Method, device, storage medium and equipment for identifying false litigation

The method and device for identifying false litigation through attribute and case information profiling improve the accuracy and efficiency of detecting false lawsuits, safeguarding the legal system and stakeholders.

CN112581326BActive Publication Date: 2024-12-06BEIJING GRIDSUM TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN201910943317.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2019-09-30
Publication Date
2024-12-06
Estimated Expiration
2039-09-30

AI Technical Summary

Technical Problem

The increasing number of false civil lawsuits is damaging the legal system, judicial resources, and the concept of fairness and justice, necessitating a method to identify such cases to protect legitimate rights and interests.

Method used

A method and device for identifying false litigation by extracting and constructing attribute and case information profiles using radar charts, comparing them with known false litigation data to output indication information on potential false litigation.

Benefits of technology

Enhances the efficiency and intelligence of identifying false litigation, preventing erroneous court decisions and protecting stakeholders' rights.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112581326B_ABST
    Figure CN112581326B_ABST
Patent Text Reader

Abstract

The present disclosure relates to a method, device, storage medium and equipment for identifying false litigation. The method comprises: first, extracting the attribute information of the target party from the document to be identified, then constructing the attribute portrait of the target party based on the attribute information, and finally, outputting the indication information for indicating whether the target party is a party to the false litigation based on the attribute portrait of the target party and the attribute portrait of the parties to the known false litigation. In this way, the purpose of automatically identifying false litigation or illegal litigation can be achieved, the efficiency of identifying false litigation is improved, and the intelligence of identifying false litigation is improved. In addition, the indication information for indicating whether the target party is a party to the false litigation can also be output to avoid the court from making an erroneous ruling or execution and to ensure the legitimate rights and interests of the stakeholders.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of legal litigation, and in particular, to a method, apparatus, storage medium and device for identifying false litigation. Background Art

[0002] Civil litigation should be an important way for citizens, legal persons and other organizations to safeguard their legitimate rights and interests and resolve disputes. However, in recent years, parties have taken advantage of loopholes in my country's legal system to seek improper benefits and file false lawsuits with the intention of obtaining illegal benefits through the "legal" judgments of the people's courts. The so-called civil false litigation behavior refers to the behavior of one or more parties in a civil lawsuit to make wrong decisions or executions by means of fictitious legal relationships, fabricating case facts, forging and altering evidence, etc., and then seeking illegal benefits or achieving illegal purposes by filing civil lawsuits, arbitration awards, and applying for execution of notarized documents. The increasing number of civil false lawsuits has not only seriously damaged the interests of the state, the collective and others, but also seriously damaged the authority of the judiciary and the concept of fairness and justice, wasted the already limited judicial resources, interfered with the normal working order of the court, and posed a severe challenge to the dignity of the law. Therefore, it is necessary to identify false lawsuits to avoid damaging the legitimate rights and interests of stakeholders. Summary of the invention

[0003] The purpose of the present disclosure is to provide a method, device, storage medium and equipment for identifying false litigation, so as to achieve the purpose of automatically identifying false litigation.

[0004] In order to achieve the above objectives, the present disclosure provides a method for identifying false litigation, comprising:

[0005] Extract the target party's attribute information from the documents to be screened;

[0006] Constructing an attribute profile of the target party according to the attribute information;

[0007] Based on the attribute portrait of the target party and the attribute portraits of parties involved in known false litigation, output indication information indicating whether the target party is a party involved in false litigation.

[0008] Optionally, after outputting the indication information indicating that the target party is a party to a false lawsuit, the method further includes:

[0009] extracting case information from the document to be screened, wherein the case information at least includes legal relations;

[0010] constructing a case information profile based on the case information;

[0011] In the known false litigation documents, construct a false litigation case information profile targeting the target parties and the legal relationship;

[0012] Based on the case information portrait and the false litigation case information portrait, output indication information for indicating whether the case corresponding to the document to be screened is a false litigation case.

[0013] Optionally, the document to be screened is a litigation document, and the case information further includes: litigation purpose and evidence materials;

[0014] The step of constructing a case information profile based on the case information includes:

[0015] A radar chart of the case information is constructed based on the legal relationship, the litigation purpose and the evidentiary materials.

[0016] Optionally, the document to be screened is a judgment document, and the case information further includes: litigation purpose, evidence materials, ruling results and judgment results, and the judgment results include winning or losing;

[0017] The step of constructing a case information profile based on the case information includes:

[0018] A radar chart of the case information is constructed based on the legal relationship, the litigation purpose, the evidence materials, the ruling results and the judgment results.

[0019] Optionally, constructing a false litigation case information profile targeting the target party and the legal relationship in the known false litigation documents includes:

[0020] Determine, from among the known documents of false litigation, the target judgment document of the false litigation corresponding to the target party and the legal relationship;

[0021] According to the target judgment document, determine the parameter value of the legal relationship, the parameter value of the litigation purpose, the average parameter value of the evidence material, the average parameter value of the ruling result, and the winning rate;

[0022] According to the parameter value of the legal relationship, the parameter value of the litigation purpose, the average parameter value of the evidence material, the average parameter value of the ruling result and the winning rate, a radar chart of the false litigation case information portrait is constructed.

[0023] Optionally, outputting indication information indicating whether the target party is a party to a false lawsuit based on the attribute portrait of the target party and the attribute portrait of parties to known false lawsuits includes:

[0024] If there is a portrait matching the attribute portrait of the target party in the attribute portraits of the parties to the false litigation, first indication information is output to indicate that the target party is a party to the false litigation.

[0025] Optionally, the attribute information includes a plurality of features; and outputting indication information indicating whether the target party is a party to a false lawsuit according to the attribute portrait of the target party and the attribute portrait of parties to known false lawsuits includes:

[0026] If there is no profile matching the attribute profile of the target party in the attribute profile of the party to the false litigation, then determining the average value of each feature in the attribute profile of the party to the false litigation;

[0027] For each feature, determining a deviation value of the feature in the attribute profile of the target party from an average value of the feature;

[0028] If there is a feature whose deviation value is less than or equal to the first preset threshold, second indication information is outputted to indicate that the target party is suspected of being a party to a false lawsuit.

[0029] Optionally, the attribute portrait is a radar portrait; and outputting indication information indicating whether the target party is a party to a false lawsuit based on the attribute portrait of the target party and the attribute portraits of parties to known false lawsuits includes:

[0030] If there is no portrait matching the attribute portrait of the target party in the attribute portraits of the parties to the false litigation, determining the area of ​​the attribute portrait of the target party;

[0031] Determine the minimum area deviation value between the area of ​​the attribute portrait of the target party and the area of ​​the attribute portrait of the party to the false litigation;

[0032] If the minimum area deviation value is less than or equal to a second preset threshold, second indication information is outputted to indicate that the target party is suspected of being a party to a false lawsuit.

[0033] A second aspect of the present disclosure provides a device for identifying false litigation, comprising:

[0034] The first extraction module is used to extract the attribute information of the target party from the document to be screened;

[0035] A first construction module, used to construct an attribute portrait of the target party according to the attribute information;

[0036] The first output module is used to output indication information indicating whether the target party is a party to a false lawsuit based on the attribute portrait of the target party and the attribute portraits of parties to known false lawsuits.

[0037] Optionally, the device further comprises:

[0038] A second extraction module is used to extract case information from the document to be screened, wherein the case information at least includes legal relations;

[0039] A second construction module is used to construct a case information portrait based on the case information;

[0040] The third construction module is used to construct a false litigation case information profile targeting the target party and the legal relationship in the known false litigation documents;

[0041] The second output module is used to output indication information indicating whether the case corresponding to the document to be identified is a false litigation case based on the case information portrait and the false litigation case information portrait.

[0042] Optionally, the document to be screened is a litigation document, and the case information further includes: litigation purpose and evidence materials;

[0043] The second construction module is further used to construct a radar chart of the case information based on the legal relationship, the litigation purpose and the evidence materials.

[0044] Optionally, the document to be screened is a judgment document, and the case information further includes: litigation purpose, evidence materials, ruling results and judgment results, and the judgment results include winning or losing;

[0045] The second construction module is further used to construct a radar chart of the case information based on the legal relationship, the litigation purpose, the evidence materials, the ruling results and the judgment results.

[0046] Optionally, the third building block includes:

[0047] The first determination submodule is used to determine, from among the known false litigation documents, a target judgment document of a false litigation corresponding to the target party and the legal relationship;

[0048] A second determination submodule is used to determine the parameter value of the legal relationship, the parameter value of the litigation purpose, the average parameter value of the evidence material, the average parameter value of the ruling result, and the winning rate according to the target judgment document;

[0049] A submodule is constructed to construct a radar chart of the false litigation case information portrait based on the parameter value of the legal relationship, the parameter value of the litigation purpose, the average parameter value of the evidence material, the average parameter value of the ruling result and the winning rate.

[0050] Optionally, the first output module includes:

[0051] The first output submodule is used to output first indication information indicating that the target party is a party to the false litigation if there is a portrait matching the attribute portrait of the target party in the attribute portraits of the parties to the false litigation.

[0052] Optionally, the attribute information includes multiple features; and the first output module includes:

[0053] A third determination submodule is used to determine the average value of each feature in the attribute portrait of the party to the false litigation if there is no portrait matching the attribute portrait of the target party in the attribute portrait of the party to the false litigation;

[0054] A fourth determination submodule is used to determine, for each feature, a deviation value of the feature in the attribute profile of the target party from an average value of the feature;

[0055] The second output submodule is used to output second indication information indicating that the target party is suspected of being a party to a false lawsuit if there is a feature whose deviation value is less than or equal to the first preset threshold.

[0056] Optionally, the attribute portrait is a radar portrait; and the first output module includes:

[0057] A fifth determination submodule, for determining the area of ​​the attribute portrait of the target party if there is no portrait matching the attribute portrait of the target party in the attribute portraits of the parties to the false litigation;

[0058] A sixth determination submodule, for determining a minimum area deviation value between the area of ​​the attribute portrait of the target party and the area of ​​the attribute portrait of the party to the false litigation;

[0059] The third output submodule is used to output second indication information indicating that the target party is suspected of being a party to a false lawsuit if the minimum area deviation value is less than or equal to a second preset threshold.

[0060] The third aspect of the present disclosure provides a storage medium having a program stored thereon, which, when executed by a processor, implements the steps of the method provided in the first aspect of the present disclosure.

[0061] A fourth aspect of the present disclosure provides a device, the device comprising:

[0062] At least one processor, and at least one memory and bus connected to the processor;

[0063] Wherein, the processor and the memory communicate with each other through the bus;

[0064] The processor is used to call the program instructions in the memory to execute the steps of the method provided in the first aspect of the present disclosure.

[0065] Through the above technical solution, first, the attribute information of the target party is extracted from the document to be identified, then, the attribute portrait of the target party is constructed based on the attribute information, and finally, based on the attribute portrait of the target party and the attribute portrait of the parties to the known false litigation, the indication information for indicating whether the target party is a party to the false litigation is output. In this way, the purpose of automatically identifying false litigation or illegal litigation can be achieved, the efficiency of identifying false litigation is improved, and the intelligence of identifying false litigation is improved. In addition, the indication information for indicating whether the target party is a party to the false litigation can also be output to avoid the court from making wrong decisions or executions and to protect the legitimate rights and interests of stakeholders.

[0066] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0068] Figure 1 The present invention is a flowchart of a method for identifying false litigation according to an exemplary embodiment.

[0069] Figure 2 The diagram is a radar chart showing attribute information according to an exemplary embodiment.

[0070] Figure 3 The present invention is a flowchart of a method for identifying false litigation according to another exemplary embodiment.

[0071] Figure 4 The present invention is a block diagram of a device for identifying false litigation according to an exemplary embodiment.

[0072] Figure 5 It is a block diagram of a device according to an exemplary embodiment. DETAILED DESCRIPTION

[0073] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0074] First, the cases and fields that may need to be identified for false litigation are explained. False litigation is mainly concentrated in the fields of private lending, division of marriage property, enterprise bankruptcy and restructuring, real estate demolition, trademark recognition, etc. Specific case types include: private lending cases, property dispute cases where one party in a divorce case is the defendant, property dispute cases where insolvent enterprises, other organizations, and natural persons are the defendants, property dispute cases where state-owned and collective enterprises in restructuring are the defendants, division of property, inheritance, and house sale and purchase contract disputes where natural persons within the demolition area are the litigation subjects, and cases involving the recognition of well-known trademarks.

[0075] Among them, the most common are false litigation cases filed on the grounds of private lending due to disputes involving the division of divorce property. With the change of divorce concepts and the development of social economy, divorce is more common in modern society, and divorce inevitably involves the issue of dividing the common property of husband and wife. As a kind of gratuitous behavior, the cause and behavior of private lending cases can be separated. When the court examines them, the perpetrator generally does not need to fabricate specific reasons for borrowing and objective evidence to prove the existence of the reason. The main evidence in private lending cases is generally a loan note or IOU, which is the easiest for the perpetrator to forge. Therefore, once people encounter divorce litigation or the possibility of divorce, in order to get more property when the marriage relationship is dissolved, they often choose to conspire with relatives and friends to file a false lawsuit on the grounds of private lending.

[0076] In view of this, the present disclosure provides a method, apparatus, storage medium and device for identifying false litigation. Figure 1 FIG. 1 is a flow chart showing a method for identifying false litigation according to an exemplary embodiment. Figure 1 As shown, the method may include the following steps.

[0077] In step 11, attribute information of the target party is extracted from the document to be screened.

[0078] It should be noted that the document to be screened can be a litigation document that has not been tried, or it can be a judgment document formed after trial, and the present disclosure does not make specific limitations on this. However, both litigation documents and judgment documents contain the attribute information of the parties. In addition, using the existing document automatic segmentation model, the screened documents can be accurately segmented to obtain party information segments that include the attribute information of the parties. In this way, the attribute information of the target party can be extracted from the party information segments obtained after segmentation. Among them, the target party can be the plaintiff and / or defendant in the document to be screened.

[0079] In the present disclosure, the party attribute information may include the name, type, and litigation status of the target party included in the document to be screened. If the party type is a natural person, the party attribute information may also include the party's gender, age, occupation, education level, nationality, household registration, place of residence, etc. If the party type is a legal person organization or an unincorporated organization, the party attribute information may also include the party's domicile or business license number or unified social credit code, etc. Litigation status includes plaintiff or defendant.

[0080] Specifically, the attribute information of the target party can be extracted in the following ways:

[0081] In one embodiment, the name, type and litigation status of the target party can be extracted through part of speech, dependency syntactic relationship and named entity recognition technology. For example, as shown in Table 1, [] in Table 1 represents part of speech, () represents dependency syntactic relationship, that is, according to the recognition technology of part of speech and dependency syntactic relationship, the target party status - plaintiff, the target party name - branch of XX Commercial Bank Co., Ltd. can be identified. In addition, according to the named entity recognition technology, it can further identify: plaintiff - role; bank - administrative management classification; branch of XX Commercial Bank Co., Ltd. - organization name.

[0082] Table 1 Name, type and status of the target parties extracted

[0083]

[0084] Among them, n represents nouns, ns represents place names, HED represents core relationships, wp and WP represent symbols, and COO represents parallel relationships.

[0085] In another embodiment, a dictionary can be combed according to the legal mark and matched with the dictionary to extract the date of birth and age of the target party. For example, Table 2 shows a result of extracting the date of birth of the target party, where ADV represents the date. It should be noted that the age [Year] can be obtained according to the formula: age [Year] = date in the document to be screened - date of birth [Year] + 1.

[0086] Table 2 Extraction of the target party’s date of birth

[0087]

[0088]

[0089] In step 12, an attribute profile of the target party is constructed based on the attribute information.

[0090] It should be noted that, usually, the document to be screened includes at least two parties, the plaintiff and the defendant, and in the document to be screened, there is a clear boundary between the location where the plaintiff's information is recorded and the location where the defendant's information is recorded. For example, the plaintiff's information and the defendant's information are recorded in sections. In this way, the status, type, name, gender, age, occupation, education level, nationality, household registration, place of residence, etc. of the parties can be extracted in the same section. After extracting the above attribute information, the name of the target party and other attribute information extracted in the same section are associated and stored. For example, the name of the target party - other attribute information of the target party.

[0091] In this way, after extracting the attribute information of the target party, an attribute profile of the target party can be constructed based on the attribute information.

[0092] Among them, the attribute portrait of the target party can be a radar chart. When constructing a radar chart of the attributes of the target party, the attribute information must first be preprocessed according to preset rules. For example, a standard value of 1 can be set for each attribute, and the identified attribute value can be output based on the deviation between the identified attribute and the standard attribute. For example, if the standard value of the gender attribute "male" is 1, then "-1", "0", etc. are output respectively according to the deviation of the identified attribute information "female" and "none" from the standard value. It should be noted that the above only shows a possible case of setting the standard value to 1. Different values ​​can be set according to actual needs, such as 2, 3, etc.

[0093] Assume that the attribute information of the target party may include status, gender, age, education level and occupation, and the preset parameter value is 1 when the status is "plaintiff", and the preset parameter value is 2 when it is "defendant"; the preset parameter value is 3 when the gender is "male", the preset parameter value is 2 when it is "female", and the preset parameter value is 1 when it is "none"; the preset parameter values ​​are 2, 3 and 1 when the age is "18-30", "31-40" and "41-50" respectively; the preset parameter values ​​are 1, 2, 3 and 4 when the education level is "undergraduate and above", "junior college", "high school" and "junior high school and below" respectively; the preset parameter values ​​are 1, 2, 3, 4 and 5 when the occupation is "scientific research and education", "politics", "manufacturing and production processing", "business management" and "rural agriculture" respectively. When the extracted attribute information of the target party indicates that the target party's status is "plaintiff", gender is "male", age is "18-30", education level is "junior high school and below", and occupation is "rural agriculture", the radar chart of the attribute information created is as follows: Figure 2 shown.

[0094] In step 13, based on the attribute portrait of the target party and the attribute portraits of parties involved in known false litigation, indication information is output to indicate whether the target party is a party involved in false litigation.

[0095] The attribute portrait of the parties to the false litigation is known, and the attribute portrait of the parties to the false litigation can also be a radar chart, and the parameter value rules used when creating the radar chart of the attribute information of the parties to the false litigation are the same as the parameter value rules used when creating the radar chart of the attribute information of the target party. In this way, after creating the radar chart of the attribute information of the target party, it can be determined whether the target party is a party to the false litigation based on the known radar chart of the attribute information of the parties to the false litigation, and output indication information for indicating whether the target party is a party to the false litigation.

[0096] In one embodiment, if there is a portrait matching the attribute portrait of the target party in the attribute portraits of the parties to the false litigation, the first indication information for indicating that the target party is the party to the false litigation is output. In this embodiment, the match can be considered to be consistent, that is, the attribute portrait of the target party can be completely consistent with at least one of the attribute portraits of the parties to the false litigation. In this case, the target party can be considered to be the party to the false litigation. For example, if the above attribute portraits are all radar charts, then the radar chart of the attribute information of the target party completely overlaps with at least one of the radar charts of the attribute information of the parties to the false litigation, and the first indication information can be output so that the judge can further perform subsequent operations based on the first indication information, such as dismissing the lawsuit, or punishing the target party, etc. This disclosure does not make specific limitations on this.

[0097] In another embodiment, the attribute information includes multiple features, for example, name is a feature, gender is a feature, etc. In this case, first, if there is no portrait matching the attribute portrait of the target party in the attribute portrait of the party to the false litigation, the average value of each feature in the attribute portrait of the party to the false litigation is determined, and then, for each feature, the deviation value between the feature in the attribute portrait of the target party and the average value of the feature is determined, and finally, if there is a feature whose deviation value is less than or equal to the first preset threshold, the second indication information for indicating that the target party is suspected to be a party to the false litigation is output.

[0098] Specifically, if there is no portrait that is completely consistent with the attribute portrait of the target party in the attribute portrait of the party to the false lawsuit, it can be further determined whether the target party may be a party to the false lawsuit. In the present disclosure, the average value of each feature in the attribute portrait of the party to the false lawsuit can be further determined, and the parameter value of the feature in the attribute portrait of the target party is compared with the average value of the above feature to determine the deviation value. Among them, the larger the deviation value, the smaller the probability that the target party is a party to the false lawsuit, and the smaller the deviation value, the greater the probability that the target party is a party to the false lawsuit. The deviation value can be the difference between the parameter value of the feature and the average value of the feature, or the ratio of the difference between the parameter value of the feature and the average value of the feature to the average value of the feature, and so on. The present disclosure does not make specific restrictions on this. In addition, the first preset threshold value is a preset value, which can be, for example, a numerical value of 2, 4, or a ratio of 5%, 10%, etc., and the present disclosure does not make specific restrictions on this.

[0099] For example, taking age characteristics as an example, the parameter value of age in the attribute portrait of each party to a false lawsuit is determined respectively, and all the determined age parameter values ​​are averaged to obtain the average value of the age characteristics. The deviation value is determined based on the parameter value of the age characteristic in the attribute portrait of the target party and the average value of the above age characteristics.

[0100] According to the above method, the average value of each feature included in the attribute portrait of the party to the false litigation can be calculated respectively, and the parameter value of each feature in the attribute portrait of the target party and the deviation value of the average value of the feature can be calculated respectively. If there is at least one feature whose deviation value is less than or equal to the first preset threshold value among the multiple deviation values, it indicates that the target party may be a party to the false litigation, or it indicates that the risk of the target party being a party to the false litigation is relatively high. Therefore, in this case, the second indication information is output to inform the judge that the target party is suspected to be a party to the false litigation.

[0101] In another embodiment, the attribute portrait is a radar portrait. Specifically, if there is no portrait matching the attribute portrait of the target party among the attribute portraits of the parties to the false litigation, the area of ​​the attribute portrait of the target party is determined; the minimum area deviation value between the area of ​​the attribute portrait of the target party and the area of ​​the attribute portrait of the parties to the false litigation is determined; if the minimum area deviation value is less than or equal to a second preset threshold value, second indication information is output to indicate that the target party is suspected to be a party to the false litigation.

[0102] Specifically, the above attribute portrait is a radar portrait, such as Figure 2As shown, the radar image is a closed figure, and the area of ​​the closed figure can be calculated. Therefore, in the present disclosure, the area of ​​the attribute portrait (radar map) of each party to the false litigation and the area of ​​the attribute portrait (radar map) of the target party can be calculated respectively, and the minimum area deviation value between the area of ​​the attribute portrait (radar map) of the target party and the area of ​​the attribute portrait of the known party to the false litigation is determined. Similarly, the larger the area deviation value, the smaller the probability that the target party is a party to the false litigation, and the smaller the area deviation value, the greater the probability that the target party is a party to the false litigation. The area deviation value can be the difference between the area of ​​the attribute portrait (radar map) of the target party and the area of ​​the attribute portrait (radar map) of the known party to the false litigation, or it can be the ratio of the difference between the area of ​​the attribute portrait (radar map) of the target party and the area of ​​the attribute portrait (radar map) of the party to the false litigation to the area of ​​the attribute portrait (radar map) of the party to the false litigation, etc., and the present disclosure does not make specific restrictions on this. In addition, the second preset threshold is a preset value, which may be, for example, a numerical value such as 2 or 4, or a ratio such as 5% or 10%, and the present disclosure does not make any specific limitation on this.

[0103] In addition, the present disclosure only shows the above three situations of outputting indication information. In practical applications, other situations of outputting indication information are also applicable to the present disclosure.

[0104] By adopting the above technical solution, first, the attribute information of the target party is extracted from the document to be identified, then, the attribute profile of the target party is constructed based on the attribute information, and finally, based on the attribute profile of the target party and the attribute profile of the parties to the known false litigation, the indication information for indicating whether the target party is a party to the false litigation is output. In this way, the purpose of automatically identifying false litigation or illegal litigation can be achieved, the efficiency of identifying false litigation is improved, and the intelligence of identifying false litigation is improved. In addition, the indication information for indicating whether the target party is a party to the false litigation can also be output to avoid the court from making an erroneous ruling or execution and to protect the legitimate rights and interests of the stakeholders.

[0105] In addition, in addition to identifying whether the target party is a party to a false lawsuit based on the party's attribute profile, it is also possible to further identify whether the case corresponding to the document to be identified is a false lawsuit case based on the case information profile created based on the case information. Figure 3 As shown, after outputting the indication information for indicating that the target party is a party to a false lawsuit, the method may further include the following steps.

[0106] In step 14, case information is extracted from the document to be screened, and the case information at least includes the legal relationship.

[0107] It should be noted that the existing document automatic segmentation model can be used to accurately segment the identified documents. In addition to the above-mentioned party information segment, the case information segment can also be obtained. In this way, the case information of the case can be extracted from the case information segment, and the case information at least includes the legal relationship, where the legal relationship can be a private loan dispute, a property dispute case in which one party in a divorce case is the defendant, and so on.

[0108] For example, the legal relationship and region (determined by the name of the court) can be named as an entity respectively through a dictionary, and the legal relationship and region can be extracted using entity recognition technology. Among them, the region can be matched according to the three-level dictionary table and output as "region = province-city-county"; the evidence segment in the case information segment can also be located to extract the evidence materials submitted by the target party, match them with the evidence dictionary table, and associate the extracted evidence group with the target party, and output and store the content as "party name-litigation status-evidence group", etc. The purpose of the litigation can also be identified through word segmentation, NLP (Natural Language Processing), semantic role type and other methods, among which the types of the purpose of the litigation are mainly divided into the following three types: obtaining illegal benefits, circumventing legal obligations and damaging legitimate rights and interests. In this disclosure, case information and the specific method of extracting case information are not limited.

[0109] In step 15, a case information profile is constructed based on the case information.

[0110] Among them, the case information portrait can also be a radar chart, and the method of creating a radar chart of case information based on case information is similar to the method of creating a radar chart of attribute information based on attribute information, which will not be repeated here.

[0111] It should be noted that the method for identifying false litigation provided by the present disclosure can be applied in the scenario before the judge's trial to assist the judge in trying the litigation, and can also be applied in the scenario after the judge's trial to achieve the purpose of verifying the trial results, etc.

[0112] In one embodiment, the method for identifying false litigation is applied in a scenario before a judge conducts a trial. In this scenario, the document to be identified may be a litigation document. Considering that a litigation document mainly includes the attribute information of the parties, the legal relationship of the case, the purpose of the litigation, and the evidence materials provided, when the document to be identified is a litigation document, the extracted case information may include the legal relationship, the purpose of the litigation, and the evidence materials. That is, the specific implementation method of constructing a case information portrait based on case information may be: constructing a radar chart of case information based on the legal relationship, the purpose of the litigation, and the evidence materials.

[0113] For example, the parameter values ​​of the legal relationships of "private lending disputes", "property dispute cases in which one party to a divorce case is the defendant" and "contract dispute cases" can be set to 3, 2 and 1 respectively; the parameter values ​​of the litigation purposes of "obtaining illegal benefits", "circumventing legal obligations" and "damaging legitimate rights and interests" can be set to 3, 2 and 1 respectively; the parameter values ​​of the evidence materials of "complete" and "incomplete" can be set to 3 and 1 respectively, and so on. According to the parameter values ​​set above, a radar chart of the case information is constructed. It should be noted that the present disclosure only shows one possible way of setting parameter values, and other ways of setting parameter values ​​are also applicable to the present disclosure.

[0114] In another embodiment, the method for identifying false litigation is applied in a scenario after the judge's trial. In this scenario, the document to be identified can be a judgment document. Considering that the judgment document mainly includes the attribute information of the parties, the legal relationship of the case, the purpose of the litigation and the evidence materials provided, it also includes the ruling result and the judgment result, wherein the ruling result may include support, non-support, partial support, and so on. The judgment result includes winning or losing the case. Therefore, when the document to be identified is a judgment document, the extracted case information may include the legal relationship, the purpose of the litigation, the evidence materials, the ruling result and the judgment result. That is, the specific implementation method of constructing the case information portrait according to the case information can be: constructing a radar chart of the case information according to the legal relationship, the purpose of the litigation, the evidence materials, the ruling result and the judgment result. Among them, the radar chart of the case information is still constructed according to the preset parameter values. The specific construction process refers to the method described in the previous text, which will not be repeated this time. It should be noted that in this disclosure, the parameter value of the judgment result of winning is set to 1, and the parameter value of the judgment result of losing is set to 0.

[0115] In addition, in practical applications, the judgment result may also include a partial victory. For the convenience of description, this disclosure only takes the judgment result including a victory or a defeat as an example for explanation.

[0116] In another embodiment, for the same litigation case, the method for identifying false litigation can also be applied in the scenario before the judge's trial and in the scenario after the judge's trial. The specific implementation method is as described above and will not be repeated here.

[0117] In step 16, a false litigation case information profile is constructed for the target parties and legal relationships in the known false litigation documents.

[0118] Specifically, first, among the known false litigation documents, the target judgment document of the false litigation corresponding to the target party and the legal relationship is determined. For example, assuming that the target party is Mr. Wang and the type of legal relationship is "private loan dispute", among the known massive false litigation documents, the target judgment document of the false litigation whose party is Mr. Wang and the type of legal relationship is "private loan dispute" is determined.

[0119] Next, according to the target judgment document determined above, the parameter value of the legal relationship, the parameter value of the litigation purpose, the average parameter value of the evidence material, the average parameter value of the ruling result, and the winning rate are determined. Among them, the target judgment document determined above can be one or more. When there is one target judgment document, it is only necessary to determine the parameter value of the legal relationship, the parameter value of the litigation purpose, the parameter value of the evidence material, the parameter value of the ruling result, and the winning rate of 0 or 1 from one target judgment document. Finally, a radar chart of the false litigation case information portrait for the target parties and legal relationships is constructed based on the parameter values ​​and winning rate values ​​determined above.

[0120] When there are multiple target judgment documents, since the multiple target judgment documents are determined based on the same legal relationship, the legal relationship and litigation purpose of the multiple target judgment documents are the same, that is, the parameter values ​​of the legal relationship and the parameter values ​​of the litigation purpose in the multiple target judgment documents are also the same, and only one parameter value of the legal relationship and one parameter value of the litigation purpose need to be extracted. However, for different judgment documents, the completeness of the evidence materials and the ruling results included are different, so it is necessary to determine the parameter values ​​of the evidence materials and the parameter values ​​of the ruling results in each target judgment document respectively, and calculate the average parameter value of the evidence materials and the average parameter value of the ruling results. In addition, it is also necessary to count the number of wins in the multiple target judgment documents and then determine the winning rate. It should be noted that the determined winning rate can be directly set as its parameter value. For example, if the calculated winning rate is 0.8, then its corresponding parameter value is 0.8, and if the winning rate is 0.6, its corresponding parameter value is 0.6, and so on. Finally, according to the parameter values ​​of the legal relationship, the parameter values ​​of the litigation purpose, the average parameter values ​​of the evidence materials, the average parameter values ​​of the ruling results and the winning rate, a radar chart of the information portrait of false litigation cases is constructed.

[0121] In step 17, based on the case information portrait and the false litigation case information portrait, indication information is output to indicate whether the case corresponding to the document to be screened is a false litigation case.

[0122] Specifically, the case information portrait constructed in step 15 and the false litigation case information portrait constructed in step 16 can be compared. If the two portraits are relatively similar, such as the difference between the parameter value of the evidence material and the average parameter value of the evidence material is small, the difference between the parameter value of the ruling result and the average parameter value of the ruling result is small, and the judgment result in the document to be screened is consistent with the winning rate in the false litigation case information portrait (for example, the winning rate in the false litigation case information portrait is 0.1, and the judgment result in the document to be screened is a losing case), etc. At this time, it can be determined that the case corresponding to the document to be screened is a false litigation case, and the first indication information for indicating that the case is a false litigation case information is output, and when the two portraits are greatly different, the second indication information for indicating that the case is not a false litigation case information is output. Among them, according to actual needs, by setting the difference between the parameter value and the tie parameter value and the size of the threshold, it can be determined whether the case corresponding to the document to be screened is a false litigation case, and this is not specifically limited in the present disclosure.

[0123] In addition, the accuracy of the judgment result in the document to be screened can be further reviewed based on the winning rate in the false litigation case information portrait. For example, if the winning rate in the false litigation case information portrait is 0.1 and the judgment result in the document to be screened is winning, the third indication information can be output to allow the judge to confirm again whether the judgment result is accurate.

[0124] By adopting the above technical scheme, after determining that the target party is a party to a false lawsuit, it is possible to further determine whether the case corresponding to the document to be identified is a false lawsuit case through the case information portrait. In this way, the accuracy of false litigation identification can be improved. In addition, since a false litigation case information portrait is constructed for the target party and the legal relationship, the number of constructed case information images is reduced, and the number of images compared when determining whether a case is a false lawsuit is smaller, thereby improving the rate of identifying false litigation.

[0125] Based on the same inventive concept, the present disclosure also provides a device for identifying false litigation. Figure 4 FIG. 1 is a block diagram of a device for identifying false litigation according to an exemplary embodiment. Figure 4 As shown, the device 40 may include:

[0126] The first extraction module 41 is used to extract the attribute information of the target party from the document to be screened;

[0127] A first constructing module 42, configured to construct an attribute profile of the target party according to the attribute information;

[0128] The first output module 43 is used to output indication information indicating whether the target party is a party to a false lawsuit based on the attribute portrait of the target party and the attribute portraits of parties to known false lawsuits.

[0129] Optionally, the device may further include:

[0130] A second extraction module is used to extract case information from the document to be screened, wherein the case information at least includes legal relations;

[0131] A second construction module is used to construct a case information portrait based on the case information;

[0132] The third construction module is used to construct a false litigation case information profile targeting the target party and the legal relationship in the known false litigation documents;

[0133] The second output module is used to output indication information indicating whether the case corresponding to the document to be identified is a false litigation case based on the case information portrait and the false litigation case information portrait.

[0134] Optionally, the document to be screened is a litigation document, and the case information further includes: litigation purpose and evidence materials;

[0135] The second construction module is further used to construct a radar chart of the case information based on the legal relationship, the litigation purpose and the evidence materials.

[0136] Optionally, the document to be screened is a judgment document, and the case information further includes: litigation purpose, evidence materials, ruling results and judgment results, and the judgment results include winning or losing;

[0137] The second construction module is further used to construct a radar chart of the case information based on the legal relationship, the litigation purpose, the evidence materials, the ruling results and the judgment results.

[0138] Optionally, the third building block may include:

[0139] The first determination submodule is used to determine, from among the known false litigation documents, a target judgment document of a false litigation corresponding to the target party and the legal relationship;

[0140] A second determination submodule is used to determine the parameter value of the legal relationship, the parameter value of the litigation purpose, the average parameter value of the evidence material, the average parameter value of the ruling result, and the winning rate according to the target judgment document;

[0141] A submodule is constructed to construct a radar chart of the false litigation case information portrait based on the parameter value of the legal relationship, the parameter value of the litigation purpose, the average parameter value of the evidence material, the average parameter value of the ruling result and the winning rate.

[0142] Optionally, the first output module 43 may include:

[0143] The first output submodule is used to output first indication information indicating that the target party is a party to the false litigation if there is a portrait matching the attribute portrait of the target party in the attribute portraits of the parties to the false litigation.

[0144] Optionally, the attribute information includes multiple features; the first output module 43 may include:

[0145] A third determination submodule is used to determine the average value of each feature in the attribute portrait of the party to the false litigation if there is no portrait matching the attribute portrait of the target party in the attribute portrait of the party to the false litigation;

[0146] A fourth determination submodule is used to determine, for each feature, a deviation value of the feature in the attribute profile of the target party from an average value of the feature;

[0147] The second output submodule is used to output second indication information indicating that the target party is suspected of being a party to a false lawsuit if there is a feature whose deviation value is less than or equal to the first preset threshold.

[0148] Optionally, the attribute portrait is a radar portrait; the first output module 43 may include:

[0149] A fifth determination submodule, for determining the area of ​​the attribute portrait of the target party if there is no portrait matching the attribute portrait of the target party in the attribute portraits of the parties to the false litigation;

[0150] A sixth determination submodule, for determining a minimum area deviation value between the area of ​​the attribute portrait of the target party and the area of ​​the attribute portrait of the party to the false litigation;

[0151] The third output submodule is used to output second indication information indicating that the target party is suspected of being a party to a false lawsuit if the minimum area deviation value is less than or equal to a second preset threshold.

[0152] The device for identifying false litigation includes a processor and a memory. The above-mentioned first extraction module, first construction module, first output module, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0153] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and false lawsuits can be identified by adjusting kernel parameters.

[0154] An embodiment of the present invention provides a storage medium on which a program is stored. When the program is executed by a processor, the method for identifying false litigation is implemented.

[0155] An embodiment of the present invention provides a processor, which is used to run a program, wherein the method for identifying false litigation is executed when the program is running.

[0156] An embodiment of the present invention provides a device, such as Figure 5 As shown, the device 50 includes at least one processor 501, at least one memory 502 connected to the processor 501, and a bus 503; wherein the processor 501 and the memory 502 communicate with each other through the bus 503; the processor is used to call the program instructions in the memory to execute the above-mentioned method for identifying false litigation. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0157] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing the following method steps:

[0158] Extract the attribute information of the target party from the documents to be screened;

[0159] Constructing an attribute profile of the target party according to the attribute information;

[0160] Based on the attribute portrait of the target party and the attribute portraits of parties involved in known false litigation, output indication information indicating whether the target party is a party involved in false litigation.

[0161] Optionally, after outputting the indication information indicating that the target party is a party to a false lawsuit, the method further includes:

[0162] extracting case information from the document to be screened, wherein the case information at least includes legal relations;

[0163] constructing a case information profile based on the case information;

[0164] In the known false litigation documents, construct a false litigation case information profile targeting the target parties and the legal relationship;

[0165] Based on the case information portrait and the false litigation case information portrait, output indication information for indicating whether the case corresponding to the document to be screened is a false litigation case.

[0166] Optionally, the document to be screened is a litigation document, and the case information further includes: litigation purpose and evidence materials;

[0167] The step of constructing a case information profile based on the case information includes:

[0168] A radar chart of the case information is constructed based on the legal relationship, the litigation purpose and the evidentiary materials.

[0169] Optionally, the document to be screened is a judgment document, and the case information further includes: litigation purpose, evidence materials, ruling results and judgment results, and the judgment results include winning or losing;

[0170] The step of constructing a case information profile based on the case information includes:

[0171] A radar chart of the case information is constructed based on the legal relationship, the litigation purpose, the evidence materials, the ruling results and the judgment results.

[0172] Optionally, constructing a false litigation case information profile targeting the target party and the legal relationship in the known false litigation documents includes:

[0173] Determine, from among the known documents of false litigation, the target judgment document of the false litigation corresponding to the target party and the legal relationship;

[0174] According to the target judgment document, determine the parameter value of the legal relationship, the parameter value of the litigation purpose, the average parameter value of the evidence material, the average parameter value of the ruling result, and the winning rate;

[0175] According to the parameter value of the legal relationship, the parameter value of the litigation purpose, the average parameter value of the evidence material, the average parameter value of the ruling result and the winning rate, a radar chart of the false litigation case information portrait is constructed.

[0176] Optionally, outputting indication information indicating whether the target party is a party to a false lawsuit based on the attribute portrait of the target party and the attribute portrait of parties to known false lawsuits includes:

[0177] If there is a portrait matching the attribute portrait of the target party in the attribute portraits of the parties to the false litigation, first indication information is output to indicate that the target party is a party to the false litigation.

[0178] Optionally, the attribute information includes a plurality of features; and outputting indication information indicating whether the target party is a party to a false lawsuit according to the attribute portrait of the target party and the attribute portrait of parties to known false lawsuits includes:

[0179] If there is no profile matching the attribute profile of the target party in the attribute profile of the party to the false litigation, then determining the average value of each feature in the attribute profile of the party to the false litigation;

[0180] For each feature, determining a deviation value of the feature in the attribute profile of the target party from an average value of the feature;

[0181] If there is a feature whose deviation value is less than or equal to the first preset threshold, second indication information is outputted to indicate that the target party is suspected of being a party to a false lawsuit.

[0182] Optionally, the attribute portrait is a radar portrait; and outputting indication information indicating whether the target party is a party to a false lawsuit based on the attribute portrait of the target party and the attribute portraits of parties to known false lawsuits includes:

[0183] If there is no portrait matching the attribute portrait of the target party in the attribute portraits of the parties to the false litigation, determining the area of ​​the attribute portrait of the target party;

[0184] Determine the minimum area deviation value between the area of ​​the attribute portrait of the target party and the area of ​​the attribute portrait of the party to the false litigation;

[0185] If the minimum area deviation value is less than or equal to a second preset threshold, second indication information is outputted to indicate that the target party is suspected of being a party to a false lawsuit.

[0186] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0187] In a typical configuration, the device includes one or more processors (CPU), memory and bus. The device may also include input / output interface, network interface and the like.

[0188] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.

[0189] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0190] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0191] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0192] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for identifying false litigation. It is characterized in that include: Extract the attribute information of the target party from the documents to be screened; Constructing an attribute profile of the target party according to the attribute information; Outputting indication information indicating whether the target party is a party to a false lawsuit based on the attribute portrait of the target party and the attribute portraits of parties to known false lawsuits; After outputting the indication information for indicating that the target party is a party to a false lawsuit, the method further includes: extracting case information from the document to be screened, wherein the case information at least includes legal relations; constructing a case information profile based on the case information; In the known false litigation documents, construct a false litigation case information profile targeting the target parties and the legal relationship; Based on the case information portrait and the false litigation case information portrait, output indication information for indicating whether the case corresponding to the document to be screened is a false litigation case.

2. The method according to claim 1, It is characterized in that The document to be screened is a litigation document, and the case information also includes: litigation purpose and evidence materials; The step of constructing a case information profile based on the case information includes: A radar chart of the case information is constructed based on the legal relationship, the litigation purpose and the evidentiary materials.

3. The method according to claim 1, It is characterized in that The document to be screened is a judgment document, and the case information also includes: litigation purpose, evidence materials, ruling results and judgment results, and the judgment results include winning or losing; The step of constructing a case information profile based on the case information includes: A radar chart of the case information is constructed based on the legal relationship, the litigation purpose, the evidence materials, the ruling results and the judgment results.

4. The method according to claim 3, It is characterized in that The method of constructing a false litigation case information profile targeting the target party and the legal relationship in the known false litigation documents includes: Determine, from among the known documents of false litigation, the target judgment document of the false litigation corresponding to the target party and the legal relationship; According to the target judgment document, determine the parameter value of the legal relationship, the parameter value of the litigation purpose, the average parameter value of the evidence material, the average parameter value of the ruling result, and the winning rate; According to the parameter value of the legal relationship, the parameter value of the litigation purpose, the average parameter value of the evidence material, the average parameter value of the ruling result and the winning rate, a radar chart of the false litigation case information portrait is constructed.

5. The method according to claim 1, It is characterized in that The outputting, based on the attribute portrait of the target party and the attribute portrait of the parties to the known false litigation, indication information for indicating whether the target party is a party to the false litigation comprises: If there is a portrait matching the attribute portrait of the target party in the attribute portraits of the parties to the false litigation, first indication information is output to indicate that the target party is a party to the false litigation.

6. The method according to claim 5, It is characterized in that The attribute information includes a plurality of features; the outputting, based on the attribute portrait of the target party and the attribute portrait of the parties to the known false litigation, indication information for indicating whether the target party is a party to the false litigation includes: If there is no profile matching the attribute profile of the target party in the attribute profile of the party to the false litigation, then determining the average value of each feature in the attribute profile of the party to the false litigation; For each feature, determining a deviation value of the feature in the attribute profile of the target party from an average value of the feature; If there is a feature whose deviation value is less than or equal to the first preset threshold, second indication information is outputted to indicate that the target party is suspected of being a party to a false lawsuit.

7. A device for identifying false litigation, It is characterized in that include: The first extraction module is used to extract the attribute information of the target party from the document to be screened; A first construction module, used to construct an attribute portrait of the target party according to the attribute information; A first output module, configured to output indication information indicating whether the target party is a party to a false lawsuit based on the attribute portrait of the target party and the attribute portraits of parties to known false lawsuits; A second extraction module is used to extract case information from the document to be screened, wherein the case information at least includes legal relations; A second construction module is used to construct a case information portrait based on the case information; The third construction module is used to construct a false litigation case information profile targeting the target party and the legal relationship in the known false litigation documents; The second output module is used to output indication information indicating whether the case corresponding to the document to be identified is a false litigation case based on the case information portrait and the false litigation case information portrait.

8. A computer-readable storage medium having a computer program stored thereon, It is 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 6 are implemented.

9. A computer device, It is characterized in that The computer device comprises: At least one processor, and at least one memory and bus connected to the processor; Wherein, the processor and the memory communicate with each other through the bus; The processor is used to call the program instructions in the memory to execute the steps of the method in any one of claims 1-6.