Collaborative law enforcement resource scheduling optimization method and system, terminal and medium

Abstract

The invention discloses a collaborative law enforcement resource scheduling optimization method and system, a terminal and a medium, and relates to the technical field of resource scheduling, and the technical scheme is characterized in that a knowledge graph of each law enforcement subject is constructed; solving resource deployment distribution information by taking minimization of cross-point scheduling cost and / or maximization of task coverage as a first target; performing spatial superposition on different resource deployment distribution information to generate an initial collaborative scheduling strategy; according to the resource availability and the collaborative link completeness, analyzing the probability distribution of each law enforcement point for completing the burst task; and solving to obtain a final collaborative scheduling strategy by taking the balance of the maximized probability distribution as a second target. According to the method, the multi-dimensional relationship is integrated through the knowledge graph, and intelligent scheduling and conflict detection of cross-department resources are realized; and moreover, the probability distribution balance of the law enforcement point for completing the burst task is optimized through a two-stage optimization mechanism, and the situations of insufficient resource utilization rate and unbalanced emergency response can be effectively reduced in a cross-network collaborative scene.

Description

Technical Field

[0001] The present invention relates to the field of resource scheduling technology, and more specifically, to a collaborative law enforcement resource scheduling optimization method, system, terminal and medium. Background Art

[0002] Collaborative law enforcement refers to a systematic working model in which multiple law enforcement departments jointly respond to complex law enforcement tasks through resource sharing, information exchange, and coordinated actions. Its purpose is to break down departmental barriers and improve law enforcement efficiency. In the past, in the scheduling of law enforcement resources, each department mostly adopted an independent operation model, which had the following technical bottlenecks: 1) Resource allocation relied on manual experience, which easily led to high scheduling costs and response delays when collaborating across departments; 2) Task coverage assessment lacked dynamic modeling capabilities, making it difficult to cope with the uneven temporal and spatial distribution of case types; 3) There was a lack of intelligent detection methods when multiple sources of resources were deployed and superimposed, resulting in frequent problems of duplicate coverage and equipment conflicts; 4) The handling of emergency tasks relied on fixed plans and had poor flexibility. Therefore, how to research and design a collaborative law enforcement resource scheduling optimization method, system, terminal, and medium that can overcome the above-mentioned shortcomings is an issue that we urgently need to solve. Summary of the Invention

[0003] In order to address the deficiencies in the prior art, the purpose of the present invention is to provide a collaborative law enforcement resource scheduling optimization method, system, terminal and medium, which integrates multi-dimensional relationships through knowledge graphs to achieve intelligent scheduling and conflict detection of cross-departmental resources; and optimizes the probability distribution balance of law enforcement points in completing emergency tasks through a two-stage optimization mechanism. In a cross-network collaborative scenario, it can effectively reduce the occurrence of insufficient resource utilization and imbalanced emergency response.

[0004] The above technical objectives of the present invention are achieved through the following technical solutions:

[0005] In a first aspect, a collaborative law enforcement resource scheduling optimization method is provided, comprising the following steps:

[0006] Construct a knowledge graph of each law enforcement entity. The entities of the knowledge graph include law enforcement departments, law enforcement personnel, law enforcement targets, case types, and law enforcement resources, and mark the horizontal collaboration relationships, vertical guidance relationships, and resource sharing relationships between the entities;

[0007] Obtaining the task volume distribution information of the law enforcement entity, and optimizing and solving the resource deployment distribution information of the law enforcement entity with the first goal of minimizing cross-point scheduling costs and / or maximizing task coverage;

[0008] Spatially superimposing the resource deployment distribution information of different law enforcement entities, and detecting duplicate coverage issues and / or equipment conflicts of law enforcement resources through the knowledge graph, and generating an initial collaborative scheduling strategy after resolving the issues;

[0009] Allocating burst tasks to the enforcement points in the task volume distribution information, and analyzing the probability distribution of each enforcement point completing the burst tasks based on the resource availability and cooperative link completeness of the enforcement point in the initial cooperative scheduling strategy;

[0010] With the second goal of maximizing the balance of the probability distribution, the resource allocation of each law enforcement point in the initial collaborative scheduling strategy is adjusted, and the final collaborative scheduling strategy is obtained by optimization.

[0011] Furthermore, the objective function of minimizing the cross-point scheduling cost adopts a linear programming model based on multi-enforcement point resource matching, and the constraints include at least one of a task coverage constraint, a resource capacity constraint, and a maximum response distance constraint;

[0012] Alternatively, the objective function for minimizing the cross-point scheduling cost adopts a dynamic cost model that introduces task priorities, and the dynamic cost model is configured with a time update mechanism and / or an adaptive weight adjustment strategy.

[0013] Furthermore, the objective function of maximizing task coverage adopts a weighted coverage model based on spatiotemporal density, and the constraints include at least one of a total resource limit constraint, a minimum response unit constraint, and a cross-network collaboration constraint;

[0014] Alternatively, the objective function of maximizing task coverage adopts a dynamic priority coverage network model, and the dynamic cost model is configured with a dynamic update mechanism including at least one of a task priority function and resource utility decay.

[0015] Furthermore, spatially superimposing the resource deployment distribution information of different law enforcement entities includes:

[0016] Loading the resource deployment distribution information of different law enforcement entities into the same space-time coordinate system;

[0017] Adaptively planning the grid size in the space-time coordinate system according to the superposition priority and the task urgency;

[0018] And, generating corresponding resource feature codes according to the resource information of each grid in the space-time coordinate system.

[0019] Furthermore, detecting the duplication of law enforcement resources through the knowledge graph includes:

[0020] Extracting and constructing a resource deployment subgraph from the knowledge graph, wherein the elements of the resource deployment subgraph include nodes and edges, wherein the nodes are law enforcement departments, resource types, and geographic grids, and the edges include deployment relationships and location relationships;

[0021] Generate a node embedding vector using a GraphSAGE model, and embed the node embedding vector into the corresponding node in the resource deployment subgraph, wherein the node embedding vector includes resource node features and edge weights;

[0022] A type conflict and / or function redundancy detection is performed on the resource deployment subgraph after the node embedding vector is embedded.

[0023] Alternatively, the detection of duplicate coverage of law enforcement resources through the knowledge graph is implemented by a spatiotemporal-semantic dual-channel verification method, which includes spatiotemporal channel analysis, semantic channel analysis and conflict logic judgment.

[0024] Furthermore, the analyzing the probability distribution of each law enforcement point completing the burst task based on the resource availability and cooperative link completeness of the law enforcement point in the initial cooperative scheduling strategy includes:

[0025] Based on the emergency task, performing resource availability analysis on each of the law enforcement resources in the law enforcement point to obtain a first analysis value;

[0026] Based on the emergency task, performing collaborative link integrity on the collaborative link of the law enforcement point to obtain a second analysis value;

[0027] The first analysis value and the second analysis value are input into the Sigmoid function, and the probability distribution of each law enforcement point completing the emergency task is mapped.

[0028] Furthermore, the objective function for maximizing the balance of the probability distribution adopts a dynamic equilibrium model driven by entropy;

[0029] Alternatively, the objective function for maximizing the balance of the probability distribution adopts a balance optimization model based on time and space constraints.

[0030] In a second aspect, a collaborative law enforcement resource scheduling optimization system is provided, which is used to implement a collaborative law enforcement resource scheduling optimization method as described in any one of the first aspects, including:

[0031] A graph construction module is used to construct a knowledge graph for each law enforcement entity. The entities of the knowledge graph include law enforcement departments, law enforcement personnel, law enforcement objects, case types, and law enforcement resources, and to identify the horizontal collaboration relationships, vertical guidance relationships, and resource sharing relationships between the entities;

[0032] A deployment solution module is used to obtain the task volume distribution information of the law enforcement entity and optimize the resource deployment distribution information of the law enforcement entity with the first goal of minimizing cross-point scheduling costs and / or maximizing task coverage;

[0033] A strategy generation module is used to spatially overlay the resource deployment distribution information of different law enforcement entities, detect duplicate coverage issues and / or equipment conflicts of law enforcement resources through the knowledge graph, and generate an initial collaborative scheduling strategy after resolving the issues;

[0034] a probability generation module, configured to configure burst tasks to the enforcement points in the task volume distribution information, and analyze the probability distribution of each enforcement point completing the burst task based on the resource availability and cooperative link completeness of the enforcement point in the initial cooperative scheduling strategy;

[0035] The strategy optimization module is used to adjust the resource allocation of each enforcement point in the initial collaborative scheduling strategy with the second goal of maximizing the balance of the probability distribution, and optimize the solution to obtain the final collaborative scheduling strategy.

[0036] In a third aspect, a computer terminal is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a collaborative law enforcement resource scheduling optimization method as described in any one of the first aspects is implemented.

[0037] In a fourth aspect, a computer-readable medium is provided, on which a computer program is stored. The computer program is executed by a processor to implement a collaborative law enforcement resource scheduling optimization method as described in any one of the first aspects.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] 1. The present invention provides a collaborative law enforcement resource scheduling optimization method that integrates multi-dimensional relationships through a knowledge graph to achieve intelligent scheduling and conflict detection of cross-departmental resources. Furthermore, a two-stage optimization mechanism is used to optimize the probability distribution balance of law enforcement points completing emergency tasks. In cross-network collaborative scenarios, this method can effectively reduce the occurrence of insufficient resource utilization and imbalanced emergency response.

[0040] 2. This invention achieves visual expression and semantic reasoning of law enforcement entity relationships by constructing a knowledge graph that includes horizontal collaboration, vertical guidance, and resource sharing relationships. Furthermore, it uses the GraphSAGE model to generate node embedding vectors, which can accurately identify functional redundancy and equipment conflicts in resource deployment, effectively improving the accuracy of conflict detection.

[0041] 3. The present invention can reduce cross-point scheduling costs by integrating a linear programming model with a time-space density weighted model. Furthermore, the entropy-driven equilibrium model is adopted to improve the resource allocation balance of most law enforcement points by improving the Sigmoid function to map the probability distribution of burst task completion.

[0042] 4. The present invention realizes grid fusion of multi-source data through 16-bit resource feature coding (including spatiotemporal tags and collaborative identifiers), supports dynamic adjustment of spatiotemporal coordinate system grid granularity according to task urgency, and improves resource matching efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0044] Figure 1 This is a flowchart of Example 1 of the present invention;

[0045] Figure 2 This is a system block diagram in Example 2 of the present invention. DETAILED DESCRIPTION

[0046] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with examples and drawings. The exemplary embodiments of the present invention and their descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0047] Example 1: A collaborative law enforcement resource scheduling optimization method, such as Figure 1 As shown, the following steps are included:

[0048] S1: Construct a knowledge graph of each law enforcement entity. The entities in the knowledge graph include law enforcement departments, law enforcement personnel, law enforcement targets, case types, and law enforcement resources, and identify the horizontal collaboration relationships, vertical guidance relationships, and resource sharing relationships between entities.

[0049] S2: Obtain the task volume distribution information of the law enforcement entity, and optimize the resource deployment distribution information of the law enforcement entity with the primary goal of minimizing the cross-point scheduling cost and / or maximizing the task coverage;

[0050] S3: Spatially overlay the resource deployment distribution information of different law enforcement entities, and detect duplicate coverage issues and / or equipment conflicts of law enforcement resources through knowledge graphs. After resolving these issues, an initial collaborative scheduling strategy is generated.

[0051] S4: Allocate burst tasks to the enforcement points in the task volume distribution information, and analyze the probability distribution of each enforcement point completing the burst tasks based on the resource availability and coordination link completeness of the enforcement point in the initial coordination scheduling strategy;

[0052] S5: With the second goal of maximizing the balance of probability distribution, adjust the resource allocation of each enforcement point in the initial collaborative scheduling strategy, and optimize the solution to obtain the final collaborative scheduling strategy.

[0053] In step S1, for law enforcement entities such as public security, traffic police, and urban management, horizontal collaboration refers to the joint law enforcement relationship between departments at the same level / across fields, vertical guidance refers to the command and supervision relationship between superior and subordinate departments, and resource sharing refers to the cross-departmental resource calling and data intercommunication relationship.

[0054] In step S2, the first goal can be to minimize the cross-point scheduling cost, or to maximize the task coverage, or to minimize the cross-point scheduling cost as the first sub-goal and maximize the task coverage as the second sub-goal, and then calculate the weights of the two sub-goals.

[0055] In some examples, the objective function of minimizing cross-point scheduling costs can adopt a linear programming model based on multi-enforcement point resource matching, and the constraints include one or more of task coverage constraints, resource capacity constraints, and maximum response distance constraints.

[0056] For example, the function expression of the linear programming model based on multi-enforcement point resource matching is:

[0057]

[0058] Among them, d ij represents the scheduling distance or time cost from enforcement point i to task point j, dimensionless; x ij represents the number of dispatches from enforcement point i to task point j, with a value of 0 or 1; α represents the weight coefficient of dispatch distance or time cost, such as 0.6; represents the available resource vector of enforcement point i; represents the resource demand vector of task point j; y ij represents the resource matching decision variable, with a value range of [0,1]; β represents the weight coefficient of resource matching, such as 0.4; D max represents the maximum response distance; n represents the number of enforcement points; m represents the number of mission points.

[0059] This invention combines physical distance with resource compatibility to optimize scheduling, avoiding the problem of under-matched resources over long distances. For example, if point A has three law enforcement vehicles but no drones, and point B has drones but insufficient vehicles, the invention can automatically select point C (slightly farther away but with sufficient resources) for scheduling, reducing duplicate scheduling.

[0060] In some examples, the objective function of minimizing the cross-point scheduling cost adopts a dynamic cost model that introduces task priorities, and the dynamic cost model is configured with a time update mechanism and / or an adaptive weight adjustment strategy.

[0061] For example, the expression of the dynamic cost model is:

[0062]

[0063] Among them, T represents the total time window; K represents the number of tasks; w k represents the priority weight of task k, such as 1.5 for criminal cases and 1.0 for routine inspections; d k (t) represents the remaining dispatch distance of task k at time t; v(t) represents the road network traffic efficiency coefficient at time t, such as 0.7 during the morning peak period and 1.0 during the off-peak period; γ represents the time delay penalty factor, such as 1 km / min; represents the latest response time of task k; d k (t+1) represents the remaining scheduling distance of task k at time t+1; s q represents the moving speed of the law enforcement unit q, such as 300 km / h for helicopters and 80 km / h for police cars; Q represents the number of law enforcement units; δ qk represents a binary variable, with a value of 1 indicating that the enforcement unit q is assigned to task k, and a value of 0 indicating that the enforcement unit q is not assigned to task k; w k (t) represents the priority weight of task k at time t; It represents the basic weight of the task, such as 1 for regular tasks and 2 for cross-region pursuit tasks; ψ represents the case correlation, with a value range of [0,1].

[0064] It should be noted that s q δ qk The original form is s q δ qk (t+1-t), so its unit is distance unit.

[0065] This invention integrates the dynamic characteristics of time and space to improve dispatch efficiency during peak hours. For example, if a cross-provincial pursuit mission occurs 200 kilometers away, the model prioritizes dispatching helicopters over conventional vehicles. Although the cost per trip increases, the success rate of the arrest is significantly improved.

[0066] In some examples, the objective function of maximizing task coverage adopts a weighted coverage model based on spatiotemporal density, and the constraints include one or more of total resource limit constraints, minimum response unit constraints, and cross-network collaboration constraints.

[0067] For example, the function expression of the weighted coverage model based on spatiotemporal density is:

[0068]

[0069] Where G represents the total number of geographic grids; w g represents the task weight of grid g; X represents the number of resource types; represents the total resource demand of grid g; r xgrepresents the amount of resources of type x deployed to grid g; λ represents the time decay coefficient; represents the delay time for the x-th type of resource to reach the grid g; Indicates the total system resource capacity of the x-type resource; δ indicates the basic ratio, such as 0.6; r xh represents the amount of resources of type x deployed to grid h; represents the total resource demand of grid h; ε represents the difference ratio, such as 0.3.

[0070] In some examples, the objective function of maximizing task coverage adopts a dynamic priority coverage network model, and the dynamic cost model is configured with a dynamic update mechanism including at least one of a task priority function and resource utility decay.

[0071] In some examples, the dynamic priority coverage network model prioritizes high-priority tasks and tasks with large resource gaps by maximizing the weighted coverage of all tasks in all time periods.

[0072] In some examples, the task priority determined by the task priority function increases dynamically with the proportion of real-time resource demand, and the higher the demand, the greater the increase in priority.

[0073] In some examples, resource utility decay implements exponential decay of resource utility based on the remaining working time and task duration. If a resource works for a long time or a task times out, the utility will drop significantly, forcing the system to reallocate resources.

[0074] In step S3, the resource deployment distribution information of different law enforcement entities is spatially superimposed, including: loading the resource deployment distribution information of different law enforcement entities into the same space-time coordinate system; adaptively planning the grid size in the space-time coordinate system based on the superposition priority and task urgency; and generating corresponding resource feature codes based on the resource information of each grid in the space-time coordinate system.

[0075] For example, resource deployment and distribution information from multiple departments can be loaded into the same spatiotemporal coordinate system. Grid sizes are then divided based on task urgency, such as 500m×500m for routine patrol areas and 200m×200m for high-incidence areas. In some examples, if a task in a given area involves both traffic and urban management cases, grid division can be based on the higher-priority case, or the two can be weighted to balance the grid division requirements. In some examples, the resource feature code consists of 16 digits. Digits 1-4 indicate the resource type, such as 0001 for vehicle, 0010 for drone, and 0100 for inspection equipment. Digits 5-8 indicate the department to which the task belongs, such as 0001 for transportation, 0010 for fire protection, and 0100 for health and medical care. Digits 9-12 indicate the time window. Digits 13-16 indicate collaboration flags, such as 12 for requiring cross-departmental collaboration and 13 for containing sensitive equipment. For example, the code for a traffic drone during the morning and evening rush hours is 0010-0001-0010-1000.

[0076] In some examples, the problem of duplicate coverage of law enforcement resources is detected through knowledge graphs, including: extracting and constructing a resource deployment subgraph from the knowledge graph, the elements of the resource deployment subgraph include nodes and edges, the nodes are law enforcement departments, resource types and geographic grids, and the edges include deployment relationships and location relationships; using the GraphSAGE (GraphSAmpleandAggreGatE) model to generate node embedding vectors, and embedding the node embedding vectors into corresponding nodes in the resource deployment subgraph, the node embedding vectors include resource node features and edge weights; and performing type conflict and / or functional redundancy detection on the resource deployment subgraph after embedding the node embedding vectors.

[0077] Specifically, the resource node characteristics include function type, remaining power, etc. The function type can be coded in 0-1, and the remaining power can be a normalized value.

[0078] Type conflict can be determined by first calculating the cosine similarity and spatial distance of similar resource nodes, and triggering an alarm when the cosine similarity is greater than 0.85 and the spatial distance is less than 1km.

[0079] Functional redundancy can be: if the Jaccard functional intersection of heterogeneous resource nodes is greater than 0.7 (such as infrared cameras and thermal imagers), it is determined to be redundant deployment.

[0080] In some examples, the problem of duplicate coverage of law enforcement resources can be detected through knowledge graphs by using a spatiotemporal-semantic dual-channel verification method, which includes spatiotemporal channel analysis, semantic channel analysis, and conflict logic judgment.

[0081] Spatiotemporal channel analysis primarily involves constructing a spatiotemporal cube model, mapping resource deployment to three-dimensional space (longitude, latitude, and timestamp). The DBSCAN clustering algorithm is then used to detect dense areas, such as when the number of departments within a 2km radius reaches three. Semantic channel analysis primarily extracts task description text, such as "Nighttime Drunk Driving Investigation," generates semantic vectors using the BERT model, and then calculates semantic similarity between tasks. Conflict logic detection identifies overlapping tasks within the same spatiotemporal cluster when their semantic similarity exceeds a set value. This effectively facilitates task consolidation and joint law enforcement.

[0082] Device conflict refers to the problem that different devices cannot coexist at the same time and place.

[0083] In step S4, the probability distribution of each law enforcement point completing the burst task is analyzed based on the resource availability and collaborative link completeness of the law enforcement point in the initial collaborative scheduling strategy, including: based on the burst task, performing resource availability analysis on each law enforcement resource in the law enforcement point to obtain a first analysis value; based on the burst task, performing collaborative link completeness on the collaborative link of the law enforcement point to obtain a second analysis value; inputting the first analysis value and the second analysis value into the Sigmoid function, and mapping to obtain the probability distribution of each law enforcement point completing the burst task.

[0084] In some examples, the Sigmoid function uses an improved Sigmoid function, and the specific expression is:

[0085]

[0086] in, represents the probability of law enforcement point i completing the emergency task; σ(·) represents the Sigmoid function, which is used to map the linear combination to probability; represents the available quantity of the xth type of resource in enforcement point i; W represents the total demand of the x-th type of resources for the sudden task; x Indicates the weight coefficient of the x-th type of resources; C link represents the collaborative link integrity score; C max Indicates the upper limit of the collaborative link integrity score.

[0087] For example, a certain task requires the linkage of three departments, and actually completes the collaborative verification of two departments. Assuming that the upper limit of the collaborative link integrity score is 100, then the collaborative link integrity score is about 67.

[0088] In step S5, the objective function for maximizing the balance of the probability distribution adopts a dynamic equilibrium model driven by entropy.

[0089] In some examples, the function expression of the entropy-driven dynamic equilibrium model is:

[0090]

[0091] Among them, H(P) represents the Shannon entropy value, which measures the balance of resource distribution. The larger the entropy value, the more balanced it is; D g represents the case density of grid g; W g represents the priority weight of the grid g; T g represents the response time for a resource to reach grid g; a, b, and c are all proportional coefficients, such as 1.4, 0.5, and 1.0, respectively. It should be noted that the above function is dimensionless.

[0092] In some examples, the objective function of maximizing the balance of the probability distribution adopts a balance optimization model based on spatiotemporal constraints.

[0093] The optimization logic of the balance optimization model under spatiotemporal constraints is as follows: minimize the deviation between the demand ratio of each grid resource and the global mean; then impose a linear penalty on the response timeout area; and finally, achieve resource allocation proportional to demand intensity while satisfying the time constraint.

[0094] Example 2: A collaborative law enforcement resource scheduling optimization system, which is used to implement a collaborative law enforcement resource scheduling optimization method as described in Example 1, such as Figure 2 As shown, it includes a graph construction module, a deployment solution module, a strategy generation module, a probability generation module and a strategy optimization module.

[0095] Among them, the graph construction module is used to construct the knowledge graph of each law enforcement entity. The entities of the knowledge graph include law enforcement departments, law enforcement personnel, law enforcement objects, case types and law enforcement resources, and the horizontal collaboration relationship, vertical guidance relationship and resource sharing relationship between the entities are calibrated; the deployment solution module is used to obtain the task volume distribution information of the law enforcement entity, and optimize the resource deployment distribution information of the law enforcement entity with the first goal of minimizing the cross-point scheduling cost and / or maximizing the task coverage; the strategy generation module is used to spatially superimpose the resource deployment distribution information of different law enforcement entities, and detect the repeated coverage problem and / or equipment conflict problem of law enforcement resources through the knowledge graph, and generate the initial collaborative scheduling strategy after resolving the problem; the probability generation module is used to configure burst tasks to the law enforcement points in the task volume distribution information, and analyze the probability distribution of each law enforcement point completing the burst task based on the resource availability and collaborative link completeness of the law enforcement point in the initial collaborative scheduling strategy; the strategy optimization module is used to adjust the resource allocation of each law enforcement point in the initial collaborative scheduling strategy with the second goal of maximizing the balance of the probability distribution, and optimize the solution to obtain the final collaborative scheduling strategy.

[0096] The present invention also records a computer terminal, which includes a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, it implements a collaborative law enforcement resource scheduling optimization method as described in Example 1.

[0097] The present invention also records a computer-readable medium on which a computer program is stored. The computer program is executed by a processor to implement a collaborative law enforcement resource scheduling optimization method as described in Example 1.

[0098] Working Principle: This invention integrates multi-dimensional relationships through knowledge graphs to achieve intelligent scheduling and conflict detection of cross-departmental resources. It also optimizes the probability distribution balance of law enforcement points completing emergency tasks through a two-stage optimization mechanism. In cross-network collaborative scenarios, it can effectively reduce the occurrence of insufficient resource utilization and imbalanced emergency response.

[0099] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0100] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0101] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0102] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0103] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A collaborative law enforcement resource scheduling optimization method, characterized in that: The following steps are involved: Construct a knowledge graph of each law enforcement entity. The entities of the knowledge graph include law enforcement departments, law enforcement personnel, law enforcement targets, case types, and law enforcement resources, and mark the horizontal collaboration relationships, vertical guidance relationships, and resource sharing relationships between the entities; Obtaining the task volume distribution information of the law enforcement entity, and optimizing and solving the resource deployment distribution information of the law enforcement entity with the first goal of minimizing cross-point scheduling costs and / or maximizing task coverage; Spatially superimposing the resource deployment distribution information of different law enforcement entities, and detecting duplicate coverage issues and / or equipment conflicts of law enforcement resources through the knowledge graph, and generating an initial collaborative scheduling strategy after resolving the issues; Allocating burst tasks to the enforcement points in the task volume distribution information, and analyzing the probability distribution of each enforcement point completing the burst tasks based on the resource availability and cooperative link completeness of the enforcement point in the initial cooperative scheduling strategy; With the second goal of maximizing the balance of the probability distribution, the resource allocation of each law enforcement point in the initial collaborative scheduling strategy is adjusted, and the final collaborative scheduling strategy is obtained by optimization.

2. A collaborative law enforcement resource scheduling optimization method according to claim 1, characterized in that: The objective function of minimizing the cross-point scheduling cost adopts a linear programming model based on multi-enforcement point resource matching, and the constraints include at least one of a task coverage constraint, a resource capacity constraint, and a maximum response distance constraint; Alternatively, the objective function for minimizing the cross-point scheduling cost adopts a dynamic cost model that introduces task priorities, and the dynamic cost model is configured with a time update mechanism and / or an adaptive weight adjustment strategy.

3. A collaborative law enforcement resource scheduling optimization method according to claim 1, characterized in that: The objective function for maximizing task coverage adopts a weighted coverage model based on spatiotemporal density, and the constraints include at least one of a total resource limit constraint, a minimum response unit constraint, and a cross-network collaboration constraint; Alternatively, the objective function of maximizing task coverage adopts a dynamic priority coverage network model, and the dynamic cost model is configured with a dynamic update mechanism including at least one of a task priority function and resource utility decay.

4. A collaborative law enforcement resource scheduling optimization method according to claim 1, characterized in that: The spatially superimposing the resource deployment distribution information of different law enforcement entities includes: Loading the resource deployment distribution information of different law enforcement entities into the same space-time coordinate system; Adaptively planning the grid size in the space-time coordinate system according to the superposition priority and the task urgency; And, generating corresponding resource feature codes according to the resource information of each grid in the space-time coordinate system.

5. A collaborative law enforcement resource scheduling optimization method according to claim 1, characterized in that: The detecting of duplicate coverage of law enforcement resources through the knowledge graph includes: Extracting and constructing a resource deployment subgraph from the knowledge graph, wherein the elements of the resource deployment subgraph include nodes and edges, wherein the nodes are law enforcement departments, resource types, and geographic grids, and the edges include deployment relationships and location relationships; Generate a node embedding vector using a GraphSAGE model, and embed the node embedding vector into the corresponding node in the resource deployment subgraph, wherein the node embedding vector includes resource node features and edge weights; A type conflict and / or function redundancy detection is performed on the resource deployment subgraph after the node embedding vector is embedded. Alternatively, the detection of duplicate coverage of law enforcement resources through the knowledge graph is implemented by a spatiotemporal-semantic dual-channel verification method, which includes spatiotemporal channel analysis, semantic channel analysis and conflict logic judgment.

6. A collaborative law enforcement resource scheduling optimization method according to claim 1, characterized in that: The analyzing the probability distribution of each law enforcement point completing the burst task based on the resource availability and cooperative link completeness of the law enforcement point in the initial cooperative scheduling strategy includes: Based on the emergency task, performing resource availability analysis on each of the law enforcement resources in the law enforcement point to obtain a first analysis value; Based on the emergency task, performing collaborative link integrity on the collaborative link of the law enforcement point to obtain a second analysis value; The first analysis value and the second analysis value are input into the Sigmoid function, and the probability distribution of each law enforcement point completing the emergency task is mapped.

7. A collaborative law enforcement resource scheduling optimization method according to claim 1, characterized in that: The objective function for maximizing the balance of the probability distribution adopts a dynamic equilibrium model driven by entropy; Alternatively, the objective function for maximizing the balance of the probability distribution adopts a balance optimization model based on time and space constraints.

8. A collaborative law enforcement resource scheduling optimization system, characterized in that: The system is used to implement a collaborative law enforcement resource scheduling optimization method as described in any one of claims 1 to 7, comprising: A graph construction module is used to construct a knowledge graph for each law enforcement entity. The entities of the knowledge graph include law enforcement departments, law enforcement personnel, law enforcement objects, case types, and law enforcement resources, and to identify the horizontal collaboration relationships, vertical guidance relationships, and resource sharing relationships between the entities; A deployment solution module is used to obtain the task volume distribution information of the law enforcement entity and optimize the resource deployment distribution information of the law enforcement entity with the first goal of minimizing cross-point scheduling costs and / or maximizing task coverage; A strategy generation module is used to spatially overlay the resource deployment distribution information of different law enforcement entities, detect duplicate coverage issues and / or equipment conflicts of law enforcement resources through the knowledge graph, and generate an initial collaborative scheduling strategy after resolving the issues; a probability generation module, configured to configure burst tasks to the enforcement points in the task volume distribution information, and analyze the probability distribution of each enforcement point completing the burst task based on the resource availability and cooperative link completeness of the enforcement point in the initial cooperative scheduling strategy; The strategy optimization module is used to adjust the resource allocation of each enforcement point in the initial collaborative scheduling strategy with the second goal of maximizing the balance of the probability distribution, and optimize the solution to obtain the final collaborative scheduling strategy.

9. A computer terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, it implements a collaborative law enforcement resource scheduling optimization method as described in any one of claims 1-7.

10. A computer-readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement a collaborative law enforcement resource scheduling optimization method as described in any one of claims 1-7.

Images