An arson case analysis and evidence chain construction method, device and equipment based on a Bayesian network and a medium

Abstract

The present application relates to a kind of arson case analysis and evidence chain construction method, device and medium based on Bayesian network, comprising: combing historical arson case, determine the scene element contained in arson case;The scene element of the arson case to be analyzed is regarded as the Bayesian network node, the connection relationship is established between different Bayesian network nodes, and the detection reasoning model framework based on Bayesian network model is established;Based on the detection reasoning model framework of Bayesian network model, the posterior probability of conditional element hypothesis and behavior element hypothesis is calculated using Netica software, and the evidence chain is extracted based on the probability calculation result.The present application can be widely applied in the field of criminal investigation and criminal analysis science.

Description

Technical Field

[0001] This invention relates to the field of criminal investigation and crime analysis science, and in particular to a method, apparatus, equipment and medium for analyzing arson cases and constructing evidence chains based on Bayesian networks. Background Technology

[0002] Social security is an important component of national security, a necessary condition for economic and social development, and a fundamental guarantee for people's peaceful and prosperous lives and the construction of a harmonious society.

[0003] The investigation and management of public security cases is a crucial area of ​​research in public security governance. Public security cases are highly harmful, numerous, and often have serious consequences and widespread impact. A critical task during the investigation of public security cases is identifying the perpetrator and their actions. However, this task often becomes extremely difficult when essential evidence is insufficient. In such cases, a general investigative reasoning model is needed to scientifically and rationally infer and analyze the perpetrator and their criminal behavior, providing a reference for investigative work.

[0004] Arson cases constitute a major component of social security incidents and are typical serious violent crimes that severely impact social and public safety. Arson cases are highly challenging to solve, and traditional experience is no longer sufficient to meet the demands for rapid and accurate investigation. Analyzing cases using computer-aided modeling methods is a recent research trend. This approach makes the analysis process traceable and transparent, providing better decision support for crime analysis experts and reducing wrongful convictions. Simultaneously, the semi-automation and automation of case analysis can improve efficiency, save on investigative costs, and achieve high-efficiency utilization of limited investigative resources.

[0005] The scientific essence of investigative reasoning in arson cases lies in the uncertainty of evidence. This involves finding reasons that explain the evidence through available information. While the actual facts of the case necessarily explain the evidence, other assumptions may also exist. The uncertainty in this reasoning process is primarily cognitive uncertainty, caused mainly by incomplete information. The information gathered through investigation and examination is limited and incomplete, leading to uncertainty in the inferred results. Therefore, quantifying the uncertainty in investigative reasoning in arson cases is a key technical issue.

[0006] At the same time, evidence includes various types. How to extract useful data information that is consistent with the reasoning of the case from multi-source heterogeneous data such as videos and texts is another key technical problem in the investigation and reasoning of arson cases. Summary of the Invention

[0007] In view of the limitations of existing arson case investigation and reasoning, the purpose of this invention is to provide a method, apparatus, equipment and medium for arson case analysis and evidence chain construction based on Bayesian networks.

[0008] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for arson case analysis and evidence chain construction based on Bayesian networks, including: By reviewing historical arson cases, the contextual elements involved in arson cases can be identified. The scenario elements of the arson case to be analyzed are used as Bayesian network nodes. Connections are established between different Bayesian network nodes to build a detection reasoning model framework based on the Bayesian network model. The investigation reasoning model framework based on Bayesian network model uses Netica software to calculate the posterior probabilities of conditional element hypotheses and behavioral element hypotheses, and extracts the evidence chain based on the probability calculation results.

[0009] Furthermore, the scenario elements include conditional elements, behavioral elements, and consequence elements; the conditional elements are categorized by attributes into people, objects, and environment; the behavioral elements are categorized by the act of committing the crime into the preparation stage, the fire prevention stage, and the escape stage; and the consequence elements are categorized into items, traces, and information.

[0010] Furthermore, the step of using the scenario elements of the arson case to be analyzed as Bayesian network nodes, establishing connections between different Bayesian network nodes, and building a Bayesian network-based investigative reasoning model framework includes: The situational elements of the arson case to be analyzed are analyzed to obtain the corresponding conditional elements, behavioral elements, and consequence elements of the arson case to be analyzed. The conditional elements, behavioral elements, and consequence elements corresponding to the arson case to be analyzed are used as nodes in a Bayesian network, and connections are established between different Bayesian network nodes. By integrating all the connections, a detection and reasoning model framework based on a Bayesian network model is obtained.

[0011] Furthermore, the step of using the conditional elements, behavioral elements, and consequence elements corresponding to the arson case to be analyzed as Bayesian network nodes, and establishing connections between different Bayesian network nodes, includes: Construct the connection relationship between consequence element nodes and behavior element nodes; Construct the connection relationship between behavioral element nodes and condition element nodes; Construct the connection relationship between consequence element nodes and condition element nodes.

[0012] Furthermore, the construction of the connection relationship between consequence element nodes and behavior element nodes includes: Based on the "single responsibility principle" and "relationship modeling principle" in data modeling, behavioral element nodes are divided into behavioral nodes and behavioral location nodes; among them, behavioral nodes represent the action or activity itself, and behavioral location nodes represent the place or location where the action or activity takes place. Based on the category of consequence element nodes, establish the relationships between consequence element nodes of items, traces, and information, and behavior nodes and behavior location nodes respectively.

[0013] Furthermore, the construction of the connection relationship between behavioral element nodes and condition element nodes includes: The behavioral element nodes are analyzed and divided into first behavioral element nodes that contain only behavior and second behavioral element nodes that contain both behavior and location. Establish connection relationships between the first row element node and the second row element node and the condition element node respectively, and establish connection relationships between the first row element node and the second row element node.

[0014] Furthermore, the Bayesian network-based investigative reasoning model framework utilizes Netica software to calculate the posterior probabilities of conditional and behavioral hypotheses, and extracts the evidence chain based on the probability calculation results, including: Based on Netica software, a Bayesian network structure for the arson case to be analyzed is constructed. The values ​​of the acquired consequence elements are input into the constructed Bayesian network structure to obtain the values ​​and probabilities of the behavioral element nodes and condition element nodes in the arson case to be analyzed, and the evidence chain that meets the preset requirements is obtained based on the probability calculation results.

[0015] Secondly, the present invention provides an apparatus for arson case analysis and evidence chain construction based on Bayesian networks, comprising: The element analysis module is used to analyze historical arson cases and determine the situational elements contained in the arson cases; wherein, the situational elements include conditional elements, behavioral elements, and consequence elements. The framework construction module is used to take the scenario elements of the arson case to be analyzed as Bayesian network nodes, establish connection relationships between different Bayesian network nodes, and build a detection reasoning model framework based on the Bayesian network model. The evidence chain extraction module is used in the investigation reasoning model framework based on the Bayesian network model. It uses Netica software to calculate the posterior probabilities of conditional element hypotheses and behavioral element hypotheses, and extracts the evidence chain based on the probability calculation results.

[0016] Thirdly, the present invention provides a computer-readable storage medium for storing one or more programs, said one or more programs including instructions that, when executed by a computing device, cause the computing device to perform any of the methods.

[0017] Fourthly, the present invention provides a computing device comprising: one or more processors and a memory, wherein the memory stores one or more programs and is configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the methods.

[0018] The present invention has the following advantages due to the adoption of the above technical solutions: This invention systematically analyzes the contextual elements of arson cases, including conditional elements, behavioral elements, and consequence elements. Based on Bayesian networks, it calculates the probability of reasoning about evidence and assumptions about facts in arson cases, and analyzes the evidence chain with the highest probability. This helps to improve the scientific and systematic nature of investigative reasoning in arson cases, reconstruct the context of the case, and achieve high-efficiency utilization of limited investigative resources.

[0019] Therefore, this invention can be widely applied in the fields of criminal investigation and crime analysis science. Attached Figure Description

[0020] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts. In the drawings: Figure 1 This is a flowchart of a method for analyzing arson cases and constructing a chain of evidence based on Bayesian networks according to an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the acquisition of plot elements according to an embodiment of the present invention; Figure 3 This is a framework for an investigative reasoning model for arson cases according to an embodiment of the present invention; Figure 4 This is a behavior-consequence network structure according to an embodiment of the present invention; Figure 5 It is a condition-behavior network structure according to an embodiment of the present invention; Figure 6 It is a condition-consequence network structure according to an embodiment of the present invention; Figure 7 This is a network structure according to an embodiment of the present invention; Figure 8 It is a Bayesian network structure according to an embodiment of the present invention; Figure 9 This is an example of a Bayesian network inference result according to an embodiment of the present invention; Figure 10This is a schematic diagram of a device for analyzing arson cases and constructing evidence chains based on Bayesian networks according to an embodiment of the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention are within the scope of protection of the present invention.

[0022] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0023] In some embodiments of the present invention, a method for analyzing arson cases and constructing evidence chains based on Bayesian networks is provided. By analyzing the conditional elements, behavioral elements, and consequence elements in arson cases, a Bayesian network structure suitable for arson cases is constructed, and posterior probability calculations of conditional element hypotheses and behavioral element hypotheses are carried out, providing support for reasoning in arson cases and the next stage of investigation.

[0024] Correspondingly, in other embodiments of the present invention, an apparatus, device, and medium for arson case analysis and evidence chain construction based on Bayesian networks are provided.

[0025] Example 1 like Figure 1 As shown, this embodiment provides a method for arson case analysis and evidence chain construction based on Bayesian networks, which includes the following steps: 1) Review historical arson cases to identify the situational elements involved, including conditional elements, behavioral elements, and consequence elements; 2) The scenario elements of the arson case to be analyzed are used as Bayesian network nodes. Connections are established between different Bayesian network nodes to build a detection reasoning model framework based on the Bayesian network model. 3) A Bayesian network model-based investigative reasoning framework is used to calculate the posterior probabilities of conditional and behavioral assumptions using Netica software, and the evidence chain is extracted based on the probability calculation results.

[0026] Furthermore, in step 1) above, after sorting out historical arson cases, this embodiment divides the situational elements of arson cases into three categories: conditional elements, behavioral elements, and consequence elements.

[0027] Specifically, the conditional elements are the entities constituting the act of committing the crime in an arson case, and the act of committing the crime can be seen as the interaction between the conditional elements. The conditional elements are categorized into three types according to their attributes: people, objects, and environment. Among these, people are further divided into perpetrators (offenders), victims (victims), and other persons, based on their roles in the arson case. The perpetrator is the subject who commits the crime, the victim is the person who suffers the consequences of the crime, and other persons include witnesses and other individuals related to the case. Similarly, objects are further divided into tools used in the crime, tools used for transfer, and other objects. Tools used in the crime refer to the tools used by the perpetrator when committing the violent crime; tools used for transfer refer to the tools used by the perpetrator to enter or leave the scene; other objects refer to all other objects related to the crime but not included in the above categories. The environment includes the central scene and related scenes. The central scene (also called the main scene) refers to the place where the perpetrator commits the violent crime, and related scenes refer to other places related to the crime. The conditional elements of an arson case are shown in Table 1.

[0028] Table 1. Conditions and Elements of Arson Cases

[0029] The criminal behavior in arson cases is analyzed, and the cases are divided into the preparation stage, the arson stage, and the escape stage. The criminal behavior in each stage is analyzed to obtain the behavioral elements.

[0030] Specifically, the preparation phase mainly includes seven criminal acts: reconnaissance and scouting, preparing arson tools (self-provided), preparing arson tools (others), preparing transfer tools (self-provided), preparing transfer tools (others), forming a gang, and skills training.

[0031] The arson phase mainly includes five acts: entering the crime scene, preparing arson tools (using readily available materials), setting up the scene, placing accelerants, and igniting the fire. Entering the crime scene refers to the perpetrator entering the location where the crime was committed through various means; preparing arson tools (using readily available materials) means the perpetrator directly obtains tools for arson at the crime scene, such as finding a lighter and using it for ignition; setting up the scene refers to the perpetrator's actions at the scene, typically including placing flammable materials and closing doors and windows; placing accelerants means the perpetrator places accelerants at the scene to amplify the consequences of the arson, such as pouring gasoline at the scene; and igniting the fire means the perpetrator ignites the fire at the scene.

[0032] The escape phase mainly includes two actions: providing medical assistance and destroying evidence. Providing medical assistance refers to the perpetrator's self-rescue, helping others, or fighting the fire; destroying evidence refers to the perpetrator cleaning up the scene and discarding the tools used in the crime. The behavioral elements of arson cases are shown in Table 2.

[0033] Table 2 Behavioral Elements in Arson Cases

[0034] Consequence elements are those formed by the occurrence of the crime. Consequence elements are divided into three categories: objects, traces, and information. Object elements refer to those that primarily connect a person or object through their material composition, specifically including corpse parts, bloodstains, biological materials, trace substances, and other items. Trace elements refer to those that primarily connect a person or object through their external structural characteristics, further divided into fingerprints, footprints, burn marks, and other traces. Unlike object and trace elements, information elements primarily provide assistance in case reasoning through the information they contain, including witness testimonies, audiovisual materials, and electronic data, mainly corresponding to evidence other than physical evidence. The consequence elements of arson cases are analyzed and shown in Table 3.

[0035] Table 3. Consequences of Arson Cases

[0036] For consequence elements, it is necessary to extract their effective features to support the reasoning in the case. Based on the possible categories and attributes of consequence elements, different intelligence extraction techniques are proposed. For example, for textual evidence, a method based on natural language processing is proposed; for image evidence, a method based on optical symbol recognition is proposed. Information classification methods related to the elements of the case are reviewed, and evidence-related intelligence is fixed from aspects such as the perpetrator (O), victim (V), weapon (T), and crime scene (E), thereby achieving standardized guidance for evidence intelligence extraction. A schematic diagram of the information extraction framework for specific consequence elements is shown below. Figure 2 As shown.

[0037] Furthermore, in step 2) above, when conducting investigative reasoning in arson cases, based on the actual work processes of case investigation and adhering to the principles of scientific rigor, systematic approach, and operability, a Bayesian network of nodes for the arson case investigative reasoning model is established. Based on expert consultation and suggestions, a Bayesian network reasoning model is constructed to facilitate further investigation and interrogation. Based on the principle of operability, within the framework of the scenario elements of arson cases, the Bayesian network model is applied to construct the framework of the arson case investigative reasoning model.

[0038] Specifically, such as Figure 3 As shown, it includes the following steps: 2.1) Analyze the situational elements of the arson case to be analyzed to obtain the corresponding conditional elements, behavioral elements, and consequence elements of the arson case to be analyzed; 2.2) The conditional elements, behavioral elements, and consequence elements corresponding to the arson case to be analyzed are used as Bayesian network nodes, and connections are established between different Bayesian network nodes; 2.3) Integrate all connections to obtain a detection reasoning model framework based on a Bayesian network model.

[0039] This embodiment takes an arson case as an example. In an arson case, a criminal O used a container T to place an accelerant A at point C on the scene and ignited it, causing a fire.

[0040] In this arson case, based on the analysis of the case's contextual elements, four conditional element nodes, two behavioral element nodes, and six consequence element nodes can be obtained. The Bayesian network nodes of the constructed case are shown in Table 4.

[0041] Table 4 shows the Bayesian network nodes in the implementation cases.

[0042] Furthermore, in step 3) above, after establishing the investigation and reasoning model framework based on the Bayesian network model, it is necessary to establish connection relationships based on the associations between different scenario elements.

[0043] Specifically, such as Figures 4-6 As shown, it includes the following steps: 2.2.1) Construct the connection relationship between consequence element nodes and behavior element nodes; 2.2.2) Construct the connection relationship between behavioral element nodes and conditional element nodes; 2.2.3) Construct the connection relationship between consequence element nodes and condition element nodes.

[0044] Furthermore, in step 2.2.1) above, the child nodes of the behavior element node are consequence element nodes, because the behavior caused the corresponding consequences and evidence to appear.

[0045] For evidence such as traces of objects, the contextual element association provides a correspondence between behavior and consequences, which can be used to connect nodes. It should be noted that if the template parameters of a consequence element node for traces of objects do not include items related to the perpetrator, then that node is not connected to the behavior node, because the consequence element cannot clearly point to the possible perpetrator's criminal behavior.

[0046] Specifically, such as Figure 4 As shown, the steps for constructing the behavioral element-consequence element network structure are as follows: 2.2.1.1) Based on the "single responsibility principle" and "relationship modeling principle" in data modeling, behavioral element nodes are divided into behavioral nodes and behavioral location nodes. Among them, behavioral nodes represent the action or activity itself, focusing on "what to do"; behavioral location nodes represent the place or location where the action or activity occurs, focusing on "where to do it". 2.2.1.2) Based on the consequence element node category, establish the relationship between the consequence element nodes of items, traces and information and the behavior nodes and behavior location nodes respectively.

[0047] Furthermore, in step 2.2.2 above, it should be noted that there is a connection between behavior nodes and behavior location nodes in the behavior element layer. Specifically, a behavior node is the parent node of the corresponding behavior location node, because whether or not a behavior node occurs will have a direct causal impact on the state of the location node.

[0048] Specifically, such as Figure 5 As shown, the steps for constructing the condition element-behavioral element network structure include: 2.2.2.1) Analyze the behavioral element nodes and divide them into first behavioral element nodes that contain only behavior and second behavioral element nodes that contain both behavior and location; 2.2.2.2) Establish connection relationships between the first row element node and the second row element node and the condition element node respectively, and establish connection relationships between the first row element node and the second row element node.

[0049] Furthermore, in step 2.2.3) above, as... Figure 6 The diagram shows the constructed condition element-consequence element network structure. When constructing the connection between consequence element nodes and condition element nodes, it is necessary to infer that a certain condition element node will have a causal impact on the state of evidence regarding that condition element. Therefore, it is inferred that the condition element node is the parent node of the corresponding consequence element node.

[0050] Furthermore, in step 3) above, after step 2), the establishment of the relationships between the Bayesian network nodes in this case is completed, such as... Figure 7 As shown, probability calculations need to be performed on the constructed Bayesian network to obtain the possible probabilities of the conditional elements.

[0051] Specifically, it includes the following steps: 3.1) Based on Netica software, construct a Bayesian network structure for the arson cases to be analyzed.

[0052] For any variable in a Bayesian Network (BN), and belonging to the probability space { The set of} The elements of a Bayesian network are in a one-to-one correspondence, where n is an integer greater than 1. The probability space of a Bayesian network consists of three parts. The first part is the space... , It is the structure or diagram of a Bayesian network, in which These are nodes (or variables) in a Bayesian network. It is the set of directed edges between variables in a network. The variables and directed edges together form a directed acyclic graph. The second part is the space. ,yes The space of all possible states The third part is space. It is all related to and Related The probability distribution.

[0053] definition It is the set of all possible Bayesian networks. .in, It is an adjoint parameter A directed acyclic graph, .parameter , is a node A Conditional Probability Table (CPT) is a table that lists nodes in tabular form. Each state is related to its parent node The conditional probability of a state, i.e., P( When a node has no parent node, its conditional probability table is directly derived from the prior probability distribution P(…). Given. Any node The conditional probability table can be initialized based on the user's prior knowledge or learned through a training set. For the node space... Sampling is One observation at each node in the database. For node space The assembly of d-sampling operations. When all values ​​of all variables are known, it is considered that... There are no missing values. This assumes that each sample is taken individually. They are independent of each other and have the same unknown distribution.

[0054] Bayesian network analysis is a mathematical model based on the application of Bayesian rules to analyze obtained data. When variables are given... The value of the child node Bayes' theorem can be used to calculate variables. The posterior probability distribution is calculated using formula (1).

[0055] (1) in, Prior probability yes state ( The known probability distribution of (). Likelihood function , including with The instantiation conditional probability of contiguous sub-variables. When all instantiated variables are known... Therefore, there is The marginalization of observed variables, This explains the relationship between instantiated variables and... The relationship between all possible states is shown in Equation (2).

[0056] (2) in, It is a variable The instantiation value of the j-th variable of all p child nodes. The posterior probability is given by Representation, also known as The marginal probability is expressed as its confidence level, representing the probability of its occurrence given the evidence. Finally, Is there? It can be deduced from formula (1).

[0057] like Figures 7-9 As shown, each consequence element node has two states: "Yes" and "No", corresponding to "evidence exists" and "evidence does not exist" respectively; each behavior element node has two states: "Yes" and "No", corresponding to "behavior occurred" and "behavior did not occur" respectively; each condition element node has two states: "Yes" and "No", corresponding to "hypothesis is true" and "hypothesis is false" respectively.

[0058] For condition element nodes, it is impossible to determine whether the hypothesis is true in the initial state. Therefore, their prior probability distribution is 50% for both "yes" and "no", as shown in Table 5.

[0059] Table 5 Prior Probability Table of Condition Element Nodes

[0060] 3.2) Input the values ​​of the acquired consequence elements into the constructed Bayesian network structure to obtain the values ​​and probabilities of the behavioral element nodes and condition element nodes in the arson case to be analyzed, and obtain the evidence chain that meets the preset requirements based on the probability calculation results.

[0061] The conditional probabilities of behavioral element nodes and consequence element nodes can be determined using methods such as experimentation, statistics, and expert consultation. This embodiment uses expert consultation to determine the conditional probability table for consequence elements, as shown in Table 6 below.

[0062] Table 6 Conditional Probability Table

[0063] For example, when we obtain the consequence element nodes F1 and F2 from the scene... 2、 F 3、 In all four states of F4, i.e., when C contains biological material related to O, O contains trace amounts of material related to A, T contains fingerprints related to O, and C contains trace amounts of material related to A, it can be inferred that the probability of person O being the perpetrator is 81.3%, the probability of tool A being an accelerant is 97.4%, the probability of tool T being a container is 88.6%, and the probability of location C being the central crime scene is 95.8%. Figure 7 As shown, compared to the 50% probability before collecting consequence information, the probability of the conditional element node assumptions being true increased significantly after collecting consequence information. This verifies that the model can effectively reason about this case. Simultaneously, the model also indicates that the probability of informational evidence that O committed arson at point C is 75.9%, while the probability of informational evidence that O placed accelerants is 48.3%. Therefore, the next step in the investigation could be to begin collecting "informational evidence that O committed arson at point C." This can also provide guidance and reference for the next investigative direction, improving work efficiency.

[0064] Example 2 The above-described embodiment 1 provides a Bayesian network-based arson case investigation reasoning method. Correspondingly, this embodiment provides a Bayesian network-based arson case investigation reasoning device. The device provided in this embodiment can implement the Bayesian network-based arson case investigation reasoning method of embodiment 1. This device can be implemented through software, hardware, or a combination of both. For example, the device may include integrated or separate functional modules or functional units to execute the corresponding steps in the methods of embodiment 1. Since the device in this embodiment is basically similar to the method embodiment, the description process of this embodiment is relatively simple. Relevant details can be found in the description of embodiment 1. The embodiment of the device provided in this embodiment is merely illustrative.

[0065] like Figure 10 As shown, the arson case investigation reasoning device based on Bayesian networks provided in this embodiment includes: The element analysis module is used to analyze historical arson cases and determine the situational elements contained in the arson cases; wherein, the situational elements include conditional elements, behavioral elements, and consequence elements. The framework construction module is used to take the scenario elements of the arson case to be analyzed as Bayesian network nodes, establish connection relationships between different Bayesian network nodes, and build a detection reasoning model framework based on the Bayesian network model. The evidence chain extraction module is used in the investigation reasoning model framework based on the Bayesian network model. It uses Netica software to calculate the posterior probabilities of conditional element hypotheses and behavioral element hypotheses, and extracts the evidence chain based on the probability calculation results.

[0066] Example 3 This embodiment provides a processing device corresponding to the arson case investigation reasoning method based on Bayesian networks provided in Embodiment 1. The processing device can be a client-side processing device, such as a mobile phone, laptop, tablet computer, desktop computer, etc., to execute the method of Embodiment 1.

[0067] The processing device includes a processor, a memory, a communication interface, and a bus. The processor, memory, and communication interface are connected via the bus to enable communication between them. The memory stores a computer program that can run on the processor. When the processor runs the computer program, it executes the arson case investigation reasoning method based on Bayesian networks provided in Embodiment 1.

[0068] Preferably, the memory may be high-speed random access memory (RAM), and may also include non-volatile memory (n-volatile memory), such as at least one disk storage device.

[0069] Preferably, the processor can be any type of general-purpose processor such as a central processing unit (CPU) or a digital signal processor (DSP), and there is no limitation herein.

[0070] Example 4 The arson case investigation reasoning method based on Bayesian networks in Embodiment 1 can be specifically implemented as a computer program product. The computer program product may include a computer-readable storage medium on which computer-readable program instructions for executing the arson case investigation reasoning method based on Bayesian networks described in Embodiment 1 are loaded.

[0071] A computer-readable storage medium can be a tangible device that holds and stores instructions for use by an instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof.

[0072] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes. These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0073] 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 it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for analyzing arson cases and constructing evidence chains based on Bayesian networks, characterized in that, include: By reviewing historical arson cases, the contextual elements involved in arson cases can be identified. The scenario elements of the arson case to be analyzed are used as Bayesian network nodes. Connections are established between different Bayesian network nodes to build a detection reasoning model framework based on the Bayesian network model. The investigation reasoning model framework based on Bayesian network model uses Netica software to calculate the posterior probabilities of conditional element hypotheses and behavioral element hypotheses, and extracts the evidence chain based on the probability calculation results.

2. The method for analyzing arson cases and constructing evidence chains based on Bayesian networks as described in claim 1, characterized in that, The scenario elements include conditional elements, behavioral elements, and consequence elements; the conditional elements are categorized by attributes into people, objects, and environment; the behavioral elements are categorized by the act of committing the crime into the preparation stage, the fire prevention stage, and the escape stage; and the consequence elements are categorized into items, traces, and information.

3. The method for analyzing arson cases and constructing evidence chains based on Bayesian networks as described in claim 1, characterized in that, The process involves using the scenario elements of the arson case to be analyzed as Bayesian network nodes, establishing connections between different Bayesian network nodes, and building a Bayesian network-based investigative reasoning model framework, including: The situational elements of the arson case to be analyzed are analyzed to obtain the corresponding conditional elements, behavioral elements, and consequence elements of the arson case to be analyzed. The conditional elements, behavioral elements, and consequence elements corresponding to the arson case to be analyzed are used as nodes in a Bayesian network, and connections are established between different Bayesian network nodes. By integrating all the connections, a detection and reasoning model framework based on a Bayesian network model is obtained.

4. The method for analyzing arson cases and constructing a chain of evidence based on Bayesian networks as described in claim 3, characterized in that, The process of using the conditional, behavioral, and consequence elements corresponding to the arson case to be analyzed as Bayesian network nodes and establishing connections between different Bayesian network nodes includes: Construct the connection relationship between consequence element nodes and behavior element nodes; Construct the connection relationship between behavioral element nodes and condition element nodes; Construct the connection relationship between consequence element nodes and condition element nodes.

5. The method for analyzing arson cases and constructing a chain of evidence based on Bayesian networks as described in claim 4, characterized in that, The connection relationship between the consequence element nodes and the behavior element nodes includes: Based on the "single responsibility principle" and "relationship modeling principle" in data modeling, behavioral element nodes are divided into behavioral nodes and behavioral location nodes; among them, behavioral nodes represent the action or activity itself, and behavioral location nodes represent the place or location where the action or activity takes place. Based on the category of consequence element nodes, establish the relationships between consequence element nodes of items, traces, and information, and behavior nodes and behavior location nodes respectively.

6. The method for analyzing arson cases and constructing a chain of evidence based on Bayesian networks as described in claim 4, characterized in that, The construction of the connection relationship between behavioral element nodes and condition element nodes includes: The behavioral element nodes are analyzed and divided into first behavioral element nodes that contain only behavior and second behavioral element nodes that contain both behavior and location. Establish connection relationships between the first row element node and the second row element node and the condition element node respectively, and establish connection relationships between the first row element node and the second row element node.

7. The method for analyzing arson cases and constructing evidence chains based on Bayesian networks as described in claim 2, characterized in that, The aforementioned Bayesian network-based investigative reasoning model framework utilizes Netica software to calculate the posterior probabilities of conditional and behavioral hypotheses, and extracts the chain of evidence based on the probability calculation results, including: Based on Netica software, a Bayesian network structure for the arson case to be analyzed is constructed. The values ​​of the acquired consequence elements are input into the constructed Bayesian network structure to obtain the values ​​and probabilities of the behavioral element nodes and condition element nodes in the arson case to be analyzed, and the evidence chain that meets the preset requirements is obtained based on the probability calculation results.

8. A device for analyzing arson cases and constructing evidence chains based on Bayesian networks, characterized in that, include: The element analysis module is used to analyze historical arson cases and determine the situational elements contained in the arson cases; wherein, the situational elements include conditional elements, behavioral elements, and consequence elements. The framework construction module is used to take the scenario elements of the arson case to be analyzed as Bayesian network nodes, establish connection relationships between different Bayesian network nodes, and build a detection reasoning model framework based on the Bayesian network model. The evidence chain extraction module is used in the investigation reasoning model framework based on the Bayesian network model. It uses Netica software to calculate the posterior probabilities of conditional element hypotheses and behavioral element hypotheses, and extracts the evidence chain based on the probability calculation results.

9. A computer-readable storage medium for storing one or more programs, characterized in that, The one or more programs include instructions that, when executed by a computing device, cause the computing device to perform any of the methods described in claims 1 to 7.

10. A computing device, characterized in that, include: One or more processors and a memory, wherein the memory stores one or more programs and is configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the methods described in claims 1 to 7.

Images