A lawsuit-related information recommendation method and device, and a storage medium

Abstract

The embodiment of the specification discloses a kind of related information recommendation method, device and storage medium of prosecution case, the method includes: inputting the complaint of prosecution case;The content of the complaint is segmented, and the cause information and criminal fact information of the prosecution case are structured and parsed;Filter the same case information as the cause information from the case knowledge base;The first similarity of the criminal fact information and the case information is calculated;The case information with the first similarity higher than the first preset threshold is used as the first recommended information of the prosecution case.This scheme can reduce the query workload of the related information of prosecution case, improve the efficiency of prosecutor's case handling, and also improve the accuracy of information recommendation.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus and storage medium for recommending relevant information in a lawsuit. Background Technology

[0002] During the handling of a case, prosecutors need to prepare a court appearance plan before the trial. This plan includes preparing applicable laws and regulations, expert opinions, points of contention, and key points for rebuttal. Currently, various case-handling tools generally allow for the search of similar cases.

[0003] However, similar case information lacks relevant information such as applicable laws and regulations, expert opinions, points of contention, and key points for defense. When preparing court appearance plans, prosecutors still need to consult relevant materials to compile the above information, which takes a lot of time and cannot guarantee accuracy. Summary of the Invention

[0004] In view of this, embodiments of this application provide a method, apparatus, and storage medium for recommending relevant information in prosecution cases, which reduces the workload of querying relevant information, improves accuracy, and enhances the efficiency of prosecutors in handling cases.

[0005] To solve the above-mentioned technical problems, the embodiments in this specification are implemented as follows:

[0006] A method for recommending relevant information in a lawsuit, the method comprising:

[0007] Enter the indictment for the case being filed;

[0008] The contents of the indictment are segmented and structured to extract the cause of action and facts of the crime.

[0009] Filter case information that is identical to the stated cause of action information from the case knowledge base;

[0010] Calculate the first similarity between the crime fact information and the case information;

[0011] Case information with a similarity higher than a first preset threshold is used as the first recommended information for the prosecution case.

[0012] Optionally, the method further includes:

[0013] Filter out laws and regulations that are identical to the stated cause of action from the case knowledge base;

[0014] Calculate the second similarity between the criminal fact information and the legal regulations;

[0015] The laws and regulations with a similarity higher than a second preset threshold are used as the second recommended information for the lawsuit.

[0016] Optionally, the method further includes:

[0017] Filter expert opinions from the case knowledge base that are identical to the stated cause of action information;

[0018] Calculate the third similarity between the stated crime facts and the expert opinion;

[0019] The expert opinions with a third similarity higher than a third preset threshold are used as the third recommended information for the prosecuted case.

[0020] Optionally, the method further includes:

[0021] Select the points of contention and key points of defense that are identical to the stated cause of action information from the case knowledge base;

[0022] Calculate the fourth similarity between the criminal fact information and the disputed issue.

[0023] The points of contention and key points of response with a fourth similarity higher than a fourth preset threshold are used as the fourth recommended information for the lawsuit.

[0024] Optionally, the case information includes: case ID, cause of action information, and facts of the crime, wherein the facts of the crime and the cause of action information have a one-to-one relationship.

[0025] Optionally, the laws and regulations include: law and regulation ID, case information, and law and regulation content, wherein the case information and laws and regulations have a one-to-many relationship.

[0026] Optionally, the expert opinion includes: expert opinion ID, case information, and expert opinion content, wherein the case information and the expert opinion content have a one-to-many relationship.

[0027] Optionally, the points of contention include: a point of contention ID, case information, content of the point of contention, and key points of the response, wherein the case information and the content of the point of contention have a one-to-many relationship; and the content of the point of contention and the key points of the response have a one-to-one relationship.

[0028] A device for recommending information related to a lawsuit, the device comprising:

[0029] The input module is used to input the indictment for a lawsuit.

[0030] The parsing module is used to segment the contents of the indictment and parse out the cause of action and facts of the crime in a structured manner.

[0031] The filtering module is used to filter case information that is the same as the cause of action information from the case knowledge base;

[0032] The similarity calculation module is used to calculate the first similarity between the crime fact information and the case information;

[0033] The recommendation module is used to select case information with a first similarity higher than a first preset threshold as the first recommended information for the case to be prosecuted.

[0034] A storage medium storing computer-readable instructions that can be executed by a processor to implement the aforementioned method for recommending information related to a prosecution case. The at least one technical solution employed in the embodiments of this specification can achieve the following beneficial effects:

[0035] By calculating the similarity between the input indictment and case information in the knowledge base, the similarity score of two cases is determined. Similar cases are then recommended based on their similarity scores. Simultaneously, relevant information such as applicable laws and regulations, expert opinions, points of contention, and key points for defense are also recommended. This solution reduces the workload of searching for relevant information for indicted cases, improves prosecutors' efficiency, and enhances the accuracy of information recommendations. Attached Figure Description

[0036] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0037] Figure 1 A flowchart illustrating a method for recommending relevant information for a lawsuit, provided as an embodiment of this specification;

[0038] Figure 2 The embodiments provided in this specification correspond to Figure 1 A schematic diagram of a device for recommending information related to a lawsuit. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0040] To address the aforementioned issues, this application aims to provide a method, apparatus, electronic device, and storage medium for calculating the similarity of case indictments. By calculating the similarity between the input indictment and case information in a knowledge base, the similarity score between two cases is determined. Similar cases are then recommended based on their similarity scores, along with applicable laws and regulations, expert opinions, points of contention, and key points for defense. This method can serve as an auxiliary tool for developing courtroom response plans, reducing the workload of searching for relevant information and improving the efficiency of prosecutors.

[0041] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0042] Figure 1 This is a flowchart illustrating a method for recommending relevant information for a lawsuit, as provided in an embodiment of this specification.

[0043] like Figure 1 As shown, the process may include the following steps:

[0044] Step 110: Enter the complaint for the case;

[0045] Step 120: Segment the contents of the indictment and parse out the cause of action and facts of the crime in the case in a structured manner;

[0046] Step 130: Filter case information from the case knowledge base that is identical to the stated cause of action information;

[0047] Step 140: Calculate the first similarity between the crime fact information and the case information;

[0048] Step 150: Use the case information with the first similarity higher than the first preset threshold as the first recommended information for the case to be prosecuted.

[0049] In addition, based on the above methods, relevant information such as laws and regulations, expert opinions, points of contention, and key points of defense can be recommended according to the facts of the crime.

[0050] based on Figure 1 In addition to the method described herein, this specification also provides some specific implementation methods of this method, which will be described below.

[0051] Implementation process:

[0052] (I) Knowledge Base

[0053] The knowledge base stores relevant information in four dimensions: case information (facts of the crime), laws and regulations, expert opinions, points of contention, and key points of defense. Each of these four dimensions contains information about the cause of action.

[0054] The facts of the crime and the information about the cause of action are related in a one-to-one manner;

[0055] Case information and laws and regulations have a one-to-many relationship;

[0056] Case information and expert opinions have a one-to-many relationship;

[0057] The cause of action and the points of contention have a one-to-many relationship;

[0058] The points of contention and the key points of the response are related one-to-one.

[0059] Table 1 Case Information

[0060] Case ID Case information criminal facts

[0061] Table 2 Laws and Regulations

[0062] Legal ID Case information Legal and regulatory content

[0063] Table 3 Expert Opinions

[0064] Expert Opinion ID Case information Expert Opinions

[0065] Table 4. Points of Contention

[0066] Controversial Focus ID Case information Controversial Focus Key points for the defense

[0067] (II) Structured Analysis

[0068] A standard complaint format is as follows:

[0069] The defendant, Zou Moumou, male, was sentenced to seven months imprisonment by the XX People's Court on March 10, 2003, for the crime of provoking trouble; he was administratively detained for 15 days by the XX Branch Bureau on December 13, 1983, for assaulting others and insulting women without cause; he was administratively detained for 7 days by the XX Branch Bureau on February 7, 2004, for disturbing public order; and he was criminally detained by the XX Branch Bureau on September 3, 2015, on suspicion of intentional injury, and was arrested by the XX Branch Bureau on November 5 of the same year with the approval of the XX District People's Procuratorate.

[0070] This case was investigated and concluded by the XX Branch Bureau, and on December 16, 2015, the defendant, Zou Moumou, was suspected of intentional injury and transferred to the XX District People's Procuratorate for review and prosecution. After review, the procuratorate informed the defendant on December 18 of the same year of his right to appoint a defense lawyer, and the victim's close relatives of his right to appoint a litigation agent. The case was submitted to this procuratorate for review and prosecution on January 6, 2016. After accepting the case, this procuratorate interrogated the defendant in accordance with the law, listened to the opinions of the defendant's defense lawyer, and reviewed all case materials.

[0071] After investigation in accordance with the law, it was found that:

[0072] On September 3, 2015, at approximately 3:40 PM, the defendant, Zou Moumou, due to a family dispute near XXX, intercepted an electric bicycle ridden by his sister, the victim Zou Moujia, and Zou Mouyi. He then attacked Zou Moujia and Zou Mouyi with an axe, causing Zou Moujia's immediate death and Zou Mouyi's injuries. An autopsy determined that Zou Moujia died from craniocerebral injury caused by being struck in the head, face, and both upper limbs with a sharp object; Zou Mouyi sustained minor injuries including scalp contusions, scalp wounds, and multiple soft tissue injuries to her limbs from external force.

[0073] At approximately 7:00 PM that day, the defendant, Zou, was apprehended by police officers waiting at the entrance of his temporary residence. Further evaluation revealed that Zou suffers from schizotypal disorder, and in this case, he should be assessed as having limited criminal responsibility, but currently, he should be assessed as having the capacity to stand trial.

[0074] The above facts are proven by the following evidence:

[0075] 1. The statement of the victim Zou Mouyi, the testimonies of witnesses XX et al., the identification records of XX et al., the confession of the defendant Zou Moumou, the "Seizure List" of XX Branch Bureau, and the physical evidence of an axe, etc., prove that: the defendant Zou Moumou used an axe to chop at the victims Zou Moujia and Zou Mouyi, and then threw the axe into the nearby green belt before fleeing the scene.

[0076] 2. Evidence including the "Scene Investigation Record" from the Criminal Science and Technology Research Institute of XX Branch Bureau, the "Appraisal Opinion" from the Forensic Science and Technology Research Institute, the "Appraisal Report" from the Evidence Identification Center of XX Municipal Public Security Bureau, and the "Forensic DNA Identification Report" from the Evidence Identification Center of XX Municipal Public Security Bureau, confirms that: According to the forensic examination, the victim, Zou Jia, died from craniocerebral injury caused by being struck on the head, face, and both upper limbs with a sharp object; the victim, Zou Yi, suffered minor injuries including scalp contusions, scalp wounds, and multiple soft tissue injuries to the limbs due to external force; the possibility that the bloodstains on the inside of the right shoe of the brown leather shoes worn by the defendant, Zou Moumou, were left by Zou Jia cannot be ruled out, and the circumstances of the scene investigation, bloodstain extraction, and identification cannot be ignored.

[0077] 3. Evidence such as the statement of the victim Zou Mouyi, the testimony of witnesses XX et al., the confession of the defendant Zou Moumou, copies of relevant agreements, and the "Certificate" issued by the XX Community Affairs Service Center proves that the defendant Zou Moumou had family conflicts with the victims Zou Mouyi and Zou Moujia.

[0078] 4. Evidence such as the "Investigation Process" issued by the XX Branch Bureau, the "Basic Information of Permanent Residents" and registration form of the defendant Zou Moumou, the "Appraisal Opinion" of the Judicial Appraisal Center of the Institute of Judicial Appraisal Science and Technology, and the "Criminal Judgment" of the XX District People's Court proves that: the defendant Zou Moumou suffers from schizophrenia, has limited criminal responsibility in this case, is currently capable of standing trial, and provides information on his arrival at the scene, his identity, and his prior criminal record.

[0079] The aforementioned evidence was obtained and collected legally, and its content is objective and truthful, sufficient to establish the facts of the charges.

[0080] This court finds that the defendant, Zou, intentionally killed one person and caused minor injury to another. His actions violate Article 232 of the Criminal Law of the People's Republic of China. The facts of the crime are clear, and the evidence is conclusive and sufficient. He should be held criminally liable for intentional homicide. The defendant, Zou, has diminished criminal responsibility and should be subject to Article 18, Paragraph 3 of the Criminal Law of the People's Republic of China. In accordance with Article 172 of the Criminal Procedure Law of the People's Republic of China, this public prosecution is hereby initiated, and a trial is requested in accordance with the law.

[0081] Analyzing the above document reveals that the indictment comprises the following sections: "Defendant Information," "Facts of the Crime," "List of Evidence," and "The Court's Opinion." Based on phrases such as "Defendant," "Upon investigation and verification according to law:," "The above facts are proven by the following evidence:," and "The Court's Opinion," the input indictment can be segmented. After segmentation, the "Cause of Action" and "Facts of the Crime" information of the input case can be structurally parsed.

[0082] (III) Similarity Calculation

[0083] The processing flow is as follows:

[0084] Case Filtering: For cases with a cause of action derived from structured parsing, such as "intentional injury," only relevant information from four dimensions—case information, laws and regulations, expert opinions, points of contention, and key points for defense—is loaded from the knowledge base.

[0085] The similarity of the "criminal facts" obtained from the structured analysis with the content in the knowledge base in four dimensions: criminal facts, laws and regulations, expert opinions, points of contention, and key points of defense.

[0086] Sort the similarity calculation results of the above four dimensions in reverse order and return the sorted results.

[0087] Prosecutors can examine similarities across four dimensions and export the necessary data as supplementary material for developing courtroom response plans.

[0088] Based on the same idea, embodiments of this specification also provide apparatus corresponding to the above methods. Figure 2 The embodiments provided in this specification correspond to Figure 1 A schematic diagram of a device for recommending information related to a lawsuit. (For example...) Figure 2 As shown, the device may include:

[0089] Input module 210 is used to input the indictment for a case being filed;

[0090] The parsing module 220 is used to segment the contents of the indictment and parse out the cause of action and criminal facts of the case in a structured manner.

[0091] The filtering module 230 is used to filter case information that is the same as the cause of action information from the case knowledge base;

[0092] Similarity calculation module 240 is used to calculate the first similarity between the crime fact information and the case information;

[0093] The recommendation module 250 is used to use case information with the first similarity higher than the first preset threshold as the first recommendation information for the prosecution case.

[0094] In some embodiments, the filtering module 230 is further configured to filter laws and regulations that are the same as the cause of action information from the case knowledge base;

[0095] The similarity calculation module 240 is also used to calculate a second similarity between the crime fact information and the laws and regulations;

[0096] The recommendation module 250 is further configured to use laws and regulations with a second similarity higher than a second preset threshold as the second recommendation information for the lawsuit.

[0097] In some embodiments, the filtering module 230 is further configured to filter expert opinions from the case knowledge base that are the same as the cause of action information;

[0098] The similarity calculation module 240 is also used to calculate the third similarity between the crime fact information and the expert opinion;

[0099] The recommendation module 250 is further configured to use expert opinions with a third similarity higher than a third preset threshold as third recommendation information for the prosecuted case.

[0100] In some embodiments, the filtering module 230 is further configured to filter the points of contention and key points of defense that are the same as the cause of action information from the case knowledge base;

[0101] The similarity calculation module 240 is also used to calculate the fourth similarity between the criminal fact information and the points of contention and the key points of defense;

[0102] The recommendation module 250 is further configured to use the disputed points and defense points with a fourth similarity higher than a fourth preset threshold as the fourth recommendation information for the lawsuit.

[0103] Optionally, the case information includes: case ID, cause of action information, and facts of the crime, wherein the facts of the crime and the cause of action information have a one-to-one relationship.

[0104] Optionally, the laws and regulations include: law and regulation ID, case information, and law and regulation content, wherein the case information and laws and regulations have a one-to-many relationship.

[0105] Optionally, the expert opinion includes: expert opinion ID, case information, and expert opinion content, wherein the case information and the expert opinion content have a one-to-many relationship.

[0106] Optionally, the points of contention include: a point of contention ID, case information, content of the point of contention, and key points of the response, wherein the case information and the content of the point of contention have a one-to-many relationship; and the content of the point of contention and the key points of the response have a one-to-one relationship.

[0107] In some embodiments, the device may include:

[0108] The court appearance plan creation module exports the user-selected content from the four types of information mentioned above into a Word document, forming a court appearance plan. Within each type of information, the data is sorted in descending order of similarity.

[0109] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0110] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0111] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A method for recommending relevant information for lawsuits, characterized in that, The method includes: Enter the indictment for the case being filed; The contents of the indictment are segmented and structured to extract the cause of action and facts of the crime. Filter case information that is identical to the stated cause of action information from the case knowledge base; Calculate the first similarity between the crime fact information and the case information; Case information with a similarity higher than a first preset threshold is used as the first recommended information for the prosecution case; Filter out laws and regulations that are identical to the stated cause of action from the case knowledge base; Calculate the second similarity between the criminal fact information and the legal regulations; Laws and regulations with a second similarity higher than a second preset threshold are used as the second recommended information for the prosecution case; Filter expert opinions from the case knowledge base that are identical to the stated cause of action information; Calculate the third similarity between the stated crime facts and the expert opinion; The expert opinions with a third similarity higher than a third preset threshold are used as the third recommendation information for the prosecuted case; Select the points of contention and key points of defense that are identical to the stated cause of action information from the case knowledge base; Calculate the fourth similarity between the criminal fact information and the disputed issue. The points of contention and key points of defense with a fourth similarity higher than a fourth preset threshold are used as the fourth recommended information for the lawsuit. The case information includes: case ID, case details, and facts of the crime, wherein the facts of the crime and the case details have a one-to-one relationship; The laws and regulations mentioned include: law and regulation ID, case information, and law and regulation content, wherein the case information and laws and regulations have a one-to-many relationship; The expert opinion includes: expert opinion ID, case information, and expert opinion content, wherein the case information and the expert opinion content have a one-to-many relationship; The points of contention include: point of contention ID, case information, content of the points of contention, and key points of the response. The case information and the content of the points of contention have a one-to-many relationship, while the content of the points of contention and the key points of the response have a one-to-one relationship.

2. A device for recommending relevant information for prosecution cases, characterized in that, The device includes: The input module is used to input the indictment for a lawsuit. The parsing module is used to segment the contents of the indictment and parse out the cause of action and facts of the crime in a structured manner. The filtering module is used to filter case information that is the same as the cause of action information from the case knowledge base; The similarity calculation module is used to calculate the first similarity between the crime fact information and the case information; The recommendation module is used to use case information with a first similarity higher than a first preset threshold as the first recommended information for the prosecution case; Filter out laws and regulations that are identical to the stated cause of action from the case knowledge base; Calculate the second similarity between the criminal fact information and the legal regulations; Laws and regulations with a second similarity higher than a second preset threshold are used as the second recommended information for the prosecution case; Filter expert opinions from the case knowledge base that are identical to the stated cause of action information; Calculate the third similarity between the stated crime facts and the expert opinion; The expert opinions with a third similarity higher than a third preset threshold are used as the third recommendation information for the prosecuted case; Select the points of contention and key points of defense that are identical to the stated cause of action information from the case knowledge base; Calculate the fourth similarity between the criminal fact information and the disputed issue. The points of contention and key points of defense with a fourth similarity higher than a fourth preset threshold are used as the fourth recommended information for the lawsuit. The case information includes: case ID, case details, and facts of the crime, wherein the facts of the crime and the case details have a one-to-one relationship; The laws and regulations mentioned include: law and regulation ID, case information, and law and regulation content, wherein the case information and laws and regulations have a one-to-many relationship; The expert opinion includes: expert opinion ID, case information, and expert opinion content, wherein the case information and the expert opinion content have a one-to-many relationship; The points of contention include: point of contention ID, case information, content of the points of contention, and key points of the response. The case information and the content of the points of contention have a one-to-many relationship, while the content of the points of contention and the key points of the response have a one-to-one relationship.

3. A storage medium having stored thereon computer-readable instructions that can be executed by a processor to implement the method for recommending relevant information in a prosecution case as described in claim 1.

Images