Multi-dimensional dynamic association decision analysis method and system based on agent atlas and medium

Abstract

The invention provides a multi-dimensional dynamic association decision analysis method and system based on an agent map and a medium. The method comprises the steps of obtaining multi-source data and performing standardization processing, identifying various agents, establishing an attribute model and constructing a multi-dimensional agent map, fusing and dynamically updating the multi-dimensional agent map, associating the multi-dimensional agent map, performing decision evaluation and credibility judgment, and obtaining and displaying an optimal credible decision scheme. Therefore, deep mining and intelligent analysis of multi-source data are realized through multi-dimensional dynamic fusion and association analysis of the unified data model and the agent graph, comprehensive and accurate decision support can be provided, and improvement of urban governance level, operation efficiency and intelligent development is facilitated.

Description

Technical Field

[0001] This application relates to the technical field of data processing and analysis. Specifically, it relates to a multi-dimensional dynamic association decision analysis method, system, and medium based on an agent graph. Background Art

[0002] With the acceleration of the urbanization process and the development of information technology, a large amount of multi-source data has been generated in cities, including government affairs data, Internet of Things perception data, Internet data, etc. Traditional urban decision analysis methods often have difficulty effectively integrating these complex and diverse data resources and cannot provide comprehensive and accurate decision support for urban governance, resource allocation, precise services, etc. from a multi-dimensional and dynamically associated perspective. For example, there are limitations in dealing with major issues such as population management, traffic congestion, and environmental pollution.

[0003] In view of the above problems, there is an urgent need for effective technical solutions. Summary of the Invention

[0004] The purpose of this application is to provide a multi-dimensional dynamic association decision analysis method, system, and medium based on an agent graph. Through a unified data model, multi-dimensional dynamic fusion and association analysis of the agent graph, as well as decision evaluation and credibility judgment, an optimal credible decision plan is obtained and displayed, realizing in-depth mining and intelligent analysis of multi-source data, helping to improve the level of urban governance and operation efficiency, and promoting the intelligent development of cities.

[0005] This application also provides a multi-dimensional dynamic association decision analysis method based on an agent graph, including the following steps: Obtain multi-source data and perform preprocessing and standardization processing to obtain standardized multi-source data; Identify various types of agents to establish a multi-dimensional agent attribute model, and construct a multi-dimensional agent graph according to the graph structure; Fuse the standardized multi-source data with the multi-dimensional agent graph, and perform data dynamic update processing on the agent graph; Associate the multi-dimensional agent graph to obtain the internal association rules of the agents; Process the internal association rules to obtain multiple decision results and evaluation results, select the optimal decision plan for evaluation and credibility judgment, and display the credible decision plan.

[0006] Optionally, in the multi-dimensional dynamic association decision analysis method based on an agent graph described in this application, the step of obtaining multi-source data and performing preprocessing and standardization processing to obtain standardized multi-source data includes: Obtain multi-source data through a predetermined urban big data source, including administrative data, perception data, and Internet data; Preprocess the multi-source data; Standardize the preprocessed multi-source data through a preset data conversion tool to obtain standardized multi-source data.

[0007] Optionally, in the multi-dimensional dynamic association decision analysis method based on the agent map in this application, the identification of various agents to establish a multi-dimensional agent attribute model and the construction of a multi-dimensional agent map according to the graph structure include: Identify various agents and extract basic features and behavior patterns; Establish a multi-dimensional agent attribute model according to the basic features and behavior patterns; Construct a graph structure according to the node and boundary relationships of the multi-dimensional agent attribute model; Annotate the graph structure through a preset NLP model to construct a multi-dimensional agent map.

[0008] Optionally, in the multi-dimensional dynamic association decision analysis method based on the agent map in this application, the fusion of the standardized multi-source data with the multi-dimensional agent map and the dynamic data update processing of the agent map include: Fuse the standardized multi-source data with the multi-dimensional agent map through a preset data processing model; Dynamically collect multi-source data according to a preset time rule to update the data of the agent map.

[0009] Optionally, in the multi-dimensional dynamic association decision analysis method based on the agent map in this application, the association of the multi-dimensional agent map to obtain the internal association rules of the agents includes: Perform multi-dimensional association analysis on the agent map through a preset multi-dimensional association analysis model to obtain an association analysis result, and the multi-dimensions include time, space, and theme; Process the association analysis result through a preset map model to obtain the association rules of the agents.

[0010] Optionally, in the multi-dimensional dynamic association decision analysis method based on the agent map in this application, the processing of the internal association rules to obtain multiple decision results and an evaluation result, select the optimal decision plan for evaluation and credibility judgment, and display the credible decision plan, including: Obtain a preset urban management operation model; Process according to the association rules in combination with the preset urban management operation model to obtain multiple decision results; Process multiple decision results through a preset decision evaluation model to obtain the evaluation results corresponding to each decision result; Sort the evaluation results corresponding to each decision result to obtain the optimal decision plan; Evaluate the optimal decision plan according to a preset decision analysis method to obtain decision evaluation parameters; Compare the decision evaluation parameters with preset evaluation thresholds to judge the credibility of the optimal decision plan; If the credibility passes, visually display the optimal decision plan.

[0011] In a second aspect, the present application provides a multi-dimensional dynamic association decision analysis system based on an agent map. The system includes: a memory and a processor. The memory includes a program of a multi-dimensional dynamic association decision analysis method based on an agent map. When the program of the multi-dimensional dynamic association decision analysis method based on an agent map is executed by the processor, the following steps are implemented: Obtain multi-source data and perform preprocessing and standardization processing to obtain standardized multi-source data; Identify various types of agents to establish a multi-dimensional agent attribute model, and construct a multi-dimensional agent map according to the graph structure; Fuse the standardized multi-source data with the multi-dimensional agent map, and perform data dynamic update processing on the agent map; Associate the multi-dimensional agent map to obtain the internal association rules of the agents; Process the internal association rules to obtain multiple decision results and evaluation results, select the optimal decision plan for evaluation and credibility judgment, and display the credible decision plan.

[0012] Optionally, in the multi-dimensional dynamic association decision analysis system based on an agent map described in the present application, the obtaining multi-source data and performing preprocessing and standardization processing to obtain standardized multi-source data includes: Obtain multi-source data through a predetermined urban big data source, including administrative data, perception data, and Internet data; Perform preprocessing on the multi-source data; Perform standardization processing on the preprocessed multi-source data through a preset data conversion tool to obtain standardized multi-source data.

[0013] Optionally, in the multi-dimensional dynamic association decision analysis system based on an agent map described in the present application, the identifying various types of agents to establish a multi-dimensional agent attribute model and constructing a multi-dimensional agent map according to the graph structure includes: Identify various types of agents and extract basic features and behavior patterns; Establish a multi-dimensional agent attribute model according to the basic features and behavior patterns; Construct a graph structure according to the node and boundary relationships of the multi-dimensional agent attribute model; Annotate the graph structure through a preset NLP model to construct a multi-dimensional agent map.

[0014] In a third aspect, the present application also provides a computer-readable storage medium storing a program for a multi-dimensional dynamic association decision analysis method based on an agent map. When the program for the multi-dimensional dynamic association decision analysis method based on the agent map is executed by a processor, the steps of the multi-dimensional dynamic association decision analysis method based on the agent map as described in any one of the above are implemented.

[0015] As can be seen from the above, the multi-dimensional dynamic association decision analysis method, system, and medium provided by the present application acquire multi-source data and perform standardized processing, identify various types of agents, establish an attribute model, construct a multi-dimensional agent map, fuse and dynamically update the multi-dimensional agent map, associate the multi-dimensional agent map, as well as perform decision evaluation and credibility judgment to obtain and display an optimal credible decision plan; thereby, through a unified data model, multi-dimensional dynamic fusion and association analysis of the agent map, as well as decision evaluation and credibility judgment, in-depth mining and intelligent analysis of multi-source data are realized, providing comprehensive, accurate, and dynamic decision support for urban decision-makers, helping to improve urban governance levels and operating efficiency, and promoting urban intelligent development.

[0016] Other features and advantages of the present application will be described in the subsequent specification, and, in part, will be obvious from the specification, or will be understood by implementing the embodiments of the present application. The objectives and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written specification and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of the multi-dimensional dynamic association decision analysis method based on an agent map provided by the embodiments of the present application; Figure 2 It is a flowchart of data collection and preprocessing of the multi-dimensional dynamic association decision analysis method based on an agent map provided by the embodiments of the present application; Figure 3 It is a flowchart of agent modeling and map construction of the multi-dimensional dynamic association decision analysis method based on an agent map provided by the embodiments of the present application; Figure 4 Flowchart of multi - dimensional dynamic data fusion for the multi - dimensional dynamic association decision - making analysis method based on an agent map provided by an embodiment of the present application. Detailed implementation manners

[0019] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying 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 the embodiments. Components of the embodiments of the present application usually described and illustrated in the accompanying 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 accompanying drawings is not intended to limit the scope of the claimed present application, but merely represents the selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0020] It should be noted that similar reference numerals and letters indicate similar items in the following drawings. Therefore, 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 the present application, terms such as "first", "second", etc. are only used for differential description and cannot be understood as indicating or implying relative importance.

[0021] Please refer to Figure 1 , Figure 1 which is a flowchart of the multi - dimensional dynamic association decision - making analysis method based on an agent map in some embodiments of the present application. The multi - dimensional dynamic association decision - making analysis method based on an agent map is used in terminal devices, such as computers, mobile phone terminals, etc. The multi - dimensional dynamic association decision - making analysis method based on an agent map includes the following steps: S11. Obtain multi - source data and perform pre - processing and standardization processing to obtain standardized multi - source data; S12. Identify various types of agents to establish a multi - dimensional agent attribute model, and construct a multi - dimensional agent map according to the graph structure; S13. Integrate the standardized multi - source data with the multi - dimensional agent map, and perform data dynamic update processing on the agent map; S14. Associate the multi - dimensional agent map to obtain the internal association rules of the agents; S15. Process the internal association rules to obtain multiple decision results and evaluation results, select the optimal decision plan for evaluation and credibility judgment, and display the credible decision plan.

[0022] Among them, various data from different big data platforms are collected and processed to establish an agent attribute model and construct a multi-dimensional agent map. At the same time, through dynamic fusion and correlation analysis of the agent map, as well as decision evaluation and credibility judgment, an optimal credible decision-making scheme is obtained and displayed, realizing in-depth mining and intelligent analysis of multi-source data, providing comprehensive, accurate, and dynamic decision-making support for urban decision-makers, helping to improve the urban governance level and operation efficiency, and promoting the intelligent development of the city.

[0023] Please refer to Figure 2 , Figure 2 is a flowchart of data collection and preprocessing of the multi-dimensional dynamic association decision-making analysis method based on the agent map in some embodiments of the present application. According to the embodiments of the present invention, the obtaining of multi-source data and performing preprocessing and standardization processing to obtain standardized multi-source data includes: S21. Obtain multi-source data through a predetermined urban big data source, including administrative data, perception data, and Internet data; S22. Perform preprocessing on the multi-source data; S23. Perform standardization processing on the preprocessed multi-source data through a preset data conversion tool to obtain standardized multi-source data.

[0024] Among them, urban data from multiple channels is obtained through a preset urban big data management platform or data source library by means of Kafka collection tools, etc. In the embodiments of this solution, the multi-source data includes administrative data, perception data, and Internet data. Among them, the administrative data includes data on urban population, regional distribution, and economy, the perception data includes real-time perception data on traffic, roads, and vehicle density, and the Internet data includes data on urban information and traffic warnings. Then, according to a preset rule engine, various types of multi-source data are denoised, repaired, and cleaned to obtain preprocessed multi-source data. Then, the multi-source data is standardized through a preset data conversion tool such as an ETL tool, including unifying the data format and encoding to obtain standardized data, ensuring the fusibility of different data sources.

[0025] Please refer to Figure 3 , Figure 3 is a flowchart of agent modeling and map construction of the multi-dimensional dynamic association decision-making analysis method based on the agent map in some embodiments of the present application. According to the embodiments of the present invention, the identifying various agents to establish a multi-dimensional agent attribute model and constructing a multi-dimensional agent map according to the graph structure includes: S31. Identify various agents and extract basic features and behavior patterns; S32. Establish a multi-dimensional agent attribute model according to the basic features and behavior patterns; S33. Construct a graph structure according to the node and boundary relationships of the multi-dimensional agent attribute model; S34. Annotate the graph structure through a preset NLP model to construct a multi-dimensional agent map.

[0026] Among them, various types of agents including residents, enterprises, institutions, facilities, and roads are identified, and corresponding basic features and behavior patterns are extracted, such as enterprise operation characteristics, resident behavior patterns, road traffic characteristics, etc. Then, a multi-dimensional agent attribute model is established according to the features and patterns to describe the associated attributes of their features and patterns. After that, taking the core attributes of the agents as nodes and connecting them with boundary relationships to obtain a graph structure, and annotating the graph structure through a preset NLP model such as the BERT model, including the types of edges such as semantic labels, weight quantization relationship strengths, and time relationship attributes, to construct a multi-dimensional agent map.

[0027] Please refer to Figure 4 , Figure 4 is a flowchart of multi-dimensional dynamic data fusion of the multi-dimensional dynamic association decision analysis method based on the agent map in some embodiments of the present application. According to the embodiments of the present invention, the standardized multi-source data is fused with the multi-dimensional agent map, and data dynamic update processing is performed on the agent map, including: S41. Through a preset data processing model, fuse the standardized multi-source data with the multi-dimensional agent map; S42. Dynamically collect multi-source data according to a preset time rule and update the data of the agent map.

[0028] Among them, the preset data processing models include the CLIP model (processing cross-modal feature alignment) and the graph embedding model (processing complex relationship structures). The processed multi-source data is fused with the multi-dimensional agent map to achieve the integration of data in the agent dimension. For example, in the embodiments of this solution, the vehicle passing data is fused with the road planning data of the Internet map to enrich the feature information of urban traffic and vehicle agents, and the dynamic operation data of enterprises is fused with the Internet of Things perception data to reflect the association between the enterprise operation state and the environment. Then, according to the preset time rule, multi-source data is dynamically collected through a preset time period to update the relevant data information in the agent map, ensuring that the map can dynamically reflect the timeliness of the change in the operation state.

[0029] According to the embodiments of the present invention, the multi-dimensional agent map is associated to obtain the internal association rules of the agents, including: Perform multi-dimensional association analysis on the agent map through a preset multi-dimensional association analysis model to obtain an association analysis result. The multi-dimensions include time, space, and theme; Process the association analysis result through a preset map model to obtain the association rules of the agents.

[0030] Among them, multi-dimensional analysis and association of the agent atlas in terms of time, space, and subject are performed. For example, the relationship between the street where the vehicle commutes at a certain time and the traffic congestion situation, the personnel travel density, and the community density distribution is analyzed to obtain the internal association analysis results. Then, the association analysis results are processed through a preset atlas model such as a distributed graph computing engine, and the internal associations of the association analysis results are mined through graph algorithms and learning models to obtain the internal association rules of the agents, providing a comprehensive perspective and in-depth insight effect for decision-making.

[0031] According to the embodiments of the present invention, processing the internal association rules to obtain multiple decision results and evaluation results, selecting the optimal decision plan for evaluation and credibility judgment, and displaying the credible decision plan includes: Obtain a preset urban management operation model; Process according to the association rules in combination with the preset urban management operation model to obtain multiple decision results; Process the multiple decision results through a preset decision evaluation model to obtain the evaluation results corresponding to each decision result; Sort the evaluation results corresponding to each decision result to obtain the optimal decision plan; Evaluate the optimal decision plan according to a preset decision analysis method to obtain decision evaluation parameters; Compare the decision evaluation parameters with a preset evaluation threshold to judge the credibility of the optimal decision plan; If the credibility passes, visually display the optimal decision plan.

[0032] Among them, according to the internal association rules (multi-dimensional dynamic association analysis results), in combination with the resource allocation and precise services of the preset urban management operation model, etc., multiple decision plans and corresponding decision results are obtained. Then, through the decision evaluation model, the decision evaluation data is analyzed for each decision result, and further calculation and processing are performed to obtain the evaluation results. Then, the corresponding optimal decision plan is selected by sorting and selecting the best. The plan is evaluated according to a preset decision analysis method such as the Analytic Hierarchy Process (AHP). For example, through the multi-criteria Analytic Hierarchy Process, the traffic flow changes, travel duration changes, operation optimization, and commuting cost changes during the implementation of the urban decision plan are analyzed to obtain the decision evaluation parameters. Then, through the threshold comparison, the credibility of the optimization results of the plan implementation is judged. The plan that meets the requirements of the preset threshold comparison is used as a credible plan, and the plan is displayed through a preset visualization medium such as a terminal device, facilitating decision-makers to understand the urban operation situation and decision change effectiveness at any time, and realizing dynamic decision analysis.

[0033] It is worth mentioning that processing the multiple decision results through a preset decision evaluation model to obtain the evaluation results corresponding to each decision result includes: Evaluate multiple decision results through a preset decision evaluation model to obtain decision evaluation data; The decision evaluation data includes cost-benefit estimation data, feasibility estimation data, and influence estimation data; Process and calculate the cost-benefit estimation data, feasibility estimation data, and influence estimation data to obtain corresponding evaluation results.

[0034] Among them, evaluate and analyze the decision results through a decision evaluation model to obtain decision evaluation data, including evaluation data on cost, difficulty feasibility, and influence. Then, perform normalization processing and weighted calculation processing on the decision evaluation data to obtain evaluation results. The weighting coefficients of each decision estimation data are weighted according to the cost, difficulty, and influence of each plan. The sum of the three weighting coefficients is 1. The weighting coefficient distributions of different plans are different. The evaluation results are obtained through normalization and weighted summation processing.

[0035] In a second aspect, the present invention also discloses a multi-dimensional dynamic association decision analysis system based on an agent graph, including a memory and a processor. The memory includes a multi-dimensional dynamic association decision analysis method program based on an agent graph. When the multi-dimensional dynamic association decision analysis method program is executed by the processor, the following steps are implemented: Obtain multi-source data and perform preprocessing and standardization processing to obtain standardized multi-source data; Identify various agents to establish a multi-dimensional agent attribute model, and construct a multi-dimensional agent graph according to the graph structure; Fuse the standardized multi-source data with the multi-dimensional agent graph, and perform data dynamic update processing on the agent graph; Associate the multi-dimensional agent graph to obtain the internal association rules of the agents; Process the internal association rules to obtain multiple decision results and evaluation results, select the optimal decision plan for evaluation and credibility judgment, and display the credible decision plan.

[0036] Among them, collect and process various data from different big data platforms, establish an agent attribute model, construct a multi-dimensional agent graph. At the same time, through dynamic fusion and association analysis of the agent graph, obtain decision plans and display them through a visual interface, realizing in-depth mining and intelligent analysis of multi-source data, providing comprehensive, accurate, and dynamic decision support for urban decision-makers, helping to improve the level of urban governance and operation efficiency, and promoting the intelligent development of cities.

[0037] According to an embodiment of the present invention, the obtaining of multi-source data and performing preprocessing and standardization processing to obtain standardized multi-source data includes: Obtain multi-source data through a predetermined urban big data source, including administrative data, perception data, and Internet data; Preprocess the multi-source data; Perform standardization processing on the preprocessed multi-source data through a preset data conversion tool to obtain standardized multi-source data.

[0038] Among them, multiple channels of urban data are obtained through a preset urban big data management platform or data source library by means of Kafka collection tools, etc. In the embodiments of this solution, the multi-source data includes administrative data, perception data, and Internet data. Among them, the administrative data includes data on urban population, regional distribution, and economy, the perception data includes real-time perception data on traffic, roads, and vehicle density, and the Internet data includes data on urban information and traffic warnings. Then, according to a preset rule engine, various types of multi-source data are denoised, repaired, and cleaned to obtain preprocessed multi-source data. Subsequently, the multi-source data is standardized through a preset data conversion tool such as an ETL tool, including unifying the data format and encoding, to obtain standardized data and ensure the fusibility of different data sources.

[0039] According to the embodiments of the present invention, the identification of various types of agents to establish a multi-dimensional agent attribute model and the construction of a multi-dimensional agent map according to the graph structure include: Identify various types of agents and extract basic features and behavior patterns; Establish a multi-dimensional agent attribute model according to the basic features and behavior patterns; Construct a graph structure according to the node and boundary relationships of the multi-dimensional agent attribute model; Annotate the graph structure through a preset NLP model to construct a multi-dimensional agent map.

[0040] Among them, various types of agents including residents, enterprises, institutions, facilities, and roads are identified, and corresponding basic features and behavior patterns are extracted, such as enterprise operation characteristics, resident behavior patterns, road traffic characteristics, etc. Then, a multi-dimensional agent attribute model is established according to the features and patterns to describe the associated attributes of their features and patterns. Subsequently, a graph structure is obtained by taking the core attributes of the agents as nodes and connecting them with boundary relationships. The graph structure is annotated through a preset NLP model such as the BERT model, including the type of edges such as semantic labels, weight quantization to represent the relationship strength, and time relationship attributes, to construct a multi-dimensional agent map.

[0041] According to the embodiments of the present invention, the fusion of the standardized multi-source data and the multi-dimensional agent map and the data dynamic update processing of the agent map include: Fuse the standardized multi-source data and the multi-dimensional agent map through a preset data processing model; Dynamically collect multi-source data according to preset time rules to update the data of the agent graph.

[0042] Among them, through preset data processing models including the CLIP model (processing cross-modal feature alignment) and the graph embedding model (processing complex relationship structures), the processed multi-source data is fused with the multi-dimensional agent graph to achieve the integration of data in the agent dimension. For example, in the embodiment of this solution, the vehicle passing data is fused with the road planning data of the Internet map to enrich the feature information of urban traffic and vehicle agents, and the dynamic operation data of enterprises is fused with the Internet of Things perception data to reflect the correlation between the enterprise operation status and the environment. Then, according to the preset time rules, multi-source data is dynamically collected through preset time periods to update the relevant data information in the agent graph, ensuring that the graph can dynamically reflect the timeliness of the change in the operation status.

[0043] According to the embodiment of the present invention, the multi-dimensional agent graph is associated to obtain the internal association rules of the agent, including: Perform multi-dimensional association analysis on the agent graph through a preset multi-dimensional association analysis model to obtain the association analysis result. The multi-dimensions include time, space, and theme; Process the association analysis result through a preset graph model to obtain the association rules of the agent.

[0044] Among them, perform multi-dimensional analysis and association of time, space, and subject on the agent graph. For example, analyze the relationship between the streets where vehicles commute during a certain time and the traffic congestion status, the density of personnel travel, and the density distribution of communities to obtain the internal association analysis result. Then, process the association analysis result through a preset graph model such as a distributed graph computing engine, and mine the internal association of the association analysis result through graph algorithms and learning models to obtain the internal association rules of the agent, providing a comprehensive perspective and in-depth insight effect for decision-making.

[0045] According to the embodiment of the present invention, the internal association rules are processed to obtain multiple decision results and evaluation results, select the optimal decision plan for evaluation and credibility judgment, and display the credible decision plan, including: Obtain a preset urban management operation model; Process according to the association rules in combination with the preset urban management operation model to obtain multiple decision results; Process multiple decision results through a preset decision evaluation model to obtain the evaluation results corresponding to each decision result; Sort the evaluation results corresponding to each decision result to obtain the optimal decision plan; Evaluate the optimal decision plan according to a preset decision analysis method to obtain decision evaluation parameters; Compare the decision evaluation parameters with the preset evaluation thresholds to judge the credibility of the optimal decision-making plan; If the credibility passes, visualize the optimal decision-making plan.

[0046] Among them, according to the internal association rules (the results of multi-dimensional dynamic association analysis), combined with the resource allocation and precise services of the preset urban management operation model, etc., multiple decision-making plans and corresponding decision results are obtained. Then, through the decision evaluation model, the decision evaluation data is obtained by analyzing each decision result. Further calculation and processing are carried out to obtain the evaluation result. Then, the optimal decision-making plan is selected by sorting and selecting the best. The plan is evaluated according to the preset decision analysis method such as the Analytic Hierarchy Process (AHP). For example, through the multi-criteria AHP, the traffic flow changes, travel time changes, business optimization, and commuting cost changes during the implementation of the urban decision-making plan are analyzed to obtain the decision evaluation parameters. Then, through the threshold comparison, the credibility of the optimization results of the plan implementation is judged. The plan that meets the preset threshold comparison requirements is used as a credible plan, and the plan is displayed through a preset visualization medium such as a terminal device, so that decision-makers can understand the urban operation situation and the effectiveness of decision changes at any time, and realize dynamic decision analysis.

[0047] It is worth mentioning that the processing of multiple decision results through the preset decision evaluation model to obtain the evaluation results corresponding to each decision result includes: Conduct decision evaluation on multiple decision results through the preset decision evaluation model to obtain decision evaluation data; The decision evaluation data includes cost-benefit estimation data, feasibility estimation data, and influence estimation data; Process and calculate the cost-benefit estimation data, feasibility estimation data, and influence estimation data to obtain the corresponding evaluation results.

[0048] Among them, through the decision evaluation model, the decision results are evaluated and analyzed to obtain the decision evaluation data, including the evaluation data of cost, difficulty feasibility, and influence. Then, the decision evaluation data is normalized and weighted calculation is carried out to obtain the evaluation result. The weighting coefficients of each decision estimation data are weighted according to the cost, difficulty, and influence of each plan. The sum of the three weighting coefficients is 1, and the weighting coefficient distribution of different plans is different. The evaluation result is obtained through normalization and weighted summation processing.

[0049] The third aspect of the present invention provides a readable storage medium, in which a program of the multi-dimensional dynamic association decision analysis method based on the agent map is stored. When the program of the multi-dimensional dynamic association decision analysis method based on the agent map is executed by a processor, the steps of the multi-dimensional dynamic association decision analysis method based on the agent map as described in any one of the above are realized.

[0050] The multi-dimensional dynamic association decision analysis method, system and medium based on the intelligent agent map disclosed by the present invention obtain multi-source data and perform standardized processing, identify various intelligent agents, establish an attribute model, construct a multi-dimensional intelligent agent map, fuse and dynamically update the multi-dimensional intelligent agent map, associate the multi-dimensional intelligent agent map, and perform decision evaluation and credibility judgment to obtain and display the optimal credible decision-making plan; thus, through a unified data model, multi-dimensional dynamic fusion and association analysis of the intelligent agent map, as well as decision evaluation and credibility judgment, the deep mining and intelligent analysis of multi-source data are realized, providing comprehensive, accurate and dynamic decision-making support for urban decision-makers, helping to improve the urban governance level and operation efficiency, and promoting the intelligent development of the city.

[0051] In 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 illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, 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. The indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0052] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0053] In addition, in each embodiment of the present invention, the functional units can all be integrated in a processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in one unit; the above integrated units can be implemented in the form of hardware, or in the form of hardware plus software functional units.

[0054] Those of ordinary skill 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 foregoing program can be stored in a readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: various media that can store program codes such as mobile storage devices, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical discs.

[0055] Alternatively, if the above integrated units of the present invention are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. The software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

Claims

1. A multi-dimensional dynamic association decision analysis method based on an agent map, characterized in that, It includes the following steps: Obtain multi-source data and perform preprocessing and standardization to obtain standardized multi-source data; Identify various types of agents, establish a multi-dimensional agent attribute model, and construct a multi-dimensional agent atlas according to the graph structure; Fuse the standardized multi-source data with the multi-dimensional agent atlas, and perform data dynamic update processing on the agent atlas; Associate the multi-dimensional agent atlas to obtain the internal association rules of the agents; Process the internal association rules to obtain multiple decision results and evaluation results, select the optimal decision plan for evaluation and credibility judgment, and display the credible decision plan.

2. The multi-dimensional dynamic association decision analysis method based on the agent graph according to claim 1, wherein The obtaining of multi-source data and performing preprocessing and standardization to obtain standardized multi-source data includes: Obtain multi-source data through a predetermined urban big data source, including administrative data, perception data, and Internet data; Perform preprocessing on the multi-source data; Perform standardization processing on the preprocessed multi-source data through a preset data conversion tool to obtain standardized multi-source data.

3. The multi-dimensional dynamic association decision analysis method based on the intelligent agent map according to claim 2, wherein The identifying of various types of agents, establishing a multi-dimensional agent attribute model, and constructing a multi-dimensional agent atlas according to the graph structure includes: Identify various types of agents and extract basic features and behavior patterns; Establish a multi-dimensional agent attribute model according to the basic features and behavior patterns; Construct a graph structure according to the node and boundary relationships of the multi-dimensional agent attribute model; Annotate the graph structure through a preset NLP model to construct a multi-dimensional agent atlas.

4. The multi-dimensional dynamic association decision analysis method based on an agent map according to claim 3, wherein The fusing of the standardized multi-source data with the multi-dimensional agent atlas and performing data dynamic update processing on the agent atlas includes: Fuse the standardized multi-source data with the multi-dimensional agent atlas through a preset data processing model; Dynamically collect multi-source data according to a preset time rule and update the data of the agent atlas.

5. The multi-dimensional dynamic association decision analysis method based on the intelligent agent map according to claim 4, wherein, The associating of the multi-dimensional agent atlas to obtain the internal association rules of the agents includes: Perform multi-dimensional association analysis on the agent atlas through a preset multi-dimensional association analysis model to obtain an association analysis result, where the multi-dimensions include time, space, and theme; Process the association analysis result through a preset atlas model to obtain the association rules of the agents.

6. The multi-dimensional dynamic association decision analysis method based on an agent map according to claim 5, characterized in that The processing of the internal association rules to obtain multiple decision results and evaluation results, selecting the optimal decision plan for evaluation and credibility judgment, and displaying the credible decision plan includes: Obtain a preset urban management operation model; Process according to the association rules in combination with the preset urban management operation model to obtain multiple decision results; Process multiple decision results through a preset decision evaluation model to obtain evaluation results corresponding to each decision result; Sort the evaluation results corresponding to each decision result to obtain the optimal decision plan; Evaluate the optimal decision plan according to a preset decision analysis method to obtain decision evaluation parameters; Compare the decision evaluation parameters with a preset evaluation threshold to judge the credibility of the optimal decision plan; If the credibility passes, perform visual display on the optimal decision plan.

7. A multi-dimensional dynamic association decision analysis system based on an agent map, characterized in that, The system includes: a memory and a processor. The memory includes a program of a multi-dimensional dynamic association decision analysis method based on an agent map. When the program of the multi-dimensional dynamic association decision analysis method based on the agent map is executed by the processor, the following steps are implemented: Obtain multi-source data, perform preprocessing and normalization processing to obtain normalized multi-source data; Identify various types of agents to establish a multi-dimensional agent attribute model, and construct a multi-dimensional agent map according to the graph structure; Fuse the normalized multi-source data with the multi-dimensional agent map, and perform data dynamic update processing on the agent map; Associate the multi-dimensional agent map to obtain the internal association rules of the agents; Process the internal association rules to obtain multiple decision results and evaluation results, select the optimal decision plan for evaluation and credibility judgment, and display the credible decision plan.

8. The multi-dimensional dynamic association decision analysis system based on the agent map according to claim 7, characterized in that, The step of obtaining multi-source data, performing preprocessing and normalization processing to obtain normalized multi-source data includes: Obtain multi-source data through a predetermined urban big data source, including administrative data, perception data, and Internet data; Perform preprocessing on the multi-source data; Perform normalization processing on the preprocessed multi-source data through a preset data conversion tool to obtain normalized multi-source data.

9. The multi-dimensional dynamic association decision analysis system based on the agent map according to claim 8, characterized in that, The step of identifying various types of agents to establish a multi-dimensional agent attribute model and constructing a multi-dimensional agent map according to the graph structure includes: Identify various types of agents and extract basic features and behavior patterns; Establish a multi-dimensional agent attribute model according to the basic features and behavior patterns; Construct a graph structure according to the node and boundary relationships of the multi-dimensional agent attribute model; Annotate the graph structure through a preset NLP model to construct a multi-dimensional agent map.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a program of a multi-dimensional dynamic association decision analysis method based on an agent map. When the program of the multi-dimensional dynamic association decision analysis method based on the agent map is executed by a processor, the steps of the multi-dimensional dynamic association decision analysis method based on the agent map as described in any one of claims 1 to 6 are implemented.

Images