Community crowd data analysis method and system based on agent atlas and medium

Abstract

The invention provides a community crowd data analysis method and system based on an agent map and a medium. The method comprises the steps of obtaining a multi-source heterogeneous data set in a preset time period in a community through a data acquisition module, performing preprocessing to obtain an optimized multi-source heterogeneous data set, extracting feature data of an intelligent agent, querying through a preset behavior rule and habit database to obtain daily behavior data of the intelligent agent, and storing the daily behavior data of the intelligent agent. A community crowd agent model is obtained through an agent construction module, a community crowd agent map is obtained through an agent map construction module after a relation edge of the community crowd agent model is obtained, the community crowd agent map is processed through a data analysis module, community crowd feature data are obtained, and visual output is carried out. Community planning and management are further optimized; therefore, the scientificity and accuracy of community management and service are improved on the basis of community crowd analysis.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and more specifically, to a method, system and medium for analyzing community population data based on an intelligent agent graph. Background Art

[0002] With the acceleration of urbanization, communities, as the basic units of cities, face many challenges and opportunities in their management and development. Traditional methods of community population analysis are often limited to simple data statistics and local surveys, which make it difficult to fully and accurately grasp the complex interpersonal relationship networks, diverse behavioral motivations, and changing demand trends within the community. For example, the previous questionnaire-based survey method could only obtain limited sample information, and the data was less timely. Conventional database statistical analysis could hardly reveal the potential connections and interaction patterns between people. Intelligent agents, as an entity abstraction with autonomy, perception, decision-making, and interaction capabilities, can well simulate individual behaviors and characteristics in the community. At the same time, graph construction technology can present many intelligent agents and their relationships in an intuitive and structured way, which helps to deeply explore the hidden information behind community population data. By integrating these two technologies, a new community population analysis framework can be constructed to effectively improve the scientificity and accuracy of community management and services.

[0003] In view of the above problems, effective technical solutions are urgently needed. Summary of the invention

[0004] The purpose of this application is to provide a community population data analysis method, system and medium based on an agent graph, which can obtain a multi-source heterogeneous data set of a preset time period in the community through a data acquisition module, and perform preprocessing to obtain an optimized multi-source heterogeneous data set, extract agent feature data, obtain agent daily behavior data through preset behavior rules and habit database queries, and obtain a community population agent model through an agent construction module, obtain the relationship edges of the community population agent model, obtain a community population agent graph through an agent graph construction module, process the community population agent graph through a data analysis module, obtain community population feature data, and perform visual output, and optimize community planning and management, thereby improving the scientificity and accuracy of community management and services based on community population analysis.

[0005] This application also provides a community population data analysis method based on an agent graph, comprising the following steps: The data acquisition module is used to obtain a multi-source heterogeneous data set within a preset time period in the community, and the multi-source heterogeneous data set is preprocessed to obtain an optimized multi-source heterogeneous data set; Extracting agent feature data according to the optimized multi-source heterogeneous data set, obtaining agent daily behavior data through querying the preset behavior rules and habit database according to the agent feature data, and obtaining a community population agent model through an agent construction module; Obtain the relationship edge of the community population agent model, and obtain the community population agent graph through the agent graph construction module; Processing the community population intelligent agent map through a data analysis module to obtain community population characteristic data; The community population characteristic data is visualized and output, and community planning and management are optimized.

[0006] Optionally, in the community population data analysis method based on the agent graph described in the present application, the multi-source heterogeneous data set of a preset time period in the community is obtained by the data acquisition module, and the multi-source heterogeneous data set is preprocessed to obtain an optimized multi-source heterogeneous data set, including: The multi-source heterogeneous data set includes basic personnel information data, residential characteristics data, daily activity trajectory data, social interaction data and consumption behavior data; Through the data collection module, basic information data of personnel is obtained from the preset community household registration information database, residential characteristics data is obtained from the preset community property system, daily activity trajectory data is obtained from the preset mobile operator database, and consumption behavior data is obtained from the preset community surrounding commercial institution platform; The personnel basic information data, residential characteristic data, daily activity trajectory data, social interaction data and consumption behavior data are cleaned and normalized respectively to obtain an optimized multi-source heterogeneous data set.

[0007] Optionally, in the community population data analysis method based on the agent graph described in the present application, extracting agent feature data according to the optimized multi-source heterogeneous data set, obtaining agent daily behavior data through preset behavior rules and habit database query according to the agent feature data, and obtaining the community population agent model through the agent construction module, including: Extracting the identity tag data and corresponding multi-dimensional attribute data of the intelligent agent according to the optimized multi-source heterogeneous data set, wherein the multi-dimensional attribute data includes physiological attribute feature data, social attribute feature data, economic attribute feature data and spatial attribute feature data; According to the identity tag data of the intelligent agent, the daily behavior data of the intelligent agent is obtained by querying the preset behavior rules and habit database; A community population agent model is obtained through an agent construction module based on the identity tag data, physiological attribute feature data, social attribute feature data, economic attribute feature data, spatial attribute feature data and the agent daily behavior data.

[0008] Optionally, in the community population data analysis method based on the agent graph described in the present application, the step of obtaining the relationship edges of the community population agent model and obtaining the community population agent graph through an agent graph construction module includes: Obtaining relationship edges of the community crowd agent model, including neighbor relationship edges, friend relationship edges, kinship relationship edges, and business relationship edges; According to the neighborhood relationship edges, friend relationship edges, kinship relationship edges and business relationship edges, a community population agent map is obtained through an agent map construction module.

[0009] Optionally, in the community population data analysis method based on the agent graph described in the present application, the community population agent graph is processed by a data analysis module to obtain community population characteristic data, including: The community population agent map is processed by a data analysis module to obtain community population characteristic data, including network structure characteristic indicator data, community characteristic data, dynamic behavior characteristic data and agent influence evaluation data; The network structure characteristic index data include network density index data, average path length data, degree centrality data, betweenness centrality data and closeness centrality index data; The community characteristic data includes community category characteristic data and corresponding demographic characteristic data, socioeconomic characteristic data, behavioral pattern characteristic data and community evolution trend data; The dynamic behavior feature data includes daily activity trajectory data and consumption behavior change data.

[0010] Optionally, the community population data analysis method based on the agent graph described in the present application further includes: Acquire the residential distribution data of the agents in the community and the distance data between the agents, query the preset neighborhood relationship weight value list according to the residential distribution data and the distance data respectively and accumulate them to obtain the neighborhood relationship weight value, and modify the neighborhood relationship edge according to the neighborhood relationship weight value to obtain the neighborhood relationship optimization edge; Obtain the interaction frequency data and interaction depth data between agents within a preset time period, query the preset social relationship weight value list according to the interaction frequency data and interaction depth data respectively and accumulate them to obtain the social relationship weight value, and modify the friend relationship edge and the relative relationship edge according to the social relationship weight value respectively to obtain the friend relationship optimization edge and the relative relationship optimization edge; Obtain consumption venue grade data and corresponding consumption amount data and consumption frequency data of the intelligent body, query and accumulate preset business relationship weight value lists according to the consumption venue grade data and the corresponding consumption amount data and consumption frequency data, obtain business relationship weight values, and modify the business relationship edges according to the business relationship weight values ​​to obtain business relationship optimization edges; The community population intelligent agent graph is optimized according to the neighborhood relationship optimization edges, friend relationship optimization edges, kinship optimization edges and business relationship optimization edges to obtain the community population intelligent agent optimization graph.

[0011] In a second aspect, the present application provides a community population data analysis system based on an agent graph, the system comprising: a memory and a processor, the memory comprising a program of a community population data analysis method based on an agent graph, and the program of the community population data analysis method based on an agent graph is executed by the processor to implement the following steps: The data acquisition module is used to obtain a multi-source heterogeneous data set within a preset time period in the community, and the multi-source heterogeneous data set is preprocessed to obtain an optimized multi-source heterogeneous data set; Extracting agent feature data according to the optimized multi-source heterogeneous data set, obtaining agent daily behavior data through querying the preset behavior rules and habit database according to the agent feature data, and obtaining a community population agent model through an agent construction module; Obtain the relationship edge of the community population agent model, and obtain the community population agent graph through the agent graph construction module; Processing the community population intelligent agent map through a data analysis module to obtain community population characteristic data; The community population characteristic data is visualized and output, and community planning and management are optimized.

[0012] Optionally, in the community population data analysis system based on the agent graph described in the present application, the data acquisition module is used to obtain a multi-source heterogeneous data set for a preset time period in the community, and the multi-source heterogeneous data set is preprocessed to obtain an optimized multi-source heterogeneous data set, including: The multi-source heterogeneous data set includes basic personnel information data, residential characteristics data, daily activity trajectory data, social interaction data and consumption behavior data; Through the data collection module, basic information data of personnel is obtained from the preset community household registration information database, residential characteristics data is obtained from the preset community property system, daily activity trajectory data is obtained from the preset mobile operator database, and consumption behavior data is obtained from the preset community surrounding commercial institution platform; The personnel basic information data, residential characteristic data, daily activity trajectory data, social interaction data and consumption behavior data are cleaned and normalized respectively to obtain an optimized multi-source heterogeneous data set.

[0013] Optionally, in the community population data analysis system based on the agent graph described in the present application, extracting agent feature data according to the optimized multi-source heterogeneous data set, obtaining agent daily behavior data through preset behavior rules and habit database query according to the agent feature data, and obtaining the community population agent model through the agent construction module, including: Extracting the identity tag data and corresponding multi-dimensional attribute data of the intelligent agent according to the optimized multi-source heterogeneous data set, wherein the multi-dimensional attribute data includes physiological attribute feature data, social attribute feature data, economic attribute feature data and spatial attribute feature data; According to the identity tag data of the intelligent agent, the daily behavior data of the intelligent agent is obtained by querying the preset behavior rules and habit database; A community population agent model is obtained through an agent construction module based on the identity tag data, physiological attribute feature data, social attribute feature data, economic attribute feature data, spatial attribute feature data and the agent daily behavior data.

[0014] In the third aspect, the present application also provides a computer-readable storage medium, which stores a program for a community population data analysis method based on an intelligent agent graph. When the program for the community population data analysis method based on an intelligent agent graph is executed by a processor, the steps of the community population data analysis method based on an intelligent agent graph as described in any one of the above items are implemented.

[0015] From the above, it can be seen that the community population data analysis method, system and medium based on the agent graph provided by the present application obtain a multi-source heterogeneous data set of a preset time period in the community through a data acquisition module, and pre-process it to obtain an optimized multi-source heterogeneous data set, extract agent feature data, obtain the agent's daily behavior data through a preset behavior rule and habit database query, and obtain the community population agent model through an agent construction module, obtain the relationship edges of the community population agent model, obtain the community population agent graph through an agent graph construction module, process the community population agent graph through a data analysis module, obtain the community population feature data, and perform visual output, and optimize community planning and management, thereby realizing the improvement of the scientificity and accuracy of community management and services based on community population analysis.

[0016] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A flowchart of a community population data analysis method based on an agent graph provided in an embodiment of the present application; Figure 2 A flow chart of obtaining a community population intelligent agent model according to a community population data analysis method based on an intelligent agent graph provided in an embodiment of the present application; Figure 3 A flowchart of obtaining a community population intelligent agent map according to a community population data analysis method based on an intelligent agent map provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0020] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0021] Please refer to Figure 1 , Figure 1The flowchart of the community population data analysis method based on the agent graph in some embodiments of the present application. The community population data analysis method based on the agent graph is used in a terminal device, such as a computer, a mobile phone terminal, etc. The community population data analysis method based on the agent graph includes the following steps: S11, obtaining a multi-source heterogeneous data set in a preset time period in the community through a data acquisition module, and preprocessing the multi-source heterogeneous data set to obtain an optimized multi-source heterogeneous data set; S12, extracting agent feature data according to the optimized multi-source heterogeneous data set, obtaining agent daily behavior data through a preset behavior rule and habit database query based on the agent feature data, and obtaining a community population agent model through an agent construction module; S13, obtaining the relationship edge of the community population agent model, and obtaining the community population agent graph through the agent graph construction module; S14, processing the community population agent map through a data analysis module to obtain community population characteristic data; S15. Visualize and output the community population characteristic data, and optimize community planning and management.

[0022] It should be noted that in order to realize the intelligent analysis of the community population, it is necessary to comprehensively collect relevant data of the community population. First, obtain the multi-source heterogeneous data set of the preset time period in the community, and pre-process the multi-source heterogeneous data set to obtain the optimized multi-source heterogeneous data set. Then extract the intelligent agent feature data and query the preset behavior law and habit database to obtain the daily behavior data of the intelligent agent, and obtain the community population intelligent agent model through the intelligent agent construction module. Among them, the preset behavior law and habit database are obtained by querying the preset community population data analysis platform, and then obtain the relationship edges between the intelligent agent models, and connect the constructed intelligent agents according to a variety of complex relationship edges. Next, the community population intelligent agent map is obtained through the intelligent agent map construction module. Finally, a variety of advanced data analysis algorithms are used to deeply mine and analyze the intelligent agent map to obtain community population characteristic data, and visualize the output to generate intuitive and easy-to-understand charts, graphical interfaces or detailed reports. The analysis results are widely used in various aspects of community planning and management practice. For example, in terms of optimizing the layout of community public facilities, based on the distribution and demand characteristics of the population, large parks, comprehensive fitness centers and other facilities are planned and built in areas with high population density and strong leisure demand, and elderly activity centers and community medical service stations are added in areas with concentrated elderly populations.

[0023] According to an embodiment of the present invention, the method of acquiring a multi-source heterogeneous data set in a preset time period in a community through a data acquisition module, and preprocessing the multi-source heterogeneous data set to obtain an optimized multi-source heterogeneous data set includes: The multi-source heterogeneous data set includes basic personnel information data, residential characteristics data, daily activity trajectory data, social interaction data and consumption behavior data; Through the data collection module, basic information data of personnel is obtained from the preset community household registration information database, residential characteristics data is obtained from the preset community property system, daily activity trajectory data is obtained from the preset mobile operator database, and consumption behavior data is obtained from the preset community surrounding commercial institution platform; The personnel basic information data, residential characteristic data, daily activity trajectory data, social interaction data and consumption behavior data are cleaned and normalized respectively to obtain an optimized multi-source heterogeneous data set.

[0024] It should be noted that in order to achieve accurate analysis of the community population, relevant data of the community population should be collected comprehensively to obtain a multi-source heterogeneous data set including basic information data of personnel, residential characteristics data, daily activity trajectory data, social interaction data and consumption behavior data, and clean and normalize the preprocessing to remove erroneous values ​​or outliers to obtain an optimized multi-source heterogeneous data set. Among them, basic information data of personnel include name and ID number data, residential characteristics data include housing area, house ownership, length of residence, property fee payment records and water and electricity usage data, daily activity trajectory data include daily travel starting point, passing location, stay time, travel frequency and periodic regularity data, social interaction data include friend list records, social group classification, chat records, interaction record data, consumption behavior data include consumption place level, consumption time, consumption category, consumption amount data.

[0025] Please refer to Figure 2 , Figure 2 It is a flow chart of obtaining a community population intelligent agent model of a community population data analysis method based on an intelligent agent graph in some embodiments of the present application. According to an embodiment of the present invention, extracting intelligent agent feature data according to the optimized multi-source heterogeneous data set, obtaining intelligent agent daily behavior data according to the intelligent agent feature data by querying a preset behavior law and habit database, and obtaining a community population intelligent agent model through an intelligent agent construction module, including: S21, extracting the identity tag data and corresponding multi-dimensional attribute data of the intelligent agent according to the optimized multi-source heterogeneous data set, where the multi-dimensional attribute data includes physiological attribute feature data, social attribute feature data, economic attribute feature data and spatial attribute feature data; S22, obtaining the daily behavior data of the agent through querying the preset behavior rules and habit database according to the identity tag data of the agent; S23. Obtain a community population agent model through an agent construction module based on the identity tag data, physiological attribute feature data, social attribute feature data, economic attribute feature data, spatial attribute feature data and the agent daily behavior data.

[0026] It should be noted that after obtaining the optimized multi-source heterogeneous data set, data extraction is performed to obtain the identity label data and corresponding multidimensional attribute data of the agent, the multidimensional attribute data includes physiological attribute feature data, social attribute feature data, economic attribute feature data and spatial attribute feature data, the physiological attribute feature data includes height, weight, and health status data, the social attribute feature data includes occupation type, work unit, position level, education level data, economic attribute feature data includes personal and family income level, asset status, debt status and consumer credit rating data, the spatial attribute feature data includes the longitude and latitude of the residential address, the scope of the activity area, and the spatial distance data between the workplace and the residence. Then, according to the identity label data, the daily behavior data of the agent is obtained by querying the preset behavior law and habit database, wherein the preset behavior law and habit database is obtained by querying the preset community population data analysis platform, and finally, according to the identity label data, the physiological attribute feature data, the social attribute feature data, the economic attribute feature data and the spatial attribute feature data as well as the daily behavior data of the agent, the community population agent model is obtained through the agent construction module for describing independent agents.

[0027] Please refer to Figure 3 , Figure 3 The method for analyzing community population data based on agent graph in some embodiments of the present application is a flow chart for obtaining an agent graph of a community population. According to an embodiment of the present invention, the step of obtaining the relationship edge of the agent model of the community population and obtaining the agent graph of the community population through an agent graph construction module includes: S31, obtaining the relationship edges of the community crowd agent model, including neighbor relationship edges, friend relationship edges, kinship relationship edges and business relationship edges; S32. Obtain a community population agent map through an agent map construction module based on the neighborhood relationship edges, friend relationship edges, kinship relationship edges and business relationship edges.

[0028] It should be noted that in order to construct independent agents into an agent graph, it is necessary to connect them based on multiple relationships to obtain the community population agent model including relationship edges of neighborhood relationship edges, friend relationship edges, relative relationship edges and business relationship edges. According to the neighborhood relationship edges, friend relationship edges, relative relationship edges and business relationship edges, the community population agent graph is obtained through the agent graph construction module, which is used to express the relationship between people in the community.

[0029] According to an embodiment of the present invention, the data analysis module is used to process the community population agent graph to obtain community population characteristic data, including: The community population agent map is processed by a data analysis module to obtain community population characteristic data, including network structure characteristic indicator data, community characteristic data, dynamic behavior characteristic data and agent influence evaluation data; The network structure characteristic index data include network density index data, average path length data, degree centrality data, betweenness centrality data and closeness centrality index data; The community characteristic data includes community category characteristic data and corresponding demographic characteristic data, socioeconomic characteristic data, behavioral pattern characteristic data and community evolution trend data; The dynamic behavior feature data includes daily activity trajectory data and consumption behavior change data.

[0030] It should be noted that technicians in this field use a variety of advanced data analysis algorithms to conduct in-depth mining and analysis of the agent graph to obtain community population characteristic data including network structure characteristic indicator data, community characteristic data, dynamic behavior characteristic data and agent influence evaluation data. The network structure characteristic indicator data include network density indicator data, average path length data, degree centrality data, betweenness centrality data and proximity centrality indicator data. Among them, the network density indicator data refers to the ratio of the actual number of agent relationship edges to the maximum possible number of relationship edges, reflecting the overall connection density of the community population. The higher the value, the closer the connection between the community population, and the more frequent the information dissemination and interaction may be. The average path length data refers to the average number of intermediate agents that need to be passed from one agent to another. The degree centrality data refers to the number of other agents directly connected to a certain agent. The betweenness centrality data refers to the number of agents directly connected to a certain agent. The data refers to the number of times an agent appears on the shortest path between other agents. The proximity centrality index data refers to the average distance between an agent and other agents. The community characteristic data includes community category characteristic data and corresponding demographic characteristic data, socioeconomic characteristic data, behavioral pattern characteristic data and community evolution trend data. Among them, demographic characteristic data include age distribution data, gender ratio and occupation distribution data, socioeconomic characteristic data include average income level and consumption capacity distribution data, behavioral pattern characteristic data include consumption habit data and travel regularity data, and community evolution trend data include community size change data and member flow record data. It can accurately locate the demand differences and behavioral characteristics of different groups in the community, and provide guidance for the accurate allocation of community resources and personalized services. Dynamic behavioral characteristic data include daily activity trajectory data and consumption behavior change data. The influence evaluation data of agents refers to the influence of agents in the community.

[0031] According to an embodiment of the present invention, it also includes: Acquire the residential distribution data of the agents in the community and the distance data between the agents, query the preset neighborhood relationship weight value list according to the residential distribution data and the distance data respectively and accumulate them to obtain the neighborhood relationship weight value, and modify the neighborhood relationship edge according to the neighborhood relationship weight value to obtain the neighborhood relationship optimization edge; Obtain the interaction frequency data and interaction depth data between agents within a preset time period, query the preset social relationship weight value list according to the interaction frequency data and interaction depth data respectively and accumulate them to obtain the social relationship weight value, and modify the friend relationship edge and the relative relationship edge according to the social relationship weight value respectively to obtain the friend relationship optimization edge and the relative relationship optimization edge; Obtain consumption venue grade data and corresponding consumption amount data and consumption frequency data of the intelligent body, query and accumulate preset business relationship weight value lists according to the consumption venue grade data and the corresponding consumption amount data and consumption frequency data, obtain business relationship weight values, and modify the business relationship edges according to the business relationship weight values ​​to obtain business relationship optimization edges; The community population intelligent agent graph is optimized according to the neighborhood relationship optimization edges, friend relationship optimization edges, kinship optimization edges and business relationship optimization edges to obtain the community population intelligent agent optimization graph.

[0032] It should be noted that in order to more accurately describe the relationship between each intelligent agent, the neighborhood relationship edges, friend relationship edges, relative relationship edges and business relationship edges are optimized respectively through the relationship weight analysis and calculation between intelligent agents to obtain the corresponding neighborhood relationship optimized edges, friend relationship optimized edges, relative relationship optimized edges and business relationship optimized edges, and the community population intelligent agent map is further optimized to obtain the community population intelligent agent optimized map, among which the preset neighborhood relationship weight value list, preset social relationship weight value list and preset business relationship weight value list are obtained by querying the preset community population data analysis platform.

[0033] It is worth mentioning that according to an embodiment of the present invention, it also includes: Processing the social relationship weight value in combination with a preset basic propagation probability value of the agent to obtain a propagation probability value of the agent; Get the number of times the agent converts the susceptible state agent to the infected state; The influence evaluation data of the intelligent agent is obtained by processing according to the propagation probability value and the frequency value.

[0034] It should be noted that in order to accurately obtain the influence evaluation data of the agent, this embodiment adopts the SIR (susceptible-infectious-recovered) model for processing. First, the social relationship weight value is combined with the preset basic propagation probability value of the agent to calculate and obtain the propagation probability value of the agent. In the SIR model, each agent in the infected state has a propagation probability, which is used to indicate the possibility of transmitting information, behavior or concept to the susceptible state agent. Among them, the susceptible state refers to the individual state that has not been exposed to specific information and has no obvious obstacles to information reception based on its agent attributes and relationship network. The infected state refers to the individual state that the agent has received the information and started to spread the information. The propagation probability value calculation formula is: ; in, is the propagation probability value, , are the social relationship weight value and the preset basic propagation probability value respectively. The preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset community population data analysis platform); Then obtain the number of times the intelligent agent converts the susceptible state intelligent agent into the infected state, perform calculations based on the transmission probability value and the number of times, and obtain the influence evaluation data of the intelligent agent; The calculation formula for the influence evaluation data is: ; in, For impact assessment data, , are the propagation probability and frequency values ​​respectively, It is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset community population data analysis platform).

[0035] It is worth mentioning that according to an embodiment of the present invention, it also includes: Obtain air quality data and water quality assessment data within the preset range of the intelligent body, process the air quality data and water quality assessment data with the preset air quality standard data and water quality assessment benchmark data respectively, and obtain the air quality deviation rate and water quality deviation rate; Obtaining the health assessment data of the intelligent body, processing it in combination with the air quality deviation rate and the water quality deviation rate, and obtaining the health risk assessment index of the intelligent body; Comparing the health risk assessment index with a preset health risk level threshold to obtain the health risk level of the agent, including high health risk, medium health risk or low health risk; Obtain the economic income data, asset data and liability data of the intelligent entity, and process them to obtain the financial risk assessment index of the intelligent entity; Compare the financial risk assessment index with a preset financial risk level threshold to obtain the financial risk level of the agent, including high financial risk, medium financial risk or low financial risk; According to the health risk level and the financial risk level, respectively query the preset weight value list to obtain the health risk weight value and the financial risk weight value; Processing the health risk assessment index and the financial risk assessment index in combination with the health risk weight value and the financial risk weight value to obtain a comprehensive risk index of the intelligent agent; Compare the comprehensive risk index with the preset risk threshold to obtain the risk status of the agent, including normal status or abnormal status; If it is less than or equal to the preset risk threshold, the risk state of the agent is determined to be normal; If it is greater than the preset risk threshold, the agent's risk state is determined to be abnormal.

[0036] It should be noted that the introduction of risk assessment evaluates various risks faced by the community population based on the multi-dimensional attributes and behavior patterns of the intelligent agent. First, the health risk level is evaluated based on the health status of the environment and the intelligent agent, and the air quality data and water quality assessment data within the preset range of the intelligent agent are obtained. The air quality data and water quality assessment data are processed with the preset air quality standard data and water quality assessment benchmark data respectively to obtain the air quality deviation rate and water quality deviation rate. Among them, the air quality deviation rate refers to the ratio of the absolute value of the difference between the air quality data and the air quality standard data to the air quality standard data. Similarly, the water quality deviation rate can be obtained and processed in combination with the health assessment data of the intelligent agent to obtain the health risk assessment index of the intelligent agent. The health risk assessment index calculation formula is: ; in, is the health risk assessment index, , , They are health assessment data, air quality deviation rate and water quality deviation rate, , The preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset community population data analysis platform); The health risk assessment index is compared with the preset health risk level threshold. In this embodiment, the preset health risk level threshold is set to (0, 0.3], (0.3, 0.7], (0.7, 1], corresponding to low health risk, medium health risk, and high health risk, respectively. For example, the obtained health risk assessment index is 0.2, corresponding to low health risk, the obtained health risk assessment index is 0.5, corresponding to medium health risk, and the obtained health risk assessment index is 0.8, corresponding to high health risk; Then, the financial risk assessment index of the intelligent entity is obtained by processing the economic income data, asset data and liability data of the intelligent entity; The calculation formula of the financial risk assessment index is: ; in, is the financial risk assessment index. , , They are economic income data, asset data and liability data. , The preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset community population data analysis platform); The obtained financial risk assessment index is compared with the preset financial risk level threshold. In this embodiment, the preset financial risk level threshold is set to (0, 0.35], (0.35, 0.75], (0.75, 1], corresponding to low financial risk, medium financial risk, and high financial risk, respectively. For example, the obtained financial risk assessment index is 0.2, corresponding to low financial risk, the obtained financial risk assessment index is 0.4, corresponding to medium financial risk, and the obtained financial risk assessment index is 0.8, corresponding to high financial risk; According to the calculated health risk level and financial risk level, the preset weight value list is queried respectively to obtain the health risk weight value and the financial risk weight value, wherein the preset weight value list is obtained by querying the preset community population data analysis platform; According to the health risk assessment index and the financial risk assessment index, the health risk weight value and the financial risk weight value are processed to obtain the comprehensive risk index of the intelligent body; The calculation formula of the comprehensive risk index is: ; in, To comprehensively evaluate the risk index, , , , are the health risk assessment index, financial risk assessment index, health risk weight value and financial risk weight value respectively. The preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset community population data analysis platform); Finally, the obtained comprehensive risk index is compared with the preset risk threshold to obtain the risk status of the agent. In this embodiment, the preset risk threshold is set to (0, 0.75], (0.75, 1], corresponding to the normal state and the abnormal state, respectively. For example, if the obtained comprehensive risk index is 0.7, the risk status of the agent is determined to be normal. If the obtained comprehensive risk index is 0.8, the risk status of the agent is determined to be abnormal. Through risk assessment and analysis, potential risk points in the community can be identified in advance, and corresponding risk prevention and response plans can be formulated.

[0037] The present invention also discloses a community population data analysis system based on an agent graph, comprising a memory and a processor, wherein the memory comprises a community population data analysis method program based on an agent graph, and when the community population data analysis method program based on an agent graph is executed by the processor, the following steps are implemented: The data acquisition module is used to obtain a multi-source heterogeneous data set within a preset time period in the community, and the multi-source heterogeneous data set is preprocessed to obtain an optimized multi-source heterogeneous data set; Extracting agent feature data according to the optimized multi-source heterogeneous data set, obtaining agent daily behavior data through querying the preset behavior rules and habit database according to the agent feature data, and obtaining a community population agent model through an agent construction module; Obtain the relationship edge of the community population agent model, and obtain the community population agent graph through the agent graph construction module; Processing the community population intelligent agent map through a data analysis module to obtain community population characteristic data; The community population characteristic data is visualized and output, and community planning and management are optimized.

[0038] It should be noted that in order to realize the intelligent analysis of the community population, it is necessary to comprehensively collect relevant data of the community population. First, obtain the multi-source heterogeneous data set of the preset time period in the community, and pre-process the multi-source heterogeneous data set to obtain the optimized multi-source heterogeneous data set. Then extract the intelligent agent feature data and query the preset behavior law and habit database to obtain the daily behavior data of the intelligent agent, and obtain the community population intelligent agent model through the intelligent agent construction module. Among them, the preset behavior law and habit database are obtained by querying the preset community population data analysis platform, and then obtain the relationship edges between the intelligent agent models, and connect the constructed intelligent agents according to a variety of complex relationship edges. Next, the community population intelligent agent map is obtained through the intelligent agent map construction module. Finally, a variety of advanced data analysis algorithms are used to deeply mine and analyze the intelligent agent map to obtain community population characteristic data, and visualize the output to generate intuitive and easy-to-understand charts, graphical interfaces or detailed reports. The analysis results are widely used in various aspects of community planning and management practice. For example, in terms of optimizing the layout of community public facilities, based on the distribution and demand characteristics of the population, large parks, comprehensive fitness centers and other facilities are planned and built in areas with high population density and strong leisure demand, and elderly activity centers and community medical service stations are added in areas with concentrated elderly populations.

[0039] According to an embodiment of the present invention, the method of acquiring a multi-source heterogeneous data set in a preset time period in a community through a data acquisition module, and preprocessing the multi-source heterogeneous data set to obtain an optimized multi-source heterogeneous data set includes: The multi-source heterogeneous data set includes basic personnel information data, residential characteristics data, daily activity trajectory data, social interaction data and consumption behavior data; Through the data collection module, basic information data of personnel is obtained from the preset community household registration information database, residential characteristics data is obtained from the preset community property system, daily activity trajectory data is obtained from the preset mobile operator database, and consumption behavior data is obtained from the preset community surrounding commercial institution platform; The personnel basic information data, residential characteristic data, daily activity trajectory data, social interaction data and consumption behavior data are cleaned and normalized respectively to obtain an optimized multi-source heterogeneous data set.

[0040] It should be noted that in order to achieve accurate analysis of the community population, relevant data of the community population should be collected comprehensively to obtain a multi-source heterogeneous data set including basic information data of personnel, residential characteristics data, daily activity trajectory data, social interaction data and consumption behavior data, and clean and normalize the preprocessing to remove erroneous values ​​or outliers to obtain an optimized multi-source heterogeneous data set. Among them, basic information data of personnel include name and ID number data, residential characteristics data include housing area, house ownership, length of residence, property fee payment records and water and electricity usage data, daily activity trajectory data include daily travel starting point, passing location, stay time, travel frequency and periodic regularity data, social interaction data include friend list records, social group classification, chat records, interaction record data, consumption behavior data include consumption place level, consumption time, consumption category, consumption amount data.

[0041] According to an embodiment of the present invention, extracting agent feature data according to the optimized multi-source heterogeneous data set, obtaining agent daily behavior data through preset behavior rules and habit database query according to the agent feature data, and obtaining a community population agent model through an agent construction module, includes: Extracting the identity tag data and corresponding multi-dimensional attribute data of the intelligent agent according to the optimized multi-source heterogeneous data set, wherein the multi-dimensional attribute data includes physiological attribute feature data, social attribute feature data, economic attribute feature data and spatial attribute feature data; According to the identity tag data of the intelligent agent, the daily behavior data of the intelligent agent is obtained by querying the preset behavior rules and habit database; A community population agent model is obtained through an agent construction module based on the identity tag data, physiological attribute feature data, social attribute feature data, economic attribute feature data, spatial attribute feature data and the agent daily behavior data.

[0042] It should be noted that after obtaining the optimized multi-source heterogeneous data set, data extraction is performed to obtain the identity label data and corresponding multidimensional attribute data of the agent, the multidimensional attribute data includes physiological attribute feature data, social attribute feature data, economic attribute feature data and spatial attribute feature data, the physiological attribute feature data includes height, weight, and health status data, the social attribute feature data includes occupation type, work unit, position level, education level data, economic attribute feature data includes personal and family income level, asset status, debt status and consumer credit rating data, the spatial attribute feature data includes the longitude and latitude of the residential address, the scope of the activity area, and the spatial distance data between the workplace and the residence. Then, according to the identity label data, the daily behavior data of the agent is obtained by querying the preset behavior law and habit database, wherein the preset behavior law and habit database is obtained by querying the preset community population data analysis platform, and finally, according to the identity label data, the physiological attribute feature data, the social attribute feature data, the economic attribute feature data and the spatial attribute feature data as well as the daily behavior data of the agent, the community population agent model is obtained through the agent construction module for describing independent agents.

[0043] According to an embodiment of the present invention, the step of obtaining the relationship edge of the community population agent model and obtaining the community population agent graph through an agent graph construction module includes: Obtaining relationship edges of the community crowd agent model, including neighbor relationship edges, friend relationship edges, kinship relationship edges, and business relationship edges; According to the neighborhood relationship edges, friend relationship edges, kinship relationship edges and business relationship edges, a community population agent map is obtained through an agent map construction module.

[0044] It should be noted that in order to construct independent agents into an agent graph, it is necessary to connect them based on multiple relationships to obtain the community population agent model including relationship edges of neighborhood relationship edges, friend relationship edges, relative relationship edges and business relationship edges. According to the neighborhood relationship edges, friend relationship edges, relative relationship edges and business relationship edges, the community population agent graph is obtained through the agent graph construction module, which is used to express the relationship between people in the community.

[0045] According to an embodiment of the present invention, the data analysis module is used to process the community population agent graph to obtain community population characteristic data, including: The community population agent map is processed by a data analysis module to obtain community population characteristic data, including network structure characteristic indicator data, community characteristic data, dynamic behavior characteristic data and agent influence evaluation data; The network structure characteristic index data include network density index data, average path length data, degree centrality data, betweenness centrality data and closeness centrality index data; The community characteristic data includes community category characteristic data and corresponding demographic characteristic data, socioeconomic characteristic data, behavioral pattern characteristic data and community evolution trend data; The dynamic behavior feature data includes daily activity trajectory data and consumption behavior change data.

[0046] It should be noted that technicians in this field use a variety of advanced data analysis algorithms to conduct in-depth mining and analysis of the agent graph to obtain community population characteristic data including network structure characteristic indicator data, community characteristic data, dynamic behavior characteristic data and agent influence evaluation data. The network structure characteristic indicator data include network density indicator data, average path length data, degree centrality data, betweenness centrality data and proximity centrality indicator data. Among them, the network density indicator data refers to the ratio of the actual number of agent relationship edges to the maximum possible number of relationship edges, reflecting the overall connection density of the community population. The higher the value, the closer the connection between the community population, and the more frequent the information dissemination and interaction may be. The average path length data refers to the average number of intermediate agents that need to be passed from one agent to another. The degree centrality data refers to the number of other agents directly connected to a certain agent. The betweenness centrality data refers to the number of agents directly connected to a certain agent. The data refers to the number of times an agent appears on the shortest path between other agents. The proximity centrality index data refers to the average distance between an agent and other agents. The community characteristic data includes community category characteristic data and corresponding demographic characteristic data, socioeconomic characteristic data, behavioral pattern characteristic data and community evolution trend data. Among them, demographic characteristic data include age distribution data, gender ratio and occupation distribution data, socioeconomic characteristic data include average income level and consumption capacity distribution data, behavioral pattern characteristic data include consumption habit data and travel regularity data, and community evolution trend data include community size change data and member flow record data. It can accurately locate the demand differences and behavioral characteristics of different groups in the community, and provide guidance for the accurate allocation of community resources and personalized services. Dynamic behavioral characteristic data include daily activity trajectory data and consumption behavior change data. The influence evaluation data of agents refers to the influence of agents in the community.

[0047] According to an embodiment of the present invention, it also includes: Acquire the residential distribution data of the agents in the community and the distance data between the agents, query the preset neighborhood relationship weight value list according to the residential distribution data and the distance data respectively and accumulate them to obtain the neighborhood relationship weight value, and modify the neighborhood relationship edge according to the neighborhood relationship weight value to obtain the neighborhood relationship optimization edge; Obtain the interaction frequency data and interaction depth data between agents within a preset time period, query the preset social relationship weight value list according to the interaction frequency data and interaction depth data respectively and accumulate them to obtain the social relationship weight value, and modify the friend relationship edge and the relative relationship edge according to the social relationship weight value respectively to obtain the friend relationship optimization edge and the relative relationship optimization edge; Obtain consumption venue grade data and corresponding consumption amount data and consumption frequency data of the intelligent body, query and accumulate preset business relationship weight value lists according to the consumption venue grade data and the corresponding consumption amount data and consumption frequency data, obtain business relationship weight values, and modify the business relationship edges according to the business relationship weight values ​​to obtain business relationship optimization edges; The community population intelligent agent graph is optimized according to the neighborhood relationship optimization edges, friend relationship optimization edges, kinship optimization edges and business relationship optimization edges to obtain the community population intelligent agent optimization graph.

[0048] It should be noted that in order to more accurately describe the relationship between each intelligent agent, the neighborhood relationship edges, friend relationship edges, relative relationship edges and business relationship edges are optimized respectively through the relationship weight analysis and calculation between intelligent agents to obtain the corresponding neighborhood relationship optimized edges, friend relationship optimized edges, relative relationship optimized edges and business relationship optimized edges, and the community population intelligent agent map is further optimized to obtain the community population intelligent agent optimized map, among which the preset neighborhood relationship weight value list, preset social relationship weight value list and preset business relationship weight value list are obtained by querying the preset community population data analysis platform.

[0049] It is worth mentioning that according to an embodiment of the present invention, it also includes: Processing the social relationship weight value in combination with a preset basic propagation probability value of the agent to obtain a propagation probability value of the agent; Get the number of times the agent converts the susceptible state agent to the infected state; The influence evaluation data of the intelligent agent is obtained by processing according to the propagation probability value and the frequency value.

[0050] It should be noted that in order to accurately obtain the influence evaluation data of the agent, this embodiment adopts the SIR (susceptible-infectious-recovered) model for processing. First, the social relationship weight value is combined with the preset basic propagation probability value of the agent to calculate and obtain the propagation probability value of the agent. In the SIR model, each agent in the infected state has a propagation probability, which is used to indicate the possibility of transmitting information, behavior or concept to the susceptible state agent. Among them, the susceptible state refers to the individual state that has not been exposed to specific information and has no obvious obstacles to information reception based on its agent attributes and relationship network. The infected state refers to the individual state that the agent has received the information and started to spread the information. The propagation probability value calculation formula is: ; in, is the propagation probability value, , are the social relationship weight value and the preset basic propagation probability value respectively. The preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset community population data analysis platform); Then obtain the number of times the intelligent agent converts the susceptible state intelligent agent into the infected state, perform calculations based on the transmission probability value and the number of times, and obtain the influence evaluation data of the intelligent agent; The calculation formula for the influence evaluation data is: ; in, For impact assessment data, , are the propagation probability and frequency values ​​respectively, It is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset community population data analysis platform).

[0051] It is worth mentioning that according to an embodiment of the present invention, it also includes: Obtain air quality data and water quality assessment data within the preset range of the intelligent body, process the air quality data and water quality assessment data with the preset air quality standard data and water quality assessment benchmark data respectively, and obtain the air quality deviation rate and water quality deviation rate; Obtaining the health assessment data of the intelligent body, processing it in combination with the air quality deviation rate and the water quality deviation rate, and obtaining the health risk assessment index of the intelligent body; Comparing the health risk assessment index with a preset health risk level threshold to obtain the health risk level of the agent, including high health risk, medium health risk or low health risk; Obtain the economic income data, asset data and liability data of the intelligent entity, and process them to obtain the financial risk assessment index of the intelligent entity; Compare the financial risk assessment index with a preset financial risk level threshold to obtain the financial risk level of the agent, including high financial risk, medium financial risk or low financial risk; According to the health risk level and the financial risk level, respectively query the preset weight value list to obtain the health risk weight value and the financial risk weight value; Processing the health risk assessment index and the financial risk assessment index in combination with the health risk weight value and the financial risk weight value to obtain a comprehensive risk index of the intelligent agent; Compare the comprehensive risk index with the preset risk threshold to obtain the risk status of the agent, including normal status or abnormal status; If it is less than or equal to the preset risk threshold, the risk state of the agent is determined to be normal; If it is greater than the preset risk threshold, the agent's risk state is determined to be abnormal.

[0052] It should be noted that the introduction of risk assessment evaluates various risks faced by the community population based on the multi-dimensional attributes and behavior patterns of the intelligent agent. First, the health risk level is evaluated based on the health status of the environment and the intelligent agent, and the air quality data and water quality assessment data within the preset range of the intelligent agent are obtained. The air quality data and water quality assessment data are processed with the preset air quality standard data and water quality assessment benchmark data respectively to obtain the air quality deviation rate and water quality deviation rate. Among them, the air quality deviation rate refers to the ratio of the absolute value of the difference between the air quality data and the air quality standard data to the air quality standard data. Similarly, the water quality deviation rate can be obtained and processed in combination with the health assessment data of the intelligent agent to obtain the health risk assessment index of the intelligent agent. The health risk assessment index calculation formula is: ; in, is the health risk assessment index, , , They are health assessment data, air quality deviation rate and water quality deviation rate, , The preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset community population data analysis platform); The health risk assessment index is compared with the preset health risk level threshold. In this embodiment, the preset health risk level threshold is set to (0, 0.3], (0.3, 0.7], (0.7, 1], corresponding to low health risk, medium health risk, and high health risk, respectively. For example, the obtained health risk assessment index is 0.2, corresponding to low health risk, the obtained health risk assessment index is 0.5, corresponding to medium health risk, and the obtained health risk assessment index is 0.8, corresponding to high health risk; Then, the financial risk assessment index of the intelligent entity is obtained by processing the economic income data, asset data and liability data of the intelligent entity; The calculation formula of the financial risk assessment index is: ; in, is the financial risk assessment index. , , They are economic income data, asset data and liability data. , The preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset community population data analysis platform); The obtained financial risk assessment index is compared with the preset financial risk level threshold. In this embodiment, the preset financial risk level threshold is set to (0, 0.35], (0.35, 0.75], (0.75, 1], corresponding to low financial risk, medium financial risk, and high financial risk, respectively. For example, the obtained financial risk assessment index is 0.2, corresponding to low financial risk, the obtained financial risk assessment index is 0.4, corresponding to medium financial risk, and the obtained financial risk assessment index is 0.8, corresponding to high financial risk; According to the calculated health risk level and financial risk level, the preset weight value list is queried respectively to obtain the health risk weight value and the financial risk weight value, wherein the preset weight value list is obtained by querying the preset community population data analysis platform; According to the health risk assessment index and the financial risk assessment index, the health risk weight value and the financial risk weight value are processed to obtain the comprehensive risk index of the intelligent body; The calculation formula of the comprehensive risk index is: ; in, To comprehensively evaluate the risk index, , , , are the health risk assessment index, financial risk assessment index, health risk weight value and financial risk weight value respectively. The preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset community population data analysis platform); Finally, the obtained comprehensive risk index is compared with the preset risk threshold to obtain the risk status of the agent. In this embodiment, the preset risk threshold is set to (0, 0.75], (0.75, 1], corresponding to the normal state and the abnormal state, respectively. For example, if the obtained comprehensive risk index is 0.7, the risk status of the agent is determined to be normal. If the obtained comprehensive risk index is 0.8, the risk status of the agent is determined to be abnormal. Through risk assessment and analysis, potential risk points in the community can be identified in advance, and corresponding risk prevention and response plans can be formulated.

[0053] The third aspect of the present invention provides a readable storage medium, which stores a program for a community population data analysis method based on an intelligent agent graph. When the program for the community population data analysis method based on an intelligent agent graph is executed by a processor, the steps of the community population data analysis method based on an intelligent agent graph as described in any one of the above items are implemented.

[0054] The community population data analysis method, system and medium based on the intelligent agent graph disclosed in the present invention obtain a multi-source heterogeneous data set of a preset time period in the community through a data acquisition module, and perform preprocessing to obtain an optimized multi-source heterogeneous data set, extract intelligent agent feature data, obtain the intelligent agent daily behavior data through a preset behavior rule and habit database query, and obtain a community population intelligent agent model through an intelligent agent construction module, obtain the relationship edges of the community population intelligent agent model, obtain a community population intelligent agent graph through an intelligent agent graph construction module, process the community population intelligent agent graph through a data analysis module, obtain community population feature data, and perform visualization output, and optimize community planning and management, thereby improving the scientificity and accuracy of community management and services based on community population analysis.

[0055] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0056] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0057] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0058] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, the aforementioned program can be stored in a readable storage medium, and when the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0059] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A community population data analysis method based on agent graph, characterized in that: The following steps are involved: The data acquisition module is used to obtain a multi-source heterogeneous data set within a preset time period in the community, and the multi-source heterogeneous data set is preprocessed to obtain an optimized multi-source heterogeneous data set; Extracting agent feature data according to the optimized multi-source heterogeneous data set, obtaining agent daily behavior data through querying the preset behavior rules and habit database according to the agent feature data, and obtaining a community population agent model through an agent construction module; Obtain the relationship edge of the community population agent model, and obtain the community population agent graph through the agent graph construction module; Processing the community population intelligent agent map through a data analysis module to obtain community population characteristic data; The community population characteristic data is visualized and output, and community planning and management are optimized.

2. The method for analyzing community population data based on agent graph according to claim 1 is characterized in that: The method of acquiring a multi-source heterogeneous data set in a preset time period in the community through a data acquisition module and preprocessing the multi-source heterogeneous data set to obtain an optimized multi-source heterogeneous data set includes: The multi-source heterogeneous data set includes basic personnel information data, residential characteristics data, daily activity trajectory data, social interaction data and consumption behavior data; Through the data collection module, basic information data of personnel is obtained from the preset community household registration information database, residential characteristics data is obtained from the preset community property system, daily activity trajectory data is obtained from the preset mobile operator database, and consumption behavior data is obtained from the preset community surrounding commercial institution platform; The personnel basic information data, residential characteristic data, daily activity trajectory data, social interaction data and consumption behavior data are cleaned and normalized respectively to obtain an optimized multi-source heterogeneous data set.

3. The method for analyzing community population data based on agent graph according to claim 2 is characterized in that: The method of extracting agent feature data according to the optimized multi-source heterogeneous data set, obtaining agent daily behavior data through a preset behavior rule and habit database query according to the agent feature data, and obtaining a community population agent model through an agent construction module includes: Extracting the identity tag data and corresponding multi-dimensional attribute data of the intelligent agent according to the optimized multi-source heterogeneous data set, wherein the multi-dimensional attribute data includes physiological attribute feature data, social attribute feature data, economic attribute feature data and spatial attribute feature data; According to the identity tag data of the intelligent agent, the daily behavior data of the intelligent agent is obtained by querying the preset behavior rules and habit database; A community population agent model is obtained through an agent construction module based on the identity tag data, physiological attribute feature data, social attribute feature data, economic attribute feature data, spatial attribute feature data and the agent daily behavior data.

4. The method for analyzing community population data based on agent graph according to claim 3 is characterized in that: The step of obtaining the relationship edge of the community population agent model and obtaining the community population agent graph through an agent graph construction module includes: Obtaining relationship edges of the community crowd agent model, including neighbor relationship edges, friend relationship edges, kinship relationship edges, and business relationship edges; According to the neighborhood relationship edges, friend relationship edges, kinship relationship edges and business relationship edges, a community population agent map is obtained through an agent map construction module.

5. The method for analyzing community population data based on agent graph according to claim 4 is characterized in that: The data analysis module processes the community population agent graph to obtain community population characteristic data, including: The community population agent map is processed by a data analysis module to obtain community population characteristic data, including network structure characteristic indicator data, community characteristic data, dynamic behavior characteristic data and agent influence evaluation data; The network structure characteristic index data include network density index data, average path length data, degree centrality data, betweenness centrality data and closeness centrality index data; The community characteristic data includes community category characteristic data and corresponding demographic characteristic data, socioeconomic characteristic data, behavioral pattern characteristic data and community evolution trend data; The dynamic behavior feature data includes daily activity trajectory data and consumption behavior change data.

6. The method for analyzing community population data based on agent graph according to claim 5 is characterized in that: Also includes: Acquire the residential distribution data of the agents in the community and the distance data between the agents, query the preset neighborhood relationship weight value list according to the residential distribution data and the distance data respectively and accumulate them to obtain the neighborhood relationship weight value, and modify the neighborhood relationship edge according to the neighborhood relationship weight value to obtain the neighborhood relationship optimization edge; Obtain the interaction frequency data and interaction depth data between agents within a preset time period, query the preset social relationship weight value list according to the interaction frequency data and interaction depth data respectively and accumulate them to obtain the social relationship weight value, and modify the friend relationship edge and the relative relationship edge according to the social relationship weight value respectively to obtain the friend relationship optimization edge and the relative relationship optimization edge; Obtain consumption venue grade data and corresponding consumption amount data and consumption frequency data of the intelligent body, query and accumulate preset business relationship weight value lists according to the consumption venue grade data and the corresponding consumption amount data and consumption frequency data, obtain business relationship weight values, and modify the business relationship edges according to the business relationship weight values ​​to obtain business relationship optimization edges; The community population intelligent agent graph is optimized according to the neighborhood relationship optimization edges, friend relationship optimization edges, kinship optimization edges and business relationship optimization edges to obtain the community population intelligent agent optimization graph.

7. The community population data analysis system based on the agent graph is characterized by: The method comprises a memory and a processor, wherein the memory comprises a program of a community population data analysis method based on an agent graph, and when the program of the community population data analysis method based on an agent graph is executed by the processor, the following steps are implemented: The data acquisition module is used to obtain a multi-source heterogeneous data set within a preset time period in the community, and the multi-source heterogeneous data set is preprocessed to obtain an optimized multi-source heterogeneous data set; Extracting agent feature data according to the optimized multi-source heterogeneous data set, obtaining agent daily behavior data through querying the preset behavior rules and habit database according to the agent feature data, and obtaining a community population agent model through an agent construction module; Obtain the relationship edge of the community population agent model, and obtain the community population agent graph through the agent graph construction module; Processing the community population intelligent agent map through a data analysis module to obtain community population characteristic data; The community population characteristic data is visualized and output, and community planning and management are optimized.

8. The community population data analysis system based on agent graph according to claim 7 is characterized in that: The method of acquiring a multi-source heterogeneous data set in a preset time period in the community through a data acquisition module and preprocessing the multi-source heterogeneous data set to obtain an optimized multi-source heterogeneous data set includes: The multi-source heterogeneous data set includes basic personnel information data, residential characteristics data, daily activity trajectory data, social interaction data and consumption behavior data; Through the data collection module, basic information data of personnel is obtained from the preset community household registration information database, residential characteristics data is obtained from the preset community property system, daily activity trajectory data is obtained from the preset mobile operator database, and consumption behavior data is obtained from the preset community surrounding commercial institution platform; The personnel basic information data, residential characteristic data, daily activity trajectory data, social interaction data and consumption behavior data are cleaned and normalized respectively to obtain an optimized multi-source heterogeneous data set.

9. The community population data analysis system based on agent graph according to claim 8 is characterized in that: The method of extracting agent feature data according to the optimized multi-source heterogeneous data set, obtaining agent daily behavior data through a preset behavior rule and habit database query according to the agent feature data, and obtaining a community population agent model through an agent construction module includes: Extracting the identity tag data and corresponding multi-dimensional attribute data of the intelligent agent according to the optimized multi-source heterogeneous data set, wherein the multi-dimensional attribute data includes physiological attribute feature data, social attribute feature data, economic attribute feature data and spatial attribute feature data; According to the identity tag data of the intelligent agent, the daily behavior data of the intelligent agent is obtained by querying the preset behavior rules and habit database; A community population agent model is obtained through an agent construction module based on the identity tag data, physiological attribute feature data, social attribute feature data, economic attribute feature data, spatial attribute feature data and the agent daily behavior data.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program for a community population data analysis method based on an agent graph. When the program for a community population data analysis method based on an agent graph is executed by a processor, the steps of the community population data analysis method based on an agent graph as described in any one of claims 1 to 6 are implemented.

Images