation in the incident, including public attention, public participation, and public satisfaction.

[0053] Among them, the four first-level indicators can be represented by M1, M2, M3, and M4 respectively, the second-level indicators corresponding to M1 can be represented by N1, N2, and N3 respectively; the second-level indicators corresponding to M2 can be represented by N4, N5, and N6 respectively; the second-level indicators corresponding to M3 can be represented by N7, N8, and N9 respectively; the second-level indicators corresponding to M4 can be represented by N10, N11, and N12 respectively, or other representation methods, which are not limited here.

[0054] Step S102, collecting indicator data of social events and preprocessing the indicator data, the indicator data includes primary indicator data and / or secondary indicator data.

[0055] Collect data related to social governance, such as population, economy, environment, security, etc.; pre-process the data, including data cleaning, missing value processing, outlier processing, etc. For example, 1) remove duplicate records in the data set; 2) directly delete missing values ​​with a low proportion; 3) for important missing values, use interpolation, mean, median, mode to fill; 4) for outliers, directly delete or replace with reasonable values; 5) convert data into a unified format and standard; 6) automatically check and verify data by setting data validation rules.

[0056] It should be noted that the number of public opinion events collected can be 50, 100, or any other reasonable number, and there is no limit here.

[0057] Step S103, obtaining conditional probability inference between the primary index and the secondary index, and constructing a Bayesian network model.

[0058] It should be noted that the Bayesian network is a probabilistic graphical model that uses a directed acyclic graph (DAG) to represent the conditional dependencies between variables and a conditional probability table (CPT) to describe the quantitative probabilities of these relationships. This model is very suitable for processing and reasoning probabilistic problems involving multiple variables, especially when there is uncertainty and causal inference is required.

[0059] In a Bayesian network, each node represents a random variable, and the directed edges between nodes represent direct dependencies between variables. This dependency is unidirectional, meaning that one variable (parent node) directly affects another variable (child node). The structure of the network is represented by a graph G = (V, E), where V is a set of nodes and E is a set of edges representing node dependencies. The conditional probability table (CPT) provides a conditional probability distribution for each node given the state of its parent node. These tables are often used to describe the probability of a node taking each possible value given that the parent node takes a specific value.

[0060] The joint probability distribution of a Bayesian network can be expressed by the chain rule of probability, which means that the probability distribution of the entire network can be decomposed into the product of the conditional probabilities of each node. Specifically, for each node X in the network i , its probability distribution P(X i |X1,X2,...,X i-1 ) depends only on its parent node π(X i ). This property is called Markov property, which greatly simplifies the reasoning process of the network.

[0061] Therefore, the joint probability of the entire network can be expressed as:

[0062] This formula shows that to calculate the joint probability of the entire network, we only need to know the probability of each node given its parent node.

[0063] Specifically, the above-mentioned first-level indicators and second-level indicators are nodes of the Bayesian network; the conditional probabilities between the nodes can be calculated according to the EM algorithm to determine the conditional probabilities between the nodes; or, the conditional probabilities between the nodes can be determined according to expert opinions and example data. In other words, a conditional probability table (CPT) is obtained.

[0064] Step S104: training and testing the Bayesian network model based on the indicator data to obtain a trained Bayesian network.

[0065] It should be noted that before training and testing the Bayesian network model based on indicator data, it also includes:

[0066] Perform Z-score standardization on the indicator data and scale the data to the interval of [-1, 1].

[0067] The standardization formula is:

[0068] in, X is the original indicator data, μ is the mean of the indicator data, and σ is the standard deviation of the indicator data;

[0069] According to the standardized indicator data, the corresponding intervals are divided, and different levels are divided according to the intervals.

[0070] In addition, the above Z-score normalization processing of the indicator data and scaling the data to the interval of [-1, 1] is only an example, and the data can also be scaled to intervals such as [0, 1], [-1, 0], etc., which is not limited here.

[0071] The standards for dividing some indicator data into different levels are shown in Table 1, which is also the discretization standard.

[0072]

[0073]

[0074] Table 1

[0075] It can be understood that the indicator data are all discrete. If the collected data is continuous data, it is standardized and then divided into corresponding intervals according to the standardized indicator data, and different levels are divided by intervals. For example, the indicators of casualties caused by the incident, property losses caused by the incident, economic impact, social stability impact, political impact, response speed, resource allocation, departmental collaboration, public attention, public participation, and public satisfaction are discretized (that is, divided into different levels) as H (high), M (medium), and L (low), and the indicators of event category attributes are discretized (that is, divided into different levels) as X (series of events), Z (natural disasters), and G (public safety).

[0076] Afterwards, the preprocessed indicator data is divided into 12 parts using the 12-fold cross-validation method, with 1 part as the test set and the other 11 parts as the training set to train and test the Bayesian network model and obtain the trained Bayesian network. For example: events 1-10 are selected as the test set, and events 11-120 are selected as the training set. Based on the Bayesian network trained with the training set, the indicator data in the test set is input into the Bayesian network model, and then the situation assessment level of the event is determined.

[0077] In addition, the discretization of the indicator data of the above 120 times is shown in Table 2.

[0078] serial number N1 N2 N3 N4 N5 N6 N7 N8 N9 N10 N11 N12 1 Z L M H M H L M N T H L 2 Z H L M L L M H N T M M 3 X M M L H H H M N F L H …… …… …… …… …… …… …… …… …… …… …… …… …… 120 G H H M H H H H N T M H

[0079] Table 2

[0080] Step S105, determining the situation of any social event based on the trained Bayesian model.

[0081] Obtain the indicator data N1, N2, N3, N4, N5, N6, N7, N8, N9, N10, N11, and N12 corresponding to any event, then clean and discretize the indicator and input it into the trained Bayesian network model to determine the situation of any social event.

[0082] It should be noted that the method may also include a human-computer interaction interface, through which the indicator data of any social event is input, and the situation of any social event is determined based on the trained Bayesian model, and the analysis results are visualized in the form of charts, reports, etc.

[0083] In summary, the embodiment of the present application constructs a dynamic multi-task situation assessment indicator system for social governance, constructs a first-level indicator of risk factors from four dimensions: event severity, social impact, response measures, and public participation assessment, and subdivides the first-level indicator to set corresponding second-level indicators; collects indicator data of social events and pre-processes the indicator data, where the indicator data includes first-level indicator data and / or second-level indicator data; obtains conditional probability inference between first-level indicators and second-level indicators, and constructs a Bayesian network model; trains and tests the Bayesian network model based on the indicator data to obtain a trained Bayesian network; determines the situation of any social event based on the trained Bayesian model; and realizes situation assessment for dynamic multi-task social governance in the city.

[0084] Combination of the above Figure 1 The situation assessment method for dynamic multi-task social governance in urban areas provided by the embodiment of the present application is described in detail. The situation assessment system for dynamic multi-task social governance in urban areas is introduced below. The system includes:

[0085] The system construction module is used to build a dynamic and multi-task situation assessment indicator system for social governance. It constructs the first-level indicators of risk factors from four dimensions: severity of incidents, degree of social impact, response measures, and public participation assessment. It also subdivides the first-level indicators and sets corresponding second-level indicators.

[0086] A collection and processing module, used to collect indicator data of a social event and pre-process the indicator data, the indicator data includes primary indicator data and / or secondary indicator data;

[0087] The acquisition module is used to obtain the conditional probability inference between the primary index and the secondary index and build a Bayesian network model;

[0088] The training and testing module is used to train and test the Bayesian network model based on the indicator data to obtain the trained Bayesian network;

[0089] The judgment module is used to judge the situation of any social event based on the trained Bayesian model.

[0090] In addition, for the above-mentioned specific implementation of the system, since it is basically similar to the method implementation, the description is relatively simple, and the relevant parts can be referred to the partial description of the method implementation. Moreover, it should be noted that in each module of the system of the present application, the components therein are logically divided according to the functions to be implemented, but the present application is not limited thereto, and the components can be re-divided or combined as needed.

[0091] The above describes the situation assessment method and system for dynamic multi-task city-wide social governance provided by the embodiments of the present application. Figure 2 A detailed description is given of a situation assessment device for executing dynamic multi-tasks for urban social governance provided in an embodiment of the present application.

[0092] Figure 2 Schematic diagram of the structure of the situation assessment device for dynamic multi-task urban social governance provided by the embodiment of the present application. Figure 2 As shown, the situation assessment device 200 for dynamic multi-task urban social governance includes: a transceiver module 201 and a processing module 202. For ease of explanation, Figure 2 Only the main components of the dynamic multi-task situation assessment device for urban social governance are shown.

[0093] Among them, the transceiver module 201 is used to perform the transceiver function of the above-mentioned situation assessment method for dynamic multi-task social governance in urban areas, and the processing module 202 is used to perform other functions of the above-mentioned situation assessment method for dynamic multi-task social governance in urban areas except the transceiver function.

[0094] Optionally, the transceiver module 201 may include a sending module ( Figure 2 ) and a receiving module ( Figure 2 (not shown in the figure). The sending module is used to realize the sending function of the situation assessment device 200 for dynamic multi-task social governance in the city, and the receiving module is used to realize the receiving function of the situation assessment device 200 for dynamic multi-task social governance in the city.

[0095] Optionally, the situation assessment device 200 for dynamic multi-task urban social governance may also include a storage module ( Figure 2(not shown), the storage module stores a program or instruction. When the processing module 202 executes the program or instruction, the situation assessment device 200 for dynamic multi-task social governance in the city can execute the situation assessment method for dynamic multi-task social governance in the embodiment of the present application.

[0096] The embodiment of the present invention also provides a computer-readable storage medium, on which computer-executable instructions are stored, and the computer-executable instructions can execute the situation assessment method for dynamic multi-task of urban social governance of the present application. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (HDD) or a solid-state drive (SSD), etc.: the storage medium can also include a combination of the above-mentioned types of memory.

[0097] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between it and other embodiments.

[0098] The above is a description of a specific embodiment of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the specific order or sequential order shown in the process depicted in the drawings is not necessarily required to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0099] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A situation assessment method and system for dynamic multi-task urban social governance, characterized in that: The method comprises: Construct a dynamic and multi-task situation assessment indicator system for social governance, construct the first-level indicators of risk factors from four dimensions: severity of incidents, degree of social impact, response measures, and public participation assessment, and subdivide the first-level indicators and set corresponding second-level indicators; Collecting indicator data of social events and preprocessing the indicator data, wherein the indicator data includes primary indicator data and / or secondary indicator data; Obtaining conditional probability inference between the primary indicator and the secondary indicator, and constructing a Bayesian network model; Based on the indicator data, the Bayesian network model is trained and tested to obtain a trained Bayesian network; The situation of any social event is determined based on the trained Bayesian model.

2. The situation assessment method for dynamic multi-task urban social governance according to claim 1 is characterized in that: The first-level indicators of risk factors are constructed from four dimensions: severity of the incident, degree of social impact, response measures, and public participation assessment. The first-level indicators are subdivided and corresponding second-level indicators are set, including: The severity of the incident includes three secondary indicators: incident category attributes, casualties caused by the incident, and property losses caused by the incident; The degree of social impact includes three secondary indicators: economic impact, social stability impact and political impact; The response measures include three secondary indicators: response speed, resource allocation, and departmental collaboration; The public participation evaluation includes three secondary indicators: public attention, public participation, and public satisfaction.

3. The situation assessment method for dynamic multi-task urban social governance according to claim 1 is characterized in that: The preprocessing of the indicator data includes at least one of the following processing methods: 1) Data deduplication, removing duplicate records in the indicator data set; 2) For missing values ​​with a low proportion, delete them directly; 3) For important missing values, interpolation, mean, median, and mode can be used to fill them; 4) For abnormal values, directly delete them or replace them with reasonable values; 5) Convert data into unified formats and standards; 6) Automatically check and verify data by setting data validation rules.

4. The situation assessment method for dynamic multi-task urban social governance according to claim 1 is characterized in that: The obtaining of the conditional probability between the primary indicator and the secondary indicator and constructing a Bayesian network model includes: The first-level index and the second-level index are nodes of a Bayesian network; According to the EM algorithm, the conditional probability between each node is calculated to determine the conditional probability between each node; or, Based on expert opinions and instance data, the conditional probabilities between nodes are determined.

5. The situation assessment method for dynamic multi-task urban social governance according to claim 1 is characterized in that: The Bayesian network model is trained and tested based on the indicator data to obtain a trained Bayesian network, including: The preprocessed index data is divided into 12 parts by a 12-fold cross-validation method, one of which is used as a test set and the other 11 are used as training sets to train and test the Bayesian network model and obtain a trained Bayesian network.

6. The situation assessment method for dynamic multi-task urban social governance according to claim 1 is characterized in that: Before training and testing the Bayesian network model based on the indicator data, the method further includes: Perform Z-score normalization on the indicator data and scale the data to the interval of [-1, 1]. The standardization processing formula is: in, X is the original indicator data, μ is the mean of the indicator data, and σ is the standard deviation of the indicator data; The standardized indicator data is divided into corresponding intervals, and different levels are divided according to the intervals.

7. The situation assessment method for dynamic multi-task urban social governance according to claim 1 is characterized in that: The method further comprises: A human-computer interaction interface is used to input the indicator data of any social event, determine the situation of any social event according to the trained Bayesian model, and display the result to the user.

8. A dynamic multi-task situation assessment system for urban social governance, characterized by: The system comprises: The system construction module is used to build a dynamic and multi-task situation assessment indicator system for social governance, construct the first-level indicators of risk factors from four dimensions: severity of the incident, degree of social impact, response measures, and public participation assessment, and subdivide the first-level indicators and set corresponding second-level indicators; A collection and processing module, used to collect indicator data of a social event and pre-process the indicator data, wherein the indicator data includes primary indicator data and / or secondary indicator data; An acquisition module, used to obtain the conditional probability inference between the primary index and the secondary index, and construct a Bayesian network model; A training and testing module, used to train and test the Bayesian network model based on the indicator data to obtain a trained Bayesian network; The judgment module is used to judge the situation of any social event according to the trained Bayesian model.

9. A situation assessment device for dynamic multi-task urban social governance, characterized in that: The apparatus comprises: a module for executing the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a computer program or instruction stored therein, and when the computer program or instruction is executed, the method according to any one of claims 1 to 7 is performed.

Images