CN117830060B - Injury crime law enforcement supervision and auxiliary decision-making system based on knowledge graph - Google Patents
Injury crime law enforcement supervision and auxiliary decision-making system based on knowledge graph Download PDFInfo
- Publication number
- CN117830060B CN117830060B CN202410240524.1A CN202410240524A CN117830060B CN 117830060 B CN117830060 B CN 117830060B CN 202410240524 A CN202410240524 A CN 202410240524A CN 117830060 B CN117830060 B CN 117830060B
- Authority
- CN
- China
- Prior art keywords
- knowledge
- crime
- case
- injury
- knowledge graph
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000006378 damage Effects 0.000 title claims abstract description 104
- 208000014674 injury Diseases 0.000 title claims abstract description 87
- 208000027418 Wounds and injury Diseases 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 claims description 47
- 230000006399 behavior Effects 0.000 claims description 36
- 238000001514 detection method Methods 0.000 claims description 34
- 230000004927 fusion Effects 0.000 claims description 29
- 241000607479 Yersinia pestis Species 0.000 claims description 21
- 230000008094 contradictory effect Effects 0.000 claims description 21
- 238000010276 construction Methods 0.000 claims description 15
- 230000008520 organization Effects 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 15
- 238000005516 engineering process Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 6
- 230000014509 gene expression Effects 0.000 description 5
- 230000001364 causal effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 239000013589 supplement Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009469 supplementation Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a system for supervising and assisting in the law enforcement of injury crimes based on a knowledge graph, which relates to the technical field of the knowledge graph, and aims at the technical problems of large workload and high technical requirement in the law enforcement supervision work and poor instant assisting decision capability of the existing information platform.
Description
Technical Field
The invention relates to the technical field of knowledge maps, in particular to a damage crime law enforcement supervision and auxiliary decision-making system based on a knowledge map.
Background
In reality, a large amount of unstructured data needs to be processed in the case handling process of the injury crime, and different cases have different characteristics, so that not only are personnel with sufficient legal knowledge and case handling experience required, but also a large amount of time is consumed to complete the work, and the processing pressure of related work is increased. This particular scenario requires urgent intelligent technical support.
Traditional electronic law enforcement and case handling systems based on processes cannot solve the problem of real-time auxiliary decision making in the processes of law enforcement supervision and case handling. And knowledge engineering technology application based on causal logic paradigms is a fundamental technical approach to solve such problems.
The defect of the prior art for assisting the law enforcement supervision of injury crimes is mainly represented by:
1. Limited to conventional flow-based information systems: traditional flow-based information systems mainly focus on aspects of processing flow specifications and data specifications when solving problems, lack of sufficient consideration for knowledge application, so that the systems cannot be seen when facing tasks with high intelligence requirements, and lack of logic and scientificity.
2. The establishment of the domain knowledge system is incomplete or difficult to realize: under the current technical environment, concept analysis cannot be mapped to specific data accurately, a machine cannot realize tasks effectively, and the establishment of a domain knowledge system has the problems of incomplete, incomplete supplement and difficult realization.
3. Problems of underutilized mapping technique: the current technical environment does not fully adopt the atlas technology, so that the processes of knowledge fusion, knowledge reasoning and the like are too complex.
The Knowledge Graph (knowledgegraph) is an important branch technology of artificial intelligence, is a structured semantic Knowledge base, is used for describing concepts and interrelationships thereof in the physical world in a symbol form, can automatically construct an industry Graph, can be applied to scenes such as intelligent search, machine reading understanding, anomaly monitoring, risk control and the like, and achieves true intelligence and automation. Knowledge-graph technology can be used to support complex reasoning processes, helping law enforcement officials to infer causal relationships.
Therefore, research combining knowledge patterns with injury-based crime law enforcement supervision is necessary.
Disclosure of Invention
The invention provides a system for law enforcement supervision and decision-making assistance of injury crimes based on a knowledge graph, which aims to solve the technical problems of large workload, high technical requirements and poor instant decision-making assistance capability of the existing information platform in the prior art.
The method for supervising and assisting decision-making of injury crime based on the knowledge graph specifically comprises the following steps:
Step S0, constructing a knowledge body: determining the knowledge body and the value condition of the knowledge body; the ontology comprises crime subjects, crimes, crime tools, harmful objects and harmful results;
Step S1, ontology expansion: expanding the knowledge body, specifically comprising expanding crimes by constructing a crime feature word bag and a public place feature word bag, and expanding a pest applying object by constructing a human body part knowledge concept tree;
step S2, obtaining data of a case to be tested: obtaining subjective fact data and objective fact data of a case to be tested;
step S3, constructing an injury crime knowledge graph: determining entity and entity relation according to the expanded knowledge body, the value condition of the knowledge body, subjective fact data and objective fact data of the cases to be tested, and constructing injury crime knowledge maps of all the cases to be tested according to the entity and entity relation;
Step S4, conflict detection: carrying out knowledge fusion on the injury crime knowledge maps of all the cases to be detected to obtain a fused knowledge map; then carrying out conflict detection according to the fused knowledge graph, and outputting a fact graph after resolving the existing conflict; the knowledge fusion is as follows: summarizing the same entities in the injury crime knowledge graph of the case to be tested to obtain a knowledge graph after entity fusion; the conflict detection is as follows: judging whether contradictory entity relations exist between different entities according to the knowledge graph after the fusion of all the entities;
step S5, case by auxiliary reasoning: and outputting a case by reasoning results according to the fact map.
Further, in the step S0, the class of the crime subject includes a suspect and a criminal organization; the crime tool comprises limbs, instruments and random objects; the criminal acts include violent infliction, language infliction, crime participation and criminal organization; the pest applying objects comprise a victim, a pest location and property; the consequences of such damage include personal injury, death, and property damage.
Further, in the step S1,
The construction of the criminal behavior characteristic word bag specifically comprises the following steps: the criminal behavior feature word bag is expanded when the word similarity between the root word and the synonym exceeds a threshold value by acquiring the criminal behavior word in the history case and expanding the criminal behavior word in the synonym and the paraphrasing;
The construction of the public place feature word bag specifically comprises the following steps: the method comprises the steps that public place words in historical cases are obtained and expanded in synonyms and paraphraseology, and when the word similarity between root words and the synonyms exceeds a threshold value, public place feature word bags are expanded;
The construction of the human body part knowledge concept tree comprises the following steps: the human body is divided according to the limb parts, a human body part knowledge conceptual tree is constructed, and a standardized human body part map is obtained.
Further, layer 0 of the human body part knowledge concept tree is a human body part total concept; layer 1 of the human body part concept tree is three major components of human body parts: head and neck, upper body and lower body.
Further, in the step S2, the subjective fact data includes an inquiry list of a person involved in the case and an inquiry list of an unrelated witness; the objective fact data includes a wound assessment report and an asset assessment report.
Further, in the step S3, the injury crime knowledge graph of the case to be tested includes: a pest applying fact knowledge graph, a pest receiving fact knowledge graph, a third person crime fact knowledge graph and an objective fact knowledge graph.
Further, collision detection is performed from the following five aspects:
summarizing the entities of interrogation strokes of different involved persons according to the injury crime knowledge graph of the case to be tested to obtain a fused knowledge graph, and judging whether contradictory entity relations exist among different entities;
summarizing criminals in the inquiry records of the involved person and entities of the extraneous witness inquiring criminals in the records according to the injury criminal knowledge graph of the case to be tested, obtaining a fused knowledge graph, and judging whether contradictory entity relationships exist among different entities;
According to the injury crime knowledge graph of the case to be tested, summarizing crime behaviors in inquiry records of suspects in the same pest application group and crime behavior entities in inquiry records of other members to obtain a fused knowledge graph, and judging whether contradictory entity relationships exist between different entities;
summarizing the criminal behavior entities in the interrogation records among different groups according to the injury criminal knowledge graph of the case to be tested to obtain a fused knowledge graph, and judging whether contradictory entity relationships exist among different entities;
And summarizing the entities of the subjective fact data and the entities of the objective fact data according to the injury crime knowledge graph of the case to be tested to obtain a fused knowledge graph, and judging whether contradictory entity relations exist between different entities.
Further, the case by supplementary reasoning includes two parts: the first part is relationship reasoning, and specifically comprises relationships between suspects and victims, between suspects and harmful parts, and between suspects and property; the second part is five cases of injury crimes by reasoning, specifically including the case of fighting others case by reasoning, the case of intentional injury case by reasoning, the case of intentional killer case by reasoning, the case of congregation by reasoning, pick a quarrel the case of intercourse case by reasoning.
A knowledge-based injury crime law enforcement supervision and decision-aiding system, using the knowledge-based injury crime law enforcement supervision and decision-aiding method as described in any one of the above, comprising the following modules:
The knowledge body construction module: the method comprises the steps of determining the knowledge body and a value condition of the knowledge body; the ontology comprises crime subjects, crimes, crime tools, harmful objects and harmful results;
The knowledge body expansion module: the system is connected with the knowledge body construction module and is used for expanding the knowledge body, and specifically comprises the steps of expanding crimes by constructing a crime characteristic word bag and a public place characteristic word bag, and expanding harmful objects by constructing a human body part knowledge concept tree;
The case data acquisition module to be tested: the knowledge body expansion module is connected with the knowledge body expansion module and is used for acquiring subjective fact data and objective fact data of the case to be tested;
Injury crime knowledge graph module: the system comprises a data acquisition module, a storage module and a storage module, wherein the data acquisition module is connected with the data acquisition module of the to-be-detected case and is used for determining entity and entity relations according to the expanded knowledge body and the value condition of the knowledge body, subjective fact data and objective fact data of the to-be-detected case and constructing injury crime knowledge maps of all to-be-detected cases according to the entity and the entity relations;
And a conflict detection module: the system comprises a damage crime knowledge graph module, a damage crime recognition module and a damage crime recognition module, wherein the damage crime knowledge graph module is connected with the damage crime knowledge graph module and is used for carrying out knowledge fusion on the damage crime knowledge graphs of all the cases to be detected to obtain a fused knowledge graph; then carrying out conflict detection according to the fused knowledge graph, and outputting a fact graph after resolving the existing conflict; the knowledge fusion is as follows: summarizing the same entities in the injury crime knowledge graph of the case to be tested to obtain a knowledge graph after entity fusion; the conflict detection is as follows: judging whether contradictory entity relations exist between different entities according to the knowledge graph after the fusion of all the entities;
The case is composed of an auxiliary reasoning module: and the conflict detection module is connected with the conflict detection module and is used for outputting a case-by-case reasoning result according to the fact map.
An electronic device, the electronic device comprising: a processor and a memory, the processor is used for executing the steps of the injury crime law enforcement supervision and auxiliary decision-making method based on the knowledge graph by calling the program or the instructions stored in the memory.
Compared with the prior art, the invention has the beneficial effects that:
Firstly, the invention abstracts and forms the knowledge body in the injury crime field by using the criminal law, public security management punishment law and experience knowledge such as injury crime disposal program, expression characteristics and the like, determines the entity according to the expanded knowledge body and the value condition of the knowledge body, determines the entity relationship according to the subjective fact data and objective fact data of the cases to be tested, constructs the injury crime knowledge map of all the cases to be tested according to the entity and the entity relationship, and can more intuitively display the potential relationship among the knowledge, thereby realizing the deeper knowledge discovery and reasoning process;
Secondly, the invention supplements the knowledge ontology in the injury crime field by constructing a concept tree of the human body part, a characteristic word bag of crime behavior and a characteristic word bag of public places, thereby providing convenience for developing subsequent knowledge calculation;
Thirdly, the complex relation among the entities is captured, the graph traversal and knowledge graph query technology is efficiently carried out, the complex knowledge calculation process can be supported, law enforcement personnel can find evidence conflicts, and knowledge calculation reasoning conforming to causal logic is carried out;
fourth, the invention also realizes the intelligent law enforcement supervision for injury crimes, greatly improves the case processing efficiency and standardization, and reduces the labor intensity; the invention can be used in any link of the whole law enforcement and case handling process, and supports the rechecking and verification of past cases.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for supervising and assisting decision-making of injury crime based on a knowledge graph;
FIG. 2 is a schematic diagram of an injury-based crime ontology;
FIG. 3 is a conceptual diagram of a human body part knowledge tree;
fig. 4 is a schematic diagram of a system for supervising and assisting decision-making of injury crime based on a knowledge graph.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the invention, are within the scope of the invention.
The following describes specific embodiments of the present application with reference to the drawings (tables).
The invention provides a system for supervising and assisting the law enforcement of a damage crime based on a knowledge graph, which aims at the technical problems of large workload and high technical requirement in the supervising work of the law enforcement and poor instant assisting decision capability of the existing information platform.
Example 1
As shown in fig. 1, the invention provides a method for supervising and assisting decision-making of injury crimes based on a knowledge graph, which specifically comprises the following steps:
Step S0, constructing a knowledge body: determining the knowledge body and the value condition of the knowledge body; the ontology comprises crime subjects, crimes, crime tools, harmful objects and harmful results.
When the ontology is constructed, the entity relationship is shown in the following table:
table 1 entity relationship description
As shown in fig. 2, the criminal subject class includes suspects and criminal organizations; the crime tool comprises limbs, instruments and random objects; the criminal acts include violent infliction, language infliction, crime participation and criminal organization; the pest applying objects comprise a victim, a pest location and property; the consequences of such damage include personal injury, death, and property damage.
The common sense knowledge and the empirical knowledge can be effectively supplemented by restricting and standardizing the values of the entity and the attribute, and a foundation is laid for knowledge reasoning. According to the ontology concept of the ontology in the injury crime field, determining attribute value conditions, as shown in table 2:
Table 2 attribute definition description
Step S1, ontology expansion: the method comprises the steps of expanding a knowledge body, specifically comprising the steps of expanding crime behaviors and crime place attributes thereof by constructing a crime behavior feature word bag and a public place feature word bag, and expanding a pest applying object by constructing a human body part knowledge concept tree.
The construction of the criminal behavior characteristic word bag specifically comprises the following steps: the criminal behavior feature word bag is expanded when the word similarity between the root word and the synonym exceeds a threshold value by acquiring the criminal behavior word in the history case and expanding the criminal behavior word in the synonym and the paraphrasing;
The construction of the public place feature word bag specifically comprises the following steps: the method comprises the steps that public place words in historical cases are obtained and expanded in synonyms and paraphraseology, and when the word similarity between root words and the synonyms exceeds a threshold value, public place feature word bags are expanded;
the construction of the human body part knowledge concept tree comprises the following steps: dividing a human body according to limb parts, constructing a human body part knowledge conceptual tree, and obtaining a standardized human body part map;
The root node of the human body part knowledge concept tree is the total concept of the human body part and is called layer 0; the layer 1 concept of the human body part concept tree is three major components of human body parts: head and neck, upper body and lower body.
And repeatedly executing the operations on the root word list, and finally generating the characteristic word bags.
Further, the concept tree is used as a knowledge supplement outside the ontology, and semantic logic relations between concept knowledge and concepts can be expressed in a layering manner. In order to complete expansion of language pest application corpus, fusion of subjective knowledge and objective knowledge and conflict detection, a human body part concept tree is constructed according to human body injury identification standard and civil police expert knowledge, and effective knowledge acquisition can be supported. As shown in fig. 3, the root node of the human body part concept tree is the total human body part concept, which is called layer 0; the layer 1 concept of the human body part concept tree is three major components of the human body part: head and neck, upper body and lower body; and continuously dividing the three components to generate the rest layers of the conceptual tree of the limb part.
Step S2, obtaining data of a case to be tested: and obtaining subjective fact data and objective fact data of the case to be tested.
The subjective fact data comprise an inquiry stroke of a person involved in a case and an inquiry stroke of an irrelevant witness; the objective fact data includes a wound assessment report and an asset assessment report.
Step S3, constructing an injury crime knowledge graph: and determining entity and entity relations according to the expanded knowledge body, the value condition of the knowledge body, subjective fact data and objective fact data of the cases to be tested, and constructing injury crime knowledge maps of all the cases to be tested according to the entity and entity relations.
And (3) establishing an entity relation table with a table header of an entity, an entity tag, an entity data attribute and an object attribute among the entities by combining with the injury crime knowledge body, and used for structurally storing subjective and objective facts and conflict data related to any link in case handling activities. Taking suspects and criminal behaviors in the ontology as examples, the table header of the entity relationship table is shown in table 3, for example:
Table 3 entity relationship table section column name description
| Column name | Column value |
| Suspicion | Suspect name in auditing results |
| Suspicious person label | Criminal Subjects;Suspect |
| Suspect attribute-identity card | Suspect identification card number in auditing result |
| Criminal act | Criminal name in auditing results |
| Criminal behavior label | Criminal Actions;Violent Harm / Organized Crime / Participate Crime / Linguistic Harm |
| Criminal behavior attribute-criminal time | Time of criminal occurrence in auditing results |
| Criminal behavior attribute-criminal location | Places where criminals occur in auditing results |
| Relationship-have criminal behavior | has_criminal Actions |
The subjective fact data comprises inquiry and inquiry strokes of the involved personnel; the objective fact data includes a wound assessment report and an asset assessment report. The transactor needs to extract the entity and entity relationship from the fact data according to the prompt.
The obtained entity relationship table includes, but is not limited to: a harmed fact entity relationship table, an objective fact entity relationship table, etc.
And (3) aligning the knowledge ontology with the entity by using entity labels in the entity relation table to complete the instantiation of the ontology knowledge, and laying a scientific foundation for legal supervision and reasoning decision-making.
Through this step, a variety of knowledge patterns can be obtained, including: a pest applying fact knowledge graph, a pest receiving fact knowledge graph, a third person crime fact knowledge graph and an objective fact knowledge graph.
Step S4, conflict detection: carrying out knowledge fusion on the injury crime knowledge maps of all the cases to be detected to obtain a fused knowledge map; then carrying out conflict detection according to the fused knowledge graph, and outputting a fact graph after resolving the existing conflict; the knowledge fusion is as follows: summarizing the same entities in the injury crime knowledge graph of the case to be tested to obtain a knowledge graph after entity fusion; the conflict detection is as follows: and judging whether contradictory entity relations exist among different entities according to the knowledge graph after the fusion of all the entities.
The subjective facts in the inquiry strokes have subjective colors of the inquired person, and the inquired person can say and missay the subjective facts related to the inquired person in order to avoid responsibility, so that knowledge fusion and conflict detection are needed. The method comprises two parts of 'knowledge fusion and conflict detection based on subjective evidence of a stroke record' and 'knowledge fusion and conflict detection based on subjective evidence of a case'.
The knowledge fusion and conflict detection based on the subjective evidence of the stroke records consists of the following four sub-links:
1. Summarizing the entities of interrogation strokes of different involved persons according to the injury crime knowledge graph of the case to be tested to obtain a fused knowledge graph, and judging whether contradictory entity relations exist among different entities;
the part is used for solving the problem that criminal suspects (victims), victims and irrelevant witness have inconsistent or incomplete expressions of criminal facts (harmful facts), harmful facts and third criminal facts in different interrogation or interrogation processes, and finally forming all subjective facts which are self-described in the same interrogation person or the record of the interrogation person, and supporting the conflict detection and resolution of the transacting person.
2. Summarizing criminals in the inquiry records of the involved person and entities of the extraneous witness inquiring criminals in the records according to the injury criminal knowledge graph of the case to be tested, obtaining a fused knowledge graph, and judging whether contradictory entity relationships exist among different entities;
The part is used for solving the problem that a certain suspected person or victim has inconsistent or incomplete expression of crime facts, and finally forming subjective fact consistency of the strokes of all crime behaviors of the same interviewee, and supporting the clash staff to detect and resolve the conflict.
3. According to the injury crime knowledge graph of the case to be tested, summarizing crime behaviors in inquiry records of suspects in the same pest application group and crime behavior entities in inquiry records of other members to obtain a fused knowledge graph, and judging whether contradictory entity relationships exist between different entities;
this section is used to solve the problem of incomplete or unrealistic expression of personal crime facts by a certain interviewee within a group partner. The invention uses the subjective fact data index of the strokes of other members of the group partner to finally form the subjective fact data of the strokes corresponding to all criminal behaviors of the inquired person, and supports the case transacting person to perform conflict detection and resolution.
4. Summarizing the criminal behavior entities in the interrogation records among different groups according to the injury criminal knowledge graph of the case to be tested to obtain a fused knowledge graph, and judging whether contradictory entity relationships exist among different entities;
This section is used to solve the problem that any n partners (n.gtoreq.2) are all interrogated personnel to express incomplete or unrealistic personal crime facts. According to the method, aiming at each group partner, subjective fact data of the records corresponding to the harmful behaviors of other group partners are compared in sequence, so that the subjective fact and conflict of the case are finally obtained, the case handling personnel is supported to take compliance means to continue to acquire data so as to resolve the conflict, and law enforcement supervision personnel is supported to find the conflict problem.
5. Summarizing the entities of subjective fact data and the entities of objective fact data according to the injury crime knowledge graph of the case to be tested to obtain a fused knowledge graph, and judging whether contradictory entity relations exist between different entities;
The objective evidence has legal basis and can be used for checking the pest applying behavior and result in the subjective evidence. Subjective and objective conflict detection can be accomplished by comparing the identified person and identified location (or identified property) in the objective evidence with the identified person and location (or property) in the subjective evidence. The method corrects subjective data by using objective evidence to form a case visualization result based on facts.
Step S5, case by auxiliary reasoning: and outputting a case by reasoning results according to the fact map.
The case by supplementary reasoning includes two parts: the first part is auxiliary rules and logic of reasoning of the injury crime case, and specifically comprises the steps of obtaining the relationship between a suspected person and a victim, the relationship between the suspected person and a damaged part and the relationship between the suspected person and property; the second part is the five crimes of injury class from the reasoning logic, specifically including the fight other case from the reasoning, the intentional injury case from the reasoning, the intentional killer case from the reasoning, the crowd fight crimes from the reasoning, the pick a quarrel breeds case from the reasoning.
The case-by-reason reasoning logic adopted by the invention is a five-class injury crime-by-reason reasoning rule defined according to public security management punishment law, basic requirements specified by the punishment law and civil police expert knowledge. The purpose of case-by-case reasoning is to realize the matching of criminal names of non-accomplice crime and suspicion suspicious persons and different group partners based on criminal facts under the constraint and assistance of the knowledge of the injury type criminal knowledge ontology, thereby providing basis for law enforcement, case handling and legal supervision.
Example 2
As shown in fig. 4, the present invention further proposes a system for supervising and assisting a harmful crime based on a knowledge graph, which uses the harmful crime supervising and assisting decision method based on a knowledge graph according to any one of embodiment 1, comprising the following modules:
The knowledge body construction module: the method comprises the steps of determining the knowledge body and a value condition of the knowledge body; the ontology comprises crime subjects, crimes, crime tools, harmful objects and harmful results;
The knowledge body expansion module: the system is connected with the knowledge body construction module and is used for expanding the knowledge body, and specifically comprises the steps of expanding crime behaviors and crime place attributes thereof by constructing a crime behavior feature word bag and a public place feature word bag, and expanding a pest applying object by constructing a human body part knowledge concept tree;
The case data acquisition module to be tested: the knowledge body expansion module is connected with the knowledge body expansion module and is used for acquiring subjective fact data and objective fact data of the case to be tested;
Injury crime knowledge graph module: the system comprises a data acquisition module, a storage module and a storage module, wherein the data acquisition module is connected with the data acquisition module of the to-be-detected case and is used for determining entity and entity relations according to the expanded knowledge body and the value condition of the knowledge body, subjective fact data and objective fact data of the to-be-detected case and constructing injury crime knowledge maps of all to-be-detected cases according to the entity and the entity relations;
And a conflict detection module: the system comprises a damage crime knowledge graph module, a damage crime recognition module and a damage crime recognition module, wherein the damage crime knowledge graph module is connected with the damage crime knowledge graph module and is used for carrying out knowledge fusion on the damage crime knowledge graphs of all the cases to be detected to obtain a fused knowledge graph; then carrying out conflict detection according to the fused knowledge graph, and outputting a fact graph after resolving the existing conflict; the knowledge fusion is as follows: summarizing the same entities in the injury crime knowledge graph of the case to be tested to obtain a fused knowledge graph of each entity; the conflict detection is as follows: judging whether contradictory entity relations exist between different entities according to the knowledge graph after the fusion of all the entities;
The case is composed of an auxiliary reasoning module: and the conflict detection module is connected with the conflict detection module and is used for outputting a case-by-case reasoning result according to the fact map.
The invention establishes a complete domain knowledge system: the method utilizes the empirical knowledge such as criminal law, public security management punishment law and injury criminal treatment program, expression characteristics and the like to abstract and form the injury criminal field knowledge body. And constructing a concept tree of the human body part, a characteristic word bag of criminal behaviors and a characteristic word bag of public places, and supplementing the ontology in the field of injury type crimes. The establishment of the knowledge body and the supplementation of the knowledge are key preconditions for developing subsequent knowledge calculation. An ontology is a formalized framework for describing concepts, entities, relationships, and attributes of a particular domain, aimed at capturing the semantic structure of knowledge. The building lays a foundation for the structured representation of knowledge so that it can be efficiently processed and utilized by a computer system. In addition, the ontology provides the basis for the reasoning mechanism. Through the ontology, the system can perform logic reasoning and explore potential relations among the knowledge, so that a deeper knowledge discovery and reasoning process is realized. This is critical to a crime-like law enforcement supervision and decision-aid system.
Law enforcement and case handling logic is more scientific: the knowledge graph technology has scientificity for supporting law enforcement and case handling logic, and standardizes the law enforcement and case handling process. The knowledge graph can comprehensively present case key information, and the knowledge graph technology can display various key information related to law enforcement and case handling in a graph form, including case related entities (such as suspects, victims and the like) and relationships. This full face presents a means to help law enforcement more fully and systematically understand various aspects of the case. The technology of capturing complex relations between entities, efficiently traversing the graph and inquiring the knowledge graph can be used for supporting a complex knowledge calculation process, helping law enforcement personnel find conflicts among evidences and carrying out knowledge calculation reasoning conforming to causal logic.
Example 3
An electronic device, the electronic device comprising:
A processor and a memory;
the processor is configured to perform the steps of the knowledge-graph-based injury crime law enforcement supervision and decision aid method according to any one of embodiment 1 by invoking a program or instructions stored in the memory.
Example 4
A computer readable storage medium comprising computer program instructions for causing a computer to perform the steps of the knowledge-graph-based injury crime enforcement supervision and aid decision method of any of embodiment 1.
The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present invention. As used in this specification, the terms "a," "an," "the," and/or "the" are not intended to be limiting, but rather are to be construed as covering the singular and the plural, unless the context clearly dictates otherwise. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method or apparatus that includes the element.
It should also be noted that the positional or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the positional or positional relationship shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or element in question must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Unless specifically stated or limited otherwise, the terms "mounted," "connected," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.
Claims (9)
1. The injury crime law enforcement supervision and auxiliary decision-making method based on the knowledge graph is characterized by comprising the following steps of:
Step S0, constructing a knowledge body: determining the knowledge body and the value condition of the knowledge body; the ontology comprises crime subjects, crimes, crime tools, harmful objects and harmful results;
Step S1, ontology expansion: expanding the knowledge body, specifically comprising expanding crimes by constructing a crime feature word bag and a public place feature word bag, and expanding a pest applying object by constructing a human body part knowledge concept tree;
step S2, obtaining data of a case to be tested: obtaining subjective fact data and objective fact data of a case to be tested;
Step S3, constructing an injury crime knowledge graph: determining entity and entity relation according to the expanded knowledge body, the value condition of the knowledge body, subjective fact data and objective fact data of the cases to be tested, and constructing injury crime knowledge maps of all the cases to be tested according to the entity and entity relation;
Step S4, conflict detection: carrying out knowledge fusion on the injury crime knowledge maps of all the cases to be detected to obtain a fused knowledge map; then carrying out conflict detection according to the fused knowledge graph, and outputting a fact graph after resolving the existing conflict; the knowledge fusion is as follows: summarizing the same entities in the injury crime knowledge graph of the case to be tested to obtain a knowledge graph after entity fusion; the conflict detection is as follows: judging whether contradictory entity relations exist between different entities according to the knowledge graph after the fusion of all the entities; collision detection occurs from five aspects:
summarizing the entities of interrogation strokes of different involved persons according to the injury crime knowledge graph of the case to be tested to obtain a fused knowledge graph, and judging whether contradictory entity relations exist among different entities;
summarizing criminals in the inquiry records of the involved person and entities of the extraneous witness inquiring criminals in the records according to the injury criminal knowledge graph of the case to be tested, obtaining a fused knowledge graph, and judging whether contradictory entity relationships exist among different entities;
According to the injury crime knowledge graph of the case to be tested, summarizing crime behaviors in inquiry records of suspects in the same pest application group and crime behavior entities in inquiry records of other members to obtain a fused knowledge graph, and judging whether contradictory entity relationships exist between different entities;
summarizing the criminal behavior entities in the interrogation records among different groups according to the injury criminal knowledge graph of the case to be tested to obtain a fused knowledge graph, and judging whether contradictory entity relationships exist among different entities;
Summarizing the entities of subjective fact data and the entities of objective fact data according to the injury crime knowledge graph of the case to be tested to obtain a fused knowledge graph, and judging whether contradictory entity relations exist between different entities;
step S5, case by auxiliary reasoning: and outputting a case by reasoning results according to the fact map.
2. The method for supervising and assisting the law enforcement of injury crimes based on a knowledge-graph according to claim 1, wherein in the step S0, the criminal subject comprises a suspect and a criminal organization; the crime tool comprises limbs, instruments and random objects; the criminal acts include violent infliction, language infliction, crime participation and criminal organization; the pest applying objects comprise a victim, a pest location and property; the consequences of such damage include personal injury, death, and property damage.
3. The method for supervising and assisting the law enforcement of crimes based on the knowledge-graph as set forth in claim 1, wherein in the step S1,
The construction of the criminal behavior characteristic word bag specifically comprises the following steps: the criminal behavior feature word bag is expanded when the word similarity between the root word and the synonym exceeds a threshold value by acquiring the criminal behavior word in the history case and expanding the criminal behavior word in the synonym and the paraphrasing;
The construction of the public place feature word bag specifically comprises the following steps: the method comprises the steps that public place words in historical cases are obtained and expanded in synonyms and paraphraseology, and when the word similarity between root words and the synonyms exceeds a threshold value, public place feature word bags are expanded;
The construction of the human body part knowledge concept tree comprises the following steps: the human body is divided according to the limb parts, a human body part knowledge conceptual tree is constructed, and a standardized human body part map is obtained.
4. The method for supervising and assisting decision-making on the basis of injury crime law enforcement based on a knowledge graph according to claim 3, wherein layer 0 of the human body part knowledge concept tree is a human body part total concept; layer 1 of the human body part concept tree is three major components of human body parts: head and neck, upper body and lower body.
5. The method for supervising and assisting the law enforcement of injury crimes based on the knowledge graph according to claim 1, wherein in the step S2, the subjective fact data includes the inquiry records of the involved person and the inquiry records of the unrelated witness; the objective fact data includes a wound assessment report and an asset assessment report.
6. The method for supervising and assisting decision-making on injury crime based on knowledge graph as set forth in claim 1, wherein in step S3, the injury crime knowledge graph of the case to be tested includes: a pest applying fact knowledge graph, a pest receiving fact knowledge graph, a third person crime fact knowledge graph and an objective fact knowledge graph.
7. The knowledge-based injury crime law enforcement supervision and decision aid method according to claim 1, wherein the case by aid reasoning comprises two parts: the first part is relationship reasoning, and specifically comprises relationships between suspects and victims, between suspects and harmful parts, and between suspects and property; the second part is five cases of injury crimes by reasoning, specifically including the case of fighting others case by reasoning, the case of intentional injury case by reasoning, the case of intentional killer case by reasoning, the case of congregation by reasoning, pick a quarrel the case of intercourse case by reasoning.
8. A knowledge-based injury crime law enforcement monitoring and decision-aiding system using the knowledge-based injury crime law enforcement monitoring and decision-aiding method according to any one of claims 1 to 7, comprising the following modules:
The knowledge body construction module: the method comprises the steps of determining the knowledge body and a value condition of the knowledge body; the ontology comprises crime subjects, crimes, crime tools, harmful objects and harmful results;
The knowledge body expansion module: the system is connected with the knowledge body construction module and is used for expanding the knowledge body, and specifically comprises the steps of expanding crimes by constructing a crime characteristic word bag and a public place characteristic word bag, and expanding harmful objects by constructing a human body part knowledge concept tree;
The case data acquisition module to be tested: the knowledge body expansion module is connected with the knowledge body expansion module and is used for acquiring subjective fact data and objective fact data of the case to be tested;
Injury crime knowledge graph module: the system comprises a data acquisition module, a storage module and a storage module, wherein the data acquisition module is connected with the data acquisition module of the to-be-detected case and is used for determining entity and entity relations according to the expanded knowledge body and the value condition of the knowledge body, subjective fact data and objective fact data of the to-be-detected case and constructing injury crime knowledge maps of all to-be-detected cases according to the entity and the entity relations;
And a conflict detection module: the system comprises a damage crime knowledge graph module, a damage crime recognition module and a damage crime recognition module, wherein the damage crime knowledge graph module is connected with the damage crime knowledge graph module and is used for carrying out knowledge fusion on the damage crime knowledge graphs of all the cases to be detected to obtain a fused knowledge graph; then carrying out conflict detection according to the fused knowledge graph, and outputting a fact graph after resolving the existing conflict; the knowledge fusion is as follows: summarizing the same entities in the injury crime knowledge graph of the case to be tested to obtain a knowledge graph after entity fusion; the conflict detection is as follows: judging whether contradictory entity relations exist between different entities according to the knowledge graph after the fusion of all the entities;
The case is composed of an auxiliary reasoning module: and the conflict detection module is connected with the conflict detection module and is used for outputting a case-by-case reasoning result according to the fact map.
9. An electronic device, the electronic device comprising: a processor and a memory for executing the steps of the knowledge-graph-based injury crime law enforcement supervision and aid decision making method according to any one of claims 1 to 7 by invoking a program or instructions stored in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410240524.1A CN117830060B (en) | 2024-03-04 | 2024-03-04 | Injury crime law enforcement supervision and auxiliary decision-making system based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410240524.1A CN117830060B (en) | 2024-03-04 | 2024-03-04 | Injury crime law enforcement supervision and auxiliary decision-making system based on knowledge graph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117830060A CN117830060A (en) | 2024-04-05 |
| CN117830060B true CN117830060B (en) | 2024-05-28 |
Family
ID=90509875
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410240524.1A Active CN117830060B (en) | 2024-03-04 | 2024-03-04 | Injury crime law enforcement supervision and auxiliary decision-making system based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117830060B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106991092A (en) * | 2016-01-20 | 2017-07-28 | 阿里巴巴集团控股有限公司 | The method and apparatus that similar judgement document is excavated based on big data |
| CN108733683A (en) * | 2017-04-17 | 2018-11-02 | 中兴通讯股份有限公司 | A kind of method and device for exploration event clue of being sounded out the people in a given scope one by one in order to break a criminal case based on data |
| CN110457443A (en) * | 2019-08-12 | 2019-11-15 | 贵州大学 | A kind of criminal offence chain building method based on criminal case |
| CN112528036A (en) * | 2020-11-30 | 2021-03-19 | 大连理工大学 | Knowledge graph automatic construction method for evidence correlation analysis |
| CN114915468A (en) * | 2022-05-10 | 2022-08-16 | 广州数智网络科技有限公司 | Intelligent analysis and detection method for network crime based on knowledge graph |
-
2024
- 2024-03-04 CN CN202410240524.1A patent/CN117830060B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106991092A (en) * | 2016-01-20 | 2017-07-28 | 阿里巴巴集团控股有限公司 | The method and apparatus that similar judgement document is excavated based on big data |
| CN108733683A (en) * | 2017-04-17 | 2018-11-02 | 中兴通讯股份有限公司 | A kind of method and device for exploration event clue of being sounded out the people in a given scope one by one in order to break a criminal case based on data |
| CN110457443A (en) * | 2019-08-12 | 2019-11-15 | 贵州大学 | A kind of criminal offence chain building method based on criminal case |
| CN112528036A (en) * | 2020-11-30 | 2021-03-19 | 大连理工大学 | Knowledge graph automatic construction method for evidence correlation analysis |
| CN114915468A (en) * | 2022-05-10 | 2022-08-16 | 广州数智网络科技有限公司 | Intelligent analysis and detection method for network crime based on knowledge graph |
Non-Patent Citations (4)
| Title |
|---|
| 伤害类犯罪案由推理辅助决策方法研究与实践;华斌等;《数据分析与知识发现》;20231225;142-154 * |
| 基于大数据的个人极端暴力犯罪防控研究;宋祥斌;《无线互联科技》;20191130;全文 * |
| 贾君枝等.《国家创新发展中的信息资源服务平台建设》.武汉大学出版社,2022,284-285. * |
| 面向社会治理的人员关系知识图谱构建与应用;左昌鑫;中国优秀硕士学位论文全文数据库社会科学Ⅰ辑;20231115;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117830060A (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gohel et al. | Explainable AI: current status and future directions | |
| WO2020253358A1 (en) | Service data risk control analysis processing method, apparatus and computer device | |
| Lagnado et al. | Legal idioms: a framework for evidential reasoning | |
| CN107180070B (en) | Automatic risk information classification, identification and early warning method and system | |
| CN106790256B (en) | Active machine learning system for dangerous host supervision | |
| CN110826316B (en) | Method for identifying sensitive information applied to referee document | |
| CN112165462A (en) | Attack prediction method and device based on portrait, electronic equipment and storage medium | |
| CN111538741B (en) | Deep learning analysis method and system for big data of alarm condition | |
| CN109903045B (en) | Behavior track monitoring method, device, computer equipment and medium | |
| CN112149135A (en) | Method and device for constructing security vulnerability knowledge graph | |
| CN111145510A (en) | Alarm receiving processing method, device and equipment | |
| CN115018214A (en) | Enterprise risk analysis and prediction method, system and medium based on cognitive map | |
| CN117830060B (en) | Injury crime law enforcement supervision and auxiliary decision-making system based on knowledge graph | |
| Tecuci et al. | Instructable Cognitive Agents for Autonomous Evidence-Based Reasoning | |
| CN117349437A (en) | Government information management system and method based on intelligent AI | |
| Sung et al. | A Study of BERT-Based Classification Performance of Text-Based Health Counseling Data. | |
| CN116205350A (en) | Reinforcement personal risk analysis and prediction system and method based on legal documents | |
| CN114420307A (en) | Artificial intelligence-based public health event registration method and device and electronic equipment | |
| Merilinna | A mechanism to enable spatial reasoning in jboss drools | |
| KR102375021B1 (en) | A method for monitoring management activity and anomalies for proper audit disposition | |
| Van Schie et al. | Predictive Policing in the Netherlands: A Critical Data Studies Approach | |
| CN113012006A (en) | Intelligent investigation and research method, system, computer equipment and storage medium | |
| Phengsuwan et al. | Context-based knowledge discovery and querying for social media data | |
| CN116630724B (en) | Data model generation method, image processing method, device and chip | |
| CN116432953B (en) | Cultural relic protection emergency response decision-making method and system based on generalization generation mode |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |