Case resource analysis matching method and system based on user information

Abstract

The application relates to the technical field of case resource matching, and relates to a case resource analysis and matching method and system based on user information, which comprises the following steps: confirming a historical case data set based on an information collection instruction, obtaining an identification case data set by using the historical case data set, constructing an initial search database based on the identification case data set, optimizing the initial search database to obtain a case search database, obtaining a user identity code of a user, obtaining a user information node based on an information analysis instruction and the user identity code, searching in the case search database by using the user information node to obtain an initial search data set, confirming a target search data sequence based on the initial search data set, and sending the target search data sequence to an initiating end of a case matching instruction by using a result feedback unit to realize analysis and matching of case resources. The application can realize analysis and matching of case resources in combination with user information.

Description

Technical Field

[0001] This invention relates to the field of case resource matching technology, and in particular to a case resource analysis and matching method and system based on user information. Background Technology

[0002] With the increasing legal awareness of residents and the growing number of disputes, the demand for case handling is also increasing. Correspondingly, the ability to accurately and intelligently retrieve a large number of similar cases from existing databases is of great significance for improving the efficiency of case handling.

[0003] Currently, most cases are retrieved manually from known case databases to find cases similar to the user's information.

[0004] While the methods described above can analyze and match user information, they require significant human and energy resources for retrieval, and the final search results are highly dependent on the experience of the personnel conducting the search. Therefore, how to combine user information with case resource analysis and matching has become a pressing issue. Summary of the Invention

[0005] This invention provides a case resource analysis and matching method based on user information and a computer-readable storage medium, the main purpose of which is to realize case resource analysis and matching by combining user information.

[0006] To achieve the above objectives, the present invention provides a case resource analysis and matching method based on user information, comprising:

[0007] The system receives a case matching instruction and confirms the case matching system based on the instruction. The case matching system includes: an information collection unit, an information analysis unit, an information matching unit, and a result feedback unit.

[0008] The system confirms receipt of an information collection instruction from the information collection unit and identifies a historical case dataset based on the information collection instruction. The historical case dataset includes multiple historical case data, which in turn includes: case file images, case storage text, and case judgment results.

[0009] Use the historical case dataset to obtain an identified case dataset, and construct an initial retrieval database based on the identified case dataset;

[0010] The initial retrieval database is optimized to obtain a case retrieval database;

[0011] Obtain the user's user identification code, confirm receipt of the information analysis instruction from the information analysis unit, obtain the user information node based on the information analysis instruction and the user identification code, wherein the user information node includes m user case data and known user data, and m is an integer greater than or equal to 0, and use the user information node to perform a search in the case retrieval database to obtain the initial retrieval dataset;

[0012] Based on the initial search dataset, a target search data sequence is identified, wherein the target search data sequence includes multiple target search data.

[0013] The result feedback unit is used to send the target retrieval data sequence to the initiator of the case matching instruction, thereby realizing the analysis and matching of case resources.

[0014] Optionally, obtaining the identified case dataset using the historical case dataset includes:

[0015] Historical case data is extracted sequentially from the historical case dataset, and the following operations are performed on the extracted historical case data:

[0016] Parse the case storage text corresponding to the historical case data to obtain the perpetrator identification code and the case execution time, and obtain the case completion time of the historical case data;

[0017] The extracted historical case data is identified by using the perpetrator identification code, case execution time, and case completion time corresponding to the historical case data, thus obtaining identified case data;

[0018] The identified case data is then aggregated to obtain the identified case dataset.

[0019] Optionally, constructing the initial retrieval database based on the identified case dataset includes:

[0020] Based on the actor identification code, the identified case data in the identified case dataset are summarized to obtain the analyzed case data set. The analyzed case data set includes multiple analyzed case data sets, and each analyzed case data set includes one or more identified case data, and the actor identification code corresponding to one or more identified case data is the same.

[0021] For each case data set in the case data set analysis group set, perform the following operations:

[0022] The identified case data in the case data group are sorted according to the order of case completion time to obtain the identified case sequence;

[0023] Initial case data is extracted sequentially from the identified case sequence, and the following operations are performed on the extracted initial case data:

[0024] Based on the initial case data, target case data is identified in the identified case sequence, wherein the target case data is the identified case data that is adjacent to and follows the initial case data;

[0025] The effective prosecution time is obtained based on the case completion time, and the effective prosecution time is compared with the case implementation time corresponding to the target case data.

[0026] If the time of the case is less than or equal to the effective prosecution time, then determine whether to associate the initial case data and the target case data;

[0027] If the initial case data and the target case data are confirmed to be associated, then the initial case data and the target case data are associated to obtain chain case data, and the target case data in the chain case data is used as the initial case data. The step of confirming the target case data in the identified case sequence based on the initial case data is returned. The identified case data in the identified case sequence that do not constitute the chain case data are summarized to obtain a single case dataset. The chain case data are summarized to obtain a chain case dataset.

[0028] An initial retrieval database is constructed based on the single case dataset and the chained case dataset.

[0029] Optionally, determining whether to associate the initial case data and the target case data includes:

[0030] Confirm receipt of information matching instructions from the information matching unit, and confirm the character recognition model and text summarization generation model based on the information matching instructions;

[0031] The case file image corresponding to the initial case data is denoised to obtain the initial case file image. The initial matching text is then identified in the initial case file image using a text recognition model.

[0032] Using a text summarization generation model, case matching summaries and case storage summaries are identified in the initial matching text and the case storage text corresponding to the initial case data, respectively.

[0033] The case matching summary and the case storage summary are vectorized respectively to obtain the case matching vector and the case storage vector.

[0034] Case similarity is obtained based on the case matching vector and the case storage vector, and the case similarity is compared with a preset similarity threshold;

[0035] If the case similarity is less than the similarity threshold, then the case update text is obtained based on the initial case file image and the case storage text, the case storage text is updated using the case update text, and the updated storage vector is obtained based on the updated case storage text. The updated storage vector is used as the case storage vector, and the process returns to the step of obtaining the case similarity based on the case matching vector and the case storage vector, until the case similarity is greater than or equal to the similarity threshold.

[0036] If the case similarity is greater than or equal to the similarity threshold, the target case similarity corresponding to the target case data is obtained. After confirming that the target case similarity is greater than or equal to the similarity threshold, the initial case data and the target case data are associated.

[0037] Optionally, the step of constructing an initial retrieval database based on the single case dataset and the chained case dataset includes:

[0038] Extract chained case data sequentially from the chained case dataset, and perform the following operations on the extracted chained case data:

[0039] Using chained case data, a chained case sequence is identified in the identified case sequence. The last identified case data is extracted from the chained case sequence, and the following operations are performed on the extracted last identified case data:

[0040] The case judgment results corresponding to the identified case data are analyzed to obtain the case accountability type, which includes: repeat offender or non-repeat offender;

[0041] After confirming that the case is a repeat offender, the case judgment result is analyzed to obtain multiple judgment text summaries. The last identified case data is removed from the chained case sequence to obtain a filtered case sequence. Multiple filtered text summary groups are obtained using the filtered case sequence. Each filtered text summary group includes one or more filtered text summaries, and the filtered text summary group corresponds one-to-one with the identified case data in the filtered case sequence.

[0042] In a combined manner, matching text nodes are obtained based on the judgment text summaries in multiple judgment text summaries and the corresponding filtering text summaries in multiple filtering text summary groups. The text node similarity is obtained based on the matching text nodes, and the text node similarity is compared with the preset recidivist similarity threshold.

[0043] If the text node similarity is greater than or equal to the repeat offender similarity threshold, the identified case data corresponding to the text node similarity is retained; otherwise, the identified case data corresponding to the text node similarity is removed, and the removed identified case data is identified as single case data.

[0044] The retained identified case data is aggregated to obtain an updated identified dataset. The chained case data is updated using the updated identified dataset to obtain updated chained data. The case identifier node of each identified case data in the multiple identified case data corresponding to the updated chained data is identified. The case identifier node includes the case definition and the case result. The updated chained data is identified using the case identifier node to obtain the identified chained data.

[0045] Based on the single case data, single identifier data is obtained, and the chain of identifier data and single identifier data are aggregated to obtain the initial retrieval database.

[0046] Optionally, the matching text node is as follows:

[0047] P = {p i ,s j(k)}

[0048] Where P represents the matching text node, p i Let s represent the i-th judgment text digest among multiple judgment text digests. j(k) This represents the k-th filtered text summary corresponding to the j-th filtered text summary group among multiple filtered text summary groups.

[0049] Optionally, optimizing the initial retrieval database to obtain a case retrieval database includes:

[0050] Obtain the implementation target type for classification, which includes adults or minors. Determine the classification type based on the implementation target type and the case accountability type, which includes: non-recidivist-adult, non-recidivist-minor, and recidivist.

[0051] Based on the classification type, the initial retrieval data in the initial retrieval database are summarized to obtain three classification datasets. The initial retrieval data consists of single-identifier data or chain-identifier data. The three classification datasets are the non-recidivist-adult classification dataset, the non-recidivist-juvenile classification dataset, and the recidivist classification dataset.

[0052] The non-recidivist-adult classification dataset is stored in a pre-built first storage unit, the non-recidivist-juvenile classification dataset is stored in a pre-built second storage unit, and the recidivist classification dataset is stored in a pre-built third storage unit to obtain the case retrieval database.

[0053] Optionally, the step of using the user information node to perform a search in the case retrieval database to obtain an initial retrieval dataset includes:

[0054] Based on the user information node, obtain the identifier analysis data or the analysis chain data that identifies the analysis identifier node. Using the identifier analysis data or the analysis chain data, retrieve the single identifier data or the chain data that is the same as the analysis identifier node from the case retrieval database to obtain the initial retrieval dataset, wherein the initial retrieval dataset includes multiple initial retrieval data.

[0055] Optionally, identifying the target retrieval data sequence based on the initial retrieval dataset includes:

[0056] For each piece of initial search data in the initial search dataset, perform the following operation:

[0057] The target retrieval vector and the user retrieval vector are obtained using the initial retrieval data, user information nodes, and a pre-constructed information dimensionality reduction model, respectively. The target retrieval vector is shown below:

[0058] M = {S, A}

[0059] Where M represents the target retrieval vector, S represents the case implementation time, and A represents the case judgment result processed based on the information dimensionality reduction model;

[0060] The analytical similarity between the target retrieval vector and the user retrieval vector is calculated using the following formula:

[0061]

[0062] Where X represents the analyzed similarity, Y represents the user retrieval vector, * represents taking the dot product, and || represents taking the modulus.

[0063] The analyzed similarities are summarized to obtain an analyzed similarity set. The analyzed similarities in the analyzed similarity set are sorted in descending order to obtain an initial analyzed similarity sequence. Based on the initial analyzed similarity sequence, the target retrieval data sequence is identified, wherein the analyzed similarity corresponding to the target retrieval data in the target retrieval data sequence is greater than a preset retrieval similarity threshold.

[0064] To achieve the above objectives, the present invention also provides a case resource analysis and matching system based on user information, comprising:

[0065] The initial database construction preparation module is used to receive case matching instructions and confirm the case matching system based on the case matching instructions. The case matching system includes: an information collection unit, an information analysis unit, an information matching unit, and a result feedback unit.

[0066] The initial database construction module is used to confirm the receipt of information collection instructions from the information collection unit, and to confirm the historical case dataset based on the information collection instructions. The historical case dataset includes multiple historical case data, and the historical case data includes: case file images, case storage text, and case judgment results.

[0067] Use the historical case dataset to obtain an identified case dataset, and construct an initial retrieval database based on the identified case dataset;

[0068] The initial database optimization module is used to optimize the initial retrieval database to obtain a case retrieval database;

[0069] The user information analysis and matching module is used to obtain the user's user identification code, confirm receipt of the information analysis instruction from the information analysis unit, obtain user information nodes based on the information analysis instruction and the user identification code, wherein the user information node includes m user case data and known user data, and m is an integer greater than or equal to 0. Using the user information node, a search is performed in the case retrieval database to obtain an initial retrieval dataset.

[0070] Based on the initial search dataset, a target search data sequence is identified, wherein the target search data sequence includes multiple target search data.

[0071] The result feedback unit is used to send the target retrieval data sequence to the initiator of the case matching instruction, thereby realizing the analysis and matching of case resources.

[0072] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0073] A memory that stores at least one instruction; and a processor that executes the instructions stored in the memory to implement the case resource analysis and matching method based on user information described above.

[0074] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned case resource analysis and matching method based on user information.

[0075] To address the problems described in the background art, this invention confirms receipt of an information collection instruction from an information collection unit. Based on this instruction, a historical case dataset is identified. This historical case dataset includes multiple historical case data, which include case file images, stored case text, and case judgment results. This invention considers not only the electronic stored case text but also the corresponding case file images. It uses information recognition in the case file images to determine the correctness of the stored case text and to update and correct it. This invention utilizes the historical case dataset to obtain an identified case dataset and constructs an initial retrieval database based on this dataset. This embodiment considers only the time factor when constructing the initial retrieval database, classifying different types of cases to reduce energy consumption during classification. Optimizing the initial retrieval database yields a case retrieval database. This invention further refines the classified cases based on different case circumstances to improve the accuracy of the constructed case retrieval database. This invention obtains a user's identification code, confirms receipt of an information analysis command from an information analysis unit, and obtains a user information node based on the information analysis command and the user identification code. The user information node includes m user case data and known user data, where m is an integer greater than or equal to 0. Using the user information node, a search is performed in the case retrieval database to obtain an initial retrieval dataset. It is evident that this invention, when combining user information for retrieval, considers both known and unknown case information within the user information and obtains a user retrieval vector based on the user information. Furthermore, when obtaining the user retrieval vector, dimensionality reduction processing is performed on the user information to improve the accuracy and timeliness of the retrieval. Therefore, this invention can achieve case resource analysis and matching combined with user information. Attached Figure Description

[0076] Figure 1 This is a flowchart illustrating a case resource analysis and matching method based on user information provided in an embodiment of the present invention.

[0077] Figure 2 This is a functional block diagram of a case resource analysis and matching system based on user information provided in an embodiment of the present invention;

[0078] Figure 3 This is a schematic diagram of the structure of an electronic device that implements the case resource analysis and matching method based on user information, according to an embodiment of the present invention.

[0079] Explanation of reference numerals in the attached figures:

[0080] 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0081] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0082] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0083] This application provides a case resource analysis and matching method based on user information. The executing entity of the case resource analysis and matching method based on user information includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application embodiment: a server, a terminal, etc. In other words, the case resource analysis and matching method based on user information can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0084] Reference Figure 1 The diagram shown is a flowchart illustrating a case resource analysis and matching method based on user information according to an embodiment of the present invention. In this embodiment, the case resource analysis and matching method based on user information includes:

[0085] S1. Receive a case matching instruction and confirm the case matching system based on the case matching instruction. The case matching system includes: an information collection unit, an information analysis unit, an information matching unit, and a result feedback unit.

[0086] It should be explained that the case matching instruction refers to an instruction used to match case resources. The case matching system refers to an APP or mini-program used to match cases, and the case matching system includes: an information collection unit, an information analysis unit, an information matching unit, and a result feedback unit. For specific applications of these units, please refer to subsequent embodiments. The main objective of this embodiment is to achieve the analysis and matching of case resources based on user information. Generally, sentencing in criminal cases usually requires consideration of multiple factors, and the circumstances of criminal cases are quite complex. Therefore, this embodiment mainly focuses on achieving the matching analysis of criminal cases.

[0087] For example, in order to obtain historical case data as a reference for judgment, Xiao Zhang issues the case matching instruction, and confirms a case matching system that can match the historical case dataset with the user's case information based on the case matching instruction. Then, the judgment result corresponding to the case information is analyzed by combining the matched historical case data.

[0088] S2. Confirm receipt of information collection instructions from the information collection unit, and confirm the historical case dataset based on the information collection instructions. The historical case dataset includes multiple historical case data, and the historical case data includes: case file images, case storage text, and case judgment results.

[0089] It should be explained that the historical case data refers to criminal cases that have been adjudicated and recorded. Optionally, the historical case dataset is obtained by recording or aggregating historical case data already stored in the files.

[0090] Furthermore, a criminal case refers to a case in which a person violates criminal law and commits an act that is seriously harmful to society, criminally illegal, and punishable by law. A case file image refers to an image of a case file containing case information. Case storage text refers to text containing case information stored on an electronic device. Ideally, the case information stored in the case file image should be consistent with the case information stored in the case storage text. A case judgment result refers to the outcome of a judgment on a case corresponding to historical case data, which includes, but is not limited to, imprisonment, economic compensation, and whether forgiveness has been obtained.

[0091] For example, in order to improve the accuracy of judgments against perpetrators, similar cases involving the perpetrator are retrieved from historical case datasets and used as references to improve the accuracy of judgments against perpetrators.

[0092] S3. Use the historical case dataset to obtain the identified case dataset, and build an initial retrieval database based on the identified case dataset.

[0093] It should be understood that obtaining the identified case dataset using the historical case dataset includes:

[0094] Historical case data is extracted sequentially from the historical case dataset, and the following operations are performed on the extracted historical case data:

[0095] Parse the case storage text corresponding to the historical case data to obtain the perpetrator identification code and the case execution time, and obtain the case completion time of the historical case data;

[0096] The extracted historical case data is identified by using the perpetrator identification code, case execution time, and case completion time corresponding to the historical case data, thus obtaining identified case data;

[0097] The identified case data is then aggregated to obtain the identified case dataset.

[0098] Understandably, the perpetrator identification code refers to the code used to identify the person subject to enforcement at the time of a case judgment. Optionally, the perpetrator's ID card number can be used as the perpetrator identification code. Generally, if a crime is committed again within the effective period of accountability following a case judgment, it may affect the sentencing. For example, if a crime is committed again within 5 years after the completion of a previous sentence or pardon, it may result in concurrent sentencing. The case completion time refers to the time after the perpetrator completes their sentence or is pardoned. The case commissioning time refers to the time when the perpetrator commits the crime. The purpose of identifying historical case data is to improve the speed of analyzing different historical case data, to adapt to the special circumstances of different historical case data, and to improve the accuracy of user information analysis and matching.

[0099] For example, if the perpetrator identification code corresponding to the historical case data is 1, and the case completion time is year A, month B, day C, and the case execution time is year A, month B, day D, then the identified case data obtained by identifying the extracted historical case data using the perpetrator identification code, the case execution time, and the case completion time is: 1-year A, month B, day D-year A, month B, day C.

[0100] Further, the construction of the initial retrieval database based on the identified case dataset includes:

[0101] Based on the actor identification code, the identified case data in the identified case dataset are summarized to obtain the analyzed case data set. The analyzed case data set includes multiple analyzed case data sets, and each analyzed case data set includes one or more identified case data, and the actor identification code corresponding to one or more identified case data is the same.

[0102] For each case data set in the case data set analysis group set, perform the following operations:

[0103] The identified case data in the case data group are sorted according to the order of case completion time to obtain the identified case sequence;

[0104] Initial case data is extracted sequentially from the identified case sequence, and the following operations are performed on the extracted initial case data:

[0105] Based on the initial case data, target case data is identified in the identified case sequence, wherein the target case data is the identified case data that is adjacent to and follows the initial case data;

[0106] The effective prosecution time is obtained based on the case completion time, and the effective prosecution time is compared with the case implementation time corresponding to the target case data.

[0107] If the time of the case is less than or equal to the effective prosecution time, then determine whether to associate the initial case data and the target case data;

[0108] If the initial case data and the target case data are confirmed to be associated, then the initial case data and the target case data are associated to obtain chain case data, and the target case data in the chain case data is used as the initial case data. The step of confirming the target case data in the identified case sequence based on the initial case data is returned. The identified case data in the identified case sequence that do not constitute the chain case data are summarized to obtain a single case dataset. The chain case data are summarized to obtain a chain case dataset.

[0109] An initial retrieval database is constructed based on the single case dataset and the chained case dataset.

[0110] It should be explained that the effective prosecution time refers to the sum of the case completion time and the preset effective accountability time. Under normal circumstances, the effective accountability time is 5 years. The purpose of obtaining the effective prosecution time is to determine whether the offender is a repeat offender from a time perspective. Here, the purpose of using only the effective prosecution time for screening is to improve the speed of screening the data of identified cases and reduce the energy consumption required for screening.

[0111] Furthermore, when adjudicating cases, the perpetrator's previous criminal record is usually considered, which influences sentencing. For example, if a perpetrator's behavior is egregious, involves multiple violations of the law within the effective prosecution period, and impacts public safety, a heavier sentence will be imposed. Determining the correlation between the initial and target case data aims to assess whether the initial case data influences the target case data, thereby improving the accuracy of case analysis and matching of user information.

[0112] For example, the case data group contains 6 identified case data. By sorting the case completion times corresponding to the 6 identified case data in chronological order, an identified case sequence is obtained. In this sequence, the case completion time corresponding to the second identified case data is less than or equal to the effective prosecution time calculated from the first identified case data. Furthermore, if the initial case data and the target case data are confirmed to be related, it is considered that the case corresponding to the first identified case data will affect the case corresponding to the second identified case data. Therefore, the initial case data and the target case data are associated. Generally, a perpetrator may not commit another crime within the effective prosecution time after committing a crime. Therefore, not all identified case data in the identified case sequence will constitute the aforementioned chain of case data. Identified case data that does not constitute a chain of case data can be used as a reference for sentencing a single crime. Since only the time factor was considered when obtaining the chain of case data, the confirmed chain of case data may not be related. For further steps on filtering the chain of case data, please refer to subsequent embodiments.

[0113] Furthermore, the determination of whether the initial case data and the target case data are associated includes:

[0114] Confirm receipt of information matching instructions from the information matching unit, and confirm the character recognition model and text summarization generation model based on the information matching instructions;

[0115] The case file image corresponding to the initial case data is denoised to obtain the initial case file image. The initial matching text is then identified in the initial case file image using a text recognition model.

[0116] Using a text summarization generation model, case matching summaries and case storage summaries are identified in the initial matching text and the case storage text corresponding to the initial case data, respectively.

[0117] The case matching summary and the case storage summary are vectorized respectively to obtain the case matching vector and the case storage vector.

[0118] Case similarity is obtained based on the case matching vector and the case storage vector, and the case similarity is compared with a preset similarity threshold;

[0119] If the case similarity is less than the similarity threshold, then the case update text is obtained based on the initial case file image and the case storage text, the case storage text is updated using the case update text, and the updated storage vector is obtained based on the updated case storage text. The updated storage vector is used as the case storage vector, and the process returns to the step of obtaining the case similarity based on the case matching vector and the case storage vector, until the case similarity is greater than or equal to the similarity threshold.

[0120] If the case similarity is greater than or equal to the similarity threshold, the target case similarity corresponding to the target case data is obtained. After confirming that the target case similarity is greater than or equal to the similarity threshold, the initial case data and the target case data are associated.

[0121] It should be explained that a text recognition model refers to a model, unit, or algorithm capable of recognizing text in an image. Optionally, an optical character recognition algorithm can be used as the text recognition model; other techniques can achieve the same effect and will not be elaborated further. A text summarization generation model refers to a model, unit, or algorithm that generates a summary of a given utterance. Optionally, a natural language processing model can be used as the text summarization generation model. Optionally, a bilateral filtering algorithm can be used to denoise the case file image; the technique of using a bilateral filtering algorithm to denoise images is existing technology and will not be elaborated further. Optionally, a natural language processing model can be used to perform vectorization transformations on the case matching summary and the case storage summary, respectively. Here, vectorization transformation refers to converting text into vectors that can be used for computation; the technique of performing vectorization transformations on text is existing technology and will not be elaborated further.

[0122] Furthermore, case files undergo multiple steps such as review and proofreading before storage, and are typically properly stored when storing case files corresponding to case file images. Therefore, the information corresponding to case file images should be accurate. However, stored case text may contain errors due to human input or other factors. Therefore, this application uses a method of mutual verification between case file images and stored case text to ensure the accuracy of the constructed case retrieval database, thereby improving the accuracy of case resource matching for user information. Optionally, the Euclidean distance between the case matching vector and the case storage vector can be used as the case similarity; other techniques can achieve the same effect, and will not be elaborated further here. Obtaining updated case text using initial case file images and stored case text refers to comparing the text information corresponding to the initial case file image with the text information corresponding to the stored case text and correcting any errors. Optionally, the correction of stored case text can be achieved manually. The method for obtaining target case similarity using target case data is the same as the method for obtaining case similarity using initial case data, and will not be elaborated further here. Generally speaking, if the initial case file images are difficult to identify due to accidental factors, the initial case data should be discarded.

[0123] It should be explained that the construction of the initial retrieval database based on the single case dataset and the chained case dataset includes:

[0124] Extract chained case data sequentially from the chained case dataset, and perform the following operations on the extracted chained case data:

[0125] Using chained case data, a chained case sequence is identified in the identified case sequence. The last identified case data is extracted from the chained case sequence, and the following operations are performed on the extracted last identified case data:

[0126] The case judgment results corresponding to the identified case data are analyzed to obtain the case accountability type, which includes: repeat offender or non-repeat offender;

[0127] After confirming that the case is a repeat offender, the case judgment result is analyzed to obtain multiple judgment text summaries. The last identified case data is removed from the chained case sequence to obtain a filtered case sequence. Multiple filtered text summary groups are obtained using the filtered case sequence. Each filtered text summary group includes one or more filtered text summaries, and the filtered text summary group corresponds one-to-one with the identified case data in the filtered case sequence.

[0128] In a combined manner, matching text nodes are obtained based on the judgment text summaries in multiple judgment text summaries and the corresponding filtering text summaries in multiple filtering text summary groups. The text node similarity is obtained based on the matching text nodes, and the text node similarity is compared with the preset recidivist similarity threshold.

[0129] If the text node similarity is greater than or equal to the repeat offender similarity threshold, the identified case data corresponding to the text node similarity is retained; otherwise, the identified case data corresponding to the text node similarity is removed, and the removed identified case data is identified as single case data.

[0130] The retained identified case data is aggregated to obtain an updated identified dataset. The chained case data is updated using the updated identified dataset to obtain updated chained data. The case identifier node of each identified case data in the multiple identified case data corresponding to the updated chained data is identified. The case identifier node includes the case definition and the case result. The updated chained data is identified using the case identifier node to obtain the identified chained data.

[0131] Based on the single case data, single identifier data is obtained, and the chain of identifier data and single identifier data are aggregated to obtain the initial retrieval database.

[0132] Understandably, the matching text nodes are as follows:

[0133] P = {p i ,s j(k)}

[0134] Where P represents the matching text node, p i Let s represent the i-th judgment text digest among multiple judgment text digests.j(k) This represents the k-th filtered text summary corresponding to the j-th filtered text summary group among multiple filtered text summary groups.

[0135] Furthermore, recidivism refers to a criminal who, after serving their sentence or being pardoned, commits another crime within the statutory period. Recidivists are typically sentenced more severely. Non-recidivists are the complement of recidivists. Generally, if a case is classified as recidivism, the previous crimes that establish recidivism are usually noted during sentencing. A judgment summary is the text of each crime that constitutes recidivism, and the judgment usually states that the offender is a recidivist or has been identified as such. Therefore, the case's classification can be determined from the judgment.

[0136] It should be explained that not every case data point in the case screening sequence can serve as evidence of recidivism. For example, in the case of negligent crime, the case data cannot serve as evidence of recidivism; negligent crime here refers to unintentional crime. Generally, the text corresponding to the case data may be more than one that characterizes the crime. Therefore, the set of screened text summaries obtained using the case data in the case screening sequence may contain more than one screened text summary. The methods for obtaining screened text summaries and judgment text summaries are the same as those for obtaining case matching summaries, and will not be repeated here.

[0137] Furthermore, text node similarity refers to the similarity between the judgment text summary and the filter text summary included in the matching text node. The method for obtaining text node similarity is the same as the method for obtaining case similarity, and will not be repeated here. The difference between the recidivism similarity threshold and the similarity threshold is that the recidivism similarity threshold is used to determine whether a criminal's previous crimes constitute recidivism, thereby filtering out case data that cannot be used as a basis for recidivism, thus improving the accuracy of case resource matching for user information. The similarity threshold, on the other hand, is used to determine whether the stored case text is correct. Therefore, under normal circumstances, the recidivism similarity threshold should be greater than the similarity threshold. Generally, if at least one text node similarity exists among one or more text node similarities corresponding to the same identified case data, the identified case data can be retained.

[0138] It is understood that the case definition refers to the definition given by laws and regulations when classifying a case. For example: burglary, attempted burglary. The case outcome refers to the result produced in the case. For example: economic loss, disability, injury. The method for obtaining single-identification data using the single case data is the same as the method for obtaining chain-identification data using the updated chain-data, and will not be repeated here. Updating chain-data refers to the chain-case data after removing identified case data that does not meet the conditions from the chain-case data.

[0139] S4. Optimize the initial retrieval database to obtain the case retrieval database.

[0140] It should be explained that optimizing the initial retrieval database to obtain the case retrieval database includes:

[0141] Obtain the implementation target type for classification, which includes adults or minors. Determine the classification type based on the implementation target type and the case accountability type, which includes: non-recidivist-adult, non-recidivist-minor, and recidivist.

[0142] Based on the classification type, the initial retrieval data in the initial retrieval database are summarized to obtain three classification datasets. The initial retrieval data consists of single-identifier data or chain-identifier data. The three classification datasets are the non-recidivist-adult classification dataset, the non-recidivist-juvenile classification dataset, and the recidivist classification dataset.

[0143] The non-recidivist-adult classification dataset is stored in a pre-built first storage unit, the non-recidivist-juvenile classification dataset is stored in a pre-built second storage unit, and the recidivist classification dataset is stored in a pre-built third storage unit to obtain the case retrieval database.

[0144] Understandably, "adult" refers to an adult who was an adult at the time of the crime, and "minor" refers to a minor who was a minor at the time of the crime. "Non-recidivist - Adult" means the offender is an adult and the case is classified as non-recidivist. "Non-recidivist - Minor" means the offender is a minor and the case is classified as non-recidivist. Generally, recidivism is only possible when the offender is an adult. The purpose of aggregating the initial search data from the initial search database according to classification type is to achieve categorized management of different types of cases, thereby improving the efficiency of case searches for users and reducing the energy consumption required for case searches.

[0145] S5. Obtain the user's user identification code, confirm receipt of the information analysis instruction from the information analysis unit, obtain the user information node based on the information analysis instruction and the user identification code, wherein the user information node includes m user case data and known user data, and m is an integer greater than or equal to 0, and use the user information node to perform a search in the case retrieval database to obtain the initial retrieval dataset.

[0146] It is understood that the user identification code refers to an identification code that can confirm the user's identity, and the definition of the user identification code is the same as that of the perpetrator identification code, which will not be repeated here. Optionally, the user information node can be obtained by searching a known database using the user identification code, and the definition of user case data is the same as that of historical case data, which will not be repeated here. Known user data refers to information about users known in a case. Optionally, the known user data can be obtained after collecting evidence of information, and other technologies can achieve the same effect, which will not be repeated here. Generally speaking, the difference between known user data and user case data is that user case data represents established facts, while known user data contains facts that have not yet been determined. For example, if a user actively cooperates with the police in collecting evidence and actively obtains a letter of forgiveness after committing a crime, it may reduce the user's sentence.

[0147] Furthermore, the step of using the user information node to perform a search in the case retrieval database to obtain an initial retrieval dataset includes:

[0148] Based on the user information node, obtain the identifier analysis data or the analysis chain data that identifies the analysis identifier node. Using the identifier analysis data or the analysis chain data, retrieve the single identifier data or the chain data that is the same as the analysis identifier node from the case retrieval database to obtain the initial retrieval dataset, wherein the initial retrieval dataset includes multiple initial retrieval data.

[0149] It should be explained that the method for obtaining the analysis identifier node is the same as the method for obtaining the case identifier node, and will not be repeated here. The definitions of analysis chain data and update chain data are the same, and will not be repeated here. The definition of identifier analysis data is the same as the definition of identifier case data, and will not be repeated here. Optionally, analysis chain data or identifier analysis data can be provided after analysis by law in conjunction with user information nodes. The initial retrieval dataset includes multiple initial retrieval data, and the initial retrieval data is single identifier data or identifier chain data retrieved from the case retrieval database.

[0150] S6. Based on the initial search dataset, a target search data sequence is identified, wherein the target search data sequence includes multiple target search data.

[0151] It is understood that identifying the target retrieval data sequence based on the initial retrieval dataset includes:

[0152] For each piece of initial search data in the initial search dataset, perform the following operation:

[0153] The target retrieval vector and the user retrieval vector are obtained using the initial retrieval data, user information nodes, and a pre-constructed information dimensionality reduction model, respectively. The target retrieval vector is shown below:

[0154] M = {S, A}

[0155] Where M represents the target retrieval vector, S represents the case implementation time, and A represents the case judgment result processed based on the information dimensionality reduction model;

[0156] The analytical similarity between the target retrieval vector and the user retrieval vector is calculated using the following formula:

[0157]

[0158] Where X represents the analyzed similarity, Y represents the user retrieval vector, * represents taking the dot product, and || represents taking the modulus.

[0159] The analyzed similarities are summarized to obtain an analyzed similarity set. The analyzed similarities in the analyzed similarity set are sorted in descending order to obtain an initial analyzed similarity sequence. Based on the initial analyzed similarity sequence, the target retrieval data sequence is identified, wherein the analyzed similarity corresponding to the target retrieval data in the target retrieval data sequence is greater than a preset retrieval similarity threshold.

[0160] It should be explained that the purpose of the information dimensionality reduction model is to remove unnecessary information from the case judgment results, retaining only the necessary information. For example, the case judgment result is: Wang committed burglary on a certain date, stealing item A and item B, causing economic losses of 30,000 yuan. The judgment against Wang is as follows: Wang is ordered to compensate the victim for economic losses totaling 40,000 yuan and is sentenced to six months imprisonment. Here, the date of the incident is the time of the incident. After processing the case judgment result through the information dimensionality reduction model, we get: economic loss of 30,000 yuan, compensation for economic losses of 40,000 yuan, and six months imprisonment. Optionally, a natural language processing model can be used as the information dimensionality reduction model; other technologies can achieve the same effect, which will not be elaborated here. It is generally understood that the purchasing power of money varies at different times; therefore, by setting the case execution time and the processed case judgment result as the basis, the accuracy of matching case resources with user information can be improved.

[0161] Furthermore, the method for obtaining the user retrieval vector is the same as the method for obtaining the target retrieval vector, and can achieve the same effect, so it will not be described again here.

[0162] S7. The target retrieval data sequence is sent to the initiating end of the case matching instruction using the result feedback unit to realize the analysis and matching of case resources.

[0163] To address the problems described in the background art, this invention confirms receipt of an information collection instruction from an information collection unit. Based on this instruction, a historical case dataset is identified. This historical case dataset includes multiple historical case data, which include case file images, stored case text, and case judgment results. This invention considers not only the electronic stored case text but also the corresponding case file images. It uses information recognition in the case file images to determine the correctness of the stored case text and to update and correct it. This invention utilizes the historical case dataset to obtain an identified case dataset and constructs an initial retrieval database based on this dataset. This embodiment considers only the time factor when constructing the initial retrieval database, classifying different types of cases to reduce energy consumption during classification. Optimizing the initial retrieval database yields a case retrieval database. This invention further refines the classified cases based on different case circumstances to improve the accuracy of the constructed case retrieval database. This invention obtains a user's identification code, confirms receipt of an information analysis command from an information analysis unit, and obtains a user information node based on the information analysis command and the user identification code. The user information node includes m user case data and known user data, where m is an integer greater than or equal to 0. Using the user information node, a search is performed in the case retrieval database to obtain an initial retrieval dataset. It is evident that this invention, when combining user information for retrieval, considers both known and unknown case information within the user information and obtains a user retrieval vector based on the user information. Furthermore, when obtaining the user retrieval vector, dimensionality reduction processing is performed on the user information to improve the accuracy and timeliness of the retrieval. Therefore, this invention can achieve case resource analysis and matching combined with user information.

[0164] like Figure 2 The diagram shown is a functional block diagram of a case resource analysis and matching system based on user information provided in an embodiment of the present invention.

[0165] The case resource analysis and matching system 100 based on user information described in this invention can be installed in an electronic device. Depending on the functions implemented, the case resource analysis and matching system 100 may include an initial database construction preparation module 101, an initial database construction module 102, an initial database optimization module 103, and a user information analysis and matching module 104. The module described in this invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0166] The initial database construction preparation module 101 is used to receive case matching instructions and confirm the case matching system based on the case matching instructions. The case matching system includes: an information collection unit, an information analysis unit, an information matching unit, and a result feedback unit.

[0167] The initial database construction module 102 is used to confirm receiving the information collection instruction from the information collection unit, and to confirm the historical case dataset based on the information collection instruction. The historical case dataset includes multiple historical case data, and the historical case data includes: case file images, case storage text, and case judgment results.

[0168] Use the historical case dataset to obtain an identified case dataset, and construct an initial retrieval database based on the identified case dataset;

[0169] The initial database optimization module 103 is used to optimize the initial retrieval database to obtain a case retrieval database;

[0170] The user information analysis and matching module 104 is used to obtain the user's user identification code, confirm receipt of the information analysis instruction from the information analysis unit, obtain user information nodes based on the information analysis instruction and the user identification code, wherein the user information node includes m user case data and known user data, and m is an integer greater than or equal to 0, and uses the user information node to perform a search in the case retrieval database to obtain an initial retrieval dataset;

[0171] Based on the initial search dataset, a target search data sequence is identified, wherein the target search data sequence includes multiple target search data.

[0172] The result feedback unit is used to send the target retrieval data sequence to the initiator of the case matching instruction, thereby realizing the analysis and matching of case resources.

[0173] In detail, the modules in the case resource analysis and matching system 100 based on user information described in this embodiment of the invention employ the same methods as described above. Figure 1The method uses the same technical means as the case resource analysis and matching method based on user information described in the article, and can produce the same technical effect, so it will not be elaborated here.

[0174] like Figure 3 The diagram shown is a structural schematic of an electronic device for implementing a case resource analysis and matching method based on user information, according to an embodiment of the present invention.

[0175] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a case resource analysis and matching method program based on user information.

[0176] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a case resource analysis and matching method program based on user information, but also to temporarily store data that has been output or will be output.

[0177] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a case resource analysis and matching method program based on user information) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0178] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0179] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0180] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management system, thereby enabling functions such as charging management, discharging management, and power consumption management through the power management system. The power supply may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0181] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0182] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0183] The case resource analysis and matching method program based on user information stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0184] The system receives a case matching instruction and confirms the case matching system based on the instruction. The case matching system includes: an information collection unit, an information analysis unit, an information matching unit, and a result feedback unit.

[0185] The system confirms receipt of an information collection instruction from the information collection unit and identifies a historical case dataset based on the information collection instruction. The historical case dataset includes multiple historical case data, and the historical case data includes: case file images, case storage text, and case judgment results.

[0186] Use the historical case dataset to obtain an identified case dataset, and construct an initial retrieval database based on the identified case dataset;

[0187] The initial retrieval database is optimized to obtain a case retrieval database;

[0188] Obtain the user's user identification code, confirm receipt of the information analysis instruction from the information analysis unit, obtain the user information node based on the information analysis instruction and the user identification code, wherein the user information node includes m user case data and known user data, and m is an integer greater than or equal to 0, and use the user information node to perform a search in the case retrieval database to obtain the initial retrieval dataset;

[0189] Based on the initial search dataset, a target search data sequence is identified, wherein the target search data sequence includes multiple target search data.

[0190] The result feedback unit is used to send the target retrieval data sequence to the initiator of the case matching instruction, thereby realizing the analysis and matching of case resources.

[0191] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0192] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0193] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0194] The system receives a case matching instruction and confirms the case matching system based on the instruction. The case matching system includes: an information collection unit, an information analysis unit, an information matching unit, and a result feedback unit.

[0195] The system confirms receipt of an information collection instruction from the information collection unit and identifies a historical case dataset based on the information collection instruction. The historical case dataset includes multiple historical case data, which in turn includes: case file images, case storage text, and case judgment results.

[0196] Use the historical case dataset to obtain an identified case dataset, and construct an initial retrieval database based on the identified case dataset;

[0197] The initial retrieval database is optimized to obtain a case retrieval database;

[0198] Obtain the user's user identification code, confirm receipt of the information analysis instruction from the information analysis unit, obtain the user information node based on the information analysis instruction and the user identification code, wherein the user information node includes m user case data and known user data, and m is an integer greater than or equal to 0, and use the user information node to perform a search in the case retrieval database to obtain the initial retrieval dataset;

[0199] Based on the initial search dataset, a target search data sequence is identified, wherein the target search data sequence includes multiple target search data.

[0200] The result feedback unit is used to send the target retrieval data sequence to the initiator of the case matching instruction, thereby realizing the analysis and matching of case resources.

[0201] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0202] The modules described as separate components may or may not be physically separate. The components shown as modules 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 modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0203] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0204] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0205] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A case resource analysis and matching method based on user information, characterized in that, The method includes: The system receives a case matching instruction and confirms the case matching system based on the instruction. The case matching system includes: an information collection unit, an information analysis unit, an information matching unit, and a result feedback unit. The system confirms receipt of an information collection instruction from the information collection unit and identifies a historical case dataset based on the information collection instruction. The historical case dataset includes multiple historical case data, and the historical case data includes: case file images, case storage text, and case judgment results. Use the historical case dataset to obtain an identified case dataset, and construct an initial retrieval database based on the identified case dataset; The step of obtaining the identified case dataset using the historical case dataset includes: Historical case data is extracted sequentially from the historical case dataset, and the following operations are performed on the extracted historical case data: Parse the case storage text corresponding to the historical case data to obtain the perpetrator identification code and the case execution time, and obtain the case completion time of the historical case data; The extracted historical case data is identified by using the perpetrator identification code, case execution time, and case completion time corresponding to the historical case data, thus obtaining identified case data; By summarizing the identified case data, an identified case dataset is obtained; The step of constructing the initial retrieval database based on the identified case dataset includes: Based on the actor identification code, the identified case data in the identified case dataset are summarized to obtain the analyzed case data set. The analyzed case data set includes multiple analyzed case data sets, and each analyzed case data set includes one or more identified case data, and the actor identification code corresponding to one or more identified case data is the same. For each case data set in the case data set analysis group set, perform the following operations: The identified case data in the case data group are sorted according to the order of case completion time to obtain the identified case sequence; Initial case data is extracted sequentially from the identified case sequence, and the following operations are performed on the extracted initial case data: Based on the initial case data, target case data is identified in the identified case sequence, wherein the target case data is the identified case data that is adjacent to and follows the initial case data; The effective prosecution time is obtained based on the case completion time, and the effective prosecution time is compared with the case implementation time corresponding to the target case data. If the time of the case is less than or equal to the effective prosecution time, then determine whether to associate the initial case data and the target case data; If the initial case data and the target case data are confirmed to be associated, then the initial case data and the target case data are associated to obtain chain case data, and the target case data in the chain case data is used as the initial case data. The step of confirming the target case data in the identified case sequence based on the initial case data is returned. The identified case data in the identified case sequence that do not constitute the chain case data are summarized to obtain a single case dataset. The chain case data are summarized to obtain a chain case dataset. An initial retrieval database is constructed based on the single case dataset and the chained case dataset; The initial retrieval database is optimized to obtain a case retrieval database; Obtain the user's user identification code, confirm receipt of the information analysis instruction from the information analysis unit, and obtain the user information node based on the information analysis instruction and the user identification code. The user information node includes m user case data and known user data, where m is an integer greater than or equal to 0. Using the user information node, a search is performed in the case retrieval database to obtain an initial retrieval dataset. The difference between the known user data and the user case data is that the user case data represents established facts, while the known user data contains facts that have not yet been determined. Based on the initial search dataset, a target search data sequence is identified, wherein the target search data sequence includes multiple target search data. The result feedback unit is used to send the target retrieval data sequence to the initiator of the case matching instruction, thereby realizing the analysis and matching of case resources.

2. The case resource analysis and matching method based on user information as described in claim 1, characterized in that, The determination of whether the initial case data and the target case data are associated includes: Confirm receipt of information matching instructions from the information matching unit, and confirm the character recognition model and text summarization generation model based on the information matching instructions; The case file image corresponding to the initial case data is denoised to obtain the initial case file image. The initial matching text is then identified in the initial case file image using a text recognition model. Using a text summarization generation model, case matching summaries and case storage summaries are identified in the initial matching text and the case storage text corresponding to the initial case data, respectively. The case matching summary and the case storage summary are vectorized respectively to obtain the case matching vector and the case storage vector. Case similarity is obtained based on the case matching vector and the case storage vector, and the case similarity is compared with a preset similarity threshold; If the case similarity is less than the similarity threshold, then the case update text is obtained based on the initial case file image and the case storage text, the case storage text is updated using the case update text, and the updated storage vector is obtained based on the updated case storage text. The updated storage vector is used as the case storage vector, and the process returns to the step of obtaining the case similarity based on the case matching vector and the case storage vector, until the case similarity is greater than or equal to the similarity threshold. If the case similarity is greater than or equal to the similarity threshold, the target case similarity corresponding to the target case data is obtained. After confirming that the target case similarity is greater than or equal to the similarity threshold, the initial case data and the target case data are associated.

3. The case resource analysis and matching method based on user information as described in claim 2, characterized in that, The construction of the initial retrieval database based on the single case dataset and the chained case dataset includes: Extract chained case data sequentially from the chained case dataset, and perform the following operations on the extracted chained case data: Using chained case data, a chained case sequence is identified in the identified case sequence. The last identified case data is extracted from the chained case sequence, and the following operations are performed on the extracted last identified case data: The case judgment results corresponding to the identified case data are analyzed to obtain the case accountability type, which includes: repeat offender or non-repeat offender; After confirming that the case is a repeat offender, the case judgment result is analyzed to obtain multiple judgment text summaries. The last identified case data is removed from the chained case sequence to obtain a filtered case sequence. Multiple filtered text summary groups are obtained using the filtered case sequence. Each filtered text summary group includes one or more filtered text summaries, and the filtered text summary group corresponds one-to-one with the identified case data in the filtered case sequence. In a combined manner, matching text nodes are obtained based on the judgment text summaries in multiple judgment text summaries and the corresponding filtering text summaries in multiple filtering text summary groups. The text node similarity is obtained based on the matching text nodes, and the text node similarity is compared with the preset recidivist similarity threshold. If the text node similarity is greater than or equal to the repeat offender similarity threshold, the identified case data corresponding to the text node similarity is retained; otherwise, the identified case data corresponding to the text node similarity is removed, and the removed identified case data is identified as single case data. The retained identified case data is aggregated to obtain an updated identified dataset. The chained case data is updated using the updated identified dataset to obtain updated chained data. The case identifier node of each identified case data in the multiple identified case data corresponding to the updated chained data is identified. The case identifier node includes the case definition and the case result. The updated chained data is identified using the case identifier node to obtain the identified chained data. Based on the single case data, single identifier data is obtained, and the chain of identifier data and single identifier data are aggregated to obtain the initial retrieval database.

4. The case resource analysis and matching method based on user information as described in claim 3, characterized in that, The matched text nodes are shown below: in, This indicates matching text nodes. Indicates the first of multiple judgment text summaries A summary of the judgment text. Indicates the first of multiple filtered text summary groups The first group of filtered text summaries corresponds to the first... Select a text summary.

5. The case resource analysis and matching method based on user information as described in claim 4, characterized in that, The optimization of the initial retrieval database to obtain a case retrieval database includes: Obtain the implementation target type for classification, which includes adults or minors. Determine the classification type based on the implementation target type and the case accountability type, which includes: non-recidivist-adult, non-recidivist-minor, and recidivist. Based on the classification type, the initial retrieval data in the initial retrieval database are summarized to obtain three classification datasets. The initial retrieval data consists of single-identifier data or chain-identifier data. The three classification datasets are the non-recidivist-adult classification dataset, the non-recidivist-juvenile classification dataset, and the recidivist classification dataset. The non-recidivist-adult classification dataset is stored in a pre-built first storage unit, the non-recidivist-juvenile classification dataset is stored in a pre-built second storage unit, and the recidivist classification dataset is stored in a pre-built third storage unit to obtain the case retrieval database.

6. The case resource analysis and matching method based on user information as described in claim 5, characterized in that, The process of using the user information node to search the case retrieval database to obtain an initial retrieval dataset includes: Based on the user information node, obtain the identifier analysis data or the analysis chain data that identifies the analysis identifier node. Using the identifier analysis data or the analysis chain data, retrieve the single identifier data or the chain data that is the same as the analysis identifier node from the case retrieval database to obtain the initial retrieval dataset, wherein the initial retrieval dataset includes multiple initial retrieval data.

7. The case resource analysis and matching method based on user information as described in claim 6, characterized in that, The step of identifying the target retrieval data sequence based on the initial retrieval dataset includes: For each piece of initial search data in the initial search dataset, perform the following operation: The target retrieval vector and the user retrieval vector are obtained using the initial retrieval data, user information nodes, and a pre-constructed information dimensionality reduction model, respectively. The target retrieval vector is shown below: in, This represents the target retrieval vector. Indicates the time of the case's execution. This indicates the case judgment result after processing based on the information dimensionality reduction model; The analytical similarity between the target retrieval vector and the user retrieval vector is calculated using the following formula: in, This indicates the similarity of the analysis. Represents the user retrieval vector. This indicates taking the dot product. Indicates the length of the modulus; The analyzed similarities are summarized to obtain an analyzed similarity set. The analyzed similarities in the analyzed similarity set are sorted in descending order to obtain an initial analyzed similarity sequence. Based on the initial analyzed similarity sequence, the target retrieval data sequence is identified, wherein the analyzed similarity corresponding to the target retrieval data in the target retrieval data sequence is greater than a preset retrieval similarity threshold.

8. A case resource analysis and matching system based on user information, characterized in that, The system includes: The initial database construction preparation module is used to receive case matching instructions and confirm the case matching system based on the case matching instructions. The case matching system includes: an information collection unit, an information analysis unit, an information matching unit, and a result feedback unit. The initial database construction module is used to confirm the receipt of information collection instructions from the information collection unit, and to confirm the historical case dataset based on the information collection instructions. The historical case dataset includes multiple historical case data, and the historical case data includes: case file images, case storage text, and case judgment results. Use the historical case dataset to obtain an identified case dataset, and construct an initial retrieval database based on the identified case dataset; The step of obtaining the identified case dataset using the historical case dataset includes: Historical case data is extracted sequentially from the historical case dataset, and the following operations are performed on the extracted historical case data: Parse the case storage text corresponding to the historical case data to obtain the perpetrator identification code and the case execution time, and obtain the case completion time of the historical case data; The extracted historical case data is identified by using the perpetrator identification code, case execution time, and case completion time corresponding to the historical case data, thus obtaining identified case data; By summarizing the identified case data, an identified case dataset is obtained; The step of constructing the initial retrieval database based on the identified case dataset includes: Based on the actor identification code, the identified case data in the identified case dataset are summarized to obtain the analyzed case data set. The analyzed case data set includes multiple analyzed case data sets, and each analyzed case data set includes one or more identified case data, and the actor identification code corresponding to one or more identified case data is the same. For each case data set in the case data set analysis group set, perform the following operations: The identified case data in the case data group are sorted according to the order of case completion time to obtain the identified case sequence; Initial case data is extracted sequentially from the identified case sequence, and the following operations are performed on the extracted initial case data: Based on the initial case data, target case data is identified in the identified case sequence, wherein the target case data is the identified case data that is adjacent to and follows the initial case data; The effective prosecution time is obtained based on the case completion time, and the effective prosecution time is compared with the case implementation time corresponding to the target case data. If the time of the case is less than or equal to the effective prosecution time, then determine whether to associate the initial case data and the target case data; If the initial case data and the target case data are confirmed to be associated, then the initial case data and the target case data are associated to obtain chain case data, and the target case data in the chain case data is used as the initial case data. The step of confirming the target case data in the identified case sequence based on the initial case data is returned. The identified case data in the identified case sequence that do not constitute the chain case data are summarized to obtain a single case dataset. The chain case data are summarized to obtain a chain case dataset. An initial retrieval database is constructed based on the single case dataset and the chained case dataset; The initial database optimization module is used to optimize the initial retrieval database to obtain a case retrieval database; The user information analysis and matching module is used to obtain the user's user identification code, confirm receipt of the information analysis instruction from the information analysis unit, and obtain user information nodes based on the information analysis instruction and the user identification code. The user information node includes m user case data and known user data, where m is an integer greater than or equal to 0. Using the user information node, a search is performed in the case retrieval database to obtain an initial retrieval dataset. The difference between known user data and user case data is that user case data represents established facts, while known user data contains facts that have not yet been determined. Based on the initial search dataset, a target search data sequence is identified, wherein the target search data sequence includes multiple target search data. The result feedback unit is used to send the target retrieval data sequence to the initiator of the case matching instruction, thereby realizing the analysis and matching of case resources.

Images