A content data prediction and analysis method based on digital twins

Abstract

This invention discloses a content data prediction and analysis method based on digital twins, belonging to the field of data prediction technology. The key technical solutions include the following steps: collecting multi-source heterogeneous data related to law enforcement cases; fusing and processing the multi-source heterogeneous data to construct a digital twin model of the law enforcement cases; extracting key elements from the law enforcement cases based on the digital twin model, determining the set of correlation influence coefficients between each key element, and determining the normal variation range of the correlation influence coefficients between each key element; determining the degree of correlation influence between the current law enforcement case and similar historical cases on key elements based on the correlation influence coefficient set to obtain the current correlation influence degree set; the effect is to predict a second risk prediction value based on these factors, and combine this with the first risk prediction value obtained based on the analysis of the key elements of the case to obtain a comprehensive prediction and analysis result.

Description

Technical Field

[0001] This invention relates to the field of data prediction technology, and more specifically, to a content data prediction and analysis method based on digital twins. Background Technology

[0002] Against the backdrop of continuous advancements in social governance and the rule of law, law enforcement work faces increasingly complex and diverse challenges. Traditional law enforcement models and case analysis methods are no longer sufficient to meet real-world needs, necessitating innovative technological solutions to enhance law enforcement efficiency and the scientific nature of decision-making. This has led to the emergence of a data prediction and analysis method for law enforcement cases based on digital twins.

[0003] Traditional methods analyze key elements such as case type, spatiotemporal characteristics, behavioral patterns of involved persons, and the relationships within the chain of evidence in isolation, failing to fully explore the inherent connections and mutual influences between these elements. For example, when analyzing cases, they rarely consider the impact of case type on the behavioral patterns of involved persons, or how spatiotemporal characteristics affect the completeness of the chain of evidence. This results in a lack of depth in understanding and judgment of the case, making it difficult to accurately grasp the development trend and potential risks of the case. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the present invention aims to provide a content data prediction and analysis method based on digital twins.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A content data prediction and analysis method based on digital twins, comprising the following steps:

[0007] Collect multi-source heterogeneous data related to law enforcement cases, and fuse and process the multi-source heterogeneous data to construct a digital twin model of the law enforcement cases;

[0008] Based on the digital twin model, key elements in law enforcement cases are extracted, and the set of correlation influence coefficients between key elements and the normal range of variation of the correlation influence coefficients between key elements are determined.

[0009] After determining the degree of correlation between current law enforcement cases and similar historical cases in terms of key elements based on the correlation influence coefficient set, the current correlation influence degree set is obtained. After processing the current correlation influence degree set, it is compared with the preset normal influence range value to obtain the comparison result.

[0010] By combining the in-depth analysis signals from the comparison results with the dynamic evolution patterns of case elements in the digital twin model of law enforcement cases, the changing trends of key elements in current law enforcement cases are predicted to generate the first prediction data set.

[0011] Based on the analysis of the first prediction data set, the current development trend of law enforcement cases is analyzed, and the first risk prediction value is obtained.

[0012] The distribution of law enforcement resources associated with statistical law enforcement cases is analyzed. Based on the distribution of law enforcement resources, social indicator data, and the first risk prediction value, a comprehensive prediction analysis is conducted on the current law enforcement cases to obtain the comprehensive prediction analysis results.

[0013] Preferably, the multi-source heterogeneous data includes basic case information, on-site investigation data, party information, and historical similar case data.

[0014] Preferably, the key elements include case type, spatiotemporal characteristics, behavioral patterns of the persons involved, and the relationship of the evidence chain.

[0015] Preferably, determining the set of correlation influence coefficients between key elements and determining the normal range of variation of the correlation influence coefficients between key elements specifically includes the following steps:

[0016] Determine the interrelationships among the key elements and establish a set of correlation influence coefficients among the key elements;

[0017] Obtain the correlation coefficients between key elements in historical normal cases and historical abnormal cases respectively, and construct the historical normal correlation coefficient set and the historical abnormal correlation coefficient set.

[0018] Based on the historical normal correlation influence coefficient set and the historical abnormal correlation influence coefficient set, determine the normal variation range of the correlation influence coefficients between each key element.

[0019] Preferably, the current set of associated influence levels is processed and compared with a preset normal influence range value to obtain a comparison result, specifically including the following steps:

[0020] If there are data whose current degree of correlation impact is greater than the preset normal impact range, the key elements of the case corresponding to the data whose current degree of correlation impact is greater than the preset normal impact range will be identified as risk warning signals for the comparison results.

[0021] If all data in the current set of associated impacts are less than the preset normal impact range value, the difference set is obtained by calculating the difference between each data in the current set of associated impacts and the preset normal impact range value.

[0022] A preset difference threshold is set. If there are data in the difference set that are greater than or equal to the difference threshold, the key elements of the current law enforcement case will continue to be analyzed in depth and the deep analysis signal of the comparison result will be output.

[0023] Preferably, the first prediction data set is generated by combining deep analysis signals with the dynamic evolution patterns of case elements in the digital twin model of law enforcement cases to predict the changing trends of key elements in current law enforcement cases. This specifically includes the following steps:

[0024] Based on the deep analysis of signals, the dynamic evolution characteristics of key elements in current law enforcement cases are extracted, and a dynamic evolution model of key elements is established by combining the dynamic evolution law of case elements in the digital twin model of law enforcement cases.

[0025] After using a dynamic evolution model to predict the changing trends of key elements in current law enforcement cases within a preset time period, a first prediction data set is generated; wherein, the first prediction data set includes the evolution trend of case type, the changing trend of spatiotemporal characteristics, the changing trend of behavior patterns of persons involved in the case, and the changing trend of evidence chain correlation.

[0026] Preferably, the analysis of the current development trend of law enforcement cases based on the first prediction data set to obtain the first risk prediction value specifically includes the following steps:

[0027] After determining the degree of influence of environmental factors on key elements of the case based on the first predictive data set and the digital twin model, the environmental impact degree set is obtained.

[0028] Based on the environmental impact degree set and the first prediction data set, a second prediction data set is used to predict the factors that affect current law enforcement cases.

[0029] Based on the second set of prediction data, the current development trend of law enforcement cases is determined, and the first risk prediction value of the current law enforcement cases is determined according to the current development trend of law enforcement cases.

[0030] Preferably, the distribution of law enforcement resources includes the number of law enforcement personnel, the availability of law enforcement equipment, and the density of law enforcement agencies.

[0031] Preferably, the social indicator data includes population density, public security status, and public opinion index.

[0032] Preferably, a comprehensive predictive analysis is conducted on current law enforcement cases based on the distribution of law enforcement resources, social indicator data, and the first risk prediction value to obtain the comprehensive predictive analysis result, specifically including the following steps:

[0033] Based on the distribution of law enforcement resources and social indicator data, predict the second risk value of current law enforcement cases;

[0034] The comprehensive predictive analysis results of current law enforcement cases are determined based on the first and second risk prediction values.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] This invention constructs a digital twin model by collecting heterogeneous data from multiple sources, extracts key elements, and analyzes their correlations and impacts. When the current set of correlation impacts is compared to a preset normal range, it can promptly capture risk warning signals. If the correlation impact of key elements exceeds the normal range, it can quickly identify potential risks in a case, enabling law enforcement to intervene early and prevent problems before they arise. Deep analysis of the signal triggering mechanism can uncover subtle anomalies, provide in-depth analysis of key elements, and predict the deterioration or transformation trend of a case in advance, such as predicting the evolution of a case type from public security to criminal, thus buying valuable time for risk prevention and control.

[0037] The analysis comprehensively considers the distribution of law enforcement resources (number of law enforcement personnel, equipment allocation, and density of institutional distribution) and social indicators (population density, public security situation, and public opinion index). Based on these factors, a second risk prediction value is generated, which is then combined with the first risk prediction value obtained from the analysis of key case elements to produce a comprehensive predictive analysis result. This helps law enforcement agencies clearly grasp the overall picture of case risks and rationally allocate resources. In areas with high case risks and strained law enforcement resources, targeted increases in personnel and equipment investment and optimization of institutional layout can be implemented to avoid resource waste, improve overall law enforcement efficiency, and ensure the efficient conduct of law enforcement work. Attached Figure Description

[0038] Figure 1 This invention provides a schematic diagram illustrating the steps of a content data prediction and analysis method based on digital twins.

[0039] Figure 2 This is a schematic diagram illustrating the steps in obtaining the normal variation range value in a content data prediction and analysis method based on digital twins proposed in this invention;

[0040] Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention.

[0041] 610. Processor; 620. Communication interface; 630. Memory; 640. Communication bus. Detailed Implementation

[0042] Reference Figures 1 to 3 As shown.

[0043] The embodiments further illustrate the content data prediction and analysis method based on digital twins proposed in this invention.

[0044] A content data prediction and analysis method based on digital twins, comprising the following steps:

[0045] Collect multi-source heterogeneous data related to law enforcement cases, and fuse and process the multi-source heterogeneous data to construct a digital twin model of the law enforcement cases;

[0046] Based on the digital twin model, key elements in law enforcement cases are extracted, and the set of correlation influence coefficients between key elements and the normal range of variation of the correlation influence coefficients between key elements are determined.

[0047] After determining the degree of correlation between current law enforcement cases and similar historical cases in terms of key elements based on the correlation influence coefficient set, the current correlation influence degree set is obtained. After processing the current correlation influence degree set, it is compared with the preset normal influence range value to obtain the comparison result.

[0048] By combining the in-depth analysis signals from the comparison results with the dynamic evolution patterns of case elements in the digital twin model of law enforcement cases, the changing trends of key elements in current law enforcement cases are predicted to generate the first prediction data set.

[0049] Based on the analysis of the first prediction data set, the current development trend of law enforcement cases is analyzed, and the first risk prediction value is obtained.

[0050] The distribution of law enforcement resources associated with statistical law enforcement cases is analyzed. Based on the distribution of law enforcement resources, social indicator data, and the first risk prediction value, a comprehensive prediction analysis is conducted on the current law enforcement cases to obtain the comprehensive prediction analysis results.

[0051] This application involves various types of data in its law enforcement work. The multi-source, heterogeneous data covers basic case information (such as the nature of the case, time and location of occurrence), on-site investigation data (on-site traces, physical evidence, and other related information), party information (party identity, past behavior records, etc.), and historical similar case data (handling procedures and results of similar past cases). This data, from different sources and with varying structures, is collected. Subsequently, this data undergoes fusion processing, primarily including data cleaning (removing errors and duplicate data) and data standardization (unifying data formats). Based on the fused data, a digital twin model of the law enforcement case is constructed. This model is a virtual mapping of the real-world situation of the law enforcement case, dynamically reflecting various types of case-related information.

[0052] Based on the constructed digital twin model, key elements of the case are extracted, including case type (e.g., public security case, criminal case), spatiotemporal characteristics (time, place, and spatial environment of the incident), behavioral patterns of the involved persons (movement trajectories, behavioral habits, etc.), and evidence chain relationships (mutual corroboration relationships between various pieces of evidence). A set of correlation influence coefficients between each key element is determined, i.e., the degree of mutual influence between elements is quantitatively analyzed. For example, the case type may affect the behavioral patterns of the involved persons, and the quantitative value of this influence is calculated. Simultaneously, to determine whether the correlation influence coefficients are within a reasonable range, the correlation influence coefficients between each key element in historical normal cases and historical abnormal cases are obtained separately, constructing historical normal correlation influence coefficient sets and historical abnormal correlation influence coefficient sets. Analysis of these two sets determines the normal range of variation values ​​for the correlation influence coefficients between each key element.

[0053] Based on the previously determined set of correlation impact coefficients, the correlation impact of current law enforcement cases with similar historical cases on key elements is compared to obtain the current correlation impact set. This current correlation impact set is then processed and compared with a preset normal impact range value. If any data in the current correlation impact set exceeds the preset normal impact range value, it indicates an anomaly in the corresponding key elements of the case, and this is identified as a risk warning signal for the comparison results. If all data in the current correlation impact set are less than the preset normal impact range value, the difference between each data point and the preset normal impact range value is calculated to obtain a difference set. When any data in the difference set is greater than or equal to a preset difference threshold, it indicates that further in-depth analysis of the key elements of the current law enforcement case is needed, and a deep analysis signal for the comparison results is output.

[0054] After obtaining the in-depth analysis signals from the comparison results, and combining them with the dynamic evolution patterns of case elements in the digital twin model of law enforcement cases (such as the changing trends of case types over time, and the changes in the behavior patterns of involved persons at different stages), the dynamic evolution characteristics of the key elements of current law enforcement cases are extracted. Based on these characteristics, a dynamic evolution model of the key elements is established. This model is used to predict the changing trends of the key elements of current law enforcement cases within a preset time period, thereby generating the first prediction data set. This set covers the evolution trend of case types, the changing trend of spatiotemporal characteristics, the changing trend of the behavior patterns of involved persons, and the changing trend of the evidence chain relationship.

[0055] Based on the first predictive data set and a digital twin model, the degree of influence of environmental factors (such as population density, security situation, and public opinion in the area where the incident occurred) on key elements of the case is determined to obtain an environmental impact degree set. Based on the environmental impact degree set and the first predictive data set, the development trend of the current law enforcement case after being affected by these factors is further predicted to obtain a second predictive data set. Based on the second predictive data set, the current development trend of the law enforcement case is determined, such as whether it is developing in a more complex and dangerous direction, or whether there is a trend of mitigation or resolution. Based on the development trend, the first risk prediction value of the current law enforcement case is determined, quantifying the risk level of the case.

[0056] This study analyzes the distribution of law enforcement resources associated with each case, including the number of law enforcement personnel, the availability of law enforcement equipment, and the density of law enforcement agencies. Simultaneously, it combines social indicator data (population density, public security situation, public opinion index, etc.) to predict the secondary risk value of current law enforcement cases based on the distribution of law enforcement resources and social indicator data. This comprehensively considers the capacity of law enforcement resources to support case handling and the impact of the social environment on cases. Finally, based on the primary and secondary risk prediction values, a comprehensive predictive analysis of current law enforcement cases is determined, providing law enforcement departments with a comprehensive and scientific basis for decision-making, assisting them in rationally allocating resources and formulating response strategies.

[0057] Multi-source heterogeneous data includes basic case information, on-site investigation data, party information, and historical similar case data.

[0058] Basic case information includes case number, time of incident, location of incident, and case type (public security, criminal, etc.).

[0059] Crime scene investigation data includes: traces (such as fingerprints, footprints, bloodstains, etc.), physical evidence (tools used in the crime, left-behind items, etc.), the scene environment (topography, building layout, etc.), and scene video data (photos, videos), obtained through professional investigation methods. Crime scene investigation data is crucial for reconstructing the course of the crime and determining its nature.

[0060] Information about the parties involved: This includes the parties' identity information (name, age, occupation, address, etc.), contact information, social relationships, and past criminal records. As the core subjects of the case, the information about the parties is crucial for understanding the motives and related factors of the case.

[0061] Historical similar case data: This data organizes the handling procedures, investigation methods, evidence collection, and final outcomes of similar past cases. By leveraging this data, common patterns can be identified, providing a reference for current cases.

[0062] Key elements include case type, temporal and spatial characteristics, behavioral patterns of those involved, and the relationship between the evidence chain.

[0063] Case type: Clarify whether the case belongs to different categories such as public security, criminal, or administrative. Different types of cases differ in terms of handling procedures, application of law, and social impact.

[0064] Spatiotemporal characteristics: These encompass the time (e.g., day or night, weekday or holiday) and space (geographical location, environment, etc.) of the incident. Spatiotemporal factors not only influence the probability and characteristics of incidents but also play a crucial role in evidence collection and clue tracking.

[0065] Behavioral patterns of involved persons: This refers to the movement patterns, language expressions, and behavioral habits of involved persons (including suspects, witnesses, victims, etc.) during the case. By analyzing these behavioral patterns, we can uncover their motivations and psychological states, providing direction for case investigation and handling.

[0066] The chain of evidence refers to the relationship between different types of evidence in a case (physical evidence, documentary evidence, witness testimony, etc.) that corroborate, supplement, or contradict each other. A clear chain of evidence is key to reconstructing the facts of a case and determining liability.

[0067] The process involves determining the set of correlation coefficients between key elements and the normal range of variation for these coefficients, specifically including the following steps:

[0068] Determine the interrelationships among the key elements and establish a set of correlation influence coefficients among the key elements;

[0069] Obtain the correlation coefficients between key elements in historical normal cases and historical abnormal cases respectively, and construct the historical normal correlation coefficient set and the historical abnormal correlation coefficient set.

[0070] Based on the historical normal correlation influence coefficient set and the historical abnormal correlation influence coefficient set, determine the normal variation range of the correlation influence coefficients between each key element.

[0071] Key elements in the enforcement cases presented in this application include case type, temporal and spatial characteristics, behavioral patterns of the individuals involved, and the relationships within the chain of evidence. These elements are not isolated but interact with each other. For example, the case type influences the behavioral patterns of the individuals involved; in theft cases, suspects may choose concealed times and locations for their crimes (influencing temporal and spatial characteristics), and their behavior will be more inclined towards clandestine theft. Furthermore, the relationships within the chain of evidence may change due to the behavioral patterns of the individuals involved; if they deliberately destroy evidence, the integrity of the chain of evidence will be compromised.

[0072] By deeply analyzing a large amount of law enforcement case data, statistical and machine learning methods are used to uncover the inherent connections between elements. For example, regression analysis is used to study the quantitative relationship between case types and the behavioral patterns of those involved; or association rule algorithms are used to identify potential rules between spatiotemporal characteristics and the chain of evidence. Based on these, the degree of mutual influence between key elements is represented by quantified values, thereby establishing a set of correlation influence coefficients, which clearly presents and measures the influence relationships between elements.

[0073] Construction of a Historical Normal Correlation Influence Coefficient Set: This involves collecting a large amount of historical law enforcement case data that is considered to have been handled normally and whose outcomes conformed to conventional expectations. Correlation influence coefficients between key elements are extracted from these cases. Normal cases typically refer to those that occurred under standardized law enforcement procedures, with conclusive evidence, and whose handling complied with legal regulations and conventional logic. For example, in a normal public security dispute case, following a predetermined process, key elements such as case type and the behavioral patterns of those involved exhibit stable correlation influence relationships. These coefficients are compiled and summarized to form a historical normal correlation influence coefficient set.

[0074] Construction of a set of historical anomaly correlation coefficients: This involves screening historical abnormal law enforcement cases with complex processing, outcomes deviating from the norm, or special circumstances. These abnormal cases may include controversial cases, cases where handling is more difficult due to special factors, etc. Similarly, the correlation coefficients between key elements are extracted to construct a set of historical abnormal correlation coefficients. For example, in a case involving new types of crime, the correlation relationships between elements such as case type and the behavioral patterns of the perpetrators differ from those in conventional cases; the coefficients reflect this particularity.

[0075] After obtaining the historical normal correlation coefficient set and the historical abnormal correlation coefficient set, statistical analysis is performed on the historical normal correlation coefficient set. Its mean, standard deviation, and other statistical measures are calculated. The mean represents the average level of the correlation coefficient under normal circumstances, and the standard deviation reflects the dispersion of the coefficient. Generally, a range within the mean ± a certain multiple of the standard deviation (e.g., ±2 standard deviations) can be considered a normal range of variation. This range is further verified and calibrated by comparing it with the historical abnormal correlation coefficient set. If a correlation coefficient exceeds this range, it means that there may be an anomaly in the relationship between the corresponding elements in the current case, requiring further attention and analysis. This provides important reference for risk warning and in-depth analysis of subsequent law enforcement cases.

[0076] The current set of associated impact levels is processed and compared with the preset normal impact range value to obtain the comparison result. The specific steps include:

[0077] If there are data whose current degree of correlation impact is greater than the preset normal impact range, the key elements of the case corresponding to the data whose current degree of correlation impact is greater than the preset normal impact range will be identified as risk warning signals for the comparison results.

[0078] If all data in the current set of associated impacts are less than the preset normal impact range, calculate the difference between each data in the current set of associated impacts and the preset normal impact range to obtain the difference set;

[0079] A preset difference threshold is set. If there are data in the difference set that are greater than or equal to the difference threshold, the key elements of the current law enforcement case will continue to be analyzed in depth and the deep analysis signal of the comparison result will be output.

[0080] In the digital twin-based law enforcement case analysis system, a digital twin model of the law enforcement case has been constructed, key elements have been extracted, and the normal range of variation of the correlation coefficients between the key elements has been determined. Simultaneously, by comparing with similar historical cases, a set of correlation influence levels of the key elements in the current law enforcement case has been obtained.

[0081] When analyzing the current set of correlation impact levels, if any data exceeds the preset normal impact range, it indicates that the correlation impact of the current law enforcement case on the corresponding key elements exceeds the scope of previous normal cases. For example, regarding the correlation impact between case type and the behavioral patterns of the involved personnel, if the current value far exceeds the normal range, it means that the case may have exhibited abnormal behavioral patterns, differing from the development trend of routine cases. This situation exceeding the normal range is highly likely to indicate potential risks in the case, such as a possible change in the nature of the case or special actions by the suspect. Therefore, the key elements of the case corresponding to this data are identified as risk warning signals, reminding law enforcement personnel to pay close attention.

[0082] If all data points in the current correlation impact set are below the preset normal impact range, further investigation of the degree of difference is needed. Calculate the difference between each data point and the preset normal impact range to obtain a difference set. This is because although these data are all below the normal range, the excessively low correlation impact of some key elements may indicate special circumstances in the case. A preset difference threshold, determined based on historical case data and law enforcement experience, is used to measure whether the difference is sufficiently significant. When there are data points in the difference set that are greater than or equal to the difference threshold, it indicates that the correlation impact of that key element deviates significantly from the normal situation. It is necessary to continue in-depth analysis of the key elements of the current law enforcement case to uncover potential anomalies or special circumstances. At this point, an in-depth analysis signal is output to guide subsequent, more in-depth investigation and analysis.

[0083] By combining deep analysis signals with the dynamic evolution patterns of case elements in digital twin models of law enforcement cases, the changing trends of key elements in current law enforcement cases are predicted to generate the first prediction dataset. This process includes the following steps:

[0084] Based on the deep analysis of signals, the dynamic evolution characteristics of key elements in current law enforcement cases are extracted, and a dynamic evolution model of key elements is established by combining the dynamic evolution law of case elements in the digital twin model of law enforcement cases.

[0085] The first prediction data set is generated by using a dynamic evolution model to predict the changing trends of key elements in current law enforcement cases within a preset time period. The first prediction data set includes the evolution trend of case types, the changing trend of spatiotemporal characteristics, the changing trend of behavior patterns of persons involved in the case, and the changing trend of evidence chain relationships.

[0086] When in-depth analysis signals are obtained, it indicates that key elements of the current law enforcement case require further investigation. At this point, it's crucial to meticulously analyze the dynamic evolution of these key elements from the digital twin model of the case. For example, regarding case type, it might be necessary to analyze whether the case shows signs of shifting from one type to another, such as evolving from a simple public security case to one involving criminal offenses. This could be reflected in escalating intrusive behavior or new evidence pointing to more serious violations. Regarding spatiotemporal characteristics, attention should be paid to whether the crime scene is shifting or whether the time of the incident exhibits regular changes. Regarding the behavioral patterns of those involved, observe whether their movements, language, and habits have significantly changed during the case's development. In terms of the chain of evidence, pay attention to whether the emergence of new evidence shakes or supplements the existing chain of evidence.

[0087] By combining the dynamic evolution patterns of numerous historical case elements accumulated in digital twin models of law enforcement cases, the dynamic evolution characteristics of key elements in current cases are extracted and integrated into these models. For example, by analyzing a large number of similar historical cases, the general path and key node conditions of case type evolution are summarized, and then adjustments are made based on the specific circumstances of the current case. Using mathematical modeling, machine learning algorithms, and other technical means, a dynamic evolution model of key elements is established. This model is a dynamic system that reflects the changes of key elements in a case over time or during the case's progress, comprehensively considering the interactions between various elements and the influence of external environmental factors.

[0088] Using a well-established dynamic evolution model, the changing trends of key elements in current law enforcement cases are predicted within a preset time period. Regarding the evolution trend of case types, the likelihood and direction of their transformation into other types of cases in the future are predicted; in terms of spatiotemporal characteristics, the expansion or relocation of crime scene locations and the concentration or dispersion of crime times are estimated; regarding the changing trends of the behavioral patterns of those involved, their potential subsequent actions and changes in their psychological state are speculated; and regarding the changing trends of the chain of evidence, the potential emergence of new evidence and whether the existing chain of evidence will be broken or further strengthened are assessed. The prediction of these key element trends ultimately generates the first predictive dataset.

[0089] Based on the analysis of the first prediction dataset, the current development trend of law enforcement cases is analyzed to obtain the first risk prediction value, specifically including the following steps:

[0090] After determining the degree of influence of environmental factors on key elements of the case based on the first predictive data set and the digital twin model, the environmental impact degree set is obtained.

[0091] Based on the environmental impact degree set and the first prediction data set, a second prediction data set is used to predict the factors that affect current law enforcement cases.

[0092] Based on the second set of prediction data, the current development trend of law enforcement cases is determined, and the first risk prediction value of the current law enforcement cases is determined according to the current development trend of law enforcement cases.

[0093] The first predictive dataset encompasses key information such as the evolutionary trends of case types, changes in spatiotemporal characteristics, changes in the behavioral patterns of involved individuals, and changes in the chain of evidence. Simultaneously, the digital twin model of law enforcement cases fully maps various elements and states of the cases. Based on this, environmental factors, such as population density, security situation, public opinion, and geographical environment of the crime scene, are considered to analyze the impact of these environmental factors on key elements of the cases.

[0094] For example, a high population density in the area where the crime occurred may affect the movement trajectory of those involved (spatial and temporal characteristics and behavioral patterns), and may also interfere with the collection and preservation of evidence (chain of evidence); a poor local security situation may increase the risk of the case escalating or leading to other illegal and criminal activities (evolution of case type). By quantifying these impacts, a set of environmental impact degrees is obtained, which characterizes the magnitude and direction of the impact of different environmental factors on each key element.

[0095] Based on the environmental impact severity set and the first prediction dataset, the development of enforcement cases after considering the effects of environmental factors is further predicted. The environmental impact severity set clarifies the ways and extent in which environmental factors affect key elements, while the first prediction dataset provides preliminary trends in the changes of key elements without considering environmental factors.

[0096] By combining these two analyses, the future trajectory of key elements of the case can be reassessed. For example, while the case type might initially be predicted to remain unchanged, the potential for public attention and pressure due to escalating local public opinion could lead to stricter case handling procedures, potentially causing the case to escalate to a more serious state. This comprehensive analysis generates a second predictive dataset that more fully and accurately reflects the case's development trend within the actual context.

[0097] The second predictive dataset is used to assess the current development trend of law enforcement cases. This trend may include different scenarios such as cases easing, maintaining the status quo, or escalating. For example, if the predicted behavior patterns of those involved gradually stabilize, the chain of evidence becomes increasingly complete and clear, the type of case shows no signs of worsening, and environmental factors do not exacerbate the situation, then the development trend of the cases can be judged as easing.

[0098] Based on the established development trend, and taking into account factors such as the severity of the case, potential harm, and difficulty of handling, the primary risk prediction value for current law enforcement cases is determined. This risk prediction value can be expressed using levels (e.g., low, medium, high risk) or specific numerical values ​​(e.g., a risk score of 0-10), providing law enforcement agencies with an intuitive risk reference to rationally allocate resources and formulate response strategies.

[0099] The distribution of law enforcement resources includes the number of law enforcement personnel, the availability of law enforcement equipment, and the density of law enforcement agencies.

[0100] Number of law enforcement personnel: Law enforcement personnel are the direct implementers of law enforcement work, and their number directly affects the efficiency and effectiveness of case handling. During case handling, a sufficient number of law enforcement personnel can respond quickly to cases, conduct on-site investigations, collect evidence, track down suspects, and promptly control the situation, reducing the risk of the case escalating. For example, sufficient police deployment during large-scale event security or major emergencies can effectively maintain order and ensure the smooth resolution of cases. Conversely, an insufficient number of law enforcement personnel may lead to delays in case handling, missing the best investigative opportunities, and increasing the difficulty of handling cases.

[0101] Law enforcement equipment availability: Advanced and comprehensive law enforcement equipment is crucial for improving law enforcement efficiency. For example, high-definition surveillance equipment helps obtain clear video footage of crime scenes, providing key clues for case solving; advanced evidence testing equipment enables more precise analysis of physical evidence, contributing to a more complete chain of evidence. Insufficient or outdated law enforcement equipment may limit the depth and breadth of law enforcement personnel's investigations, affecting the progress and quality of case handling.

[0102] Law enforcement agency density: A reasonable density of law enforcement agencies ensures effective coverage of the jurisdiction. In areas with high density of law enforcement agencies, incidents can be handled quickly and efficiently. For example, in urban centers, due to dense populations and commercial activities, a higher density of law enforcement agencies allows for rapid response to various incidents. However, in remote areas, sparse distribution of law enforcement agencies may prolong response times, negatively impacting the timeliness and effectiveness of case handling.

[0103] Social indicators include population density, public security, and public opinion index.

[0104] Population density: Population density reflects the density of people in an area. In densely populated areas, the probability of crime is relatively higher, and the impact and spread of cases may be faster. For example, in crowded urban neighborhoods, theft and disputes are more likely to occur, and the gathering of people may lead to public attention or secondary problems. At the same time, handling cases in densely populated areas may face more interference factors, increasing the difficulty of law enforcement.

[0105] Security situation: Security situation is a comprehensive reflection of the overall safety level of an area. In areas with good security, the frequency and severity of crimes are usually lower, and law enforcement work is relatively smooth. Conversely, in areas with poor security, various illegal and criminal activities may be more rampant, law enforcement agencies face greater case pressure, and may encounter more obstacles when handling cases, such as witnesses being unwilling to testify and lawbreakers resisting law enforcement.

[0106] Public Opinion Index: The public opinion index reflects public attention to law enforcement cases and public opinion trends. In today's rapidly spreading information environment, law enforcement cases easily attract public attention. Positive public opinion helps create a favorable law enforcement environment and gain public support and cooperation. However, negative public opinion or uncontrolled escalation of public opinion can put enormous pressure on law enforcement agencies, affect the case handling process, and may even trigger social instability. Law enforcement agencies need to closely monitor the public opinion index, respond to public concerns in a timely manner, and guide public opinion.

[0107] Based on the distribution of law enforcement resources, social indicator data, and the first risk prediction value, a comprehensive predictive analysis of current law enforcement cases is conducted to obtain the comprehensive predictive analysis results, which specifically include the following steps:

[0108] Based on the distribution of law enforcement resources and social indicator data, predict the second risk value of current law enforcement cases;

[0109] The comprehensive predictive analysis results of current law enforcement cases are determined based on the first and second risk prediction values.

[0110] The distribution of law enforcement resources includes the number of law enforcement personnel, the availability of law enforcement equipment, and the density of law enforcement agencies. Social indicators include population density, public security situation, and public opinion index. These factors all influence the handling of law enforcement cases.

[0111] Insufficient law enforcement personnel lead to delayed case response and handling, increasing case risk; outdated law enforcement equipment makes it difficult to obtain key evidence or effectively control the scene, also increasing risk; sparsely distributed law enforcement agencies cannot quickly reach the scene of a crime, further increasing risk. High population density increases the potential for crime and can easily trigger chain reactions during handling; poor public security and frequent illegal and criminal activities increase the difficulty and uncertainty of case handling; high public opinion index means that improper handling can easily attract social attention and negative public opinion, placing additional pressure on law enforcement.

[0112] By analyzing the distribution of law enforcement resources and social indicator data, and using appropriate analytical models (such as risk assessment models based on historical case data), the risks of current law enforcement cases are assessed to obtain a second risk prediction value. This value reflects the combined impact of law enforcement resources and social environmental factors on case risk.

[0113] The first risk prediction value is derived based on the changing trends of key elements of law enforcement cases and the impact of environmental factors on the cases, mainly focusing on the development trend and inherent risks of the cases themselves. The second risk prediction value focuses on the impact of law enforcement resources and the external social environment on the cases.

[0114] The primary and secondary risk prediction values ​​are comprehensively considered. Weighted averaging or other methods can be used to assign different weights to the two risk prediction values ​​based on the characteristics and actual circumstances of different cases. For example, for major cases requiring significant law enforcement resources, the secondary risk prediction value may be given a higher weight; for cases primarily influenced by their own factors, the primary risk prediction value may be given a higher weight. Through comprehensive calculation and analysis, the final comprehensive predictive analysis results for current law enforcement cases are determined, providing law enforcement agencies with a comprehensive and accurate basis for decision-making, assisting them in rationally allocating resources and formulating scientific response strategies.

[0115] like Figure 3As shown, the electronic device may include a processor 610, a communications interface 620, a memory 630, and a communication bus 640. The processor 610, communications interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can call logical instructions from the memory 630 to execute a content data prediction and analysis method based on digital twins.

[0116] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0117] On the other hand, the present invention also provides a computer program product, the computer program product including a computer program that can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer is able to execute a content data prediction and analysis method based on digital twins.

[0118] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform a content data prediction and analysis method based on digital twins.

[0119] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0120] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0121] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A content data prediction and analysis method based on digital twins, characterized in that, The method includes the following steps: Collect multi-source heterogeneous data related to law enforcement cases, and fuse and process the multi-source heterogeneous data to construct a digital twin model of the law enforcement cases; Based on the digital twin model, key elements in law enforcement cases are extracted, and the set of correlation influence coefficients between key elements and the normal range of variation of the correlation influence coefficients between key elements are determined. After determining the degree of correlation between current law enforcement cases and similar historical cases in terms of key elements based on the correlation influence coefficient set, the current correlation influence degree set is obtained. After processing the current correlation influence degree set, it is compared with the preset normal influence range value to obtain the comparison result. By combining the in-depth analysis signals from the comparison results with the dynamic evolution patterns of case elements in the digital twin model of law enforcement cases, the changing trends of key elements in current law enforcement cases are predicted to generate the first prediction data set. Based on the analysis of the first prediction data set, the current development trend of law enforcement cases is analyzed, and the first risk prediction value is obtained. The distribution of law enforcement resources associated with statistical law enforcement cases is analyzed. Based on the distribution of law enforcement resources, social indicator data, and the first risk prediction value, a comprehensive prediction analysis is conducted on the current law enforcement cases to obtain the comprehensive prediction analysis results.

2. The content data prediction and analysis method based on digital twins according to claim 1, characterized in that, The multi-source heterogeneous data includes basic case information, on-site investigation data, party information, and historical similar case data.

3. The content data prediction and analysis method based on digital twins according to claim 2, characterized in that, The key elements include case type, spatiotemporal characteristics, behavioral patterns of those involved, and the relationship between the evidence chain.

4. The content data prediction and analysis method based on digital twins according to claim 3, which determines the set of correlation influence coefficients between key elements and the normal range of variation of the correlation influence coefficients between key elements, specifically includes the following steps: Determine the interrelationships among the key elements and establish a set of correlation influence coefficients among the key elements; Obtain the correlation coefficients between key elements in historical normal cases and historical abnormal cases respectively, and construct the historical normal correlation coefficient set and the historical abnormal correlation coefficient set. Based on the historical normal correlation influence coefficient set and the historical abnormal correlation influence coefficient set, determine the normal variation range of the correlation influence coefficients between each key element.

5. The content data prediction and analysis method based on digital twins according to claim 4, characterized in that, The current set of associated impact levels is processed and compared with the preset normal impact range value to obtain the comparison result. The specific steps include: If there are data whose current degree of correlation impact is greater than the preset normal impact range, the key elements of the case corresponding to the data whose current degree of correlation impact is greater than the preset normal impact range will be identified as risk warning signals for the comparison results. If all data in the current set of associated impacts are less than the preset normal impact range value, the difference set is obtained by calculating the difference between each data in the current set of associated impacts and the preset normal impact range value. A preset difference threshold is set. If there are data in the difference set that are greater than or equal to the difference threshold, the key elements of the current law enforcement case will continue to be analyzed in depth and the deep analysis signal of the comparison result will be output.

6. The content data prediction and analysis method based on digital twins according to claim 5, characterized in that, By combining deep analysis signals with the dynamic evolution patterns of case elements in digital twin models of law enforcement cases, the changing trends of key elements in current law enforcement cases are predicted to generate the first prediction dataset. This process includes the following steps: Based on the deep analysis of signals, the dynamic evolution characteristics of key elements in current law enforcement cases are extracted, and a dynamic evolution model of key elements is established by combining the dynamic evolution law of case elements in the digital twin model of law enforcement cases. After using a dynamic evolution model to predict the changing trends of key elements in current law enforcement cases within a preset time period, a first prediction data set is generated; wherein, the first prediction data set includes the evolution trend of case type, the changing trend of spatiotemporal characteristics, the changing trend of behavior patterns of persons involved in the case, and the changing trend of evidence chain correlation.

7. The content data prediction and analysis method based on digital twins according to claim 6, characterized in that, Based on the analysis of the first prediction dataset, the current development trend of law enforcement cases is analyzed to obtain the first risk prediction value, specifically including the following steps: After determining the degree of influence of environmental factors on key elements of the case based on the first predictive data set and the digital twin model, the environmental impact degree set is obtained. Based on the environmental impact degree set and the first prediction data set, a second prediction data set is used to predict the factors that affect current law enforcement cases. Based on the second set of prediction data, the current development trend of law enforcement cases is determined, and the first risk prediction value of the current law enforcement cases is determined according to the current development trend of law enforcement cases.

8. The content data prediction and analysis method based on digital twins according to claim 7, characterized in that, The distribution of law enforcement resources includes the number of law enforcement personnel, the availability of law enforcement equipment, and the density of law enforcement agencies.

9. A content data prediction and analysis method based on digital twins according to claim 8, characterized in that, The social indicators data include population density, public security situation, and public opinion index.

10. A content data prediction and analysis method based on digital twins according to claim 9, characterized in that, Based on the distribution of law enforcement resources, social indicator data, and the first risk prediction value, a comprehensive predictive analysis of current law enforcement cases is conducted to obtain the comprehensive predictive analysis results, which specifically include the following steps: Based on the distribution of law enforcement resources and social indicator data, predict the second risk value of current law enforcement cases; The comprehensive predictive analysis results of current law enforcement cases are determined based on the first and second risk prediction values.

Images