Intelligent dispute analysis system based on big data

Abstract

The present application relates to the field of data reasoning technology, and in particular to a dispute intelligent analysis system based on big data. The system includes an event collection module, a dispute analysis module, a solution generation module, an emergency solution module, and an auxiliary decision generation module. The system collects dispute event description data, territorial feature data, and party background data to generate an original data set; extracts key event elements from the original data set to obtain a preliminary analysis report; combines the territorial feature data and party background data to perform a localized secondary analysis on the preliminary analysis report to generate a personalized mediation solution; when an emergency trigger condition is identified, the system integrates rescue resource data based on the event's geographic location to automatically generate an emergency response plan; and generates an auxiliary decision report based on the personalized mediation solution and the emergency response plan. The present invention can improve the efficiency of dispute resolution.

Description

Technical Field

[0001] The present application relates to the field of data reasoning technology, and in particular to a dispute intelligent analysis system based on big data. Background Art

[0002] In the field of dispute resolution, existing technologies mostly rely on manual methods for information integration and analysis, and lack the effective application of big data technology. This leads to inefficient collection and structured processing of dispute event description data, territorial characteristic data, and background data of the parties involved. It is difficult to quickly extract key elements of the event, making the generation of preliminary analysis reports time-consuming and lacking in accuracy, unable to provide efficient support for subsequent processing, and seriously restricting the overall process of dispute resolution.

[0003] At the same time, existing technologies often overlook the impact of territorial characteristics and the differentiated backgrounds of the parties involved when generating dispute mediation solutions. The resulting solutions are generally generic, lacking specificity and territorial adaptability, and result in suboptimal mediation outcomes. Furthermore, for emergency situations in disputes, existing technologies struggle to rapidly identify triggering conditions and efficiently integrate rescue resources. The generation of emergency response plans lags, and resource scheduling is irrational, hindering timely response to emergencies, further reducing the efficiency and effectiveness of dispute resolution.

[0004] To this end, this application provides a dispute intelligent analysis system based on big data. Summary of the Invention

[0005] The purpose of this application is to solve at least one technical problem raised in the background technology.

[0006] This application provides a big data-based dispute intelligent analysis system, including an event collection module, a dispute analysis module, a solution generation module, an emergency solution module, and an auxiliary decision generation module, wherein:

[0007] Event collection module: used to collect dispute event description data, territorial feature data, and party background data to generate the original data set;

[0008] Dispute analysis module: used to extract key event elements from the original data set to obtain a preliminary analysis report;

[0009] Solution generation module: used to combine the territorial characteristic data and the background data of the parties to conduct a localized secondary analysis of the preliminary analysis report and generate a personalized mediation solution;

[0010] Emergency plan module: When an emergency trigger condition is identified, it integrates rescue resource data based on the event's geographic location and automatically generates an emergency response plan;

[0011] A decision support generation module: used to generate a decision support report based on the personalized mediation plan and the emergency response plan.

[0012] In a preferred embodiment, when the event collection module collects the dispute event description data, territorial characteristic data and party background data to generate the original data set, it is specifically used to:

[0013] Extract the conflicting parties, disputed objects, and behavioral description elements from the dispute event text through natural language processing technology;

[0014] Associating the conflict subject, dispute object, and behavior description elements into a structured event tuple;

[0015] The structured event tuple is stored in a distributed database.

[0016] In a preferred embodiment, when extracting the key elements of the event from the original data set to obtain a preliminary analysis report, the dispute analysis module is specifically configured to:

[0017] Extracting emotional tendency elements, behavioral characteristic elements, and controversial focus elements from the structured event tuple;

[0018] The above factors are classified and weighted through machine learning models to generate a preliminary analysis report containing dispute type labels and severity assessments.

[0019] In a preferred embodiment, when the solution generation module performs the localized secondary analysis of the preliminary analysis report in combination with the territorial characteristic data and the background data of the parties to generate a personalized mediation solution, it is specifically configured to:

[0020] Construct a territorial characteristic matrix including local laws and regulations index, folk customs characteristics, and economic level parameters;

[0021] Encoding the party background data into an educational background vector including social relationship density and historical dispute frequency;

[0022] The territorial feature matrix and the educational background vector are fused through a feature weighting function to output a regional adaptation factor.

[0023] In a preferred embodiment, the emergency triggering condition includes:

[0024] Detection of emotional tendency elements exceeding a preset emotional intensity threshold;

[0025] Identify the elements of the behavior description that contain violent behavior keywords;

[0026] When both the emotional intensity threshold and the violent behavior keywords are met, the generation of an emergency response plan is activated.

[0027] In a preferred embodiment, the rescue resource data includes:

[0028] Establish a multi-level resource scheduling radius centered on the event's geographic location;

[0029] Dynamically matching medical emergency units, security linkage units, and legal aid units within the dispatch radius;

[0030] Generate a resource allocation graph that includes unit response priorities and path planning topology.

[0031] In a preferred embodiment, when the solution generation module performs the localized secondary analysis of the preliminary analysis report in combination with the territorial characteristic data and the background data of the parties to generate a personalized mediation solution, it is specifically configured to:

[0032] Constructing a mediation strategy decision tree including the regional adaptation factor and the dispute type label;

[0033] The weight configuration of the mediation strategy decision tree is adjusted, wherein the calculation formula of the adjustment is as follows:

[0034] ;

[0035] Where, is the weight of the mediation plan, is the territorial characteristic adjustment coefficient in the territorial characteristic data, is the social relationship density of the party’s background data, is the background vector modulus length of the party’s background data, The baseline value of the strength of the claim of the party's background data;

[0036] Adjust personnel type and process duration based on the adjusted strategic decision tree.

[0037] In a preferred embodiment, when the emergency plan module executes the method of automatically generating an emergency response plan by integrating rescue resource data based on the geographical location of the event upon identifying an emergency trigger condition, it is specifically configured to:

[0038] Calculate the optimal response path for rescue resource data:

[0039] ;

[0040] Where, is the minimum aggregate response time, For the Distance from rescue unit to incident location, is the total number of rescue units, is the average travel speed of the rescue unit, is the rescue unit availability indicator function;

[0041] Dynamically adjust the priority order of units in the resource allocation map.

[0042] In a preferred embodiment, when the emergency plan module performs multi-dimensional closed-loop control of the grid connection process based on the reliable grid connection confidence level to obtain the optimal scheduling strategy for the new energy grid connection process, it is specifically configured to:

[0043] Inputting the personalized mediation plan and the emergency response plan into a strategy fusion module;

[0044] The mediation cost and the emergency cost are balanced by the conflict resolution function, wherein the calculation formula of the conflict resolution function for balanced mediation is as follows:

[0045] ;

[0046] Where, is the optimal decision coefficient, is the mediation-emergency balance factor, is the weight of the mediation scheme, is the benchmark mediation weight, is a natural constant, is the emergency time gain coefficient, is the minimum aggregate response time;

[0047] Output a visual decision matrix containing the optimal decision coefficients.

[0048] In a preferred embodiment, after executing the step of generating the auxiliary decision report based on the personalized mediation plan and the emergency response plan, the auxiliary decision generation module is specifically configured to:

[0049] generating a mediation stage division scheme according to the visual decision matrix;

[0050] A step-by-step implementation protocol for activating the contingency plan in the event of mediation failure;

[0051] The disposal results are fed back to the territorial feature matrix for dynamic updating.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] 1. The present invention uses multiple modules such as the event collection module and the dispute analysis module to work together, and uses natural language processing technology to extract key elements in dispute events and form structured data. It can quickly generate a preliminary analysis report, and then conduct a secondary analysis based on the territorial characteristics and the background of the parties. The generated personalized mediation plan is more in line with the actual situation, effectively improving the pertinence and success rate of dispute mediation.

[0054] 2. When an emergency trigger condition is identified, the system rapidly integrates rescue resources based on the incident's geographic location and generates an optimal emergency response plan through scientific calculations, ensuring efficient dispatch of rescue resources. Furthermore, the decision-making support module integrates mediation solutions and emergency response plans to produce a decision report, providing comprehensive support for dispute resolution and significantly improving overall processing efficiency and emergency response capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a system architecture diagram of a big data-based intelligent dispute analysis system provided by one embodiment of the present invention;

[0056] Figure 2 A flowchart of the dispute analysis process of a big data-based intelligent dispute analysis system provided by one embodiment of the present invention;

[0057] Figure 3 A flowchart of a personalized mediation solution for a big data-based intelligent dispute analysis system provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0058] The following is combined with Figure 1 To the attached Figure 3 , further details of this application are given.

[0059] Please pay attention to Figure 1 , Figure 2 , Figure 3In the case of a big data-based intelligent dispute analysis system, the server-side device deployed by the big data-based intelligent dispute analysis system may actually be composed of one or more devices. The big data-based intelligent dispute analysis system can be implemented as a service instance, a virtual machine, or hardware devices. For example, the big data-based intelligent dispute analysis system can be implemented as a service instance deployed on one or more devices in a cloud node. Simply put, the big data-based intelligent dispute analysis system can be understood as software deployed on a cloud node, providing the big data-based intelligent dispute analysis system to each client. Alternatively, the big data-based intelligent dispute analysis system can be implemented as a virtual machine deployed on one or more devices in a cloud node. Application software for managing each client can be installed in the virtual machine. Alternatively, the big data-based intelligent dispute analysis system can be implemented as a server-side device composed of multiple hardware devices of the same or different types, with one or more hardware devices configured to provide the big data-based intelligent dispute analysis system to each client.

[0060] In terms of implementation, big data-based intelligent dispute analysis and the user end are mutually compatible. Specifically, if the big data-based intelligent dispute analysis system is an application installed on a cloud service platform, the user end serves as a client that establishes a communication connection with the application. Alternatively, if the big data-based intelligent dispute analysis system is implemented as a website, the user end serves as a webpage. Alternatively, if the big data-based intelligent dispute analysis system is implemented as a cloud service platform, the user end serves as a mini-program within an instant messaging application.

[0061] like Figure 1 , which is a system architecture diagram of a dispute intelligent analysis system based on big data provided by one embodiment of the present invention.

[0062] The big data-based intelligent dispute analysis system of the present invention can be installed in a cloud server. In terms of implementation, it can be implemented as one or more service devices, as an application installed in the cloud (e.g., a mobile service operator's server, server cluster, etc.), or developed as a website. Depending on the functionality implemented, the big data-based intelligent dispute analysis system can include an event collection module, a dispute analysis module, a solution generation module, an emergency solution module, and an auxiliary decision generation module. The modules described in the present invention, also referred to as units, refer to a series of computer program segments that can be executed by an electronic device processor and perform fixed functions, and are stored in the electronic device's memory.

[0063] In an embodiment of the present invention, in the dispute intelligent analysis system based on big data, each of the above modules can be implemented independently and called with other modules. The call here can be understood as a module that can connect to multiple modules of another type and provide corresponding services to the multiple modules connected to it. In the dispute intelligent analysis system based on big data provided by an embodiment of the present invention, the scope of application of the dispute intelligent analysis system architecture based on big data can be adjusted by adding modules and directly calling them without modifying the program code, thereby realizing cluster-based horizontal expansion, so as to achieve the purpose of quickly and flexibly expanding the dispute intelligent analysis system based on big data. In actual applications, the above modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in cloud servers.

[0064] The following describes the various components and specific workflows of the big data-based intelligent dispute analysis system in conjunction with specific embodiments:

[0065] The event collection module is used to collect dispute event description data, territorial feature data and party background data to generate an original data set;

[0066] In an embodiment of the present invention, when the event collection module collects the dispute event description data, the territorial characteristic data, and the party background data to generate the original data set, it is specifically used to:

[0067] Extract the conflicting parties, disputed objects, and behavioral description elements from the dispute event text through natural language processing technology;

[0068] Associating the conflict subject, dispute object, and behavior description elements into a structured event tuple;

[0069] The structured event tuple is stored in a distributed database.

[0070] In the first step, suppose we receive a text about a neighborhood dispute: "Zhang San and Li Si had an argument over the boundary of their house. Zhang San accused Li Si of encroaching on their land by expanding the wall." Using natural language processing technology, the system accurately identifies the conflicting parties as "Zhang San" and "Li Si," the disputed subject as "land along the boundary of their house," and the action description element as "an argument occurred, and Zhang San accused Li Si of encroaching on their land by expanding the wall."

[0071] In the second step, these identified elements are associated to construct structured event tuples, such as {conflict subjects: Zhang San, Li Si; dispute subject: house boundary land; behavior description element: a quarrel occurred, Zhang San accused Li Si of expanding the courtyard wall and occupying land}.

[0072] The third step is to store the constructed structured event tuples in a distributed database to facilitate subsequent calls and analysis by other modules.

[0073] In general, this method can convert unstructured dispute event text into structured data, which facilitates efficient storage and rapid processing by the system, greatly improving the efficiency and accuracy of data processing, and laying a good data foundation for subsequent dispute analysis and other work.

[0074] In the first step, for the description data of dispute events, in addition to extracting information from text through natural language processing technology, detailed information such as the process and scene of the incident can also be obtained from relevant law enforcement recorder videos, surveillance videos and other materials to comprehensively enrich the description data of dispute events.

[0075] The second step is to collect data on territorial characteristics. Taking a dispute occurring in District B of City A as an example, we collect the local law index to understand the local special regulations on handling neighborhood disputes; investigate the characteristics of folk customs, such as whether the area has specific customs of getting along with neighbors; and compile statistical economic level parameters, such as the per capita income and consumption level of the area.

[0076] The third step involves collecting background data on the parties involved. This involves investigating the density of their social relationships, such as how active they are in the local community, the number of friends they have, and the closeness of their relationships. This includes analyzing the frequency of their historical disputes to determine whether they have been frequently involved in various types of disputes. Furthermore, this includes understanding their educational background and other information. Finally, this data set is integrated to generate the original dataset.

[0077] In general, comprehensive collection of multi-dimensional data to generate original data sets can provide sufficient and comprehensive information for subsequent in-depth analysis of disputes. Taking into account the geographical characteristics of the dispute and the characteristics of the parties themselves, it helps to more accurately grasp the nature of the dispute and formulate more effective mediation plans.

[0078] The dispute analysis module is used to extract key event elements from the original data set to obtain a preliminary analysis report;

[0079] In an embodiment of the present invention, when extracting the key elements of the event from the original data set to obtain a preliminary analysis report, the dispute analysis module is specifically configured to:

[0080] Extracting emotional tendency elements, behavioral characteristic elements, and controversial focus elements from the structured event tuple;

[0081] The above factors are classified and weighted through machine learning models to generate a preliminary analysis report containing dispute type labels and severity assessments.

[0082] The first step is to retrieve previously collected neighborhood dispute data from the original dataset stored in the distributed database. The system further analyzes the structured event tuples within them. In addition to the existing elements describing the conflicting parties, the disputed subject, and the behavior, it also mines key information such as the time and location of the incident. For example, it discovered that the neighborhood dispute occurred on a weekday afternoon in a public area within the residential complex.

[0083] The second step is to analyze the handling and outcomes of similar local disputes, combined with local data. For example, it was discovered that District B in City A often referred to specific local regulations when handling similar neighborhood land disputes. Furthermore, the background data of the parties involved was used to understand Zhang San and Li Si's reputation in the community and their attitudes towards handling disputes in the past.

[0084] The third step is to integrate these key factors and generate a preliminary analysis report. The report may include information such as the core issues of the dispute, the key people and locations involved, possible applicable laws and regulations, and a preliminary assessment of the difficulty of mediation based on the background of the parties.

[0085] In general, by extracting the key elements of the original data set to generate a preliminary analysis report, we can quickly sort out the key points of the dispute incident, provide an important reference basis for the subsequent formulation of mediation plans, and make the mediation work more targeted and less blind.

[0086] The solution generation module is used to combine the territorial characteristic data and the background data of the parties to conduct a localized secondary analysis of the preliminary analysis report and generate a personalized mediation solution;

[0087] In an embodiment of the present invention, when the solution generation module performs the localized secondary analysis of the preliminary analysis report in combination with the local characteristic data and the background data of the parties to generate a personalized mediation solution, it is specifically configured to:

[0088] Construct a territorial characteristic matrix including local laws and regulations index, folk customs characteristics, and economic level parameters;

[0089] Encoding the party background data into an educational background vector including social relationship density and historical dispute frequency;

[0090] The territorial feature matrix and the educational background vector are fused through a feature weighting function to output a regional adaptation factor.

[0091] When the solution generation module performs the localized secondary analysis of the preliminary analysis report in combination with the local characteristic data and the background data of the parties to generate a personalized mediation solution, it is specifically used to:

[0092] Constructing a mediation strategy decision tree including the regional adaptation factor and the dispute type label;

[0093] The weight configuration of the mediation strategy decision tree is adjusted, wherein the calculation formula of the adjustment is as follows:

[0094] ;

[0095] Where, is the weight of the mediation plan, is the territorial characteristic adjustment coefficient in the territorial characteristic data, is the social relationship density of the party’s background data, is the background vector modulus length of the party’s background data, The baseline value of the strength of the claim of the party's background data;

[0096] Adjust personnel type and process duration based on the adjusted strategic decision tree.

[0097] The first step is to construct a territorial characteristics matrix. Continuing with the example of a neighborhood dispute in District B of City A, the collected local regulations index is organized into a detailed list of regulatory clauses. Folk customs characteristics are summarized into characteristics such as "the local area values ​​neighborhood harmony, and disputes are generally mediated by community elders." Economic level parameters are converted into numerical indicators, such as the average monthly income per capita in the area is X yuan. This information is integrated into a territorial characteristics matrix that includes the local regulations index, folk customs characteristics, and economic level parameters.

[0098] The second step is to encode the parties' background data. For example, analyzing Zhang San's social network reveals a high density of social connections, indicating close ties with many residents in the community. By analyzing the frequency of his historical disputes, we find two minor disputes in the past year. This information, along with his educational background, is encoded into an education background vector that includes the density of social connections and the frequency of historical disputes.

[0099] The third step is to combine the territorial feature matrix and the educational background vector using a feature weighting function to output a regional adaptation factor. For example, a feature weighting function can be set to assign weights to different factors based on their importance to the mediation solution. This calculation yields a regional adaptation factor that reflects the local characteristics of the dispute and the characteristics of Zhang San.

[0100] The fourth step is to construct a mediation strategy decision tree that includes the regional adaptation factor and the dispute type label (in this case, the neighborhood dispute label). In the decision tree, different mediation strategy branches are set based on the different values ​​of the regional adaptation factor and the characteristics of the dispute type.

[0101] The fifth step is to adjust the weight configuration of the mediation strategy decision tree. Use the formula for calculation, where is the territorial characteristic adjustment coefficient in the territorial characteristic data, which is set to 0.6 based on the actual situation of District B in City A; is the social relationship density of the party’s background data. Assume that Zhang San’s social relationship density is 0.8; The modulus length of the educational background vector of the party’s background data is calculated to be 1.2; is the baseline value of the party’s background data, which is set to 1. The mediation solution weight W is obtained through calculation.

[0102] The sixth step is to adjust the personnel type and process duration based on the adjusted strategic decision tree. For example, if the mediation plan weights indicate that Zhang San's social relationships have a significant impact on the mediation, then a community elder with close ties and prestige can be selected as the mediator. Based on the complexity of the dispute and the various factors previously calculated, the mediation process duration can be appropriately adjusted. For more complex disputes, the originally planned one-week mediation period can be extended to two weeks.

[0103] Furthermore, the dispute analysis process is as follows: Figure 2 shown.

[0104] In general, this method of generating personalized mediation plans by combining territorial characteristics and the background data of the parties for localized secondary analysis fully takes into account regional differences and the individual characteristics of the parties, and can formulate mediation strategies that are more in line with actual conditions, increase the probability of successful mediation, and resolve disputes more effectively.

[0105] The emergency plan module is used to automatically generate an emergency response plan by integrating rescue resource data based on the event's geographic location when an emergency trigger condition is identified;

[0106] In an embodiment of the present invention, the emergency triggering condition includes:

[0107] Detection of emotional tendency elements exceeding a preset emotional intensity threshold;

[0108] Identify the elements of the behavior description that contain violent behavior keywords;

[0109] When both the emotional intensity threshold and the violent behavior keywords are met, the generation of an emergency response plan is activated.

[0110] The rescue resource data includes:

[0111] Establish a multi-level resource scheduling radius centered on the event's geographic location;

[0112] Dynamically matching medical emergency units, security linkage units, and legal aid units within the dispatch radius;

[0113] Generate a resource allocation graph that includes unit response priorities and path planning topology.

[0114] Calculate the optimal response path for rescue resource data:

[0115] ;

[0116] Where, is the minimum aggregate response time, For the Distance from rescue unit to incident location, is the total number of rescue units, is the average travel speed of the rescue unit, is the rescue unit availability indicator function;

[0117] Dynamically adjust the priority order of units in the resource allocation map.

[0118] The first step is to determine the emergency trigger conditions. Suppose, during a dispute, through monitoring and analysis of the parties' language and behavior, one party's emotional tendencies are detected to exceed a preset threshold, such as strong anger expressed in their speech. At the same time, the behavioral description contains keywords for violent behavior, such as "beating" or "violence." When these thresholds and violent behavior keywords are met simultaneously, an emergency response plan is activated.

[0119] The second step is to integrate rescue resource data based on the incident's geographic location. If the neighborhood dispute occurs in a specific location in the community, a multi-level resource dispatch radius is established with that location as the center. For example, a first-level dispatch radius of 500 meters is set. Within this radius, a search for medical emergency units reveals a community health service station 300 meters from the dispute site. A search for security linkage units reveals the community property security office 200 meters away. A search for legal aid units reveals a law firm 400 meters away. The search continues within a second-level dispatch radius of 1,000 meters to add more possible rescue resources.

[0120] The third step is to generate a resource allocation map. This map clearly defines the response priorities of each unit. For example, the security linkage unit is given the highest priority due to its proximity and ability to quickly control the situation on the scene; the medical emergency unit is next in line; and the legal aid unit is next. The topology of the paths for each unit to reach the dispute site is also planned. For example, a security officer's route from the property management security office to the dispute site via the nearest access road is mapped out; and the optimal driving route for medical emergency personnel from the community health service station is also mapped out.

[0121] The fourth step is to calculate the optimal response path of the rescue resource data. Using the formula, is the total number of rescue units, which is 3 in this example (security linkage unit, medical emergency unit, and legal aid unit); For the The distance from the rescue unit to the incident location, such as the distance from the security linkage unit =200 meters, distance to medical emergency unit =300 meters, distance to the legal aid unit =400 meters; is the average travel speed of the rescue unit, assuming the security personnel walking speed is =1.5 m / s, the speed of the medical emergency vehicle =10 m / s (taking into account the speed limit in the residential area, etc.), the driving speed of the law firm staff =8 m / s; is the rescue unit availability indicator function, assuming that all three units are available. The minimum aggregate response time is calculated as .

[0122] The fifth step is to dynamically adjust the priority order of units in the resource allocation map. If, after calculating the optimal response path, it is found that the arrival time of the security linkage unit, which originally had the highest priority, will be significantly increased due to temporary road congestion, while the medical emergency unit will arrive faster, the priority order will be dynamically adjusted to give the medical emergency unit the highest priority.

[0123] The sixth step is to automatically generate an emergency response plan based on the adjusted resource allocation map and optimal response path. The plan includes action instructions for each rescue unit, such as security personnel arriving first to control the situation and prevent violence; medical emergency personnel arriving later to treat any injuries; and legal aid personnel stepping in at the appropriate time to provide legal support.

[0124] In general, by accurately identifying emergency trigger conditions and integrating rescue resource data based on the geographic location of the incident to generate emergency response plans, rescue resources can be quickly and reasonably deployed when disputes may escalate into emergencies, minimizing losses and harm, protecting the lives and property of the parties involved, and maintaining social order and stability.

[0125] The auxiliary decision-making generation module is used to generate an auxiliary decision-making report based on the personalized mediation plan and the emergency response plan.

[0126] When the emergency plan module executes the method of automatically generating an emergency response plan by integrating rescue resource data based on the geographical location of the event when an emergency trigger condition is identified, it is specifically used to:

[0127] In an embodiment of the present invention, when the emergency plan module performs multi-dimensional closed-loop control on the grid connection process based on the reliable grid connection confidence level to obtain the optimal scheduling strategy for the new energy grid connection process, it is specifically configured to:

[0128] Inputting the personalized mediation plan and the emergency response plan into a strategy fusion module;

[0129] The mediation cost and the emergency cost are balanced by the conflict resolution function, wherein the calculation formula of the conflict resolution function for balanced mediation is as follows:

[0130] ;

[0131] Where, is the optimal decision coefficient, is the mediation-emergency balance factor, is the weight of the mediation scheme, is the benchmark mediation weight, is a natural constant, is the emergency time gain coefficient, is the minimum aggregate response time;

[0132] Output a visual decision matrix containing the optimal decision coefficients.

[0133] After executing the generation of the auxiliary decision-making report based on the personalized mediation plan and the emergency response plan, the auxiliary decision-making generation module is specifically used to:

[0134] generating a mediation stage division scheme according to the visual decision matrix;

[0135] A step-by-step implementation protocol for activating the contingency plan in the event of mediation failure;

[0136] The disposal results are fed back to the territorial feature matrix for dynamic updating.

[0137] The first step is to input the personalized mediation plan and emergency response plan into the strategy fusion module. Assume that the personalized mediation plan specifies that the mediator will be a community elder and the mediation process will take two weeks. The emergency response plan specifies the action steps and priorities for rescue units such as security, medical care, and legal aid. These detailed plans are then input into the strategy fusion module.

[0138] The second step is to balance the mediation cost and the emergency cost through the conflict resolution function. Using the formula, is the mediation-emergency balance factor, which is set to 0.5 based on the actual situation; is the weight of the mediation scheme, which is calculated as a certain value before; is the benchmark mediation weight, set as a reference value; is a natural constant, is the emergency time gain coefficient, which is set to 0.3 based on experience; is the minimum aggregate response time, calculated previously. The optimal decision coefficient is calculated using this formula .

[0139] The third step is to output a visual decision matrix containing the optimal decision coefficients. The decision matrix clearly displays key information about the mediation plan and emergency response plan, along with comprehensive decision recommendations based on the optimal decision coefficients. For example, the matrix shows that the mediation plan will be prioritized under normal circumstances. However, when a dispute develops into a specific emergency (such as escalating violence), the emergency response plan is quickly activated, and resource allocation and action sequence are appropriately adjusted based on the optimal decision coefficients.

[0140] Furthermore, the personalized mediation process is as follows Figure 3 shown.

[0141] In general, generating auxiliary decision-making reports can provide decision makers with clear, intuitive and comprehensive decision-making basis that considers mediation and emergency situations, helping decision makers make more scientific and reasonable decisions based on actual conditions when facing disputes, thereby improving the overall effectiveness and efficiency of dispute resolution.

[0142] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0143] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. The intelligent dispute analysis system based on big data is characterized by: It includes event collection module, dispute analysis module, solution generation module, emergency solution module and auxiliary decision generation module, among which: The event collection module is used to collect dispute event description data, territorial feature data and party background data to generate an original data set; The dispute analysis module is used to extract key event elements from the original data set to obtain a preliminary analysis report; The solution generation module is used to combine the territorial characteristic data and the background data of the parties to conduct a localized secondary analysis of the preliminary analysis report and generate a personalized mediation solution; The emergency plan module is used to automatically generate an emergency response plan by integrating rescue resource data based on the event's geographic location when an emergency trigger condition is identified; The auxiliary decision-making generation module is used to generate an auxiliary decision-making report based on the personalized mediation plan and the emergency response plan; When the solution generation module performs the localized secondary analysis of the preliminary analysis report in combination with the local characteristic data and the background data of the parties to generate a personalized mediation solution, it is specifically used to: Construct a territorial characteristic matrix containing local laws and regulations index, folk customs characteristics, and economic level parameters; Encoding the party background data into a background feature vector including social relationship density and historical dispute frequency; The territorial feature matrix and the background feature vector are fused through a feature weighting function to output a regional adaptation factor; When the solution generation module performs the localized secondary analysis of the preliminary analysis report in combination with the local characteristic data and the background data of the parties to generate a personalized mediation solution, it is specifically used to: Constructing a mediation strategy decision tree including the regional adaptation factor and the dispute type label; The weight configuration of the mediation strategy decision tree is adjusted, wherein the calculation formula of the adjustment is as follows: ； Where, is the weight of the mediation plan, is the territorial characteristic adjustment coefficient in the territorial characteristic data, is the social relationship density of the party’s background data, is the background vector modulus length of the party’s background data, The baseline value of the strength of the claim of the party's background data; Adjust personnel type and process duration based on the adjusted strategic decision tree.

2. The big data-based intelligent dispute analysis system according to claim 1, characterized in that: When the event collection module collects the dispute event description data, territorial feature data, and party background data to generate the original data set, it is specifically used to: Extract the conflicting parties, disputed objects, and behavioral description elements from the dispute event text through natural language processing technology; Associating the conflict subject, dispute object, and behavior description elements into a structured event tuple; The structured event tuple is stored in a distributed database.

3. The big data-based intelligent dispute analysis system according to claim 2, characterized in that: When extracting the key elements of the event from the original data set to obtain a preliminary analysis report, the dispute analysis module is specifically configured to: Extracting emotional tendency elements, behavioral characteristic elements, and controversial focus elements from the structured event tuple; The above factors are classified and weighted through machine learning models to generate a preliminary analysis report containing dispute type labels and severity assessments.

4. The big data-based dispute intelligent analysis system according to claim 1 is characterized in that: The emergency triggering conditions include: Detection of emotional tendency elements exceeding a preset emotional intensity threshold; Identify the elements of the behavior description that contain violent behavior keywords; When both the emotional intensity threshold and the violent behavior keywords are met, the generation of an emergency response plan is activated.

5. The big data-based intelligent dispute analysis system according to claim 4 is characterized in that: When executing the process of integrating rescue resource data based on the event's geographic location, the emergency plan module is specifically configured to: Establish a multi-level resource scheduling radius centered on the event's geographic location; Dynamically matching medical emergency units, security linkage units, and legal aid units within the dispatch radius; Generate a resource allocation map that includes unit response priorities and path planning topology.

6. The big data-based dispute intelligent analysis system according to claim 1, characterized in that: When the emergency plan module executes the method of automatically generating an emergency response plan by integrating rescue resource data based on the geographical location of the event when an emergency trigger condition is identified, it is specifically used to: Calculate the optimal response path for rescue resource data ； Where, is the minimum aggregate response time, For the Distance from rescue unit to incident location, is the total number of rescue units, is the average travel speed of the rescue unit, is the rescue unit availability indicator function; Dynamically adjust the priority order of units in the resource allocation graph.

7. The big data-based dispute intelligent analysis system according to claim 6 is characterized in that When executing the generation of the auxiliary decision report, the auxiliary decision generating module is specifically used to: Inputting the personalized mediation plan and the emergency response plan into a strategy fusion module; The mediation cost and the emergency cost are balanced by the conflict resolution function, wherein the calculation formula of the conflict resolution function for balanced mediation is as follows: ； Where, is the optimal decision coefficient, is the mediation-emergency balance factor, is the weight of the mediation scheme, is the benchmark mediation weight, is a natural constant, is the emergency time gain coefficient, is the minimum aggregate response time; Output a visual decision matrix containing the optimal decision coefficients.

8. The big data-based intelligent dispute analysis system according to claim 7, characterized in that: After executing the generation of the auxiliary decision-making report based on the personalized mediation plan and the emergency response plan, the auxiliary decision-making generation module is specifically used to: generating a mediation stage division scheme according to the visual decision matrix; A step-by-step implementation protocol for activating the contingency plan in the event of mediation failure; The disposal results are fed back to the territorial feature matrix for dynamic updating.

Images