Method and device for predicting neighborhood dispute risk event

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a neighborhood dispute risk event prediction method and device.The method comprises the steps that original case information is collected from a public network platform, risk event elements are extracted, a neighborhood dispute risk event data set is generated, key influence factors of parties in the contradictory evolution process in the data set are screened out, and a neighborhood dispute risk event prediction result is obtained; therefore, a contradictory evolution mechanism is identified. Building a neighborhood dispute risk event evolution process simulation model by utilizing the mechanism so as to establish relations among internal variables of the module, and calculating each variable value of the neighborhood dispute risk event evolution process simulation model by utilizing a large language model based on the relations; and generating a final risk event prediction result through the negative emotion threshold value of any party. Therefore, the problems of data sparseness, insufficient consideration of combination features and sequence features of events, single prediction type and the like of a prediction model based on technologies such as a neural network and the like in related technologies are solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method and device for predicting neighborhood dispute risk events. Background Art

[0002] Foreign public research on social risk events mainly revolves around several misdemeanor prediction systems established by the US government. In risk event prediction, due to the scarcity of abnormal event data distribution, in addition to general data representation and prediction methods, it mainly focuses on the construction and enhancement of data sets to cope with specific tasks in specific scenarios. Domestic research mainly focuses on script event prediction tasks, and through the introduction of hierarchical GRU (Gated Recurrent Unit), graph networks, etc., events are better represented, and corresponding knowledge is introduced to achieve better prediction of the event itself. The field of risk assessment is mainly concentrated in the fields of production safety and geophysics, which require detailed modeling and analysis, and the methods used are relatively traditional. There are few public literature in the field of neighborhood dispute risks.

[0003] In related technologies, the assessment and prediction of risk events require comprehensive consideration of multiple factors. Existing prediction models based on technologies such as neural networks have problems such as sparse data, insufficient consideration of the combined characteristics and sequence characteristics of events, and a single prediction type, and they urgently need to be improved. Summary of the invention

[0004] The present application provides a method and device for predicting neighborhood dispute risk events to solve the problems in related technologies, such as data sparsity, insufficient consideration of the combined characteristics and sequence characteristics of events, and single prediction type in prediction models based on technologies such as neural networks.

[0005] The first aspect of the present application provides a method for predicting neighborhood dispute risk events, comprising the following steps: collecting original case information from a public network platform, and extracting risk event elements of the original case information to generate a neighborhood dispute risk event data set; screening out at least one key influencing factor of the parties involved in the neighborhood dispute risk event in the neighborhood dispute risk event data set in the conflict evolution process to identify the conflict evolution mechanism of the neighborhood dispute risk event; using the conflict evolution mechanism of the neighborhood dispute risk event to build a simulation model of the evolution process of the neighborhood dispute risk event to establish the relationship between the variables within the module; based on the relationship between the variables within the module, using a large language model to calculate the values ​​of each variable of the simulation model of the evolution process of the neighborhood dispute risk event to generate the final risk event prediction result through the negative emotion threshold of any party.

[0006] Through the above technical solution, the embodiment of the present application can effectively construct a neighborhood dispute risk event data set through a systematic method, combining the data collection of the public network platform with the analysis capabilities of the large language model, and identify the key influencing factors in the evolution of the conflict, which not only enhances the understanding of neighborhood dispute risk events, but also clarifies the relationship between the variables by establishing a simulation model, thereby achieving quantitative prediction of risk events. This interpretability and quantitative prediction capabilities help to identify and intervene in potential neighborhood disputes in advance and promote social harmony and stability.

[0007] Optionally, in one embodiment of the present application, the extracting of risk event elements of the original case information to generate a neighborhood dispute risk event data set includes: detecting text information of the original case information containing words related to neighborhood disputes to filter out text information related to neighborhood disputes; performing legal knowledge matching on the text information related to neighborhood disputes based on a pre-constructed list of legal knowledge of neighborhood dispute cases to obtain text data with labels of conflicting legal provisions; and applying a large language model to extract event and actor attributes from the text data to determine the risk event elements.

[0008] Through the above technical solution, the embodiment of the present application can systematically extract and filter the text related to neighborhood disputes in the original case information, and combine the application of legal knowledge matching and large language model to efficiently build a neighborhood dispute risk event data set. This process not only improves the accuracy and efficiency of data processing, but also ensures the comprehensiveness and reliability of the data, providing a solid foundation for subsequent risk event analysis and prediction.

[0009] Optionally, in one embodiment of the present application, the neighborhood dispute risk event data set includes at least one of the attributes of the actor, the chain of previous conflict events, the family and work status of the conflicting parties, the time when the conflict occurred, the location when the conflict occurred, the weather when the conflict occurred, the emotional state of the conflicting parties, and the laws involved in the conflict.

[0010] Through the above technical solution, the neighborhood dispute risk event data set in the embodiment of the present application covers information in multiple dimensions such as the attributes of the actors, the previous conflict event chain, the family and work status of the conflicting parties, etc. This comprehensive data structure helps to deeply analyze and understand the complexity of neighborhood disputes, and can more accurately identify risk factors and evolution mechanisms, thereby improving the accuracy and reliability of risk event prediction and providing a scientific basis for building a harmonious community.

[0011] Optionally, in one embodiment of the present application, the attributes of the actor include at least one of gender, age, nationality, occupation, social outlook, criminal record, and history of mental illness; the previous chain of conflict events includes at least one of the cause event, development event, and climax event; the family and work status of the conflicting parties include at least one of the marriage history and recent work situation.

[0012] Through the above technical solution, the embodiment of the present application can comprehensively and meticulously analyze and evaluate the risk of neighborhood disputes by incorporating multi-dimensional factors such as the attributes of the actor, the previous conflict event chain, and the family and work status of the conflicting parties into the neighborhood dispute risk event prediction model, thereby enhancing the accuracy and reliability of the prediction. This diversified data integration method helps to deeply understand the root causes of conflicts and their evolution process, thereby providing a scientific basis for formulating effective prevention and mediation measures and promoting social harmony and stability.

[0013] Optionally, in one embodiment of the present application, the at least one key influencing factor includes at least one of the degree to which the parties are objectively affected by the conflict, the party's family situation, the party's family participation coefficient, the party's neurotic personality traits, the party's education level, the other party's attitude towards the conflict, the actual resolution result, the party's attitude towards the solution, the actual completion efficiency of the solution, the duration of the solution, the other party's enthusiasm for implementing the solution, the other party's awareness of the rule of law, and the other party's attitude towards the handling results.

[0014] Through the above technical solution, the embodiment of the present application can comprehensively evaluate the risk evolution mechanism of neighborhood disputes by identifying and analyzing multiple key influencing factors, such as the degree to which the parties are affected by the conflict, family situation, emotional characteristics, etc. This comprehensive method not only improves the accuracy and reliability of risk event prediction, but also provides a scientific basis for relevant decision-making, which helps to intervene and resolve potential neighborhood conflicts in a timely manner, thereby maintaining social harmony and stability.

[0015] Optionally, in one embodiment of the present application, the at least one key influencing factor includes at least one of the other party's attitude towards the conflict, gender, the other party's job position, the parties' communication attitude, the other party's personality, the other party's work intensity, the degree of impact of the conflict on the other party, the other party's previous experience, the credibility of the third party, the degree of impact of the conflict on the other party, the third party's mediation time, the third party's mediation attitude, the complexity of the third party's mediation, and the third party's mediation ability.

[0016] Through the above technical solution, the key influencing factors of the embodiment of the present application cover a variety of social psychological and environmental variables related to neighborhood disputes, such as the other party's attitude towards the conflict, gender, job position, communication attitude, etc. This multi-dimensional consideration makes the risk event prediction method more comprehensive and accurate, and can better reflect the complexity and dynamics of neighborhood disputes, thereby improving the accuracy and interpretability of the prediction, and providing a scientific basis for effectively resolving neighborhood conflicts.

[0017] The second aspect of the present application provides a neighborhood dispute risk event prediction device, including: a generation module, which is used to collect original case information from a public network platform and extract risk event elements of the original case information to generate a neighborhood dispute risk event data set; an identification module, which is used to screen out at least one key influencing factor of the parties to the neighborhood dispute risk event in the conflict evolution process in the neighborhood dispute risk event data set to identify the conflict evolution mechanism of the neighborhood dispute risk event; a construction module, which is used to use the conflict evolution mechanism of the neighborhood dispute risk event to build a neighborhood dispute risk event evolution process simulation model to establish the relationship between the variables within the module; a prediction module, which is used to calculate the values ​​of each variable of the neighborhood dispute risk event evolution process simulation model based on the relationship between the variables within the module using a large language model to generate the final risk event prediction result through the negative emotion threshold of any party.

[0018] Through the above technical solution, the embodiment of the present application can effectively construct a neighborhood dispute risk event data set through a systematic method, combining the data collection of the public network platform with the analysis capabilities of the large language model, and identify the key influencing factors in the evolution of the conflict, which not only enhances the understanding of neighborhood dispute risk events, but also clarifies the relationship between the variables by establishing a simulation model, thereby achieving quantitative prediction of risk events. This interpretability and quantitative prediction capabilities help to identify and intervene in potential neighborhood disputes in advance and promote social harmony and stability.

[0019] Optionally, in one embodiment of the present application, the generation module includes: a screening unit, used to detect words related to neighborhood disputes in the text information of the original case information, so as to screen out text information related to neighborhood disputes; a matching unit, used to match the text information related to neighborhood disputes with legal knowledge based on a pre-constructed list of legal knowledge of neighborhood dispute cases, so as to obtain text data with labels of legal provisions involved in the conflict; an extraction unit, used to apply a large language model to extract event and actor attributes from the text data, so as to determine the risk event elements.

[0020] Through the above technical solution, the embodiment of the present application can systematically extract and filter the text related to neighborhood disputes in the original case information, and combine the application of legal knowledge matching and large language model to efficiently build a neighborhood dispute risk event data set. This process not only improves the accuracy and efficiency of data processing, but also ensures the comprehensiveness and reliability of the data, providing a solid foundation for subsequent risk event analysis and prediction.

[0021] Optionally, in one embodiment of the present application, the neighborhood dispute risk event data set includes at least one of the attributes of the actor, the chain of previous conflict events, the family and work status of the conflicting parties, the time when the conflict occurred, the location when the conflict occurred, the weather when the conflict occurred, the emotional state of the conflicting parties, and the laws involved in the conflict.

[0022] Through the above technical solution, the neighborhood dispute risk event data set in the embodiment of the present application covers information in multiple dimensions such as the attributes of the actors, the previous conflict event chain, the family and work status of the conflicting parties, etc. This comprehensive data structure helps to deeply analyze and understand the complexity of neighborhood disputes, and can more accurately identify risk factors and evolution mechanisms, thereby improving the accuracy and reliability of risk event prediction and providing a scientific basis for building a harmonious community.

[0023] Optionally, in one embodiment of the present application, the attributes of the actor include at least one of gender, age, nationality, occupation, social outlook, criminal record, and history of mental illness; the previous chain of conflict events includes at least one of the cause event, development event, and climax event; the family and work status of the conflicting parties include at least one of the marriage history and recent work situation.

[0024] Through the above technical solution, the embodiment of the present application can comprehensively and meticulously analyze and evaluate the risk of neighborhood disputes by incorporating multi-dimensional factors such as the attributes of the actor, the previous conflict event chain, and the family and work status of the conflicting parties into the neighborhood dispute risk event prediction model, thereby enhancing the accuracy and reliability of the prediction. This diversified data integration method helps to deeply understand the root causes of conflicts and their evolution process, thereby providing a scientific basis for formulating effective prevention and mediation measures and promoting social harmony and stability.

[0025] Optionally, in one embodiment of the present application, the at least one key influencing factor includes at least one of the degree to which the parties are objectively affected by the conflict, the party's family situation, the party's family participation coefficient, the party's neurotic personality traits, the party's education level, the other party's attitude towards the conflict, the actual resolution result, the party's attitude towards the solution, the actual completion efficiency of the solution, the duration of the solution, the other party's enthusiasm for implementing the solution, the other party's awareness of the rule of law, and the other party's attitude towards the handling results.

[0026] Through the above technical solution, the embodiment of the present application can comprehensively evaluate the risk evolution mechanism of neighborhood disputes by identifying and analyzing multiple key influencing factors, such as the degree to which the parties are affected by the conflict, family situation, emotional characteristics, etc. This comprehensive method not only improves the accuracy and reliability of risk event prediction, but also provides a scientific basis for relevant decision-making, which helps to intervene and resolve potential neighborhood conflicts in a timely manner, thereby maintaining social harmony and stability.

[0027] Optionally, in one embodiment of the present application, the at least one key influencing factor includes at least one of the other party's attitude towards the conflict, gender, the other party's job position, the parties' communication attitude, the other party's personality, the other party's work intensity, the degree of impact of the conflict on the other party, the other party's previous experience, the credibility of the third party, the degree of impact of the conflict on the other party, the third party's mediation time, the third party's mediation attitude, the complexity of the third party's mediation, and the third party's mediation ability.

[0028] Through the above technical solution, the key influencing factors of the embodiment of the present application cover a variety of social psychological and environmental variables related to neighborhood disputes, such as the other party's attitude towards the conflict, gender, job position, communication attitude, etc. This multi-dimensional consideration makes the risk event prediction method more comprehensive and accurate, and can better reflect the complexity and dynamics of neighborhood disputes, thereby improving the accuracy and interpretability of the prediction, and providing a scientific basis for effectively resolving neighborhood conflicts.

[0029] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for predicting neighborhood dispute risk events as described in the above embodiment.

[0030] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above-mentioned method for predicting neighborhood dispute risk events.

[0031] The fifth aspect of the present application provides a computer program, including a computer program, which, when executed, is used to implement the above-mentioned method for predicting neighborhood dispute risk events.

[0032] The embodiment of the present application can combine the data collection of the public network platform with the analysis capabilities of the large language model to systematically construct a neighborhood dispute risk event data set and identify the key influencing factors in the evolution of the conflict. Not only does it enhance the understanding of neighborhood dispute risk events, but it also clarifies the relationship between the variables by establishing a simulation model, and realizes the quantitative prediction of risk events, which helps to identify and intervene in potential neighborhood disputes in advance and promote social harmony and stability. In addition, the data set covers information on multiple dimensions such as the attributes of the actors, the previous conflict event chain, and the family and work status of the conflicting parties, ensuring the comprehensiveness and reliability of the data and providing a solid foundation for subsequent risk analysis. Through the comprehensive analysis of multi-dimensional factors, it is possible to deeply understand the root causes of the conflict and its evolution process, thereby providing a scientific basis for formulating effective prevention and mediation measures and improving the accuracy and reliability of the prediction. This comprehensive consideration makes the risk event prediction method more accurate, effectively resolves neighborhood conflicts, and maintains social harmony and stability.

[0033] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0035] Figure 1 A flowchart of a method for predicting neighborhood dispute risk events provided according to an embodiment of the present application;

[0036] Figure 2 A flowchart for constructing a neighborhood dispute risk data set according to a specific embodiment of the present application;

[0037] Figure 3 This is a schematic diagram of a structured sample of a neighborhood dispute risk data set for a specific embodiment of the present application;

[0038] Figure 4 A schematic diagram of a system dynamics simulation model of a party's past conflicting emotional changes in a specific embodiment of the present application;

[0039] Figure 5 This is a schematic diagram of a dynamics simulation model of a party's negative emotion cumulative quantification system in a specific embodiment of the present application;

[0040] Figure 6 A schematic diagram of the structure of a neighborhood dispute risk event prediction device provided according to an embodiment of the present application;

[0041] Figure 7 The figure is a structural example diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0042] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0043] The following is a description of the neighborhood dispute risk event prediction method and device of the embodiment of the present application with reference to the accompanying drawings. In view of the related art mentioned in the above background technology, the prediction model based on the technology of neural network and the like has the problems of sparse data, insufficient consideration of the combination characteristics and sequence characteristics of the event, single prediction type, etc., and the present application provides a neighborhood dispute risk event prediction method, in which a systematic method can be used to combine the data collection of the public network platform with the analysis ability of the large language model to effectively construct a neighborhood dispute risk event data set, and identify the key influencing factors in the evolution of the contradiction, which not only enhances the understanding of the neighborhood dispute risk event, but also clarifies the relationship between the variables by establishing a simulation model, thereby realizing the quantitative prediction of the risk event. This interpretability and quantitative prediction ability are helpful to identify and intervene in potential neighborhood disputes in advance, and promote social harmony and stability. Thus, the problems of sparse data, insufficient consideration of the combination characteristics and sequence characteristics of the event, single prediction type, etc. in the prediction model based on the technology of neural network and the like in the related art are solved.

[0044] Specifically, Figure 1 A flowchart of a method for predicting neighborhood dispute risk events provided in an embodiment of the present application.

[0045] like Figure 1 As shown, the neighborhood dispute risk event prediction method includes the following steps:

[0046] In step S101, original case information is collected from the public network platform, and risk event elements of the original case information are extracted to generate a neighborhood dispute risk event dataset.

[0047] It is understandable that the original case information is collected from the public network platform, and the risk event elements are extracted from the original case information based on the large language model to obtain the neighborhood dispute risk event dataset.

[0048] Optionally, in one embodiment of the present application, risk event elements of the original case information are extracted to generate a neighborhood dispute risk event data set, including: detecting words related to neighborhood disputes in the text information of the original case information to filter out text information related to neighborhood disputes; matching the text information related to neighborhood disputes with legal knowledge based on a pre-constructed list of legal knowledge of neighborhood dispute cases to obtain text data with labels of legal provisions involved in the conflict; and applying a large language model to extract event and actor attributes from the text data to determine risk event elements.

[0049] In the actual implementation process, risk event feature elements are extracted from text information from public network platform information based on the large language model, including modules such as scope judgment, text filtering and target extraction. Among them, the scope judgment module screens out text information related to neighborhood disputes by judging whether the text information contains words related to neighborhood disputes. The text filtering module constructs a list of legal provisions knowledge of neighborhood dispute cases, and applies the text similarity algorithm to match the legal provisions knowledge of the screened text information related to neighborhood disputes to obtain data with the label "conflict involving legal provisions". The target extraction module applies the large language model to extract event and actor attributes from text data containing legal provisions knowledge of neighborhood dispute cases.

[0050] Optionally, in one embodiment of the present application, the neighborhood dispute risk event data set includes: attributes of the actor, previous conflict event chains, family and work status of the conflicting parties, time of conflict, location of conflict, weather when the conflict occurred, emotional state of the conflicting parties, and at least one of the laws involved in the conflict.

[0051] Among them, the attributes of the perpetrator include at least one of gender, age, nationality, occupation, social status, criminal record, and history of mental illness; the previous chain of conflict events includes at least one of the cause event, development event, and climax event; the family and work status of the conflicting parties includes at least one of the marriage history and recent work situation.

[0052] The step S101 is described below with reference to a specific embodiment.

[0053] This embodiment preferably collects original case information from the Judgment Documents Network, China Legal Service Network-Case Library-People's Mediation Work, downloads a total of about 70,000 case data, and saves them in CSV format.

[0054] like Figure 2 As shown, the data processing flow includes:

[0055] Step S201: input of original collected data.

[0056] Step S202: Scope judgment: filter out data with words such as "neighborhood disputes, land occupation, ventilation, lighting, passage, water use, drainage, noise, and environmental sanitation".

[0057] Filter out text information related to neighborhood disputes through words.

[0058] Step S203: Legal provision matching: Based on the Jaccard similarity algorithm, the similarity threshold is set to 0.6, and data related to legal provisions such as "intentional injury, intentional homicide, and negligent homicide" are identified, and each piece of data is labeled with a legal provision based on the calculation results.

[0059] Jaccard similarity J(A,B) = |A∩B| / |A∪B|, where A is the legal text and B is the case text. The similarity of the neighborhood dispute text information and the legal text information is calculated to obtain data with the label "the conflict involves legal provisions".

[0060] Step S204: Target extraction: deploy the ChatGLM3-6B-32K large language model, design the large language model prompt word template according to the data structure of the neighborhood dispute risk data set, and extract events and actor attributes from the data.

[0061] The prompt words of the designed large language model are: actor attributes, previous conflict event chain, family and work status of both parties in conflict, time of conflict, location of conflict, weather when conflict occurs, emotional state of both parties in conflict, whether conflict breaks out; actor attributes include gender, age, ethnicity, occupation, social outlook, criminal record, history of mental illness, etc.; previous conflict event chain includes causal events, development events, and climax events; family and work status of both parties in conflict includes marital history and recent work status. Event extraction and actor attribute extraction are performed on the data, and a total of 1,654 structured data are obtained. The structured data samples are as follows: Figure 3 shown.

[0062] Step S205: Output structured data.

[0063] The embodiment of the present application can generate a neighborhood dispute risk event data set by collecting original case information from a public network platform and using a large language model to extract risk event elements from this information. The specific process includes three modules: scope judgment, legal provision matching, and target extraction, to ensure that text information related to neighborhood disputes is screened out, and legal provision knowledge matching is performed, and finally the event and actor attributes are extracted. The advantage of this method is that it can systematically process and analyze a large amount of case data, improve the prediction accuracy and interpretability of neighborhood dispute risk events, and thus provide a scientific basis for creating a harmonious community.

[0064] In step S102, at least one key influencing factor of the parties involved in the neighborhood dispute risk event in the conflict evolution process is screened out in the neighborhood dispute risk event data set to identify the conflict evolution mechanism of the neighborhood dispute risk event.

[0065] It is understandable that based on the dataset of neighborhood dispute risk events, the Delphi method was used to screen out the key influencing factors of the conflict evolution process, such as the changes in the past conflicting emotions of the parties involved in the neighborhood dispute risk events and the accumulation of negative emotions of the parties involved.

[0066] Specifically, the key influencing factors of the parties involved in neighborhood dispute risk events on the changes in their past conflicting emotions include: the degree to which the parties are objectively affected by the conflict, the parties' family situation, the parties' family participation coefficient, the parties' neurotic personality traits, the parties' education level, the other party's attitude towards the conflict, the actual resolution results, the parties' attitude towards the solution, the actual completion efficiency of the solution, the duration of the solution, the other party's enthusiasm for implementing the solution, the other party's awareness of the rule of law, and at least one of the other party's attitude towards the handling results.

[0067] The key influencing factors for the accumulation of negative emotions of the parties involved in neighborhood dispute risk events include at least one of the other party's attitude towards the conflict, gender, the other party's job position, the parties' communication attitude, the other party's personality, the other party's work intensity, the impact of the conflict on the other party, the other party's previous experience, the credibility of the third party, the impact of the conflict on the other party, the time for third-party mediation, the attitude of the third party mediation, the complexity of the third-party mediation, and the ability of the third-party mediation.

[0068] The step S102 is described below with reference to a specific embodiment.

[0069] This embodiment preferably invites 10 experts in the field, and uses anonymous communication to solicit expert opinions. The specific situation and relevant requirements of the prediction of neighborhood dispute risk events are introduced to the experts. The neighborhood dispute risk event data set materials, the key influencing factor candidates for the changes in the parties' past conflicting emotions, and the key influencing factor candidates for the accumulation of the parties' negative emotions are attached, and the specific implementation steps are explained to the experts. The experts put forward opinions on the adjustment of key influencing factors and specific quantification methods based on the received materials. The experts' first judgment opinions are collected and listed in charts and compared, and then distributed to the experts again, asking them to compare their opinions with those of other experts and modify their opinions. Finally, all the experts' revised opinions are collected and sorted, and distributed to them again for a second revision. This is repeated for two to three rounds until the experts do not change their opinions. The key influencing factors formed and their quantification methods are shown in Table 1, which is as follows:

[0070] Table 1

[0071]

[0072]

[0073]

[0074]

[0075]

[0076]

[0077] Among them, (+) means that the larger the number, the more positive it is; (-) means that the larger the number, the more negative it is; (T) means that the quantity is time.

[0078] The embodiment of the present application can screen out the key influencing factors of the parties in the process of conflict evolution in the neighborhood dispute risk event data set through the Delphi method, thereby identifying the conflict evolution mechanism of neighborhood dispute risk events. Specifically, experts anonymously evaluate and adjust the key influencing factors of the parties' past conflicting emotional changes and accumulated negative emotions, and finally form a quantitative standard after multiple rounds of feedback. The advantage of this technical solution is that through the collective wisdom and experience of experts, it can effectively identify and quantify the multidimensional factors that affect the evolution of neighborhood disputes, thereby providing a scientific basis for the prediction of risk events, improving the accuracy and reliability of predictions, and promoting the harmony and stability of the community.

[0079] In step S103, a neighborhood dispute risk event evolution process simulation model is built using the neighborhood dispute risk event conflict evolution mechanism to establish the relationship between the internal variables of the module.

[0080] It is understandable that, based on the key influencing factors of the evolution of conflicts in neighborhood dispute risk events, a module on the changes in the parties' emotions about past conflicts and a module on the accumulation of the parties' negative emotions are constructed, and the relationship between the internal variables of the modules is established.

[0081] In the actual implementation process, the researchers constructed two modules: the changes in the parties' emotions about past conflicts and the accumulation of negative emotions. These two modules focus on different emotional dynamics: the former focuses on the fluctuations and changes in the emotions of the parties when facing conflicts; the latter focuses on the cumulative effects of the parties' emotions, especially how negative emotions gradually accumulate over time, thereby affecting their reactions and handling of neighborhood disputes. For each module, the research team will define a series of key variables. These variables may include the emotional state of the parties, the severity of the conflict, the influence of the external environment, etc. At the same time, the team will develop standardized quantitative methods to ensure comparability and consistency in different situations. Figure 4 and Figure 5Based on the structure shown in Figure 1, the researchers integrated these variables into a system dynamics model. This model can not only capture the changes in a single variable, but also simulate the interactions between multiple variables. For example, the emotional changes of the parties involved may be affected by multiple factors such as family support, neighborhood relations, and external interventions, which will be presented in the form of dynamic relationships in the model.

[0082] Furthermore, in the model, the researchers will clarify the relationship between different variables. For example, the accumulation of negative emotions may lead to the intensification of conflicts, and the intensification of conflicts may further affect the emotional state of the parties. By establishing these relationships, the model can more realistically reflect the evolution of neighborhood disputes. After the initial construction is completed, the research team will verify the model through historical cases. By comparing the emotional changes predicted by the model with the emotional evolution in actual cases, researchers can continuously adjust and optimize the model parameters to improve the accuracy and reliability of its predictions.

[0083] The embodiment of the present application can utilize the conflict evolution mechanism of neighborhood dispute risk events. The research team has constructed a simulation model of the evolution process of neighborhood dispute risk events, aiming to clarify the relationship between the variables within the module. The model includes two core modules: the changes in the parties' past conflicting emotions and the accumulation of negative emotions, which focus on the dynamic process of emotional fluctuations and emotional accumulation respectively. By defining key variables and formulating standardized quantitative methods, researchers can ensure the comparability and consistency of the model in different situations. In addition, the model can also simulate the interaction between multiple variables to truly reflect the evolution process of neighborhood disputes. Through comparative verification with historical cases, the research team can continuously optimize the model parameters, improve the accuracy and reliability of predictions, and thus provide a scientific basis for the prevention and handling of neighborhood disputes.

[0084] In step S104, based on the relationship between the internal variables of the module, the large language model is used to calculate the values ​​of each variable of the simulation model of the neighborhood dispute risk event evolution process, so as to generate the final risk event prediction result through the negative emotion threshold of any party.

[0085] It is understandable that by using the neighborhood dispute risk event dataset as a knowledge base and using a large language model to obtain the values ​​of various variables involved in the constructed simulation model, the negative emotions of the parties involved can be calculated, and by judging whether the negative emotions of the parties involved exceed the emotional threshold, the final risk event prediction results can be obtained.

[0086] The step S104 is described below with reference to a specific embodiment.

[0087] This example uses the Zhang Koukou murder case as a test example, and provides the following prompt to the ChatGLM3-6B-32K large language model, traversing from past conflicts to negative emotions and obtaining the required custom variable values. The code is as follows:

[0088] You are a community expert on neighborhood disputes. Your task is to read the parties, scoring terms, scoring criteria, and case description text provided to you, and give a score to the scoring terms based on the text and scoring criteria.

[0089] The request is as follows:

[0090] - If you think the text does not contain the rated term, output unk.

[0091] - Your output should only contain the scores themselves.

[0092] party:

[0093] {criminal}

[0094] Rating terms:

[0095] {target}

[0096] Scoring criteria:

[0097] {standard}

[0098] Case description text:

[0099] {query}

[0100] The terms are explained as follows:

[0101] Criminal: criminal, party involved, to facilitate the large model to determine the analysis perspective

[0102] target: the object to be rated

[0103] standard: The previously defined scoring standard for this object

[0104] query: Complete case description

[0105] After obtaining the scores of various influencing factors given by the large model, the variable values ​​are calculated, and the negative emotions of the parties are obtained according to the simulation model of the evolution process of the neighborhood dispute risk event built in step S103. Then, by judging whether the negative emotions of the parties exceed the set threshold, the final risk event prediction result is obtained.

[0106] The embodiment of the present application can effectively quantify and predict the risk events of neighborhood disputes by constructing a simulation model of the evolution process of neighborhood dispute risk events and using a large language model to accurately calculate each variable. Specifically, using the reasoning ability of the large language model, the negative emotions of the parties can be analyzed and it can be determined whether they exceed the set emotional threshold, thereby generating reliable risk prediction results. This method not only improves the accuracy of the prediction, but also combines the advantages of knowledge-driven and data-driven, making the prediction process more scientific and explainable, which helps to timely identify and deal with potential neighborhood disputes and maintain social harmony and stability.

[0107] According to the neighborhood dispute risk event prediction method proposed in the embodiment of the present application, a neighborhood dispute risk event data set can be effectively constructed through a systematic method, combining the data collection of the public network platform with the analysis capabilities of the large language model, and identifying the key influencing factors in the evolution of the conflict, which not only enhances the understanding of neighborhood dispute risk events, but also clarifies the relationship between the variables by establishing a simulation model, thereby achieving quantitative prediction of risk events. This interpretability and quantitative prediction ability help to identify and intervene in potential neighborhood disputes in advance and promote social harmony and stability.

[0108] Next, the neighborhood dispute risk event prediction device proposed in accordance with the embodiment of the present application is described with reference to the accompanying drawings.

[0109] Figure 6 It is a block diagram of a neighborhood dispute risk event prediction device according to an embodiment of the present application.

[0110] like Figure 6 As shown, the neighborhood dispute risk event prediction device 10 includes: a generation module 100, an identification module 200, a construction module 300 and a prediction module 400.

[0111] Specifically, the generation module 100 is used to collect original case information from the public network platform and extract risk event elements of the original case information to generate a neighborhood dispute risk event data set.

[0112] The identification module 200 is used to screen out at least one key influencing factor of the parties involved in the neighborhood dispute risk event in the neighborhood dispute risk event data set in the conflict evolution process, so as to identify the conflict evolution mechanism of the neighborhood dispute risk event.

[0113] The construction module 300 is used to build a simulation model of the evolution process of neighborhood dispute risk events by using the contradiction evolution mechanism of neighborhood dispute risk events, so as to establish the relationship between the variables within the module.

[0114] The prediction module 400 is used to calculate the values ​​of various variables in the simulation model of the evolution process of neighborhood dispute risk events based on the relationship between the variables within the module, using a large language model, so as to generate the final risk event prediction result through the negative emotion threshold of any party.

[0115] Optionally, in one embodiment of the present application, the generation module 100 includes: a screening unit, a matching unit and an extraction unit.

[0116] The screening unit is used to detect words related to neighborhood disputes in the text information of the original case information, so as to screen out text information related to neighborhood disputes.

[0117] The matching unit is used to match the legal knowledge of the text information related to the neighborhood dispute based on the pre-built legal knowledge list of the neighborhood dispute case, so as to obtain the text data with the label of the legal article involved in the conflict.

[0118] The extraction unit is used to apply a large language model to extract event and actor attributes from text data to determine risk event elements.

[0119] Optionally, in one embodiment of the present application, the neighborhood dispute risk event data set includes at least one of the attributes of the actor, the chain of previous conflict events, the family and work status of the conflicting parties, the time when the conflict occurred, the location when the conflict occurred, the weather when the conflict occurred, the emotional state of the conflicting parties, and the laws involved in the conflict.

[0120] Optionally, in one embodiment of the present application, the attributes of the actor include at least one of gender, age, nationality, occupation, social outlook, criminal record, and history of mental illness; the previous chain of conflict events includes at least one of the causal event, the development event, and the climax event; the family and work status of the conflicting parties includes at least one of the marital history and recent work situation.

[0121] Optionally, in one embodiment of the present application, at least one key influencing factor includes at least one of the degree to which the parties are objectively affected by the conflict, the party's family situation, the party's family participation coefficient, the party's neurotic personality traits, the party's education level, the other party's attitude towards the conflict, the actual resolution result, the party's attitude towards the solution, the actual completion efficiency of the solution, the duration of the solution, the other party's enthusiasm for implementing the solution, the other party's awareness of the rule of law, and the other party's attitude towards the handling results.

[0122] Optionally, in one embodiment of the present application, at least one key influencing factor includes at least one of the other party's attitude towards the conflict, gender, the other party's job position, the parties' communication attitude, the other party's personality, the other party's work intensity, the degree of impact of the conflict on the other party, the other party's previous experience, the credibility of the third party, the degree of impact of the conflict on the other party, the third party's mediation time, the third party's mediation attitude, the complexity of the third party's mediation, and the third party's mediation ability.

[0123] It should be noted that the aforementioned explanation of the embodiment of the method for predicting neighborhood dispute risk events is also applicable to the neighborhood dispute risk event prediction device of this embodiment, and will not be repeated here.

[0124] According to the neighborhood dispute risk event prediction device proposed in the embodiment of the present application, a neighborhood dispute risk event data set can be effectively constructed through a systematic method, combining the data collection of the public network platform with the analysis capabilities of the large language model, and identifying the key influencing factors in the evolution of the conflict. It not only enhances the understanding of neighborhood dispute risk events, but also clarifies the relationship between the variables by establishing a simulation model, thereby achieving quantitative prediction of risk events. This interpretability and quantitative prediction ability help to identify and intervene in potential neighborhood disputes in advance and promote social harmony and stability.

[0125] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0126] A memory 701 , a processor 702 , and a computer program stored in the memory 701 and executable on the processor 702 .

[0127] When the processor 702 executes the program, the neighborhood dispute risk event prediction method provided in the above embodiment is implemented.

[0128] Furthermore, the electronic device further comprises:

[0129] The communication interface 703 is used for communication between the memory 701 and the processor 702 .

[0130] The memory 701 is used to store computer programs that can be executed on the processor 702 .

[0131] The memory 701 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0132] If the memory 701, the processor 702 and the communication interface 703 are implemented independently, the communication interface 703, the memory 701 and the processor 702 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0133] Optionally, in a specific implementation, if the memory 701, the processor 702 and the communication interface 703 are integrated on a chip, the memory 701, the processor 702 and the communication interface 703 can communicate with each other through an internal interface.

[0134] The processor 702 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0135] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for predicting neighborhood dispute risk events.

[0136] An embodiment of the present application also provides a computer program, including a computer program, which, when executed, is used to implement the above-mentioned method for predicting neighborhood dispute risk events.

[0137] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0138] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0139] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0140] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0141] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of multiple of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0142] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0143] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0144] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for predicting neighborhood dispute risk events, characterized in that: The following steps are involved: Collecting original case information from a public network platform and extracting risk event elements of the original case information to generate a neighborhood dispute risk event data set; Screening out at least one key influencing factor of the parties involved in the neighborhood dispute risk event in the neighborhood dispute risk event data set during the conflict evolution process, so as to identify the conflict evolution mechanism of the neighborhood dispute risk event; Using the conflict evolution mechanism of the neighborhood dispute risk event, a simulation model of the neighborhood dispute risk event evolution process is constructed to establish the relationship between the variables within the module; Based on the relationship between the internal variables of the module, the large language model is used to calculate the values ​​of each variable of the simulation model of the neighborhood dispute risk event evolution process, so as to generate the final risk event prediction result through the negative emotion threshold of any party.

2. The method according to claim 1, characterized in that The step of extracting the risk event elements of the original case information to generate a neighborhood dispute risk event data set includes: Detecting whether the text information of the original case information contains words related to neighborhood disputes, so as to filter out text information related to neighborhood disputes; Based on the pre-built list of legal provisions knowledge of neighborhood dispute cases, legal provision knowledge matching is performed on the text information related to the neighborhood dispute to obtain text data with labels of legal provisions involved in the conflict; A large language model is applied to extract event and actor attributes from the text data to determine the risk event elements.

3. The method according to claim 1 or 2, characterized in that: The neighborhood dispute risk event data set includes at least one of the actor's attributes, previous conflict event chains, family and work status of both parties to the conflict, the time when the conflict occurred, the location where the conflict occurred, the weather when the conflict occurred, the emotional state of both parties to the conflict, and the legal provisions involved in the conflict.

4. The method according to claim 3, characterized in that The attributes of the actor include at least one of gender, age, nationality, occupation, social status, criminal record, and history of mental illness; the previous chain of conflict events includes at least one of the cause event, development event, and climax event; the family and work status of the conflicting parties include at least one of marital history and recent work situation.

5. The method according to claim 1, characterized in that The at least one key influencing factor includes at least one of the degree to which the parties are objectively affected by the conflict, the parties' family situation, the parties' family participation coefficient, the parties' neurotic personality traits, the parties' education level, the other party's attitude towards the conflict, the actual resolution results, the parties' attitude towards the solution, the actual completion efficiency of the solution, the duration of the solution, the other party's enthusiasm for implementing the solution, the other party's awareness of the rule of law, and the other party's attitude towards the handling results.

6. The method according to claim 1, characterized in that The at least one key influencing factor includes at least one of the other party's attitude towards the conflict, gender, the other party's job position, the parties' communication attitude, the other party's personality, the other party's work intensity, the impact of the conflict on the other party, the other party's previous experience, the credibility of the third party, the impact of the conflict on the other party, the third party's mediation time, the third party's mediation attitude, the complexity of the third party mediation, and the third party's mediation ability.

7. A neighborhood dispute risk event prediction device, characterized in that: The following steps are involved: A generation module, used to collect original case information from the public network platform and extract risk event elements of the original case information to generate a neighborhood dispute risk event data set; An identification module, used to screen out at least one key influencing factor of the parties involved in the neighborhood dispute risk event in the neighborhood dispute risk event data set in the conflict evolution process, so as to identify the conflict evolution mechanism of the neighborhood dispute risk event; A construction module is used to build a simulation model of the evolution process of neighborhood dispute risk events by using the contradiction evolution mechanism of neighborhood dispute risk events, so as to establish the relationship between the variables within the module; The prediction module is used to calculate the values ​​of each variable of the simulation model of the evolution process of the neighborhood dispute risk event based on the relationship between the internal variables of the module, using a large language model, so as to generate the final risk event prediction result through the negative emotion threshold of any party.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for predicting neighborhood dispute risk events as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method for predicting neighborhood dispute risk events as described in any one of claims 1-6.

10. A computer program product, characterized in that It comprises a computer program, characterized in that the computer program is executed to implement the neighborhood dispute risk event prediction method as described in any one of claims 1-6.

Images