Information matching method, device, computer equipment and storage medium

Through the legal knowledge graph and information matching method, combined with the deadline factor in the criminal fact text, the legal incidents and punishment methods are quickly positioned and screened out, which solves the problem of low information processing efficiency in the legal field and improves the work efficiency of legal workers.

CN111611397BActive Publication Date: 2024-11-05GUANGZHOU HUIRUI SITONG INFORMATION SCI & TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN201910143418.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2019-02-26
Publication Date
2024-11-05
Estimated Expiration
2039-02-26

Smart Images

  • Figure CN111611397B_ABST
    Figure CN111611397B_ABST
Patent Text Reader

Abstract

The present application relates to an information matching method, apparatus, computer equipment and storage medium, the method comprising: obtaining a target legal event determined according to a crime fact text, determining a target benchmark penalty method corresponding to the target legal event according to a legal knowledge graph, the legal knowledge graph containing a correspondence between legal events and benchmark penalty methods, obtaining a time limit factor from the crime fact text, and selecting a target penalty method corresponding to the time limit factor from the target benchmark penalty methods. The target legal event corresponding to the crime fact text is quickly located by querying the legal knowledge graph, the target benchmark penalty method corresponding to the target legal event is screened according to the time limit factor obtained from the scope fact text, and the target penalty method corresponding to the legal event is quickly searched according to the correspondence between the legal event and the benchmark penalty method in the legal knowledge graph, making data retrieval easier and more accurate, and further improving the work efficiency of legal workers.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an information matching method, apparatus, computer device and storage medium. Background Art

[0002] In recent years, with the increasing maturity of artificial intelligence technology, especially knowledge graphs, many fields, such as natural language processing, speech recognition, spam filtering, machine translation, advertising recommendations, smart home appliances, etc., have made rapid progress using artificial intelligence technology. In the legal field, however, there is less integration with artificial intelligence, and most legal work is still done by manpower.

[0003] Law is a highly professional field. Non-professionals often cannot obtain the expected legal knowledge by searching for information, and relying on professional legal advice is both time-consuming and costly. On the other hand, for legal workers themselves, the legal knowledge and case knowledge they have are limited. In some special cases, they also need to seek help from other channels. Legal workers cannot process case information quickly, resulting in slow progress of work. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides an information matching method, apparatus, computer device and storage medium.

[0005] In a first aspect, the present application provides an information matching method, comprising:

[0006] Obtain the target legal event determined according to the text of the crime facts;

[0007] Determine the target benchmark penalty method corresponding to the target legal event according to the legal knowledge graph, where the legal knowledge graph contains the correspondence between the legal event and the benchmark penalty method;

[0008] The time limit factor is obtained from the crime fact text, and the target penalty method corresponding to the time limit factor is selected from the target benchmark penalty methods.

[0009] In a second aspect, the present application provides an information matching device, comprising:

[0010] A target legal event acquisition module is used to acquire a target legal event determined according to the crime fact text;

[0011] A target benchmark penalty method determination module is used to determine the target benchmark penalty method corresponding to the target legal event based on the legal knowledge graph, where the legal knowledge graph contains the correspondence between the legal event and the benchmark penalty method;

[0012] The target punishment method determination module is used to obtain the time limit factor from the crime fact text and select the target punishment method corresponding to the time limit factor from the target benchmark punishment method.

[0013] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0014] Obtain the target legal event determined according to the text of the crime facts;

[0015] Determine the target benchmark penalty method corresponding to the target legal event according to the legal knowledge graph, where the legal knowledge graph contains the correspondence between the legal event and the benchmark penalty method;

[0016] The time limit factor is obtained from the crime fact text, and the target penalty method corresponding to the time limit factor is selected from the target benchmark penalty methods.

[0017] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0018] Obtain the target legal event determined according to the text of the crime facts;

[0019] Determine the target benchmark penalty method corresponding to the target legal event according to the legal knowledge graph, where the legal knowledge graph contains the correspondence between the legal event and the benchmark penalty method;

[0020] The time limit factor is obtained from the crime fact text, and the target penalty method corresponding to the time limit factor is selected from the target benchmark penalty methods.

[0021] The above-mentioned information matching method, device, computer equipment and storage medium, the method includes: obtaining a target legal event determined according to the crime fact text, determining a target benchmark penalty method corresponding to the target legal event according to the legal knowledge graph, the legal knowledge graph contains the correspondence between legal events and benchmark penalty methods, obtaining a term factor from the crime fact text, and selecting a target penalty party corresponding to the term factor from the target benchmark penalty method. By querying the legal knowledge graph, the target legal event corresponding to the crime fact text is quickly located, the target benchmark penalty method corresponding to the target legal event is screened according to the term factor obtained from the scope fact text, and the target penalty method corresponding to the legal event is quickly searched according to the correspondence between the legal event and the benchmark penalty method in the legal knowledge graph, making data retrieval easier and more accurate, and further improving the work efficiency of legal workers. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0024] Figure 1 An application environment diagram of an information matching method in an embodiment;

[0025] Figure 2 is a schematic diagram of a flow chart of an information matching method in an embodiment;

[0026] Figure 3 is a structural block diagram of an information matching device in an embodiment;

[0027] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0029] Figure 1 FIG. 1 is an application environment diagram of an information matching method in an embodiment. Figure 1 , the information matching method is applied to the information matching system. The information matching system includes a terminal 110 and a server 120. The terminal 110 and the server 120 are connected via a network. The terminal or the server obtains a legal knowledge graph, the legal knowledge graph contains the correspondence between legal events and benchmark punishment methods, obtains a target legal event determined according to the crime fact text, determines the target benchmark punishment method corresponding to the target legal event according to the legal knowledge graph, obtains a time limit factor from the crime fact text, and selects a target punishment method corresponding to the time limit factor from the target benchmark punishment method. The terminal 110 can specifically be a desktop terminal or a mobile terminal, and the mobile terminal can specifically be at least one of a mobile phone, a tablet computer, a laptop computer, etc. The server 120 can be implemented by an independent server or a server cluster consisting of multiple servers.

[0030] like Figure 2 As shown, in one embodiment, an information matching method is provided. This embodiment mainly applies this method to the above Figure 1 The terminal 110 (or server 120) in FIG. Figure 2 , the information matching method specifically includes the following steps:

[0031] Step S201, obtaining a target legal event determined based on the crime fact text.

[0032] Specifically, the target legal event refers to the legal event committed by the implementing subject corresponding to the crime fact text, and the legal event is obtained by analyzing the crime fact text. The analysis of the crime fact text can be the result of manual analysis by legal workers, or the result of analyzing the text through a text analysis model. Obtain the target legal event determined by the legal worker or the target legal event obtained by automatically analyzing the crime fact text.

[0033] Step S202, determining the target benchmark penalty method corresponding to the target legal event based on the legal knowledge graph, the legal knowledge graph containing the correspondence between the legal event and the benchmark penalty method.

[0034] Specifically, the legal knowledge graph refers to the data used to store various legal data and the corresponding relationships between legal data. For example, it includes the corresponding relationship between legal events and benchmark punishment methods, the corresponding relationship between legal events and legal provisions, the corresponding relationship between legal events and the four elements of legal events, the relationship between legal provisions, the relationship between legal texts, and so on. Query the target benchmark punishment method corresponding to the target legal event. One legal event may correspond to one target benchmark punishment method, or it may correspond to multiple target benchmark punishment methods. When it corresponds to multiple target benchmark punishment methods, it is necessary to further determine the target benchmark punishment method based on the text of the crime facts until there is a unique target benchmark punishment method. The target legal event is an event that defines a legal event. Taking criminal law as an example, the target legal event refers to the crime, and the target benchmark punishment method is the target benchmark punishment.

[0035] In one embodiment, determining a target benchmark penalty method corresponding to a target legal event based on a legal knowledge graph also includes: determining whether there are multiple benchmark penalty methods corresponding to the target legal event, and when there are multiple benchmark penalty methods, obtaining the severity of the crime corresponding to the crime fact text, and determining the corresponding target benchmark penalty method according to the severity of the crime.

[0036] Specifically, since a legal event may correspond to multiple benchmark punishment methods, after determining the target legal event, the benchmark punishment method corresponding to the target legal event can be queried through the legal knowledge graph to determine whether the number of benchmark punishment methods corresponding to the target legal event is greater than 1. When the benchmark punishment method corresponding to the target legal event is greater than 1, the severity of the crime corresponding to the criminal fact text is obtained. The severity of the crime is an evaluation index obtained by evaluating the criminal facts in the criminal fact text. Different severity levels correspond to different evaluation indicators, and different severity levels correspond to different target benchmark punishment methods. For example, intentional homicide includes the first benchmark sentence as the first benchmark punishment method: 3-5 years of fixed-term imprisonment; the second benchmark sentence as the second benchmark punishment method: death penalty, life imprisonment and more than 10 years of fixed-term imprisonment. The severity of the crime corresponding to intentional homicide includes at least two levels. The target benchmark punishment method corresponding to the first severity level is the first benchmark punishment method, and the target benchmark punishment method corresponding to the second severity level is the second benchmark punishment method. The severity of a crime is a relatively abstract concept, so when judging it, it can generally be judged by judging specific words. For example, when describing the crime process in the text of the crime facts, the perpetrator abuses others in a cruel way. These descriptions are serious injuries to the victim. Therefore, when judging, if there are some words that cruelly treat the victim, the corresponding severity of the crime belongs to the serious type. Or when it has an extremely bad impact on society, has a bad attitude, etc., the corresponding severity of the crime belongs to the serious type. Therefore, according to the severity of the crime, the benchmark punishment method can be more accurately positioned, laying the foundation for the subsequent judgment period.

[0037] Step S203, obtaining a time limit factor from the crime fact text, and selecting a target penalty method corresponding to the time limit factor from the target benchmark penalty methods.

[0038] Specifically, the term factor refers to data that can affect the punishment method and term, where the term factor includes the aggravating term factor and the mitigating term factor. The aggravating term factor refers to the influencing factor of aggravating the punishment, and the aggravating term factor includes but is not limited to intentionally prolonging the duration of the crime during the commission of the crime, causing the victim to suffer more pain, or obstructing the law enforcement of law enforcement officers after the crime is committed. The mitigating term factor refers to the influencing factor of mitigating the punishment, such as the mitigating term factor includes but is not limited to surrender, meritorious service, compensation and other acts used to remedy the crime after the crime is committed. The target punishment method corresponding to the term factor is found from the target benchmark punishment method. If the term factor only includes the aggravating term factor, a more severe punishment method is selected from the target benchmark punishment method. When the term factor only includes the mitigating term factor, a lighter punishment method is selected from the target benchmark punishment method.

[0039] In one embodiment, the term factor includes an aggravating term factor and a mitigating term factor. After obtaining the term factor from the crime fact text, it also includes: judging the type of each term factor, and using the term factor determined to be aggravating as the aggravating term factor, and using the term factor determined to be mitigating as the mitigating term factor.

[0040] Specifically, after obtaining the time limit factors in the crime fact text, the types of each time limit factor are judged. The types of time limit factors include aggravation and mitigation. Aggravation corresponds to aggravation time limit factors, and mitigation corresponds to mitigation time limit factors. According to the types of each time limit factor after judgment, it is added to the corresponding time limit factor type. Classifying the time limit factors can better determine the punishment of the perpetrator of the crime.

[0041] In one embodiment, when the term factor includes both a heavier term factor and a lighter term factor, a weighted sum is performed on the heavier term factor and the lighter term factor to obtain a corresponding weighted factor. When the weighted factor is greater than a preset threshold, the heavier penalty method in the benchmark penalty method is used as the target penalty method. When the weighted factor is equal to the preset threshold, the intermediate penalty method in the benchmark penalty method is used as the target penalty method. When the weighted factor is less than the preset threshold, the lighter penalty method in the benchmark penalty method is used as the target penalty method, wherein the time limit of the heavier penalty method is greater than the time limit of the intermediate penalty method, and the time limit of the intermediate penalty method is greater than the time limit of the lighter penalty method.

[0042] Specifically, a weighting coefficient is set for the aggravating term factor, and a weighting coefficient is set for the mitigating term factor. According to the weighting coefficient set for the aggravating term factor and the weighting coefficient set for the mitigating term factor, the aggravating term factor and the mitigating term factor are weighted and summed to obtain the corresponding weighting factor, and it is determined whether the weighting factor is greater than a preset threshold. Among them, the preset threshold is a pre-set critical value for determining the target punishment method. If it is greater than the critical value, the aggravating punishment method is selected, and if it is less than the critical value, the mitigating punishment method is selected. When the weighting factor is greater than the preset threshold, it means that the perpetrator's performance is relatively bad, and the aggravating punishment method with a heavier penalty in the target benchmark punishment method is selected. When the weighting factor is equal to the preset threshold, the intermediate punishment method in the target benchmark punishment method is selected. When the weighting factor is less than the preset threshold, it means that the perpetrator has implemented the corresponding remedial behavior, and the mitigating punishment method with a lighter penalty in the target benchmark punishment method is selected.

[0043] In one embodiment, after determining the target benchmark penalty method corresponding to the target legal event based on the legal knowledge graph, it also includes: judging whether the target benchmark penalty method includes multiple penalty methods; when the target benchmark penalty method includes multiple penalty methods, obtaining a time limit factor from the crime fact text, and selecting a target penalty method corresponding to the time limit factor from the target benchmark penalty method.

[0044] Specifically, a target benchmark penalty method may include multiple penalty methods. Therefore, after determining the target benchmark penalty method, first determine whether the number of penalty methods corresponding to the target benchmark penalty method is multiple. When the number of target benchmark penalty methods is multiple, it is necessary to determine which penalty method to select from the target benchmark penalty method based on the term factor. Therefore, the step of obtaining the term factor from the crime fact text and selecting the target penalty method corresponding to the term factor from the target benchmark penalty method is entered.

[0045] In one embodiment, after step S203, the method further includes: determining a target deadline corresponding to the target penalty method according to the deadline corresponding to the penalty method.

[0046] Specifically, the correspondence between the punishment method and the term is determined by the correspondence in each legal text. After the target punishment method is determined, the term corresponding to the target punishment method is queried through the correspondence between the punishment method and the term, and the term corresponding to the target punishment method is used as the target term, where the target term can be a specific term or an interval term. The specific term refers to the specific length of time, such as a fifteen-year fixed-term imprisonment or a ten-year fixed-term imprisonment, etc. The interval term refers to a period of time, such as a fixed-term imprisonment of more than ten years.

[0047] In one embodiment, after selecting the target penalty method corresponding to the term factor from the target benchmark penalty method, it includes: judging whether the target penalty method is a fixed-term imprisonment, and when the target penalty method is a fixed-term imprisonment, entering the step of determining the target term corresponding to the target penalty method according to the term corresponding to the penalty method.

[0048] Specifically, after determining the target penalty method corresponding to the target benchmark penalty method, the type of the target penalty method is determined. When the target penalty method is imprisonment, the term of the imprisonment needs to be determined. Generally, the term of imprisonment is a time interval, such as imprisonment of more than 10 years, imprisonment of 3-5 years, etc. When it is determined that the target penalty method is imprisonment, the range of the term of imprisonment can be further narrowed. For example, imprisonment of more than 10 years can be determined to be 13 years, or 10-15 years. By narrowing the term, people who use this information matching method can get a more accurate reference term, which can help legal workers better understand cases, improve work efficiency, etc.

[0049] The above-mentioned information matching method, information matching method, device, computer equipment and storage medium, the method includes: obtaining a target legal event determined according to the crime fact text, the legal knowledge graph contains the correspondence between the legal event and the benchmark punishment method, determining the target benchmark punishment method corresponding to the target legal event according to the legal knowledge graph, obtaining the term factor from the crime fact text, and selecting the target punishment method corresponding to the term factor from the target benchmark punishment method. By querying the legal knowledge graph, the target legal event corresponding to the crime fact text is quickly located, the target punishment method corresponding to the target legal event is screened according to the term factor obtained from the scope fact text, and the target punishment method corresponding to the target legal event is quickly searched according to the correspondence between the legal event and the benchmark punishment method in the legal knowledge graph, making data retrieval easier and more accurate, and further improving the work efficiency of legal workers.

[0050] In a specific embodiment, the above information matching method includes:

[0051] Obtain legal events. Extract the subject, object, subjective aspect and objective aspect from the crime fact text, and then determine the target legal event of the criminal perpetrator in the crime fact text through filtering and matching.

[0052] Determination of the benchmark penalty method. After obtaining the target legal event, the benchmark penalty method corresponding to the target legal event is searched in the legal knowledge graph. In the legal knowledge graph, the same legal event may correspond to multiple benchmark penalty methods. It is determined whether the target legal event contains multiple benchmark penalty methods. If it contains multiple benchmark penalty methods, the only target benchmark penalty method is determined based on the severity of the criminal behavior of the criminal perpetrator in the criminal fact text.

[0053] The specific punishment method is determined. A benchmark punishment method may correspond to one or more punishment methods. The multiple punishment methods corresponding to the same benchmark punishment method belong to the same level of punishment methods with different degrees of severity. Therefore, it is necessary to determine a unique target punishment method from the benchmark punishment method. In the process of determining the target punishment method, it is necessary to consider the severity of the crime, so it is necessary to quantify the term factors that affect sentencing. The term factors include aggravating term factors and mitigating term factors. Aggravating term factors will cause sentencing to tend to heavier punishment methods, and mitigating term factors will cause sentencing to tend to lighter punishment methods. In the actual judgment process, the term factors extracted from the crime fact text are classified, and the aggravating term factors and mitigating term factors are calculated comprehensively. Aggravating behaviors in the crime process can be remedied after the crime, such as surrendering, making meritorious contributions, and compensation, so it is necessary to comprehensively consider aggravating term factors and mitigating term factors. For example, if the aggravating period factor is set to positive and the mitigating period factor is set to negative, the aggravating period factor and the mitigating period factor are added together. When the result of the addition is greater than zero, the aggravating punishment method corresponding to the aggravating period factor is selected. Otherwise, if it is less than zero, the aggravating punishment method corresponding to the aggravating period factor is selected. If it is equal to zero, the middle punishment is selected.

[0054] Term lock. If the selected punishment is not a fixed-term imprisonment, it will be given directly. If it is a fixed-term imprisonment, the term factor will be combined to further narrow the range of the fixed-term imprisonment. For example, if a fixed-term imprisonment of more than ten years is given, the term factor will be combined to narrow the term to ten to fifteen years of fixed-term imprisonment. Then, a specific term can be locked within this range based on the sentencing factors, such as twelve years of fixed-term imprisonment.

[0055] Results are presented. There are three forms of sentencing results. The first is a non-quantified punishment, such as death penalty and life imprisonment; the second is a fixed-term imprisonment period, such as more than ten years in prison, that is, ten to twenty-five years; the third is a specific term of imprisonment, such as fifteen years in prison.

[0056] Most of the existing computer technology-assisted legal systems are based on structured legal knowledge and case databases, and provide legal advice through simple matching queries. This method is not flexible and has a large workload. Knowledge graphs can simplify the complex and clarify the logical relevance of the case, providing good support for intelligent determination of deadlines, that is, they can quickly process the crime text and give the corresponding criminal legal events and corresponding deadlines.

[0057] Figure 2 FIG. 1 is a flow chart of an information matching method in one embodiment. It should be understood that although Figure 2The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0058] In one embodiment, Figure 3 As shown, an information matching device is provided, comprising:

[0059] The target legal event acquisition module 201 is used to acquire the target legal event determined according to the crime fact text.

[0060] The target benchmark penalty method determination module 202 is used to determine the target benchmark penalty method corresponding to the target legal event based on the legal knowledge graph, and the legal knowledge graph contains the correspondence between legal events and benchmark penalty methods.

[0061] The target punishment method determination module 203 is used to obtain the time limit factor from the crime fact text and select the target punishment method corresponding to the time limit factor from the target benchmark punishment methods.

[0062] In one embodiment, the information matching device further includes:

[0063] The term factor processing module is used to determine the type of each term factor, and to use the term factor determined to be heavier as the heavier term factor, and to use the term factor determined to be lighter as the lighter term factor.

[0064] In one embodiment, the target penalty method determination module includes:

[0065] The term factor calculation unit is used to perform weighted summation of the heavier term factor and the lighter term factor to obtain a corresponding weighted factor.

[0066] The target penalty method determination unit is used to use the heavier penalty method in the benchmark penalty method as the target penalty method when the weighting factor is greater than a preset threshold value, and to use the intermediate penalty method in the benchmark penalty method as the target penalty method when the weighting factor is equal to the preset threshold value; and to use the lighter penalty method in the benchmark penalty method as the target penalty method when the weighting factor is less than the preset threshold value, wherein the time limit of the heavier penalty method is greater than the time limit of the intermediate penalty method, and the time limit of the intermediate penalty method is greater than the time limit of the lighter penalty method.

[0067] In one embodiment, the target benchmark penalty method determination module is also used to determine whether the number of benchmark penalty methods corresponding to the target legal event is multiple. When the number of benchmark penalty methods is multiple, the severity of the crime circumstances corresponding to the criminal fact text is obtained and the corresponding target benchmark penalty method is determined according to the severity of the crime circumstances.

[0068] In one embodiment, the information matching device further includes:

[0069] The penalty method determination module is used to determine whether the target benchmark penalty method includes multiple penalty methods.

[0070] The multiple penalty method processing module is used to enter the target penalty method determination module when the target benchmark penalty method includes multiple penalty methods.

[0071] In one embodiment, the information matching device further includes:

[0072] The fixed-term imprisonment judgment module is used to judge whether the target punishment method is a fixed-term imprisonment.

[0073] The fixed-term imprisonment processing module is used to determine the target term corresponding to the target punishment method according to the term corresponding to the punishment method when the target punishment method is fixed-term imprisonment.

[0074] Figure 4 The internal structure diagram of a computer device in one embodiment is shown. The computer device may specifically be Figure 1 The terminal 110 (or server 120) in FIG. Figure 4 As shown, the computer device includes a processor, a memory, a network interface, an input device and a display screen connected through a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program, which, when executed by the processor, enables the processor to implement the information matching method. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to execute the information matching method. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0075] Those skilled in the art will understand that Figure 4The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0076] In one embodiment, the information matching device provided by the present application can be implemented in the form of a computer program. The computer program can be Figure 4 The computer device shown in the figure is run. The memory of the computer device can store various program modules constituting the information matching device, for example, Figure 3 The target legal event acquisition module 201, the target benchmark penalty method determination module 202 and the target penalty method determination module 203 are shown. The computer program composed of each program module enables the processor to execute the steps of the information matching method of each embodiment of the present application described in this specification.

[0077] For example, Figure 4 The computer device shown can be Figure 3 The target legal event acquisition module 201 in the information matching device shown acquires the target legal event determined according to the crime fact text. The computer device can determine the target benchmark punishment method corresponding to the target legal event according to the legal knowledge graph through the target benchmark punishment method determination module 202, and the legal knowledge graph contains the corresponding relationship between the legal event and the benchmark punishment method. The computer device can obtain the term factor from the crime fact text through the target punishment method determination module 203, and select the target punishment method corresponding to the term factor from the target benchmark punishment method. In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: acquiring the target legal event determined according to the crime fact text, determining the target benchmark punishment method corresponding to the target legal event according to the legal knowledge graph, the legal knowledge graph contains the corresponding relationship between the legal event and the benchmark punishment method, acquiring the term factor from the crime fact text, selecting the target punishment method corresponding to the term factor from the target benchmark punishment method, and determining the target term corresponding to the target punishment method according to the term corresponding to the punishment method.

[0078] In one embodiment, the term factors include aggravating term factors and mitigating term factors. After obtaining the term factors from the crime fact text, the processor also implements the following steps when executing the computer program: determining the type of each term factor, using the term factors determined to be aggravating as aggravating term factors, and using the term factors determined to be mitigating as mitigating term factors.

[0079] In one embodiment, a target penalty method corresponding to the term factor is selected from the target benchmark penalty method, including: weighted summation of the aggravating term factor and the mitigating term factor to obtain a corresponding weighted factor; when the weighted factor is greater than a preset threshold, the aggravating penalty method in the benchmark penalty method is used as the target penalty method; when the weighted factor is equal to the preset threshold, the intermediate penalty method in the benchmark penalty method is used as the target penalty method; when the weighted factor is less than the preset threshold, the mitigating penalty method in the benchmark penalty method is used as the target penalty method, wherein the time limit of the aggravating penalty method is greater than the time limit of the intermediate penalty method, and the time limit of the intermediate penalty method is greater than the time limit of the mitigating penalty method.

[0080] In one embodiment, determining a target benchmark penalty method corresponding to a target legal event based on a legal knowledge graph also includes: determining whether there are multiple benchmark penalty methods corresponding to the target legal event, and when there are multiple benchmark penalty methods, obtaining the severity of the crime corresponding to the crime fact text, and determining the corresponding target benchmark penalty method according to the severity of the crime.

[0081] In one embodiment, after determining the target benchmark penalty method corresponding to the target legal event based on the legal knowledge graph, the processor also implements the following steps when executing the computer program: determining whether the target benchmark penalty method includes multiple penalty methods, and when the target benchmark penalty method includes multiple penalty methods, executing the steps of obtaining a time limit factor from the crime fact text, and selecting a target penalty method corresponding to the time limit factor from the target benchmark penalty method.

[0082] In one embodiment, after selecting a target penalty method corresponding to a term factor from the target benchmark penalty method, the processor further implements the following steps when executing the computer program: determining whether the target penalty method is a fixed-term imprisonment, and when the target penalty method is a fixed-term imprisonment, determining a target term corresponding to the target penalty method based on the term corresponding to the penalty method.

[0083] In one embodiment, the target term is a specific term in years or a term interval.

[0084] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: obtaining a target legal event determined based on a crime fact text, determining a target benchmark penalty method corresponding to the target legal event based on a legal knowledge graph, the legal knowledge graph containing a correspondence between legal events and benchmark penalty methods, obtaining a time limit factor from the crime fact text, and selecting a target penalty method corresponding to the time limit factor from the target benchmark penalty methods.

[0085] In one embodiment, the term factors include aggravating term factors and mitigating term factors. After obtaining the term factors from the crime fact text, the processor also implements the following steps when executing the computer program: determining the type of each term factor, using the term factors determined to be aggravating as aggravating term factors, and using the term factors determined to be mitigating as mitigating term factors.

[0086] In one embodiment, a target penalty method corresponding to the term factor is selected from the target benchmark penalty method, including: weighted summation of the aggravating term factor and the mitigating term factor to obtain a corresponding weighted factor; when the weighted factor is greater than a preset threshold, the aggravating penalty method in the benchmark penalty method is used as the target penalty method; when the weighted factor is equal to the preset threshold, the intermediate penalty method in the benchmark penalty method is used as the target penalty method; when the weighted factor is less than the preset threshold, the mitigating penalty method in the benchmark penalty method is used as the target penalty method, wherein the time limit of the aggravating penalty method is greater than the time limit of the intermediate penalty method, and the time limit of the intermediate penalty method is greater than the time limit of the mitigating penalty method.

[0087] In one embodiment, determining a target benchmark penalty method corresponding to a target legal event based on a legal knowledge graph also includes: determining whether there are multiple benchmark penalty methods corresponding to the target legal event, and when there are multiple benchmark penalty methods, obtaining the severity of the crime corresponding to the crime fact text, and determining the corresponding target benchmark penalty method according to the severity of the crime.

[0088] In one embodiment, after determining the target benchmark penalty method corresponding to the target legal event based on the legal knowledge graph, the computer program also implements the following steps when executed by the processor: determining whether the target benchmark penalty method includes multiple penalty methods, and when the target benchmark penalty method includes multiple penalty methods, executing the steps of obtaining a time limit factor from the crime fact text, and selecting a target penalty method corresponding to the time limit factor from the target benchmark penalty method.

[0089] In one embodiment, after selecting a target penalty method corresponding to a term factor from the target benchmark penalty method, the computer program also implements the following steps when executed by the processor: determining whether the target penalty method is a fixed-term imprisonment, and when the target penalty method is a fixed-term imprisonment, determining a target term corresponding to the target penalty method based on the term corresponding to the penalty method.

[0090] In one embodiment, the target term is a specific term in years or a term interval.

[0091] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0092] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0093] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. An information matching method, characterized in that: The method comprises: Obtain the target legal event determined according to the text of the crime facts; Determining a target benchmark penalty method corresponding to the target legal event according to the legal knowledge graph, wherein the legal knowledge graph includes a correspondence between legal events and benchmark penalty methods; Obtaining a time limit factor from the crime fact text, and selecting a target penalty method corresponding to the time limit factor from the target benchmark penalty methods; The determining of the target benchmark penalty method corresponding to the target legal event according to the legal knowledge graph also includes: Determine whether there are multiple benchmark penalty methods corresponding to the target legal event; When there are multiple baseline punishment methods, obtaining the severity of the crime corresponding to the criminal fact text; Determine the corresponding target benchmark punishment method according to the severity of the crime; After determining the target benchmark penalty method corresponding to the target legal event according to the legal knowledge graph, the method further includes: Determining whether the target benchmark penalty method includes multiple penalty methods; When the target benchmark penalty method includes multiple penalty methods, the step of obtaining a time limit factor from the crime fact text and selecting a target penalty method corresponding to the time limit factor from the target benchmark penalty method is entered; The term factor includes a heavier term factor and a lighter term factor. After obtaining the term factor from the crime fact text, the following is also included: Determine the type of each term factor; Adding the term factor with the judgment type of heavier to the term factor of heavier; adding the term factor of which the judgment type is lenient to the lenient term factor; The selecting a target penalty method corresponding to the deadline factor from the target benchmark penalty methods includes: Performing a weighted summation on the heavier deadline factor and the lighter deadline factor to obtain a corresponding weighted factor; When the weighting factor is greater than a preset threshold, the heavier penalty method in the benchmark penalty method is used as the target penalty method; When the weighting factor is equal to the preset threshold, the middle penalty method in the benchmark penalty method is used as the target penalty method; When the weighting factor is less than the preset threshold, the lighter punishment method in the benchmark punishment method is used as the target punishment method, wherein the time limit of the heavier punishment method is greater than the time limit of the intermediate punishment method, and the time limit of the intermediate punishment method is greater than the time limit of the lighter punishment method.

2. The method according to claim 1, characterized in that After selecting the target penalty method corresponding to the deadline factor from the target benchmark penalty method, the method includes: Determine whether the target punishment is a fixed-term imprisonment; When the target punishment method is fixed-term imprisonment, the target term corresponding to the target punishment method is determined according to the term corresponding to the punishment method.

3. The method according to claim 1, characterized in that The target deadline is a specific deadline or an interval deadline.

4. An information matching device, characterized in that: The device comprises: A target legal event acquisition module is used to acquire a target legal event determined according to the crime fact text; A target benchmark penalty method determination module, used to determine a target benchmark penalty method corresponding to the target legal event based on a legal knowledge graph, wherein the legal knowledge graph includes a correspondence between legal events and benchmark penalty methods; A target punishment method determination module is used to obtain a time limit factor from the crime fact text and select a target punishment method corresponding to the time limit factor from the target benchmark punishment methods; The determining of the target benchmark penalty method corresponding to the target legal event according to the legal knowledge graph also includes: Determine whether there are multiple benchmark penalty methods corresponding to the target legal event; When there are multiple baseline punishment methods, obtaining the severity of the crime corresponding to the criminal fact text; Determine the corresponding target benchmark punishment method according to the severity of the crime; After determining the target benchmark penalty method corresponding to the target legal event according to the legal knowledge graph, the method further includes: Determining whether the target benchmark penalty method includes multiple penalty methods; When the target benchmark penalty method includes multiple penalty methods, the step of obtaining a time limit factor from the crime fact text and selecting a target penalty method corresponding to the time limit factor from the target benchmark penalty method is entered; The term factor includes a heavier term factor and a lighter term factor. After obtaining the term factor from the crime fact text, the following is also included: Determine the type of each term factor; Adding the term factor with the judgment type of heavier to the term factor of heavier; adding the term factor of which the judgment type is lenient to the lenient term factor; The selecting a target penalty method corresponding to the deadline factor from the target benchmark penalty methods includes: Performing a weighted summation on the heavier deadline factor and the lighter deadline factor to obtain a corresponding weighted factor; When the weighting factor is greater than a preset threshold, the heavier penalty method in the benchmark penalty method is used as the target penalty method; When the weighting factor is equal to the preset threshold, the middle penalty method in the benchmark penalty method is used as the target penalty method; When the weighting factor is less than the preset threshold, the lighter punishment method in the benchmark punishment method is used as the target punishment method, wherein the time limit of the heavier punishment method is greater than the time limit of the intermediate punishment method, and the time limit of the intermediate punishment method is greater than the time limit of the lighter punishment method.

5. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.