CN118332455B - Jurisdictional organization identification method and jurisdictional organization identification device - Google Patents
Jurisdictional organization identification method and jurisdictional organization identification device Download PDFInfo
- Publication number
- CN118332455B CN118332455B CN202410758766.XA CN202410758766A CN118332455B CN 118332455 B CN118332455 B CN 118332455B CN 202410758766 A CN202410758766 A CN 202410758766A CN 118332455 B CN118332455 B CN 118332455B
- Authority
- CN
- China
- Prior art keywords
- jurisdictional
- case
- information
- name
- organization
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 80
- 230000008520 organization Effects 0.000 title claims abstract description 80
- 230000033228 biological regulation Effects 0.000 claims abstract description 41
- 238000012549 training Methods 0.000 claims abstract description 25
- 230000008569 process Effects 0.000 claims description 21
- 238000000605 extraction Methods 0.000 claims description 19
- 230000001105 regulatory effect Effects 0.000 claims description 17
- 230000015654 memory Effects 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 14
- 238000002372 labelling Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 230000003542 behavioural effect Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 claims 2
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 230000007246 mechanism Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013145 classification model Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000007474 system interaction Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the field of big data, and provides a jurisdictional organization identification method and device, wherein the model building method comprises the following steps: receiving a case complaint file to be distributed; extracting crime name/case name information and element information from the case complaint files to be distributed by using a pre-established case name/crime name recognition model and element recognition model, wherein the element information comprises address information and jurisdiction level influence information, and the case name/crime name recognition model and the element recognition model are obtained by training historical case complaint files and marked crime names/case names and element information; obtaining a jurisdictional organization by matching information and element information with a pre-established knowledge base by utilizing the crime name/proposal; the knowledge base stores the entity and the relation set among the entity relevant to the jurisdiction in each law and regulation. The application can assist the user to quickly sort the jurisdiction of the cases, save labor cost and time and improve the determination efficiency and accuracy of the jurisdiction organization.
Description
Technical Field
The application belongs to the field of artificial intelligence, and particularly relates to a jurisdictional organization identification method and device.
Background
In the prior art, after the case complaints are submitted, the jurisdiction right recognition modes mainly include the following modes:
One is that before the case is found, the jurisdiction of the case is analyzed and judged by a judicial person, and for the case with the jurisdiction objection or complex case, the judicial person also needs to search the legal application range and the jurisdiction rule from the legal and regulation data, and then determines the case according to the legal application range and the jurisdiction rule. The determination mode of the jurisdiction organization has the problems of low processing efficiency, easy error and labor waste.
An automatic identification method based on XML templates, comprising the following steps: firstly, extracting element information of a target case through a preset XML template; then, judging the jurisdiction rule through the jurisdiction judging module to obtain the region information corresponding to the element information, wherein the jurisdiction rule comprises the case type, the case definition and the custom judgment of the element information; searching jurisdictional information associated with the region information according to the region information; and finally pushing the jurisdictional result information to the user side. In the method, jurisdictional rules are artificial custom judgment rules, and are influenced by human factors, so that jurisdictional objection cases and complex cases are difficult to meet, and the method has the problem of low recognition accuracy.
Another address-based automatic identification method includes: acquiring a case text; carrying out semantic analysis on the case text, obtaining an address element list in the case text, and determining an address processing strategy of the case according to the type of a second address element of the next level of the designated level in the address element list under the condition that the first address element of the designated level is not contained in the address element list; and then, processing the address element list by utilizing a processing strategy to determine the jurisdictional organization of the case. In the method, address element lists are processed by utilizing different processing strategies, and jurisdictional institutions of cases are determined, and if the jurisdictional authorities meet jurisdictional authority objection cases and complex cases, the strategies are manually adjusted, so that relevant jurisdictional authority suggestions cannot be given in real time. Therefore, the method is not suitable for jurisdiction determination of jurisdictional objection cases and complex cases, and the jurisdiction determination has the problems of low efficiency and narrow application range. In addition, the method only takes the case address as the condition of jurisdiction discrimination, but in practice, the jurisdiction is determined only by the case address, so that the problem of one-sided and inaccurate is solved.
Disclosure of Invention
The application is used for solving the problems that the automatic identification method of the jurisdictional organization in the prior art has low accuracy and is not suitable for jurisdictional authority objection cases and complex cases.
In order to solve the above technical problems, an aspect of the present application provides a jurisdictional organization identification method, including:
Receiving a case complaint file to be distributed;
extracting crime name/case name information and element information from the case complaint files to be distributed by using a pre-established case name/crime name recognition model and element recognition model, wherein the element information comprises address information and jurisdiction level influence information, and the case name/crime name recognition model and the element recognition model are obtained by training historical case complaint files and marked crime names/case names and element information;
Obtaining a jurisdictional organization by matching information and element information with a pre-established knowledge base by utilizing the crime name/proposal; the knowledge base stores the entity and the relation set among the entity relevant to the jurisdiction in each law and regulation.
In a further embodiment of the present application, the knowledge base establishment process includes:
Obtaining legal and regulation data;
Segmenting each legal and regulatory data to obtain a plurality of paragraphs of each legal and regulatory data;
Searching jurisdictional keywords for each paragraph of each legal and regulatory data, and determining jurisdictional rule content paragraphs according to search results;
Labeling entities in the jurisdictional rule content paragraphs and relationships among the entities;
and establishing a knowledge base by utilizing the entities of the legal and regulation data and the relation among the entities.
In a further embodiment of the present application, after obtaining the legal and regulatory data, the method further includes:
carrying out format standardization processing on the legal and regulatory data;
And filtering the redundant information of the standardized legal and regulation data, and converting the filtered legal and regulation data into text contents.
In a further embodiment of the present application, labeling entities and relationships between entities in a jurisdictional rule content paragraph includes:
Grouping all jurisdictional rule content paragraphs to obtain a first group of jurisdictional rule content and a second group of jurisdictional rule content;
The receiver marks the entity of the first group of jurisdictional rule content and the association relation between the entities;
training to obtain an entity identification model according to the content of the first group of jurisdiction rules and the marked entity;
Training to obtain a relation extraction model according to the incidence relation between the first group of jurisdictional rule contents and the marked entities;
and identifying the second group of jurisdictional rule contents by the entity identification model and the relation extraction model to obtain the entity and the association relation among the entities of each jurisdictional rule content paragraph in the second group of jurisdictional rule contents.
In a further embodiment of the present application, the method for extracting crime name/case by information and element information from the case complaint file to be distributed by using a pre-established case by/crime name recognition model and element recognition model includes: processing the case complaint file to be distributed by using a regularization expression to obtain head information, tail information and intermediate information;
analyzing each paragraph of the intermediate information by utilizing a paragraph segmentation model to obtain labels of all paragraphs, wherein the paragraph labels comprise principal information paragraphs and case paragraphs;
identifying a case paragraph of the case prosecution file to be distributed by using a case name/crime identification model to obtain crime name/case name information of the case prosecution file to be distributed;
and extracting element information from the principal information paragraphs in the case complaint file to be distributed by using an element identification model.
In a further embodiment of the present application, the address information includes: one or more of principal premises, frequent residence, behavioral, crime outcome, contract fulfillment, corporate premises, transportation origins and destinations, infringement, accident occurrence;
the jurisdictional impact information includes: victims, casualties, target amount of money, and social influence.
In a further embodiment of the present application, after obtaining the jurisdiction, the method further includes:
Determining a level of jurisdiction;
Obtaining the jurisdictional amount standard range of the jurisdictional organization from the knowledge base according to the level of the jurisdictional organization;
judging whether the amount of the object in the case complaint file to be distributed is within the standard range of the jurisdictional amount, if so, outputting the jurisdictional organization, and if not, outputting the jurisdictional organization and sending out manual verification reminding information.
A second aspect of the present application provides a jurisdictional organization identification apparatus comprising:
the receiving unit is used for receiving the file of the case to be distributed;
The recognition unit is used for extracting crime name/case name information and element information from the case complaint files to be distributed by utilizing a pre-established case name/crime name recognition model and element recognition model, wherein the element information comprises address information and jurisdiction level influence information, and the case name/crime name recognition model and the element recognition model are obtained by training historical case complaint files and marked crime name/case names and element information;
The matching unit is used for matching the information and the element information with a pre-established knowledge base to obtain a jurisdictional organization by utilizing the crime name/scheme; the knowledge base stores the entity and the relation set among the entity relevant to the jurisdiction in each law and regulation.
A third aspect of the application provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any of the preceding embodiments when the computer program is executed.
A fourth aspect of the application provides a computer storage medium having stored thereon a computer program which, when executed by a processor of a computer device, implements a method according to any of the preceding embodiments.
A fifth aspect of the application provides a computer program product comprising a computer program which, when executed by a processor of a computer device, implements a method according to any of the preceding embodiments.
According to the jurisdictional organization identification method and device provided by the application, the case complaint file to be distributed is received; extracting crime name/case name information and element information from the case complaint files to be distributed by using a pre-established case name/crime name recognition model and element recognition model, wherein the element information comprises address information and jurisdiction level influence information, and the case name/crime name recognition model and the element recognition model are obtained by training historical case complaint files and marked crime names/case names and element information; obtaining a jurisdictional organization by matching information and element information with a pre-established knowledge base by utilizing the crime name/proposal; the knowledge base stores the relevant entity and the relation set among the entities in each legal regulation, the knowledge base can be determined based on the legal regulations and the jurisdictional organization identification can be performed based on the knowledge base, the jurisdictional rules are prevented from being set by users, the knowledge base can be suitable for the jurisdictional organization determination of various cases, when the jurisdictional organization is determined, the jurisdictional level influence information and the case/criminal name information are considered in addition to the address information, the jurisdictional scope of the cases can be assisted by users to be rapidly arranged, the labor cost and time are saved, and the determination efficiency and accuracy of the jurisdictional organization are improved.
The foregoing and other objects, features and advantages of the application will be apparent from the following more particular description of preferred embodiments, as illustrated in the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 illustrates a schematic diagram of a jurisdictional recognition system in accordance with an embodiment of the present application;
FIG. 2 illustrates a flow chart of a jurisdictional recognition system interaction process of an embodiment of the present application;
FIG. 3A illustrates a flow chart of a jurisdictional organization identification method of an embodiment of the present application;
FIG. 3B is a flow chart illustrating a jurisdictional organization identification method in accordance with an embodiment of the present application;
FIG. 4 is a flow chart illustrating a knowledge base creation process, in accordance with an embodiment of the application;
FIG. 5A is a flowchart showing an entity and an association relationship labeling process between entities according to an embodiment of the present application;
FIG. 5B is a diagram showing an example of a process for recognizing an entity recognition model according to an embodiment of the present application;
FIG. 5C is a diagram showing an example of a relationship extraction model identification process according to an embodiment of the present application;
Fig. 6 is a flowchart showing a crime name/case information and element information extraction process according to an embodiment of the present application;
FIG. 7 is a schematic diagram of a process for segmenting a paragraph using a paragraph segmentation model according to an embodiment of the present application;
FIG. 8 is a schematic diagram showing a case recognition process by the crime recognition model according to an embodiment of the present application;
FIG. 9 is a schematic diagram showing an element recognition model recognition process according to an embodiment of the present application;
FIG. 10 illustrates another flow chart of a jurisdictional recognition method of an embodiment of the present application;
FIG. 11 is a block diagram of a jurisdictional organization identification apparatus according to an embodiment of the present application;
FIG. 12 shows a block diagram of a computer device according to an embodiment of the application.
Description of the drawings:
101. A client;
102. a server;
103. A database;
1101. a receiving unit;
1102. An identification unit;
1103. A matching unit;
1202. a computer device;
1204. A processor;
1206. A memory;
1208. a driving mechanism;
1210. An input/output module;
1212. an input device;
1214. An output device;
1216. A presentation device;
1218. a graphical user interface;
1220. A network interface;
1222. a communication link;
1224. a communication bus.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, apparatus, article, or device that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or device.
The present specification provides method operational steps as described in the examples or flowcharts, but may include more or fewer operational steps based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution. When a system or apparatus product in practice is executed, it may be executed sequentially or in parallel according to the method shown in the embodiments or the drawings.
The jurisdictional organization of the application refers to various levels of courts, and each court jurisdictions cases in the respective responsibility areas according to responsibility division. The historical case complaint file of the application comprises: a prosecution book/prosecution form made by an inspection agency and a prosecution case prosecution book/prosecution form directly accepted by the national institutes are disclosed on the web (for example, an inspection web).
In an embodiment of the present application, a jurisdictional organization identification system is provided, as shown in fig. 1 and fig. 2, for solving the problem that the existing jurisdictional organization identification method has low accuracy and is not suitable for jurisdictional organization objection cases and complex cases. Specifically, as shown in fig. 1 and 2, the jurisdictional organization identification system includes: client 101, server 102, and database 103.
The client 101 is configured to send a file to be distributed to the server 102. In detail, the case complaint file to be distributed according to the present application is a complaint/complaint form of an undetermined jurisdiction, and after the client 101 sends the case complaint file to be distributed to the server 102, the client identifies the case complaint file to be distributed according to the information in the case complaint file to be distributed, so as to obtain a recommended jurisdiction, and the user determines a final jurisdiction according to the recommended jurisdiction and adds the final jurisdiction to the case complaint file to be distributed. In some embodiments of the present description, the client may be a desktop computer, a tablet computer, a notebook computer, a smart phone, a digital assistant, a smart wearable device, or the like. Wherein, intelligent wearable equipment can include intelligent bracelet, intelligent wrist-watch, intelligent glasses, intelligent helmet etc.. Of course, the client is not limited to the electronic device with a certain entity, and may also be software running in the electronic device.
The server 102 is used for receiving a file of a case to be distributed; extracting crime name/case name information and element information from the case complaint files to be distributed by using a pre-established case name/crime name recognition model and element recognition model, wherein the element information comprises address information and jurisdiction level influence information, and the case name/crime name recognition model and the element recognition model are obtained by training historical case complaint files and marked crime names/case names and element information; obtaining a jurisdictional organization by matching information and element information with a pre-established knowledge base by utilizing the crime name/proposal; the knowledge base stores the entity and the relation set among the entity relevant to the jurisdiction in each law and regulation.
The database 103 stores a knowledge base and a jurisdictional organization identification model for the server 102 to call.
In detail, the address information includes: one or more of principal premises, frequent habitation, behavioral occurrence, crime outcome occurrence, contract fulfillment, corporate location, transportation origin and destination, infringement, accident occurrence. The jurisdictional impact information includes: victims, casualties, target amount of money, and social influence.
The criminal name information is, for example, intentional injury crime, fraud crime, etc. The case-by information is, for example, divorce disputes, contract disputes, intellectual property disputes and the like.
The knowledge base is established according to the existing legal and regulation data, and the knowledge base stores the entity and the relation set among the entities for managing the related content in each legal and regulation. Legal regulations include legal regulations, litigation laws, and related judicial interpretations thereof. Jurisdictional-related content in a law is content that relates to jurisdiction, such as jurisdictional chapter content. The relationship between entities refers to jurisdictional organization based on attribution of the entities, and the entities are parameters for determining jurisdictional organization, in one embodiment, the entities include: the case is composed of/criminal name information, element information and the like, for example, a first criminal case governed by a twenty-third highest national court is a nationwide major criminal case, wherein an entity is the first criminal case; the relationship is that of the highest national court jurisdiction. Specifically, the knowledge base stores the following table 1:
TABLE 1
Assuming that legal information in the case complaint file to be distributed is of the first legal regulation type and the first legal regulation, matching the relationship among entities of the first legal regulation type in the knowledge base. According to the embodiment, a knowledge base is established by analyzing relevant contents of all legal and legal jurisdictions; extracting case name information and element information of a case prosecution file to be distributed; the crime name/proposal is utilized to obtain the jurisdictional organization by matching the information and the element information with the pre-established knowledge base, and compared with the mode of manually identifying the jurisdictional organization according to the element information and the jurisdictional content in the laws and regulations, the method has the advantages of high efficiency and high accuracy. The method provides an auxiliary basis for determining jurisdictional institutions in case prosecution books, and can effectively avoid withholding or competing for case jurisdictional rights before each jurisdictional institution. Meanwhile, the jurisdictional organization identification method can provide basis for the jurisdictional organization determination when the party autonomously posts a case, and the user can select the jurisdictional organization according to the recommended jurisdictional organization.
In one embodiment, a jurisdictional organization identification method is provided, as shown in fig. 3A and 3B, comprising:
step 301, receiving a case complaint file to be distributed.
In detail, in step 301, the case complaint file to be distributed is a complaint file of an undetermined jurisdiction.
Step 302, extracting crime name/case by information and element information from the case complaint file to be allocated by using a pre-established case by/crime name recognition model and element recognition model, wherein the element information comprises address information and jurisdiction level influence information, and the case by/crime name recognition model and element recognition model are obtained by training historical case complaint files and marked crime names/cases and element information thereof.
Specifically, the crime name/crime name recognition model is utilized to extract the crime name/crime name information from the case complaint file to be distributed, and the element recognition model is utilized to extract the element information from the case complaint file to be distributed.
Step 303, obtaining a jurisdictional organization by matching information and element information with a pre-established knowledge base by using the crime name/scheme; the knowledge base stores the entity and the relation set among the entity relevant to the jurisdiction in each law and regulation.
Specifically, the implementation process of the step comprises the following steps: firstly, matching a knowledge base according to crime name/case information through rules, and determining the case type; if the case type is civil case and is special case, the corresponding jurisdictional court is taken out from the knowledge base; if the case type is criminal case, regular matching is carried out on the knowledge base according to the case information and the address element information, and a corresponding jurisdiction area is obtained; and matching the knowledge base by the jurisdiction area and the jurisdiction level element information through rules to obtain the final jurisdictional court.
In practice, step 303 may be packaged as a jurisdictional organization identification module, and the jurisdictional organization may be obtained by invoking and running the jurisdictional organization identification module.
Specific examples of the present embodiment are as follows: for example, the existing criminal cases relate to theft crimes, the case occurrence place is Shanghai city, and the case is a trial case. The process of identifying jurisdictional courts is as follows:
(1) The crime name is classified as a theft crime using a case by/crime name recognition model.
(2) And determining the case location as a city according to the region related elements.
(3) And determining the case as a trial case according to the relevant factors of the jurisdiction level.
(4) And (3) matching a basic court of a certain city (such as a national court in XX area of the certain city) from a knowledge base according to the theft crime, the certain city and a trial as a jurisdictional court by applying a rule matching method.
The jurisdictional organization identification method provided by the embodiment can save the time of artificial judgment, the establishment of an XML template and the artificial setting rules, is applicable to the determination of the jurisdictional organization of complex cases, and improves the efficiency and the accuracy.
In one embodiment of the present application, as shown in fig. 4, the knowledge base establishment process includes:
step 401, obtaining legal and regulatory data.
In particular, the legal and regulatory data may be crawled from the internet, where the legal and regulatory data formats for crawling the internet include TXT, HTML, DOCX, etc.
In order to improve the accuracy of the identification of the subsequent legal regulation data, format standardization processing is also carried out on the legal regulation data; and filtering the redundant information of the standardized legal and regulation data, and converting the filtered legal and regulation data into text contents.
In practice, the python tool may be used to clean the content and delete special characters like u 3000.
Step 402, segmenting each legal and regulation data to obtain a plurality of paragraphs of each legal and regulation data.
When the step is implemented, standard legal and legal data are segmented by using a regularization method, specifically, the standard legal and legal data are segmented according to rules, chapters, laws and regulations and the like, and the standard legal and legal data are stored in a database in a form of (rules, chapters, laws and regulations and laws contents).
Step 403, searching the jurisdictional keyword for each paragraph of each legal and regulatory data, and determining the jurisdictional rule content paragraph according to the search result.
In detail, the jurisdictional key is preconfigured according to the characteristics described by the address, such as "residence", "address", "case-issuing place", "household" and the like.
Step 404, annotating entities and relationships between entities in the jurisdictional rule content paragraphs.
Step 405, building a knowledge base by using entities of each legal and regulation data and relationships among the entities. The knowledge base storage is shown in table 1 above.
In one embodiment of the present application, as shown in FIG. 5A, labeling entities and relationships between entities in a jurisdictional rule content section includes:
step 501, grouping all jurisdictional rule content paragraphs to obtain a first group of jurisdictional rule content and a second group of jurisdictional rule content.
Step 502, the receiver marks the entity and the association relationship between the entities for the first group of jurisdictional rule content.
Step 503, training to obtain an entity identification model according to the content of the first group of jurisdictional rules and the marked entities thereof.
Step 504, training to obtain a relation extraction model according to the association relation between the first group of jurisdictional rule contents and the marked entities.
And 505, identifying the second group of jurisdictional rule contents by the entity identification model and the relation extraction model to obtain the entity and the association relation among the entities of each jurisdictional rule content paragraph in the second group of jurisdictional rule contents.
In this embodiment, steps 501 to 504 are pre-executed steps for training to obtain a entity recognition model and a relationship extraction model. After the training of the entity identification model and the relation extraction model is completed, the entity identification model and the relation extraction model can be utilized to identify the jurisdictional rule content so as to determine the entity of the jurisdictional rule content paragraph and the association relation between the entities.
In step 501, the jurisdictional rule content segments may be grouped by a random method, where the first jurisdictional rule content has a small amount of data and the second jurisdictional rule content has a large amount of data, and the specific data amount may be set according to the actual situation, which is not limited herein.
In step 502, the data in the first set of jurisdictional rule content is analyzed by the experienced staff to determine the entities and the association relationship between the entities in the first set of jurisdictional rule content, the entities including the records/criminal name information.
In step 503, the entity recognition model may perform entity recognition model training by using GlobalPointer method, and the entity recognition model recognition example is shown in fig. 5B, and the jurisdictional rule content "litigation due to contract disputes" is input into the entity recognition model, so as to obtain entity "contract disputes". The relationship extraction model may employ GPLinker joint extraction methods for relationship extraction. As shown in fig. 5C, the relationship extraction model identification example is that the entity relationship "Li Mou, criminal detention, two months", "Li Mou, reprieve, two months", "two months, reprieve, three months" can be obtained by inputting the jurisdiction rule content "civil litigation extracted for citizens" by the residential court of the person to be told into the relationship extraction model.
In step 505, after the entity is identified by using the entity identification model and the association relationship between the entities is identified by using the relationship extraction model, the automatic identification result can be checked by adopting a manual check mode, so that the accuracy of the data labeling is enhanced. And finally, storing the verified entity and entity relation into a knowledge base for later determination of the jurisdictional organization.
According to the embodiment, the manual labeling and the automatic labeling are combined, so that the efficiency of the entity and the relation between the entities can be improved.
In an embodiment of the present application, as shown in fig. 6, the step 302 of extracting the crime name/crime name information and the element information from the case complaint file to be allocated by using the pre-established case name/crime name recognition model and the element recognition model includes: and step 601, processing the file to be distributed for case complaints by using a regularization expression to obtain head information, tail information and intermediate information.
In detail, the head information includes the document type, case number, etc., and the tail information includes personnel information, accessories, etc. The intermediate information is not information other than the head information and the tail information.
In the specific implementation, in order to improve the analysis precision and efficiency, after obtaining the case complaint book to be distributed, the method further comprises the following steps: and (3) carrying out data cleaning treatment on the case complaints to be distributed, and removing other special characters similar to u3000, blank spaces and the like to obtain plain text contents.
Step 602, analyzing each paragraph of the intermediate information by using a paragraph segmentation model to obtain labels of each paragraph, wherein the paragraph labels comprise principal information paragraphs and case paragraphs.
In this step, as shown in fig. 7, in the implementation, the paragraph segmentation model is trained by the Bert classification model. Specifically, firstly, dividing paragraphs of intermediate information of a historical case prosecution book and manually labeling each paragraph label, wherein the principal information comprises principal names, ages, professions and the like, and the case information comprises prosecution, examination and finding, facts and reasons and the like; and then training the Bert classification model by using the intermediate information paragraph of the historical case complaint book and the manually identified paragraph labels to obtain a paragraph segmentation model.
And step 603, identifying the case paragraphs of the case prosecution file to be distributed by using a case name/crime name identification model to obtain the crime name/case name information of the case prosecution file to be distributed.
In detail, the case-by-crime recognition model training process includes: a schematic diagram of the case-by-crime identification model for identifying the case-by-crime is shown in fig. 8.
Step 604, extracting element information from the principal information paragraphs in the case complaint file to be distributed by using an element identification model.
In detail, the element recognition model training process includes: selecting the content of the principal information in the segmented paragraphs, and manually labeling the related information such as the name, sex, frequent residence, present address and the like of the principal; and then training the Global Pointer model by the marked data set, and outputting the model as specific entity element information such as names, frequent residence places, present addresses and the like.
A schematic diagram of the element identification model identifying element information is shown in fig. 9.
According to the embodiment, the case complaint text case, the crime name and the element information can be extracted efficiently and accurately through the case recognition model and the element recognition model.
In an embodiment of the present application, as shown in fig. 10, after the step 303 obtains the jurisdiction, the method further includes:
Step 1001, determining a level of jurisdictional organization.
Step 1002, obtaining the jurisdictional amount standard range of the jurisdictional organization from the knowledge base according to the level of the jurisdictional organization.
Step 1003, judging whether the amount of the object in the case complaint file to be distributed is within the standard range of the jurisdictional amount, if so, outputting the jurisdictional organization, and if not, outputting the jurisdictional organization and sending out the manual verification reminding information.
According to the embodiment, whether the jurisdictional amount standard range corresponding to the level of the jurisdictional organization is within the jurisdictional amount standard range is analyzed, so that verification of the jurisdictional organization can be achieved, and the identification accuracy of the jurisdictional organization is improved.
Based on the same inventive concept, the application also provides a jurisdictional organization identification device, as described in the following embodiments. Because the principle of solving the problem of the jurisdictional organization identification device is similar to that of the jurisdictional organization identification method, the implementation of the jurisdictional organization identification device can refer to the jurisdictional organization identification method, and the repetition is not repeated. Specifically, as shown in fig. 11, the jurisdictional organization identification apparatus includes:
a receiving unit 1101, configured to receive a case complaint file to be allocated;
The identifying unit 1102 is configured to extract crime/case-by-information and element information from the case complaint file to be allocated by using a pre-established case-by-crime/case-by-name identifying model and an element identifying model, where the element information includes address information and jurisdiction level influence information, and the case-by-crime/case-by-name identifying model and the element identifying model are obtained by training historical case complaint files and marked crime/case-by-name and element information thereof;
a matching unit 1103, configured to obtain a jurisdictional organization by matching the information and the element information with a pre-established knowledge base by using the crime name/scheme; the knowledge base stores the entity and the relation set among the entity relevant to the jurisdiction in each law and regulation.
The jurisdiction organization identifying device provided in the foregoing two embodiments extracts the crime/case complaint information and the element information from the case complaint file to be allocated by using a pre-established case/crime identification model and an element identification model, wherein the element information includes address information and jurisdiction level influence information, and the case/crime identification model and the element identification model are obtained by training the historical case complaint file and the marked crime/case by using the element information; obtaining a jurisdictional organization by matching information and element information with a pre-established knowledge base by utilizing the crime name/proposal; the knowledge base stores the relevant entity and the relation set among the entities in each legal regulation, so that the user can be assisted to quickly sort the jurisdiction range of the case, the cost and time are saved, and the determination efficiency and accuracy of the jurisdiction institution are improved.
In one embodiment of the application, as shown in FIG. 12, a computer device 1202 is also provided, the computer device 1202 may include one or more processors 1204, such as one or more Central Processing Units (CPUs), each of which may implement one or more hardware threads. Computer device 1202 may also include any memory 1206 for storing any kind of information, such as code, settings, data, etc. For example, and without limitation, memory 1206 may include any one or more of the following combinations: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any memory may store information using any technique. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent fixed or removable components of computer device 1202. In one case, when the processor 1204 executes associated instructions stored in any memory or combination of memories, the computer device 1202 can perform any of the operations of the associated instructions. The computer device 1202 also includes one or more drive mechanisms 1208 for interacting with any memory, such as a hard disk drive mechanism, optical disk drive mechanism, and the like.
The computer device 1202 may also include an input/output module 1210 (I/O) for receiving various inputs (via an input device 1212) and for providing various outputs (via an output device 1214). One particular output mechanism may include a presentation device 1216 and an associated graphical user interface 1218 (GUI). In other embodiments, input/output module 1210 (I/O), input device 1212, and output device 1214 may not be included as only one computer device in a network. Computer device 1202 may also include one or more network interfaces 1220 for exchanging data with other devices via one or more communication links 1222. One or more communication buses 1224 couple the above-described components together.
The communication link 1222 may be implemented in any manner, for example, through a local area network, a wide area network (e.g., the internet), a point-to-point connection, etc., or any combination thereof. The communication link 1222 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.
The present application also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the method of any of the preceding embodiments.
Embodiments of the present application also provide a computer readable instruction, wherein the program therein causes a processor to perform the method of any of the previous embodiments when the processor executes the instruction.
Embodiments of the present application also provide a computer program product comprising a computer program which, when executed by a processor of a computer device, implements the method of any of the preceding embodiments.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
It should also be understood that, in the embodiment of the present application, the term "and/or" is merely an association relationship describing the association object, indicating that three relationships may exist. For example, a and/or B may represent: a exists alone, A and B exist together, and B exists alone. In the present application, the character "/" generally indicates that the front and rear related objects are an or relationship.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and the various illustrative elements and steps are described above in terms of functions generally in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices, or elements, or may be an electrical, mechanical, or other form of connection.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment of the present application.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The principles and embodiments of the present application have been described in detail with reference to specific examples, which are provided to facilitate understanding of the method and core ideas of the present application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Claims (6)
1. A jurisdictional organization identification method, comprising:
Receiving a case complaint file to be distributed;
extracting crime name/case name information and element information from the case complaint files to be distributed by using a pre-established case name/crime name recognition model and element recognition model, wherein the element information comprises address information and jurisdiction level influence information, and the case name/crime name recognition model and the element recognition model are obtained by training historical case complaint files and marked crime names/case names and element information;
Obtaining a jurisdictional organization by matching information and element information with a pre-established knowledge base by utilizing the crime name/proposal; the knowledge base stores the relation set among the entity relevant to the jurisdiction in each law and regulation;
Determining a level of jurisdiction;
Obtaining the jurisdictional amount standard range of the jurisdictional organization from the knowledge base according to the level of the jurisdictional organization;
Judging whether the amount of the object in the case complaint file to be distributed is within the standard range of the jurisdictional amount, if so, outputting the jurisdictional organization, and if not, outputting the jurisdictional organization and sending out manual verification reminding information;
the knowledge base establishment process comprises the following steps:
Obtaining legal and regulation data;
Segmenting each legal and regulatory data to obtain a plurality of paragraphs of each legal and regulatory data;
Searching jurisdictional keywords for each paragraph of each legal and regulatory data, and determining jurisdictional rule content paragraphs according to search results;
Labeling entities in the jurisdictional rule content paragraphs and relationships among the entities;
Establishing a knowledge base by utilizing entities of all legal and regulation data and relationships among the entities;
The method further comprises the following steps of:
carrying out format standardization processing on the legal and regulatory data;
filtering redundant information of the standardized legal and regulation data, and converting the filtered legal and regulation data into text content;
the labeling of the entity and the relationship among the entities in the jurisdictional rule content section comprises the following steps:
Grouping all jurisdictional rule content paragraphs to obtain a first group of jurisdictional rule content and a second group of jurisdictional rule content;
The receiver marks the entity of the first group of jurisdictional rule content and the association relation between the entities;
training to obtain an entity identification model according to the content of the first group of jurisdiction rules and the marked entity;
Training to obtain a relation extraction model according to the incidence relation between the first group of jurisdictional rule contents and the marked entities;
and identifying the second group of jurisdictional rule contents by the entity identification model and the relation extraction model to obtain the entity and the association relation among the entities of each jurisdictional rule content paragraph in the second group of jurisdictional rule contents.
2. The method of claim 1, wherein extracting crime name/case response information and element information from the case prosecution file to be distributed using a pre-established case response/crime name recognition model and element recognition model, comprises: processing the case complaint file to be distributed by using a regularization expression to obtain head information, tail information and intermediate information;
analyzing each paragraph of the intermediate information by utilizing a paragraph segmentation model to obtain labels of all paragraphs, wherein the paragraph labels comprise principal information paragraphs and case paragraphs;
identifying a case paragraph of the case prosecution file to be distributed by using a case name/crime identification model to obtain crime name/case name information of the case prosecution file to be distributed;
and extracting element information from the principal information paragraphs in the case complaint file to be distributed by using an element identification model.
3. The method of claim 1, wherein the address information comprises: one or more of principal premises, frequent residence, behavioral, crime outcome, contract fulfillment, corporate premises, transportation origins and destinations, infringement, accident occurrence;
the jurisdictional impact information includes: victims, casualties, target amount of money, and social influence.
4. A jurisdictional organization identification device, comprising:
the receiving unit is used for receiving the file of the case to be distributed;
The recognition unit is used for extracting crime name/case name information and element information from the case complaint files to be distributed by utilizing a pre-established case name/crime name recognition model and element recognition model, wherein the element information comprises address information and jurisdiction level influence information, and the case name/crime name recognition model and the element recognition model are obtained by training historical case complaint files and marked crime name/case names and element information;
The matching unit is used for matching the information and the element information with a pre-established knowledge base to obtain a jurisdictional organization by utilizing the crime name/scheme; the knowledge base stores the relation set among the entity relevant to the jurisdiction in each law and regulation;
further comprises: for determining a level of jurisdiction; obtaining the jurisdictional amount standard range of the jurisdictional organization from the knowledge base according to the level of the jurisdictional organization; judging whether the amount of the object in the case complaint file to be distributed is within the standard range of the jurisdictional amount, if so, outputting the jurisdictional organization, and if not, outputting the jurisdictional organization and sending out the manual verification reminding information;
the knowledge base establishment process comprises the following steps:
Obtaining legal and regulation data;
Segmenting each legal and regulatory data to obtain a plurality of paragraphs of each legal and regulatory data;
Searching jurisdictional keywords for each paragraph of each legal and regulatory data, and determining jurisdictional rule content paragraphs according to search results;
Labeling entities in the jurisdictional rule content paragraphs and relationships among the entities;
Establishing a knowledge base by utilizing entities of all legal and regulation data and relationships among the entities;
The method further comprises the following steps of:
carrying out format standardization processing on the legal and regulatory data;
filtering redundant information of the standardized legal and regulation data, and converting the filtered legal and regulation data into text content;
the labeling of the entity and the relationship among the entities in the jurisdictional rule content section comprises the following steps:
Grouping all jurisdictional rule content paragraphs to obtain a first group of jurisdictional rule content and a second group of jurisdictional rule content;
The receiver marks the entity of the first group of jurisdictional rule content and the association relation between the entities;
training to obtain an entity identification model according to the content of the first group of jurisdiction rules and the marked entity;
Training to obtain a relation extraction model according to the incidence relation between the first group of jurisdictional rule contents and the marked entities;
and identifying the second group of jurisdictional rule contents by the entity identification model and the relation extraction model to obtain the entity and the association relation among the entities of each jurisdictional rule content paragraph in the second group of jurisdictional rule contents.
5. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 3 when executing the computer program.
6. A computer storage medium having stored thereon a computer program, which when executed by a processor of a computer device implements the method of any of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410758766.XA CN118332455B (en) | 2024-06-13 | 2024-06-13 | Jurisdictional organization identification method and jurisdictional organization identification device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410758766.XA CN118332455B (en) | 2024-06-13 | 2024-06-13 | Jurisdictional organization identification method and jurisdictional organization identification device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118332455A CN118332455A (en) | 2024-07-12 |
| CN118332455B true CN118332455B (en) | 2024-08-20 |
Family
ID=91770568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410758766.XA Active CN118332455B (en) | 2024-06-13 | 2024-06-13 | Jurisdictional organization identification method and jurisdictional organization identification device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118332455B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110162539A (en) * | 2019-05-29 | 2019-08-23 | 北京市律典通科技有限公司 | A kind of jurisdiction of case intelligent decision system, method, electronic equipment and storage medium |
| CN111859936A (en) * | 2020-07-09 | 2020-10-30 | 大连理工大学 | Cross-domain establishment oriented legal document professional jurisdiction identification method based on deep hybrid network |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113689195A (en) * | 2021-08-27 | 2021-11-23 | 北京市律典通科技有限公司 | Case administration intelligent judgment method and device, electronic equipment and storage medium |
| CN114979067B (en) * | 2022-05-11 | 2024-03-05 | 北京圣博润高新技术股份有限公司 | Determination method, device, equipment and medium of unit jurisdiction organization |
| US20240160845A1 (en) * | 2022-11-10 | 2024-05-16 | Vertex, Inc. | Generation of jurisdictions lists for input text |
-
2024
- 2024-06-13 CN CN202410758766.XA patent/CN118332455B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110162539A (en) * | 2019-05-29 | 2019-08-23 | 北京市律典通科技有限公司 | A kind of jurisdiction of case intelligent decision system, method, electronic equipment and storage medium |
| CN111859936A (en) * | 2020-07-09 | 2020-10-30 | 大连理工大学 | Cross-domain establishment oriented legal document professional jurisdiction identification method based on deep hybrid network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118332455A (en) | 2024-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110765770B (en) | Automatic contract generation method and device | |
| CN112182246B (en) | Method, system, medium, and application for creating an enterprise representation through big data analysis | |
| CN110083623B (en) | Business rule generation method and device | |
| CN111241367A (en) | Method and system for supervising network catering platform based on custom rule | |
| EP3642766A1 (en) | Machine-learning system for servicing queries for digital content | |
| CN111104798A (en) | Analysis method, system and computer readable storage medium for criminal plot in legal document | |
| CN110737821B (en) | Similar event query method, device, storage medium and terminal equipment | |
| WO2021098651A1 (en) | Method and apparatus for acquiring risk entity | |
| CN113282955A (en) | Method, system, terminal and medium for extracting privacy information in privacy policy | |
| CN109902151A (en) | Recording method, device and the electronic equipment of interrogation record | |
| CN113220875A (en) | Internet information classification method and system based on industry label and electronic equipment | |
| CN113159796A (en) | Trade contract verification method and device | |
| CN112347254A (en) | News text classification method and device, computer equipment and storage medium | |
| CN108170691A (en) | It is associated with the determining method and apparatus of document | |
| Morillo et al. | How to automatically identify major research sponsors selecting keywords from the WoS Funding Agency field | |
| Moon et al. | Automatic review of construction specifications using natural language processing | |
| CN116775639A (en) | Data processing method, storage medium and electronic device | |
| CN116719997A (en) | Policy information pushing method and device and electronic equipment | |
| CN115238688A (en) | Electronic information data association relation analysis method, device, equipment and storage medium | |
| CN111914542A (en) | Suspected illegal investment market subject identification method, device, terminal and storage medium | |
| CN113254651A (en) | Method and device for analyzing referee document, computer equipment and storage medium | |
| CN115080709A (en) | Text recognition method and device, nonvolatile storage medium and computer equipment | |
| CN118332455B (en) | Jurisdictional organization identification method and jurisdictional organization identification device | |
| CN109542845A (en) | Text metadata extraction method based on keyword expression | |
| CN113807256A (en) | Bill data processing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |