Method, device, computer equipment and storage medium for analyzing and processing evidence materials

Through the analysis and processing methods of evidence materials for intelligent decision-making, the character recognition and evidence analysis model are used to automatically review the arbitration application materials and evidence materials, solving the problem of low audit efficiency in arbitration cases and achieving efficient and accurate review of evidence materials and arbitration Case handling.

CN110532543BActive Publication Date: 2024-11-08PING AN TECH (SHENZHEN) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN201910646371.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2019-06-14
Filing Date
2019-07-17
Publication Date
2024-11-08
Estimated Expiration
2039-07-17

Smart Images

  • Figure CN110532543B_ABST
    Figure CN110532543B_ABST
Patent Text Reader

Abstract

The present application relates to an analysis and processing method, device, computer equipment and storage medium for evidence materials based on intelligent decision-making. The method includes: obtaining arbitration application materials and evidence materials uploaded by a terminal; obtaining a preset character recognition model, performing character recognition on the arbitration application materials and evidence materials through the character recognition model, and obtaining corresponding recognition result data; extracting arbitration application information and evidence data corresponding to preset fields from the recognition result data; obtaining a preset evidence analysis model, analyzing the arbitration application information and evidence data through the evidence analysis model, and obtaining corresponding analysis results; when the analysis result indicates that the evidence review has passed, the evidence materials are determined to be valid, and the evidence materials are accepted. This method can accurately and effectively perform data analysis on arbitration application materials and evidence materials, thereby effectively improving the review efficiency of arbitration materials and the processing efficiency of arbitration cases.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, computer equipment and storage medium for analyzing and processing evidence materials based on intelligent decision-making. Background Art

[0002] With the rapid development of artificial intelligence technology, the way of assisting court trials is becoming more intelligent. In judicial practice, countries around the world have made a lot of fruitful explorations in the construction of court informatization and modernization, and have further realized the high quality and efficiency of trial work by leveraging the power of modern technology.

[0003] Currently, there are construction projects such as smart courts, which can verify the identity of the parties through facial recognition, but application materials and evidence materials still need to rely on manual review and filing. For arbitration cases, as the number of cases gradually increases, the workload of staff is heavy, and the efficiency of manual review of application materials and evidence materials is low, and there are also errors, resulting in low review accuracy and processing efficiency of arbitration cases. Therefore, how to accurately and effectively review the accuracy and efficiency of arbitration materials to improve the processing efficiency of arbitration cases has become a technical problem that needs to be solved at present. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment and storage medium for analyzing and processing evidence materials, which can accurately and effectively perform data analysis on arbitration application materials and evidence materials, thereby effectively improving the review efficiency of arbitration materials and the efficiency of arbitration case handling.

[0005] A method for analyzing and processing evidence materials, the method comprising:

[0006] Obtain arbitration application materials and evidence materials uploaded by the terminal;

[0007] Obtaining a preset character recognition model, and performing character recognition on the arbitration application materials and the evidence materials using the character recognition model to obtain corresponding recognition result data;

[0008] Extracting arbitration application information and evidence data corresponding to preset fields from the recognition result data;

[0009] Obtaining a preset evidence analysis model, and analyzing the arbitration application information and the evidence data through the evidence analysis model to obtain corresponding analysis results;

[0010] When the analysis result indicates that the evidence has passed the review, the evidence material is determined to be valid and is accepted.

[0011] In one embodiment, the step of performing character recognition on the arbitration application materials and the evidence materials through the character recognition model to obtain corresponding recognition result data includes: preprocessing the arbitration application materials and the evidence materials to obtain corresponding grayscale image data; performing character segmentation on the grayscale image data to obtain a plurality of segmented character data; performing feature extraction on the plurality of segmented character data to obtain a plurality of corresponding feature vectors; and performing recognition and analysis on the plurality of feature vectors through the character recognition model to obtain corresponding recognition result data.

[0012] In one embodiment, the step of analyzing the arbitration application information and the evidence data through the evidence analysis model to obtain the corresponding analysis results includes: extracting request information, fact information and reason information from the identification result data through the evidence analysis model; performing feature extraction on the request information, fact information and reason information and the evidence data respectively through the evidence analysis model to obtain corresponding multiple feature information; performing decision analysis on the arbitration request information, arbitration fact information and arbitration reason information and multiple feature information corresponding to the evidence data according to multiple decision nodes in the evidence analysis model; until traversing to the target decision node in the evidence analysis model, generating the corresponding analysis results according to the target decision node.

[0013] In one of the embodiments, the method also includes: receiving the reply materials and evidence materials uploaded by the respondent's terminal; obtaining a preset character recognition model, performing character recognition on the reply materials and evidence materials through the character recognition model, and obtaining corresponding recognition result data; extracting the reply data and evidence data corresponding to the preset fields from the recognition result data; obtaining a preset evidence analysis model, analyzing the reply data and evidence data through the evidence analysis model, and obtaining corresponding analysis results; when the analysis result indicates that the review is passed, determining that the evidence materials are valid, and accepting the evidence materials.

[0014] In one embodiment, the method further includes: obtaining all evidence materials corresponding to the arbitration application; obtaining a preset data mining model, performing correlation analysis on multiple pieces of evidence materials corresponding to the arbitration case through the data mining model, and obtaining associated evidence tags; and adding corresponding correlation tags to the evidence materials according to the associated evidence tags.

[0015] An analysis and processing device for evidence materials, the device comprising:

[0016] The data acquisition module is used to acquire arbitration application materials and evidence materials uploaded by the terminal;

[0017] A character recognition module, used to obtain a preset character recognition model, and perform character recognition on the arbitration application materials and the evidence materials through the character recognition model to obtain corresponding recognition result data;

[0018] The data acquisition module is also used to extract arbitration application information and evidence data corresponding to preset fields from the recognition result data;

[0019] The evidence analysis module is used to obtain a preset evidence analysis model, analyze the arbitration application information and the evidence data through the evidence analysis model, and obtain corresponding analysis results; when the analysis result indicates that the evidence review has passed, it is determined that the evidence materials are valid and the evidence materials are accepted.

[0020] In one of the embodiments, the character recognition module is also used to pre-process the arbitration application materials and the evidence materials to obtain corresponding grayscale image data; perform character segmentation on the grayscale image data to obtain a plurality of segmented character data; perform feature extraction on the plurality of segmented character data to obtain a corresponding plurality of feature vectors; perform recognition and analysis on the plurality of feature vectors through the character recognition model to obtain corresponding recognition result data.

[0021] In one of the embodiments, the evidence analysis module is also used to extract request information, factual information and reason information from the identification result data through the evidence analysis model; perform feature extraction on the request information, factual information, reason information and evidence data respectively through the evidence analysis model to obtain corresponding multiple feature information; perform decision analysis on the arbitration request information, arbitration factual information, arbitration reason information and multiple feature information corresponding to the evidence data according to multiple decision nodes in the evidence analysis model; until traversing to the target decision node in the evidence analysis model, generate the corresponding analysis result according to the target decision node.

[0022] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for analyzing and processing evidence materials provided in any embodiment of the present application are implemented.

[0023] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for analyzing and processing evidence materials provided in any embodiment of the present application.

[0024] The above-mentioned method, device, computer equipment and storage medium for analyzing and processing evidence materials obtain the arbitration application materials and evidence materials uploaded by the terminal, obtain a preset character recognition model, and perform character recognition on the arbitration application materials and evidence materials through the character recognition model, thereby effectively obtaining the corresponding recognition result data. Then, the arbitration application information and evidence data corresponding to the preset fields are extracted from the recognition result data, and the preset evidence analysis model is obtained, and the arbitration application information and evidence data are analyzed through the evidence analysis model to obtain the corresponding analysis results. When the analysis result indicates that the evidence review has passed, it is determined that the evidence materials are valid, and the evidence materials are accepted. After the data in the arbitration application materials and evidence materials are identified by the character recognition model, the evidence analysis model is further used to analyze the evidence data according to the application information, thereby accurately and effectively analyzing whether the evidence materials meet the requirements, thereby effectively improving the efficiency of the evidence material review, reducing labor costs, and effectively improving the processing efficiency of arbitration cases. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is an application scenario diagram of a method for analyzing and processing evidence materials in an embodiment;

[0026] Figure 2 A schematic diagram of a flow chart of a method for analyzing and processing evidence materials in one embodiment;

[0027] Figure 3 A flowchart of a step of performing character recognition on arbitration application materials and evidence materials by using a character recognition model in one embodiment;

[0028] Figure 4 A flowchart of steps for analyzing arbitration application information and evidence data by using an evidence analysis model in one embodiment;

[0029] Figure 5 is a structural block diagram of an analysis and processing device for evidence materials in one embodiment;

[0030] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0032] The analysis and processing method of evidence materials provided in this application can be applied to Figure 1In the application environment shown, the terminal 102 communicates with the server 104 through the network. The terminal 102 may include a terminal corresponding to the applicant, or may include a terminal corresponding to the respondent. The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0033] In one embodiment, Figure 2 As shown, a method for analyzing and processing evidence materials is provided, and the method is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0034] Step 202: Acquire arbitration application materials and evidence materials uploaded by the terminal.

[0035] The arbitration applicant may first register on the Internet arbitration platform through the corresponding terminal and fill in the identity information, which may include information corresponding to fields such as user type, certificate type, certificate number, mobile phone number, verification code and password, and may also include the user's identity document in picture format.

[0036] After the applicant has registered, he can initiate an arbitration application request on the Internet arbitration platform through the terminal. The online arbitration system is running on the server, and the server can return the arbitration application page to the terminal according to the arbitration application request. Specifically, the applicant can select the agency type and arbitration case on the Internet arbitration platform, and fill in the applicant information, the respondent information, the arbitration-related contract, the arbitration application, the arbitration clause, the arbitration application request, the arbitration facts and reasons, and the subject amount and other arbitration application information. The arbitration application materials can also include entrustment materials, which can include attorney entrustment materials and other agent entrustment materials. The applicant can also upload evidence materials and entrustment materials to the Internet arbitration platform through the terminal, where the evidence materials can include documents, pictures and other forms of files. For example, the evidence materials include the corresponding evidence list, which can include the name of the evidence file, the source of the evidence, the content of the evidence and the number of pages.

[0037] After the terminal fills in and uploads the application materials and evidence materials on the Internet arbitration platform, it further sends an arbitration application request to the server based on the application materials and evidence materials. The arbitration application request carries the arbitration application materials and evidence materials.

[0038] Step 204: Obtain a preset character recognition model, perform character recognition on the arbitration application materials and evidence materials using the character recognition model, and obtain corresponding recognition result data.

[0039] Among them, the arbitration application materials and evidence materials may contain application information in the form of pictures, photocopies, scans, and PDFs. This type of information cannot be directly recognized by the server, so the server is required to further identify the information in the arbitration application materials and evidence materials.

[0040] The server obtains the arbitration application materials and evidence materials uploaded by the terminal, and obtains a preset character recognition model, and recognizes the arbitration application materials and evidence materials through the character recognition model. Specifically, the server can grayscale, reduce noise, binarize, character segment and normalize the image format data in the arbitration application materials and evidence materials. After the server pre-processes the arbitration application materials and evidence materials, it further extracts features and reduces the dimension of the pre-processed data to obtain the corresponding feature vector, and then the server inputs the obtained feature vector into the preset character recognition model, wherein the character recognition model can be a machine learning model based on a neural network. Multiple feature vectors are identified and classified by the character recognition model to obtain corresponding recognition data.

[0041] Furthermore, after the server obtains recognition data by identifying and classifying multiple feature vectors through a character recognition model, it can further obtain a preset semantic analysis model, perform context analysis and correction on the recognition data through the semantic analysis model, and then obtain recognition result data. For example, keyword information in arbitration application materials and evidence materials can be captured through an OCR (Optical Character Recognition) character recognition model. For example: the OCR technology of the lawyer's certificate uploaded by the user identifies whether there is the keyword "lawyer's certificate" in the text. By using the OCR character recognition model to identify the arbitration application materials and evidence materials, the application information and evidence data in the arbitration application materials and evidence materials can be accurately and effectively identified.

[0042] Step 206: extract arbitration application information and evidence data corresponding to the preset fields from the recognition result data.

[0043] The server uses a character recognition model to identify the arbitration application materials and evidence materials. After obtaining the corresponding recognition result data, the recognition result data may include multiple field names and corresponding field contents. The server further extracts the application information and evidence data corresponding to the preset fields from the recognition result data. For example, the server can identify and obtain the identity information corresponding to the preset fields such as the name and certificate number of the applicant and the respondent; arbitration application information such as arbitration clauses, arbitration application requests, arbitration facts, arbitration reasons, arbitration institutions, and the subject amount; and entrustment data such as the name of the evidence file, the source of evidence, the content of the evidence, and the number of pages.

[0044] Step 208: Obtain a preset evidence analysis model, analyze the arbitration application information and evidence data using the evidence analysis model, and obtain corresponding analysis results.

[0045] Step 210: When the analysis result indicates that the evidence has passed the review, the evidence material is determined to be valid and the evidence material is accepted.

[0046] After the server extracts the arbitration application information and evidence data corresponding to the preset fields from the recognition result data, it further obtains the preset evidence analysis model, wherein the evidence analysis model can be a model based on a neural network or a model based on a decision tree. The server inputs the arbitration application information and evidence data into the evidence analysis model, extracts features of the arbitration application information and evidence data through the evidence analysis model, obtains multiple feature information corresponding to the arbitration application information and evidence data, and analyzes the multiple feature information after feature extraction to obtain the corresponding analysis results. When the evidence review is passed, the analysis result may include a label of evidence review passing, and the server determines that the evidence material is valid and accepts the evidence material. Specifically, after the server determines that the evidence material is valid, it can add a valid label to the evidence material and add the evidence material to the arbitration case file data corresponding to the arbitration case. When the evidence review fails, the reason for failure and the failure label are added to the analysis result. The server can also further send the evidence material to the corresponding audit terminal so that the audit terminal reviews the evidence material.

[0047] For example, the evidence analysis model can analyze the arbitration type, application facts, and application reasons in the arbitration application information, and then analyze whether the evidence materials are complete, whether there are any errors, whether they are related to the arbitration case, and the claim confirmation, such as the date and amount, based on the arbitration application information. For example, Puhui's evidence materials can be as follows: loan agreement, letter of certification, loan certificate, insurance application form, insurance policy, Ping An personal loan guarantee insurance terms and rates, insurance terms and special agreements, insurance compensation confirmation, Shenzhen Ping An Puhui Microfinance Co., Ltd. corporate information disclosure system screenshots, etc. By analyzing the data in the arbitration application materials and evidence materials, it is possible to accurately and effectively analyze whether the evidence materials meet the requirements, thereby effectively improving the review efficiency of the evidence materials.

[0048] Furthermore, when the arbitration application materials and evidence materials are uploaded by the applicant user through the terminal when initiating an arbitration application request on the Internet arbitration platform, the server shall also pre-register and review the arbitration application materials and the entrustment information. Among them, the application information may include the current face picture of the applicant user, and the arbitration application materials include arbitration application information and entrustment information. Specifically, the server may first perform facial recognition on the applicant based on the identity information and the current face picture to verify whether the applicant's identity information is authentic and valid.

[0049] After the applicant's identity recognition is passed, the server can further obtain a preset case filing review model, and analyze the application information and entrustment information in the identification result data through the case filing review model to analyze whether the application information and entrustment information meet the requirements, and obtain the corresponding analysis results. Among them, the case filing review model can be a decision tree model based on a neural network, and the case filing review model includes multiple decision nodes. For example, the case filing review model includes preset review rules, and the review rules can include three modules: subject qualification review, arbitration condition review, and entrustment procedure review. Specifically, the server inputs the application information and entrustment information into the case filing review model, and extracts features of the application information and entrustment information through the case filing review model to obtain multiple feature vectors. According to the multiple decision nodes in the case filing review model, multiple feature vectors are traversed to perform decision analysis. Until the target node corresponding to the multiple feature vectors is traversed, the corresponding analysis results are obtained. When the analysis result indicates that the analysis is passed, the server assigns the corresponding case identifier to the arbitration application request, and the arbitration application request has been filed for the corresponding case.

[0050] Furthermore, when the arbitration application materials and evidence materials are uploaded by the respondent user when initiating an arbitration defense request through a terminal on the Internet arbitration platform, the defense request information may include the respondent user's current face picture, and the arbitration application materials include arbitration defense information and entrustment information. Specifically, the server may first perform facial recognition on the applicant based on the identity information and the current face picture to verify whether the applicant's identity information is authentic and valid.

[0051] Further obtain the preset evidence analysis model, and input the arbitration application information and evidence data into the evidence analysis model, extract features from the arbitration application information and evidence data through the evidence analysis model, obtain multiple feature information corresponding to the arbitration application information and evidence data, and analyze the multiple feature information after feature extraction to obtain corresponding analysis results. When the evidence review is passed, the analysis result may include an evidence review passed label, and the server determines that the evidence materials are valid and accepts the evidence materials. This is to facilitate the subsequent processing of the arbitration case. By automatically reviewing the arbitration application materials and evidence materials uploaded by the applicant and the respondent, the processing efficiency of arbitration cases can be effectively improved.

[0052] In the above-mentioned method for analyzing and processing evidence materials, after the server obtains the arbitration application materials and evidence materials uploaded by the terminal, it obtains a preset character recognition model, and performs character recognition on the arbitration application materials and evidence materials through the character recognition model, thereby effectively obtaining the corresponding recognition result data. The server then extracts the arbitration application information and evidence data corresponding to the preset fields from the recognition result data, and obtains the preset evidence analysis model, and analyzes the arbitration application information and evidence data through the evidence analysis model to obtain the corresponding analysis results. When the analysis result indicates that the evidence review has passed, it is determined that the evidence materials are valid, and the evidence materials are accepted. After the data in the arbitration application materials and evidence materials are identified by the character recognition model, the evidence analysis model is further used to analyze the evidence data according to the application information, thereby accurately and effectively analyzing whether the evidence materials meet the requirements, thereby effectively improving the efficiency of evidence review and reducing labor costs, thereby effectively improving the processing efficiency of arbitration cases.

[0053] In one embodiment, Figure 3 As shown, the steps of performing character recognition on arbitration application materials and evidence materials through a character recognition model to obtain corresponding recognition result data specifically include the following:

[0054] Step 302: pre-process the arbitration application materials and evidence materials to obtain corresponding grayscale image data.

[0055] Step 304 , segment the grayscale image data into characters to obtain a plurality of segmented character data.

[0056] Step 306: extract features from the multiple segmented character data to obtain corresponding multiple feature vectors.

[0057] Step 308: Perform recognition analysis on multiple feature vectors through a character recognition model to obtain corresponding recognition result data.

[0058] After the server obtains the arbitration application materials and evidence materials sent by the terminal, it obtains a preset character recognition model and recognizes the arbitration application materials and evidence materials through the character recognition model. Specifically, the server first pre-processes the image data in the arbitration application materials and evidence materials, wherein the server first grayscales and performs noise reduction processing on the image data to obtain grayscale image data; binarizes the grayscale image data, and then performs character segmentation according to preset rules and algorithms, and normalizes the segmented characters to obtain multiple segmented character data.

[0059] After the server preprocesses the arbitration application materials and evidence materials, it further performs feature extraction and dimensionality reduction on the multiple segmented character data after preprocessing to obtain multiple corresponding feature vectors. The server then uses the obtained feature vectors as the input of a preset character recognition model, which can be a machine learning model based on a neural network. The multiple feature vectors are then identified and classified by the character recognition model. Specifically, the server calculates the feature vectors corresponding to the multiple characters and the multiple characters similar to a preset number in a preset character library, and obtains the characters with the highest similarity, and uses the obtained characters with the highest similarity as the recognized characters, thereby obtaining recognition result data corresponding to the multiple characters. By recognizing the multiple segmented character data through the character recognition model, the character data in the application information and evidence data can be accurately and effectively identified.

[0060] Furthermore, after the server uses the character recognition model to identify and classify multiple feature vectors to obtain recognition result data, it can further obtain a preset semantic analysis model, perform context analysis and correction on the recognition data through the semantic model, and then obtain corrected recognition result data. After using the character recognition model to identify the application information and evidence data, the semantic analysis model is further used to further analyze and correct the recognition results, thereby effectively improving the accuracy of character recognition.

[0061] In one embodiment, Figure 4 As shown in the figure, the steps of analyzing the arbitration application information and evidence data through the evidence analysis model to obtain the corresponding analysis results specifically include the following:

[0062] Step 402: extract request information, fact information and reason information from the recognition result data through the evidence analysis model.

[0063] Step 404: extract features of the request information, fact information, reason information and evidence data respectively through the evidence analysis model to obtain corresponding multiple feature information.

[0064] Step 406 , performing decision analysis on the arbitration request information, arbitration fact information, arbitration reason information, and multiple feature information corresponding to the evidence data according to multiple decision nodes in the evidence analysis model.

[0065] Step 408, until the target decision node in the evidence analysis model is traversed, a corresponding analysis result is generated according to the target decision node.

[0066] Before obtaining the preset evidence analysis model, the server also needs to build an evidence analysis model. Specifically, the server can obtain a large amount of evidence data, perform big data analysis on the large amount of evidence data, and use the preset initial evidence analysis model to train and verify the large amount of evidence data, and adjust the initial evidence analysis model during the training process. After the training is completed, the required evidence analysis model is obtained. Among them, the evidence analysis model can be a model based on a neural network or a model based on a decision tree. The evidence analysis model includes decision nodes corresponding to the three modules of evidence compliance, evidence relevance, and evidence validity.

[0067] After the server obtains the arbitration application materials and evidence materials sent by the terminal, it obtains a preset character recognition model, recognizes the arbitration application materials and evidence materials through the character recognition model, and obtains corresponding recognition result data. The server extracts the arbitration application information and evidence data corresponding to the preset fields from the recognition result data, abandons further obtaining the preset evidence analysis model, analyzes the arbitration application information and evidence data through the evidence analysis model, and obtains corresponding analysis results.

[0068] Specifically, the server obtains a pre-built case filing review model, and extracts the request information, factual information and reason information in the arbitration application information from the recognition result data through the case filing review model. The request information, factual information and reason information can be extracted according to the preset fields. The server then extracts features of the request information, factual information and reason information in the arbitration application information and the evidence data to obtain corresponding multiple feature information. The evidence analysis model may include multiple decision nodes, for example, it may include an evidence compliance decision node, an evidence relevance decision node and an evidence validity decision node. Among them, each decision node may also include multiple sub-decision nodes to make multiple decisions and judgments on each piece of information to effectively review whether each piece of information meets the preset requirements.

[0069] The server then uses the request information, fact information and reason information in the arbitration application information to perform decision analysis on the evidence data through multiple decision nodes in the evidence analysis model. Specifically, the multiple feature information corresponding to the request information, fact information and reason information and the feature information corresponding to the evidence data are traversed in turn through multiple decision nodes in the case filing review model, and the multiple feature information is passed to the next corresponding decision node for analysis based on the decision results of each node. Until the target decision node in the evidence analysis model is traversed, the corresponding analysis result is generated based on the target decision node. The target decision node includes the final decision result after the case analysis of multiple pieces of information through the case filing review model, so the analysis result is whether the evidence review is passed or not.

[0070] The analysis result may include a label indicating that the evidence has been reviewed and approved. Furthermore, when the review fails, the server generates a reason for failure and adds the reason for failure to the analysis result. The server then sends the analysis result to the corresponding terminal of the corresponding party.

[0071] For example, the evidence analysis model includes preset audit rules, which may include three modules: evidence compliance audit, evidence relevance audit, and evidence validity audit. Among them, in the evidence compliance audit module, it is possible to audit whether the evidence materials comply with relevant regulations, such as the form of evidence, the type of evidence, etc. The evidence relevance audit module can audit whether the evidence materials are associated with the arbitration case, such as whether the evidence materials are evidence materials related to the arbitration case, etc. The evidence validity audit module can audit whether the evidence has legal effect, such as whether the time of the evidence materials is effective, etc. If the evidence material audit fails, the reason for failure is given, and a reminder for checking materials or a suggestion for supplementary materials is sent to the terminal. By analyzing the arbitration application information and evidence data, it is possible to accurately and effectively analyze whether the evidence materials meet the requirements, effectively improve the efficiency of the audit of evidence materials, and thus effectively improve the efficiency of processing arbitration applications.

[0072] In one embodiment, the method also includes: receiving the reply materials and evidence materials uploaded by the respondent's terminal; obtaining a preset character recognition model, performing character recognition on the reply materials and evidence materials through the character recognition model, and obtaining corresponding recognition result data; extracting the reply data and evidence data corresponding to the preset fields from the recognition result data; obtaining a preset evidence analysis model, analyzing the reply data and evidence data through the evidence analysis model, and obtaining corresponding analysis results; when the analysis result indicates that the review is passed, determining that the evidence materials are valid, and accepting the evidence materials.

[0073] When the arbitration application materials and evidence materials are uploaded by the respondent user when initiating an arbitration defense request through a terminal on the Internet arbitration platform, the defense request information may include the respondent user's current face picture, and the arbitration application materials include arbitration defense information and entrustment information. Specifically, the server may first perform facial recognition on the applicant based on the identity information and the current face picture to verify whether the applicant's identity information is authentic and valid.

[0074] Further obtain the preset evidence analysis model, and input the arbitration application information and evidence data into the evidence analysis model, extract features from the arbitration application information and evidence data through the evidence analysis model, obtain multiple feature information corresponding to the arbitration application information and evidence data, and analyze the multiple feature information after feature extraction to obtain corresponding analysis results. When the evidence review is passed, the analysis result may include an evidence review passed label, and the server determines that the evidence materials are valid and accepts the evidence materials. This is to facilitate the subsequent processing of the arbitration case. By automatically reviewing the arbitration application materials and evidence materials uploaded by the applicant and the respondent, the processing efficiency of arbitration cases can be effectively improved.

[0075] In one embodiment, the method also includes: obtaining all evidence materials corresponding to the arbitration application; obtaining a preset data mining model, performing correlation analysis on multiple pieces of evidence materials corresponding to the arbitration case through the data mining model, and obtaining associated evidence tags; and adding corresponding correlation tags to the evidence materials according to the associated evidence tags.

[0076] After the server analyzes the arbitration application information and evidence data through the evidence analysis model, when the analysis result indicates that the analysis is passed, it is determined that the evidence material is valid, and the server then performs association processing on the case corresponding to the evidence material. Specifically, the server obtains a preset data mining model, performs correlation analysis on multiple pieces of evidence materials corresponding to the arbitration case through the data mining model, and adds corresponding correlation tags to the evidence materials. For example, if the directories in the two materials are related, the correlation is mined by semantic understanding, and the related items can be displayed in the related places. Clicking on the related items can also directly link to the directory content. The server then adds the evidence materials to the case file corresponding to the arbitration case and generates the evidence document corresponding to the arbitration case.

[0077] The server further binds the arbitration case-related materials and evidence materials with the corresponding parties according to the party information of the arbitration request, generates corresponding notification information, and sends the notification information to the corresponding terminal of the corresponding party. By performing correlation analysis on its own materials, it can effectively analyze the correlation between evidence materials, effectively improve the processing efficiency of evidence material data, and effectively save labor costs.

[0078] It should be understood that although Figure 2-4 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-4At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0079] In one embodiment, Figure 5 As shown, a device for analyzing and processing evidence materials is provided, including: a data acquisition module 502, a character recognition module 504 and an evidence analysis module 506, wherein:

[0080] The data acquisition module 502 is used to acquire arbitration application materials and evidence materials uploaded by the terminal;

[0081] The character recognition module 504 is used to obtain a preset character recognition model, and perform character recognition on the arbitration application materials and evidence materials through the character recognition model to obtain corresponding recognition result data;

[0082] The data acquisition module 502 is also used to extract arbitration application information and evidence data corresponding to the preset fields from the recognition result data;

[0083] The evidence analysis module 506 is used to obtain a preset evidence analysis model, analyze the arbitration application information and evidence data through the evidence analysis model, and obtain corresponding analysis results; when the analysis result indicates that the evidence review has passed, the evidence materials are determined to be valid and the evidence materials are accepted.

[0084] In one embodiment, the character recognition module 504 is also used to pre-process the arbitration application materials and evidence materials to obtain corresponding grayscale image data; perform character segmentation on the grayscale image data to obtain multiple segmented character data; perform feature extraction on the multiple segmented character data to obtain corresponding multiple feature vectors; and perform recognition and analysis on the multiple feature vectors through a character recognition model to obtain corresponding recognition result data.

[0085] In one embodiment, the evidence analysis module 506 is also used to extract request information, fact information and reason information from the recognition result data through the evidence analysis model; perform feature extraction on the request information, fact information and reason information and the evidence data through the evidence analysis model to obtain corresponding multiple feature information; perform decision analysis on the arbitration request information, arbitration fact information and arbitration reason information and multiple feature information corresponding to the evidence data according to multiple decision nodes in the evidence analysis model; until traversing to the target decision node in the evidence analysis model, generate the corresponding analysis result according to the target decision node.

[0086] In one of the embodiments, the data acquisition module 502 is also used to receive the reply materials and evidence materials uploaded by the applicant's terminal; the character recognition module 504 is also used to obtain a preset character recognition model, and perform character recognition on the reply materials and evidence materials through the character recognition model to obtain corresponding recognition result data; the data acquisition module 502 is also used to extract the reply data and evidence data corresponding to the preset fields from the recognition result data; the evidence analysis module 506 is also used to obtain a preset evidence analysis model, and analyze the reply data and evidence data through the evidence analysis model to obtain corresponding analysis results; when the analysis result indicates that the review is passed, it is determined that the evidence materials are valid, and the evidence materials are accepted.

[0087] In one embodiment, the device also includes an evidence association module, which is used to obtain all evidence materials corresponding to the arbitration application; obtain a preset data mining model, and perform correlation analysis on multiple evidence materials corresponding to the arbitration case through the data mining model to obtain associated evidence tags; and add corresponding correlation tags to the evidence materials according to the associated evidence tags.

[0088] The specific definition of the analysis and processing device for evidence materials can be found in the definition of the analysis and processing method for evidence materials above, which will not be repeated here. Each module in the above-mentioned analysis and processing device for evidence materials can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0089] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as arbitration application materials and evidence materials. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the steps of the method for analyzing and processing evidence materials provided in any embodiment of the present application are implemented.

[0090] Those skilled in the art will understand that Figure 6The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0091] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for analyzing and processing evidence materials provided in any embodiment of the present application are implemented.

[0092] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0093] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0094] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for analyzing and processing evidence materials, the method include: Obtain arbitration application materials and evidence materials uploaded by the terminal; Obtaining a preset character recognition model, performing character recognition on the arbitration application materials and the evidence materials through the character recognition model to obtain corresponding recognition data, obtaining a preset semantic analysis model, performing context analysis and correction on the recognition data through the semantic analysis model to obtain recognition result data; Extracting arbitration application information and evidence data corresponding to preset fields from the recognition result data; Obtaining a preset evidence analysis model, and analyzing the arbitration application information and the evidence data through the evidence analysis model to obtain corresponding analysis results, wherein the evidence analysis model includes preset review rules, and the review rules include evidence compliance review, evidence relevance review, and evidence validity review; When the analysis result indicates that the evidence has passed the review, the evidence material is determined to be valid and is accepted.

2. The method according to claim 1, It is characterized in that The step of performing character recognition on the arbitration application materials and evidence materials by using the character recognition model to obtain corresponding recognition result data comprises: Preprocessing the arbitration application materials and the evidence materials to obtain corresponding grayscale image data; Performing character segmentation on the grayscale image data to obtain a plurality of segmented character data; Performing feature extraction on the plurality of segmented character data to obtain a plurality of corresponding feature vectors; The character recognition model is used to perform recognition analysis on multiple feature vectors to obtain corresponding recognition result data.

3. The method according to claim 1, It is characterized in that The step of analyzing the arbitration application information and the evidence data by using the evidence analysis model to obtain corresponding analysis results comprises: Extracting request information, fact information and reason information from the recognition result data through the evidence analysis model; By using the evidence analysis model, feature extraction is performed on the request information, fact information, reason information and evidence data to obtain corresponding multiple feature information; Performing decision analysis on the arbitration request information, arbitration fact information, arbitration reason information, and multiple feature information corresponding to the evidence data according to multiple decision nodes in the evidence analysis model; When the target decision node in the evidence analysis model is traversed, a corresponding analysis result is generated according to the target decision node.

4. The method according to claim 1, It is characterized in that The method further comprises: Receive the defense materials and evidence materials uploaded by the respondent's terminal; Obtaining a preset character recognition model, and performing character recognition on the defense materials and evidence materials using the character recognition model to obtain corresponding recognition result data; Extracting reply data and evidence data corresponding to preset fields from the recognition result data; Obtaining a preset evidence analysis model, and analyzing the defense data and the evidence data through the evidence analysis model to obtain corresponding analysis results; When the analysis result indicates that the review is passed, the evidence material is determined to be valid and the evidence material is accepted.

5. The method according to any one of claims 1 to 4, It is characterized in that The method further comprises: Obtain all evidentiary materials corresponding to the arbitration application; Obtain a preset data mining model, and use the data mining model to perform correlation analysis on multiple pieces of evidence materials corresponding to the arbitration case to obtain related evidence labels; A corresponding relevance tag is added to the evidence material according to the associated evidence tag.

6. A device for analyzing and processing evidence materials, the device include: The data acquisition module is used to acquire arbitration application materials and evidence materials uploaded by the terminal; A character recognition module, used to obtain a preset character recognition model, perform character recognition on the arbitration application materials and the evidence materials through the character recognition model to obtain corresponding recognition data, obtain a preset semantic analysis model, perform context analysis and correction on the recognition data through the semantic analysis model to obtain recognition result data; The data acquisition module is also used to extract arbitration application information and evidence data corresponding to preset fields from the recognition result data; The evidence analysis module is used to obtain a preset evidence analysis model, analyze the arbitration application information and the evidence data through the evidence analysis model, and obtain corresponding analysis results, wherein the evidence analysis model includes preset review rules, and the review rules include evidence compliance review, evidence relevance review and evidence validity review; when the analysis result indicates that the evidence review has passed, it is determined that the evidence materials are valid and the evidence materials are accepted.

7. The device according to claim 6, It is characterized in that The character recognition module is also used to pre-process the arbitration application materials and the evidence materials to obtain corresponding grayscale image data; perform character segmentation on the grayscale image data to obtain multiple segmented character data; perform feature extraction on the multiple segmented character data to obtain corresponding multiple feature vectors; and perform recognition and analysis on the multiple feature vectors through the character recognition model to obtain corresponding recognition result data.

8. The device according to claim 6, It is characterized in that The evidence analysis module is also used to extract request information, fact information and reason information from the recognition result data through the evidence analysis model; extract features of the request information, fact information, reason information and evidence data respectively through the evidence analysis model to obtain corresponding multiple feature information; Performing decision analysis on the arbitration request information, arbitration fact information, arbitration reason information, and multiple feature information corresponding to the evidence data according to multiple decision nodes in the evidence analysis model; When the target decision node in the evidence analysis model is traversed, a corresponding analysis result is generated according to the target decision node.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.