Case resource retrieval method and device based on graph database

Abstract

The invention relates to the field of case retrieval, and provides a case resource retrieval method and device based on a graph database, and the method comprises the steps: building the graph database in advance, and determining resource data and a resource relation according to a plurality of to-be-analyzed case files; storing the resource data and the resource relationship in a graph database; wherein the resource relationships comprise resource relationships in the cases and resource relationships among the cases; receiving a query statement, and obtaining data related to the query statement from the graph database; and displaying the resource relation graph according to the queried data. According to the method, full-amount automatic retrieval of the case resources can be realized, and the case resource acquisition efficiency and precision are ensured.

Description

Technical Field

[0001] The present invention relates to the field of case retrieval, and in particular to a case resource retrieval method and device based on a graph database. Background Art

[0002] In the existing judicial field, there are a large number of cases. If relevant personnel (such as court personnel) want to obtain full case information, they usually do so by manually reviewing the case files. However, this method of manually reviewing the case files has the problems of low efficiency in obtaining information, high labor costs, and long time consumption. Summary of the Invention

[0003] This application is used to solve the problems in the prior art of low efficiency, high labor cost and long time consumption in manually reviewing case files to obtain full case information.

[0004] The first aspect of the present application provides a case resource retrieval method based on a graph database, comprising:

[0005] Pre-establishing a graph database includes: determining resource data and resource relationships based on multiple case files to be analyzed; storing the resource data and resource relationships in the graph database; wherein the resource relationships include: resource relationships within a case and resource relationships between cases;

[0006] Receive a query statement and obtain data related to the query statement from the graph database;

[0007] Based on the queried data, a resource relationship map is displayed.

[0008] As a further embodiment of the present application, determining resource data based on a plurality of case files to be analyzed includes: extracting resource data of each case from each case file to be analyzed using a pre-established resource data identification model;

[0009] The resource data recognition model is trained using pre-annotated case files and their annotated case resources.

[0010] As a further embodiment of the present application, the plurality of case files to be analyzed include case files to be analyzed in multiple systems, and the multiple systems have case files to be analyzed for the same case;

[0011] After extracting the resource data of each case from each case file to be analyzed, the following steps are also included:

[0012] analyzing whether the resource data of the case file to be analyzed in the first system and the resource data of the case file to be analyzed in the second system belong to the same case; if they belong to the same case, integrating the resource data of the case file to be analyzed in the first system and the resource data of the case file to be analyzed in the second system;

[0013] The first system and the second system belong to different systems among the multiple systems.

[0014] As a further embodiment of the present application, determining resource relationships based on multiple case files to be analyzed includes:

[0015] Determine the resource relationships within each case based on the resource data of each case;

[0016] Obtain litigation request information from each case file to be analyzed;

[0017] Determine related cases based on the litigation request information of each case file to be analyzed;

[0018] Determine the resource relationship of related cases based on the litigation request information of related cases.

[0019] As a further embodiment of the present application, determining related cases based on the litigation request information of each case file to be analyzed includes:

[0020] For each case file to be analyzed, the case file to be analyzed and each other case file to be analyzed are combined into a case group, and the similarity between the litigation request information of each case file in the case group is calculated; the case group with the maximum similarity is determined as a related case.

[0021] As a further embodiment of the present application, pre-establishing a graph database further includes:

[0022] A full-text index of each case resource data and resource relationship is created in the graph database.

[0023] As a further embodiment of the present application, displaying a resource relationship map based on the queried data includes:

[0024] Create temporary node objects and temporary edge objects;

[0025] Assign the queried resource data to the temporary node object, and assign the queried resource relationship to the temporary edge object;

[0026] Draw a resource relationship graph based on temporary node objects and temporary edge objects.

[0027] As a further embodiment of the present application, the query record information includes query content, user information or device information;

[0028] Group query record information according to user information or device information;

[0029] Generate a search profile for each group based on the query content in each group;

[0030] Optimize the search interface of each group based on the search profile of each group.

[0031] Another aspect of the present application provides a case resource retrieval device based on a graph database, comprising:

[0032] A pre-processing unit is used to pre-establish a graph database, including: determining resource data and resource relationships based on multiple case files to be analyzed; storing the resource data and resource relationships in the graph database; wherein the resource relationships include: resource relationships within a case and resource relationships between cases;

[0033] An interaction unit, configured to receive a query statement and obtain data related to the query statement from the graph database;

[0034] The query unit is used to display a resource relationship map based on the queried data.

[0035] On the other hand, the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any one of the aforementioned embodiments when executing the computer program.

[0036] On the other hand, the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor of a computer device, the method described in any of the above embodiments is implemented.

[0037] The case resource retrieval method and device based on a graph database provided in the present application are applicable to the field of case retrieval in multiple systems, such as the field of judicial case retrieval, by pre-establishing a graph database, including: determining resource data and resource relationships based on multiple case files to be analyzed; storing resource data and resource relationships in the graph database; wherein resource relationships include: resource relationships within a case and resource relationships between cases; receiving a query statement, and obtaining data related to the query statement from the graph database; and displaying a resource relationship map based on the queried data, thereby realizing full automatic retrieval of case resources, improving the efficiency and accuracy of case resource acquisition, and saving labor costs and time.

[0038] In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0040] Figure 1 A structural diagram of a case resource retrieval system based on a graph database according to an embodiment of the present application is shown;

[0041] Figure 2 A flowchart of a case resource retrieval method based on a graph database according to an embodiment of the present application is shown;

[0042] Figure 3 A flowchart showing a resource relationship determination process according to an embodiment of the present application is shown;

[0043] Figure 4 A flowchart showing a resource relationship map display process according to an embodiment of the present application is shown;

[0044] Figure 5A A schematic diagram of the query results of an embodiment of the present application is shown;

[0045] Figure 5B A schematic diagram of a resource relationship map of an embodiment of the present application is shown;

[0046] Figure 6 A structural diagram of a case resource retrieval device based on a graph database according to an embodiment of the present application is shown;

[0047] Figure 7 A structural diagram of a computer device according to an embodiment of the present application is shown.

[0048] Description of the accompanying symbols:

[0049] 101. Server;

[0050] 102. Client;

[0051] 601, pre-processing unit;

[0052] 602, interactive unit;

[0053] 603, query unit;

[0054] 702. Computer equipment;

[0055] 704, processor;

[0056] 706. Memory;

[0057] 708, driving mechanism;

[0058] 710, input / output module;

[0059] 712. Input devices;

[0060] 714. Output device;

[0061] 716. Presentation equipment;

[0062] 718. Graphical User Interface;

[0063] 720, network interface;

[0064] 722, communication link;

[0065] 724. Communication bus. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0067] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0068] This specification provides method operation steps as described in the embodiments or flowcharts, but more or fewer operation steps may be included based on routine or non-creative work. The order of steps listed in the embodiments is only one way of executing the steps among many orderings and does not represent the only execution order. When a system or device product is actually executed, the method can be executed in the order shown in the embodiments or the drawings or in parallel.

[0069] It should be noted that the case resource retrieval method and device based on the graph database of the present application can be used for case resource retrieval in the judicial field. The systems in the judicial field include case filing systems, trial systems, etc.

[0070] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the acquisition, transmission, storage, use and processing of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions.

[0071] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned. They should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0072] In one embodiment of the present application, a case resource retrieval system based on a graph database is provided to solve the problems of low efficiency, high labor cost and long time consumption in the existing method of manually reviewing files to obtain full case information. Figure 1 As shown, the case resource retrieval system based on the graph database includes: a server 101 and a client 102.

[0073] Server 101 is used to pre-establish a graph database and store the graph database. Specifically, the process of establishing the graph database includes: determining resource data and resource relationships based on multiple case files to be analyzed; storing the resource data and resource relationships in the graph database; wherein the resource relationships include: resource relationships within the case and resource relationships between cases.

[0074] The client 102 is used to display a search interface, and the user enters a query request through the search interface and sends the query request to the server 101.

[0075] The server 101 is also used to obtain query statements according to query requirements, obtain data related to the query statements from the graph database, and display a resource relationship graph based on the queried data.

[0076] Among them, multiple case files to be analyzed can come from multiple systems, including but not limited to the case filing system and the trial system. Cases to be analyzed in different systems may belong to the same case. The case files to be analyzed in the case filing system include at least one of the following information: party information (such as the name, age, ethnicity, occupation, residence, contact information, etc. of the plaintiff and defendant), basic case information (such as case number, cause of action, filing date, case source, case type), case filing material information (such as the submitted indictment, list of evidence materials and corresponding evidence, acceptance notice, litigation fee payment information, etc.). The case files to be analyzed in the trial system include at least one of the following information: case process information (such as the names of judges and panel members, litigation procedures and changes in parties, jurisdiction handling, etc.), case trial information (such as court transcripts, evidence exchange records, cross-examination results, judge's trial opinions, etc.), and adjudication information (such as the content of legal documents such as judgments, rulings, and mediation agreements).

[0077] Resource data is a specific entity defined based on the information required for the case handling process in the case file to be analyzed. For example, [(2022)**0108***3] is an instance of the [Case] ​​resource data, and [Zhang XX] is an instance of the [Defendant] resource data. In a graph database, a resource data item is represented by a resource node, which is stored as a resource node instance.

[0078] The resource relationship within a case represents the relationship between resource nodes within the resource. The resource relationship between cases represents the relationship between case name nodes between cases.

[0079] The search interface contains input controls for users to enter case information to be queried, such as case name, defendant, case handler, public prosecutor, etc.

[0080] This embodiment can realize the full automatic retrieval of case resources, improve the efficiency and accuracy of case resource acquisition, and save labor costs and time. At the same time, it supports efficient multi-dimensional association queries (such as tracing all cases and related people / events involved by a certain party). Resource relationships cover the internal relationships of cases and the relationships between cases. It can explore the potential connections between different cases (such as serial cases, gang crime connections, similar legal issues, etc.), and provide data support for judicial organs to analyze case trends and discover criminal networks.

[0081] In one embodiment of the present application, Figure 2 As shown, a case resource retrieval method based on a graph database is also provided, including:

[0082] Step 201: Pre-establish a graph database.

[0083] Among them, establishing a graph database includes: determining resource data and resource relationships based on multiple case files to be analyzed; storing the resource data and resource relationships in the graph database; among them, resource relationships include: resource relationships within the case and resource relationships between cases.

[0084] Step 202: Receive a query statement and obtain data related to the query statement from the graph database.

[0085] Step 203: Display a resource relationship map based on the queried data.

[0086] In some embodiments of the present application, the above step 201 determines the resource data based on the multiple case files to be analyzed, including:

[0087] Utilize the pre-established resource data identification model to extract the resource data of each case from each case file to be analyzed.

[0088] The resource data recognition model is trained using pre-labeled case documents and their labeled case resources. Resource data labels include case number, court, procuratorate, and parties involved. During implementation, resource data labels can be organized based on actual business experience and the court's actual case handling process.

[0089] In a specific embodiment, the resource data identification model can be obtained based on training the GPLinker model. The training process includes:

[0090] (1) Data collection: 400 indictments were collected, of which 300 were annotated and used as the training set for the resource data recognition model, and 100 were used as the validation set to verify the trained resource data recognition model.

[0091] (2) Word segmentation: Word2Vec is used to segment the indictment to convert each word into a low-dimensional vector representation, so that the text data can be understood and processed by the resource data recognition model.

[0092] (3) Basic model construction: Construct a resource data identification model based on the Transformer architecture.

[0093] (4) Loss calculation: The loss function uses the multi-label cross entropy function used by GlobalPointer by default.

[0094] (5) Finally, iterative training is performed. In order to improve the accuracy of the model, sample data is randomly selected from the sample data set and the character strings in it are intercepted and randomly recombined with other sample data to increase the sample complexity.

[0095] In one embodiment of the present application, the case file to be analyzed is a complaint document, such as Figure 3 As shown, the above step 201 determines the resource relationship based on the multiple case files to be analyzed, including:

[0096] Step 301: Determine the resource relationship within each case based on the resource data of each case.

[0097] Step 302: Obtain litigation request information from each case file to be analyzed.

[0098] When this step is implemented, the litigation request information can be obtained based on the paragraph format in the case file to be analyzed.

[0099] Step 303: Determine related cases based on the litigation request information of each case file to be analyzed.

[0100] In this step, related cases can be determined in the following ways:

[0101] For each case file to be analyzed, the case file to be analyzed and each other case file to be analyzed are combined into a case group, and the similarity between the litigation request information of each case file in the case group is calculated; the case group with the maximum similarity is determined as a related case.

[0102] During implementation, the similarity between the litigation request information of each case file in the case group can be calculated based on the GTE pre-trained model.

[0103] Step 304: Determine the resource relationship of the related cases based on the litigation request information of the related cases. The resource relationship of the related cases represents the relationship between the cases, such as the first instance case, the second instance case, etc.

[0104] In some embodiments of the present application, pre-establishing a graph database further includes: creating a full-text index of each case resource data and resource relationship in the graph database, thereby improving the query performance of the graph database. For example, creating a full-text index tag ("aj") to speed up case query performance. The graph database index creation statement is:

[0105] schema.indexLabel("aj").onV("aj").by("aj").search().ifNotExist().create().

[0106] In some embodiments of the present application, Figure 4 As shown, the above step 203 displays the resource relationship map based on the queried data, including:

[0107] Step 401: Create a temporary node object and a temporary edge object.

[0108] In this step, a HashMap collection is established, and the HashMap collection includes Node attributes and Edge attributes.

[0109] The temporary node object may also be referred to as a first temporary JSONObject object, which includes a Name attribute and an Id attribute.

[0110] The temporary edge object may also be referred to as a second temporary JSONObject object, which includes a FromId attribute, a ToId attribute, and a Relationship attribute.

[0111] Step 402: Assign the queried resource data to a temporary node object, and assign the queried resource relationship to a temporary edge object.

[0112] Step 403: Draw a resource relationship graph based on the temporary node objects and the temporary edge objects.

[0113] For example, if the user input is "(2022) Xing Chu **** No.", through the query statement of the graph database, the relevant case information retrieved is as follows Figure 5A As shown, retrieve the relevant information in the graph database regarding the case name "(2022) Xing Chu **** No.". Query by the case name to obtain results such as "****** People's Procuratorate", case (2022) Jing ** Xing Chu No. 2, Judge Zhang, Zhang San, etc., and obtain the relationships between the current case name and each resource name. For example, Judge Zhang is the case handler, and Zhang San is the defendant in this case.

[0114] In the query results, assign the Name in the label type (the label type here refers to each record aj or jcy) to the Name property of the first temporary JSONObject object, and assign the Id in the label type to the Id property of the first temporary JSONObject object. According to the label type Id, parse the relationship of the edge type, assign the Relationship of the edge type to the Relationship property of the second temporary JSONObject object, assign the Id of the case name to the FromId property of the second temporary JSONObject object, and assign the Id of the edge type (the edge type here refers to aj_aj in each record) to the ToId property of the second temporary JSONObject object. Finally, form a relationship graph related to the case name, as shown in Figure 5B shown.

[0115] In some embodiments of the present application, after receiving the query statement, it further includes:

[0116] (1) Generate query record information, where the query record information includes query content, user information, or device information.

[0117] (2) Group the query record information according to user information or device information.

[0118] (3) Generate a retrieval portrait for each group according to the query content in each group.

[0119] When implementing this step, the query content in each group can be clustered, and the clustering result can be used as the retrieval portrait for each group. Through this step, the high-frequency query requirements of each group can be determined, facilitating the provision of targeted value-added services for users.

[0120] (4) Optimize the retrieval interface for each group according to the retrieval portrait of each group.

[0121] This embodiment can determine the high-frequency query requirements of users based on the user's historical query content, thereby optimizing the user's retrieval interface and improving the user's retrieval efficiency.

[0122] During specific implementation, similar case files can also be pushed to users related to the group based on the group's search profile, thereby reducing the cost of users obtaining information and improving the efficiency of judicial collaboration.

[0123] In some embodiments, the search profile includes query frequency, and user behavior is restricted based on preset query rules and query frequency. The preset query rules, for example, prohibit users from continuing to query data when the query frequency reaches a preset value, thereby ensuring data security.

[0124] The above-mentioned embodiment of the case resource retrieval method based on the graph database can realize the automatic conversion and import of the graph database format based on the GPLinker model and the GTE pre-training model, and then quickly retrieve the case-related information and the relationship graph related to the case, thereby helping court staff to quickly sort out the information required for case handling, speed up the case handling process, and save labor costs and time.

[0125] Based on the same inventive concept, this application also provides a case resource retrieval device based on a graph database, as described in the following embodiments. Because the principles for solving problems in the case resource retrieval device based on a graph database are similar to those in the case resource retrieval method based on a graph database, the implementation of the case resource retrieval device based on a graph database can refer to the case resource retrieval method based on a graph database, and any repetitions will not be repeated.

[0126] Specifically, such as Figure 6 As shown, the case resource retrieval device based on the graph database includes:

[0127] The pre-processing unit 601 is used to pre-establish a graph database, including: determining resource data and resource relationships based on multiple case files to be analyzed; storing the resource data and resource relationships in the graph database; wherein the resource relationships include: resource relationships within the case and resource relationships between cases.

[0128] The interaction unit 602 is used to receive a query statement and obtain data related to the query statement from the graph database.

[0129] The query unit 603 is used to display a resource relationship map based on the queried data.

[0130] Among them, the display process of the graph database and resource relationship graph can refer to the aforementioned embodiment and will not be described in detail here.

[0131] In one embodiment of the present application, a computer device is also provided, such as Figure 7As shown, computer device 702 may include one or more processors 704, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. Computer device 702 may also include any memory 706 for storing any type of information, such as code, settings, data, and the like. For example, and without limitation, memory 706 may include any one or more combinations of the following: any type of RAM, any type of ROM, a flash memory device, a hard disk, an optical disk, and the like. More generally, any memory may use any technology to store information. Furthermore, any memory may provide volatile or non-volatile retention of information. Furthermore, any memory may represent a fixed or removable component of computer device 702. In one embodiment, when processor 704 executes associated instructions stored in any memory or combination of memories, computer device 702 may perform any operation of the associated instructions. Computer device 702 also includes one or more drive mechanisms 708, such as a hard disk drive mechanism, an optical disk drive mechanism, and the like, for interacting with any memory.

[0132] The computer device 702 may also include an input / output module 710 (I / O) for receiving various inputs (via input devices 712) and for providing various outputs (via output devices 714). A specific output mechanism may include a presentation device 716 and an associated graphical user interface 718 (GUI). In other embodiments, the input / output module 710 (I / O), input devices 712, and output devices 714 may not be included, and the computer device 702 may simply function as a computer device in a network. The computer device 702 may also include one or more network interfaces 720 for exchanging data with other devices via one or more communication links 722. One or more communication buses 724 couple the components described above together.

[0133] The communication link 722 may be implemented in any manner, for example, via 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 722 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0134] An embodiment of the present application further provides a computer-readable storage medium, such as a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are executed.

[0135] An embodiment of the present application also provides a computer-readable instruction, wherein when a processor executes the instruction, the program therein causes the processor to execute the method described in any of the aforementioned embodiments.

[0136] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0137] It should also be understood that in the embodiments of this application, the term "and / or" is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this application generally indicates that the associated objects are in an "or" relationship.

[0138] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0139] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0140] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or can be electrical, mechanical or other forms of connection.

[0141] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0142] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0143] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or partly contributed to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0144] Specific embodiments are used in this application to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A case resource retrieval method based on a graph database, characterized in that: include: Pre-establishing a graph database includes: determining resource data and resource relationships based on multiple case files to be analyzed; storing the resource data and resource relationships in the graph database; wherein the resource relationships include: resource relationships within a case and resource relationships between cases; Receive a query statement and obtain data related to the query statement from the graph database; Based on the queried data, a resource relationship map is displayed.

2. The method according to claim 1, wherein Based on multiple case files to be analyzed, the resource data includes: Utilize the pre-established resource data identification model to extract the resource data of each case from each case file to be analyzed; The resource data recognition model is trained using pre-annotated case files and their annotated case resources.

3. The method according to claim 2, wherein The multiple case files to be analyzed include case files to be analyzed from multiple systems, and the multiple systems have case files to be analyzed for the same case; After extracting the resource data of each case from each case file to be analyzed, the following steps are also included: analyzing whether the resource data of the case file to be analyzed in the first system and the resource data of the case file to be analyzed in the second system belong to the same case; if they belong to the same case, integrating the resource data of the case file to be analyzed in the first system and the resource data of the case file to be analyzed in the second system; The first system and the second system belong to different systems among the multiple systems.

4. The method according to claim 1, wherein Based on multiple case files to be analyzed, the resource relationships include: Determine the resource relationships within each case based on the resource data of each case; Obtain litigation request information from each case file to be analyzed; Determine related cases based on the litigation request information of each case file to be analyzed; Determine the resource relationship of related cases based on the litigation request information of related cases.

5. The method according to claim 4, wherein Based on the litigation request information of each case file to be analyzed, related cases are identified, including: For each case file to be analyzed, the case file to be analyzed and each other case file to be analyzed are combined into a case group, and the similarity between the litigation request information of each case file in the case group is calculated; the case group with the maximum similarity is determined as a related case.

6. The method according to claim 1, wherein Pre-built graph databases also include: A full-text index of each case resource data and resource relationship is created in the graph database.

7. The method according to claim 1, wherein Based on the queried data, the resource relationship graph includes: Create temporary node objects and temporary edge objects; Assign the queried resource data to the temporary node object, and assign the queried resource relationship to the temporary edge object; Draw a resource relationship graph based on temporary node objects and temporary edge objects.

8. The method according to claim 1, wherein After receiving the query statement, it also includes: Generate query record information, wherein the query record information includes query content, user information or device information; Group query record information according to user information or device information; Generate a search profile for each group based on the query content in each group; Optimize the search interface of each group based on the search profile of each group.

9. A case resource retrieval device based on a graph database, characterized in that: include: A pre-processing unit is used to pre-establish a graph database, including: determining resource data and resource relationships based on multiple case files to be analyzed; storing the resource data and resource relationships in the graph database; wherein the resource relationships include: resource relationships within a case and resource relationships between cases; An interaction unit, configured to receive a query statement and obtain data related to the query statement from the graph database; The query unit is used to display a resource relationship map based on the queried data.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

Images