File processing method, electronic equipment, storage medium and computer program product

Abstract

The invention discloses a file processing method, electronic equipment, a storage medium and a computer program product, and relates to the field of large model technology and text processing. The method comprises the steps that an input instruction acting on an operation interface is responded, a to-be-processed file is displayed on the operation interface, and the to-be-processed file comprises a to-be-processed text of at least one mode; in response to a processing instruction acting on the operation interface, a processing result is displayed on the operation interface, the processing result is used for representing that the to-be-processed file is successfully named and stored based on a target processing rule, and the target processing rule is a processing rule corresponding to a target type of the to-be-processed file; the target type is determined by comparing the to-be-processed text with the preset texts contained in the plurality of preset files, and the types of different preset files are different. The technical problem of low file processing accuracy in related technologies is solved.

Description

Technical Field

[0001] This application relates to large model technology and text processing, and more specifically, to a document processing method, electronic device, storage medium, and computer program product. Background Technology

[0002] Currently, efficient and accurate text organization is key to improving text processing speed. Traditional text organization methods include manual organization, rule-based automation, and traditional machine learning methods, but each has its limitations. Manual organization is costly, inefficient, and error-prone; rule-based methods lack flexibility and struggle to adapt to the diversity of text types and changing needs, resulting in lower accuracy in text processing. Summary of the Invention

[0003] This application provides a file processing method, electronic device, storage medium, and computer program product to at least solve the technical problem of low accuracy in file processing in related technologies.

[0004] According to one aspect of the embodiments of this application, a file processing method is provided, comprising: responding to an input instruction applied to an operation interface, displaying a file to be processed on the operation interface, wherein the file to be processed contains at least one modality of text to be processed; and responding to a processing instruction applied to the operation interface, displaying a processing result on the operation interface, wherein the processing result is used to characterize the successful naming and storage of the file to be processed based on a target processing rule, the target processing rule being a processing rule corresponding to a target type of the file to be processed, the target type being determined by comparing the text to be processed with preset text contained in a plurality of preset files, the types of the different preset files being different.

[0005] According to another aspect of the embodiments of this application, a file processing method is provided, including: obtaining a file to be processed; parsing the text to be processed to obtain the text to be processed contained in the file to be processed; comparing the text to be processed with preset text contained in a plurality of preset files to determine the target type of the file to be processed, wherein the types of different preset files are different; and naming and storing the file to be processed based on the processing rules corresponding to the target type.

[0006] According to another aspect of the embodiments of this application, a file processing method is provided, comprising: receiving a judicial case file sent by a client; parsing the judicial case file to obtain judicial case file text contained in the judicial case file; comparing the judicial case file text with preset case file text contained in multiple preset case files to determine the target type of the judicial case file, wherein the types of different preset case files are different; naming and storing the judicial case file based on the processing rules corresponding to the target type to obtain a processing result; and sending the processing result to the client.

[0007] According to another aspect of the embodiments of this application, a file processing method is provided, comprising: obtaining a file to be processed by calling a first interface, wherein the first interface includes a first parameter, and the parameter value of the first parameter includes the file to be processed; parsing the text to be processed to obtain the text to be processed contained in the file to be processed; comparing the text to be processed with preset text contained in a plurality of preset files to determine the target type of the file to be processed, wherein the types of different preset files are different; naming and storing the file to be processed based on the processing rules corresponding to the target type to obtain a processing result; and outputting the processing result by calling a second interface, wherein the second interface includes a second parameter, and the parameter value of the second parameter includes the processing result.

[0008] According to another aspect of the embodiments of this application, an electronic device is provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the method of any one of the above embodiments when it runs.

[0009] According to another aspect of the embodiments of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform any of the methods described in the above embodiments.

[0010] According to another aspect of the embodiments of this application, a computer program product is provided, including a computer program, wherein the computer program is executed by a processor using any of the methods described in the above embodiments.

[0011] According to another aspect of the embodiments of this application, a computer terminal is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of this application when it runs.

[0012] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the methods of various embodiments of this application.

[0013] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the methods of various embodiments of this application.

[0014] According to another aspect of the embodiments of this application, a computer program product is also provided, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the methods in various embodiments of this application.

[0015] According to another aspect of the embodiments of this application, a computer program is also provided, which, when executed by a processor, implements the methods of the various embodiments of this application.

[0016] In this embodiment, in response to an input command applied to the operation interface, a file to be processed is displayed on the operation interface, wherein the file to be processed contains at least one modality of text to be processed; in response to a processing command applied to the operation interface, a processing result is displayed on the operation interface, wherein the processing result is used to characterize the successful naming and storage of the file to be processed based on the target processing rule, the target processing rule being a processing rule corresponding to the target type of the file to be processed, the target type being determined by comparing the text to be processed with preset texts contained in multiple preset files, the types of different preset files being different, thereby achieving the purpose of improving the accuracy of file processing; it is easy to note that for the text to be processed containing at least one modality, the target type of the text to be processed can be determined by comparing the text to be processed with preset texts contained in multiple preset files, based on the type of preset texts similar to the text to be processed, thereby effectively and automatically naming and storing the file appropriately based on the processing rule corresponding to the target type of the file to be processed, reducing manual intervention, improving processing speed and accuracy, and thus solving the technical problem of low file processing accuracy in related technologies.

[0017] It is worth noting that the general description above and the detailed description that follow are merely for illustrative purposes and do not constitute a limitation on this application. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0019] Figure 1 This is a schematic diagram illustrating an application scenario of a text processing method according to an embodiment of this application;

[0020] Figure 2 This is a flowchart of a text processing method according to an embodiment of this application;

[0021] Figure 3 This is a schematic diagram of the cataloging function of a sending address confirmation form according to an embodiment of this application;

[0022] Figure 4 This is a schematic diagram illustrating the classification and storage method of a sending address confirmation form in a court document management system according to an embodiment of this application;

[0023] Figure 5This is a flowchart of a text processing method according to an embodiment of this application;

[0024] Figure 6 This is a flowchart of a text processing method according to an embodiment of this application;

[0025] Figure 7 This is a flowchart of a text processing method according to an embodiment of this application;

[0026] Figure 8 This is a schematic diagram of a text processing device according to an embodiment of this application;

[0027] Figure 9 This is a schematic diagram of a text processing device according to an embodiment of this application;

[0028] Figure 10 This is a schematic diagram of a text processing device according to an embodiment of this application;

[0029] Figure 11 This is a schematic diagram of a text processing device according to an embodiment of this application;

[0030] Figure 12 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] The technical solution provided in this application is mainly implemented using large-scale model technology. Here, "large-scale model" refers to a deep learning model with a massive number of parameters, typically containing hundreds of millions, tens of billions, hundreds of billions, trillions, or even tens of trillions of parameters. Large-scale models can also be called foundation models. They are pre-trained using large-scale unlabeled corpora to produce pre-trained models with hundreds of millions of parameters. Such models can adapt to a wide range of downstream tasks and have good generalization ability. Examples include Large Language Models (LLMs) and multi-modal pre-training models.

[0034] It should be noted that, in practical applications, large models can be fine-tuned using a small number of samples to adapt them to different tasks. For example, large models can be widely used in Natural Language Processing (NLP), computer vision, and speech processing. Specifically, they can be applied to computer vision tasks such as Visual Question Answering (VQA), Image Captioning (IC), and Image Generation, as well as NLP tasks such as text-based sentiment classification, text summarization, and machine translation. Therefore, the main application scenarios for large models include, but are not limited to, digital assistants, intelligent robots, search, online education, office software, e-commerce, and intelligent design. In this embodiment, data processing using a text processing model in a text processing scenario is used as an example for explanation.

[0035] First, some nouns or terms that appear in the description of the embodiments of this application shall be interpreted as follows:

[0036] Retrieval-Augmented Generation (RAG) technology is a technique that combines retrieval and generation. It not only uses generative models to answer questions but also retrieves relevant information from external databases to enhance the accuracy and richness of the generated content. This means that when generating answers, it not only relies on its own pre-trained knowledge but can also retrieve relevant resources in real time, ensuring that the answers are more comprehensive and reliable.

[0037] Large models: Large models refer to highly complex and widely adaptable artificial intelligence models trained with massive amounts of data and computational resources. For example, the Generative Pre-trained Transformer 4 (GPT-4) is a typical large model; it can understand and generate natural language text and performs exceptionally well on various tasks. Large models typically have hundreds of millions or even more parameters and are capable of handling complex semantic relationships and diverse task requirements.

[0038] Few-shot learning: Few-shot learning is a machine learning method that can still perform well with only a very small number of training samples. Unlike traditional methods that require a large amount of labeled data, few-shot learning utilizes existing knowledge and experience to quickly adapt to and learn new tasks with only a small number of new samples. This technique is particularly suitable for scenarios where data is scarce and labeled data is not easily obtained, effectively reducing the cost of data labeling and acquisition.

[0039] Currently, the automated organization (classification, extraction, and naming) of judicial case files is a crucial requirement. With the ever-increasing volume of case files to be processed daily, manual organization is no longer sufficient. Therefore, large-scale modeling technology is needed to automate the organization of these judicial case files.

[0040] Large-scale model technology addresses the pain points of automated judicial file organization. Trained on massive datasets, these models are capable of handling various types and formats of materials, effectively understanding and processing procedural legal documents, records, and evidentiary materials. Through few-shot learning and fine-tuning, the training sample data is reduced to a much smaller amount, significantly lowering additional data preparation and preprocessing costs and reducing reliance on large amounts of labeled data. Whether adding new material types, changing cataloging rules, or altering processing flows, the configuration of case libraries and cataloging rule libraries meets new task requirements, reducing the workload of redevelopment and training required by traditional methods.

[0041] According to an embodiment of this application, a text processing method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0042] Considering the large number of model parameters in large models and the limited computing resources of mobile terminals, the text processing method provided in this application can be applied to, for example, Figure 1 The application scenarios shown are not limited to these. Figure 1 This is a schematic diagram illustrating an application scenario of a text processing method according to an embodiment of this application. Figure 1 In the application scenario shown, the large model is deployed on server 10. Server 10 can connect to one or more client devices 20 via a local area network (LAN), wide area network (WAN), internet connection, or other types of data network. These client devices 20 may include, but are not limited to, smartphones, tablets, laptops, PDAs, personal computers, smart home devices, and in-vehicle devices. Client devices 20 can interact with users through a graphical user interface to access the large model, thereby implementing the method provided in this embodiment.

[0043] In this embodiment, the system consisting of a client device and a server can perform the following steps: The client device uploads a file to be processed. The server responds to input commands applied to the operation interface and displays the file to be processed on the operation interface, wherein the file to be processed contains at least one modality of text to be processed; responding to processing commands applied to the operation interface, the server displays processing results on the operation interface, wherein the processing results characterize the result obtained by naming and storing the file to be processed based on the processing rules corresponding to the target type of the file to be processed. The target type is determined by comparing the text to be processed with preset texts contained in multiple preset files, and different preset files have different types. It should be noted that this embodiment can be performed on the client device if the client device's operating resources can meet the deployment and operation conditions of a large model.

[0044] Under the aforementioned operating environment, this application provides the following: Figure 2 The text processing method shown. Figure 2 This is a flowchart of a text processing method according to an embodiment of this application. For example... Figure 2 As shown, the method may include the following steps:

[0045] Step S202: In response to the input command applied to the operation interface, display the file to be processed on the operation interface.

[0046] The file to be processed contains text in at least one modality.

[0047] The aforementioned user interface is the front-end interface for user interaction with the system. Users can manipulate the relevant controls on the interface. For example, after entering the file to be processed on the interface, input commands can be generated, and the file to be processed can be displayed on the interface based on the input commands. Users can upload and process documents through this interface.

[0048] The aforementioned files to be processed can be documents uploaded by users to the operation interface for processing. These files can include, but are not limited to, Word documents, Portable Document Format (PDF), and Joint Photographic Experts Group (JPG) formats. Each file must contain at least one modality of text to be processed. Files can also include judicial files, patent examination opinions, etc.; there are no specific limitations, and the choice of file type can be determined based on the application scenario.

[0049] The above-mentioned at least one modality may include, but is not limited to, text modality, image modality, table modality, audio modality, video modality, and metadata modality. The text to be processed in at least one modality may also be plain text, a combination of text and images, a combination of text and tables, or any other combination of forms. There is no limitation on the text to be processed in at least one modality here.

[0050] The text modality refers to plain text information within a file, such as text in a Word document or text content in a PDF. Image modality files can contain images, charts, photographs, or scanned copies, which require image recognition technology for processing and understanding, such as optical character recognition (OCR) for extracting text from images. Table modality files can contain tabular data, requiring specialized table parsing technology to read and understand the structured information within the tables. Audio modality files, such as court transcripts and meeting minutes, contain audio information that needs to be converted to text using speech recognition technology before processing. Video modality files can contain video material, requiring video recognition and analysis technology for processing, potentially involving video-to-text or video-to-image conversion. Metadata modality files can contain metadata such as creation date, author, and file type.

[0051] In one optional embodiment, the user uploads or selects files to be processed, such as judicial files or patent examination opinions, through a user interface (e.g., a computer's file upload interface). The input instruction in this process can be the user's action of uploading a file in an input box on the interactive interface. After the system recognizes this action, it will display the uploaded files on the user interface. After the user uploads or selects files to be processed, the system will display these files on the user interface. These files contain at least one modality of text to be processed; that is, the files can be in formats such as Word documents, PDFs, or JPG images.

[0052] Step S204: Respond to the processing instructions applied to the operation interface and display the processing results on the operation interface.

[0053] The processing result is used to characterize the successful naming and storage of the file to be processed based on the target processing rule. The target processing rule is the processing rule corresponding to the target type of the file to be processed. The target type is determined by comparing the text to be processed with the preset text contained in multiple preset files. Different preset files have different types.

[0054] The aforementioned preset files can be pre-categorized files. By comparing the similarity between the text to be processed and the preset texts contained in these preset files, the preset texts with the highest similarity to the text to be processed can be identified. This allows the target type of the text to be processed to be determined based on the type of the preset file containing the preset text. In the judicial field, preset files refer to example files stored in a case file sample library used for comparison with the text to be processed. These examples cover different types of judicial documents, and the preset files can be examples stored in the case file sample library.

[0055] The aforementioned preset text refers to the text content in the preset file, which is used for semantic comparison and matching with the text to be processed in the file to be processed.

[0056] The target type mentioned above can be a document category identified and determined based on the content of the document to be processed. In the judicial field, the target type can be a confirmation of service, a judgment, etc.

[0057] The aforementioned processing rules can serve as standards and procedures for classifying, naming, and storing documents to be processed. In the judicial field, these processing rules can be stored in a case file cataloging rule repository. The case file cataloging rule repository is primarily responsible for storing and defining the rules and standards for classifying, naming, and storing case file materials. These rules are typically developed based on judicial practice and legal requirements, aiming to ensure that case file materials can be accurately and consistently classified and named to facilitate subsequent management and retrieval.

[0058] The processing rules in the case file cataloging rule base may include, but are not limited to, classification rules, naming rules, storage rules, and retrieval rules. Classification rules define which category different types of judicial materials should be placed in; for example, classifying "indictment," "judgment," and "list of evidence" into different directories. Naming rules specify the naming format for different materials, including key elements such as case number, file type, date, and party names. Storage rules determine the storage location and method of materials in the system, including the physical path, file structure, and storage format of electronic files. Retrieval rules define how to retrieve specific case file materials based on keywords, case information, etc.

[0059] The above-mentioned comparison of the text to be processed with the preset text contained in multiple preset files can be a semantic similarity comparison or a structural similarity comparison. The type of similarity comparison is not limited here, and the type of text similarity comparison can be determined according to actual needs.

[0060] In one optional embodiment, the user clicks the "Process" button on the user interface. Upon receiving the processing instruction, the system begins processing the uploaded file. The processing instruction is actively triggered by the user in the interactive interface, and the file to be processed is analyzed and archived according to the processing rules corresponding to the target type. The file to be processed can be named and stored based on the target type of the file, utilizing processing rules stored in the case file cataloging rule base. The target type is determined by comparing the text to be processed with preset texts of multiple preset files stored in the case file sample library. The preset files can be different types of legal documents, such as service confirmations, judgments, etc., which serve as references in the sample library to help the system identify and classify the file to be processed. The file category can be determined by comparing the similarity between the text to be processed and the preset texts.

[0061] After inputting the file to be processed, it can be provided to the Intelligent Document Processing (IDP) system. The IDP system can parse the document structure of the file, extract key information, identify the meaning of the text, and classify and retrieve the document, greatly improving the efficiency and accuracy of document processing.

[0062] A large model can be used to compare the text to be processed with the preset text contained in multiple preset files. Through the generalization ability of the large model and its ability to process information of different modalities, it can ensure accurate classification of files even when there are insufficient samples.

[0063] In the field of judicial case file organization, a user uploaded a document titled "A Address Confirmation Form," which is a JPG image. In step S202, after the user uploads the file, the interface displays the image, ready for processing. In step S204, the user clicks the "Process" button to extract the document's category, title, summary, and keywords. Then, the system searches the case file sample library for cases most similar to this information to determine the file's exact type. Based on rules in the case file cataloging rule base, the document can be automatically renamed and archived to the correct directory. This process is fully automated, requiring no manual intervention from the user, significantly improving the efficiency and accuracy of judicial case file processing. Through this process, the system can not only quickly and accurately identify and classify documents but also rename and archive them according to custom rules.

[0064] The document processing methods described above enable automated processing and archiving of judicial case files, improving processing efficiency, reducing operating costs, and ensuring the consistency and accuracy of archiving. Furthermore, by employing few-shot learning technology (comparing the text to be processed with preset texts contained in multiple preset files to determine the target type) and generative retrieval technology, the system can flexibly adapt to new file types and rule changes, exhibiting high adaptability and scalability.

[0065] Through the above steps, in response to input commands applied to the operation interface, the file to be processed is displayed on the operation interface, wherein the file to be processed contains at least one modality of text to be processed; in response to processing commands applied to the operation interface, the processing result is displayed on the operation interface, wherein the processing result is used to characterize the successful naming and storage of the file to be processed based on the target processing rule, the target processing rule is the processing rule corresponding to the target type of the file to be processed, the target type is determined by comparing the text to be processed with the preset text contained in multiple preset files, the types of different preset files are different, thus achieving the purpose of improving the accuracy of file processing; it is easy to note that for the text to be processed containing at least one modality, the target type of the text to be processed can be determined by comparing the text to be processed with the preset text contained in multiple preset files, and the type of the preset text similar to the text to be processed can be determined, thereby effectively and automatically naming and storing the file appropriately based on the processing rule corresponding to the target type of the file to be processed, reducing manual intervention, improving processing speed and accuracy, and thus solving the technical problem of low file processing accuracy in related technologies.

[0066] In the above embodiments of this application, in response to a processing instruction applied to the operation interface, the method further includes: displaying target multidimensional information of the file to be processed on the operation interface, wherein the target multidimensional information is information extracted from the text to be processed using a text processing model; in response to a confirmation instruction applied to the target multidimensional information, displaying a target file that matches the file to be processed among multiple preset files on the operation interface, wherein the target file is a file determined from multiple preset files by comparing the target multidimensional information with preset multidimensional information of multiple preset files; in response to a confirmation instruction applied to the target file, displaying the target type of the file to be processed on the operation interface, wherein the target type is the type of the target file; and in response to a confirmation instruction applied to the target type, displaying the processing result on the operation interface.

[0067] The aforementioned multidimensional target information refers to information extracted from the file to be processed, including but not limited to the file's category, title, summary, and category keywords. This information is a refined representation of the file content and is used in subsequent file matching and type confirmation processes.

[0068] The aforementioned text processing model is an artificial intelligence model used to understand and process text data. This model can be based on deep learning, such as a Large Language Model (LLM), used to extract semantic features from text and construct multidimensional information representations. In the field of judicial case file organization, text processing models based on LLM technology can efficiently process and understand textual information in judicial case files, classifying and cataloging materials. This text processing model can also be used in Intelligent Document Processing (IDP) systems. IDPs can parse multimodal materials, extract and process their content, and transmit the results to a case file index and a case file cataloging rule base.

[0069] The aforementioned preset multidimensional information can be multidimensional information associated with multiple preset files, including file category, title, summary, and category keywords, etc., used for comparison with the target multidimensional information of the file to be processed.

[0070] The target file mentioned above is a file that has a high degree of matching with the multidimensional information of the file to be processed among multiple preset files. The target file can be used to determine the classification and archiving rules of the file to be processed.

[0071] The above processing results refer to the final results of the system automatically organizing the files to be processed, including file classification, renaming, and archiving location in the system.

[0072] In one optional embodiment, a text processing model can be used to extract target multidimensional information from the file to be processed, including file category, title, abstract, and keywords, and this information can be displayed on the user interface. Users can check the accuracy of the information by viewing the target multidimensional information displayed on the interface. The target multidimensional information can be compared with preset multidimensional information of multiple preset files to find the target file most similar to the file to be processed, and these matching results can be displayed on the user interface. After the user confirms the target file, the type of the target file can be automatically identified and displayed as the target type of the file to be processed, further confirming the accuracy of the classification. Based on the target type, the file to be processed can be automatically archived to the correct directory and standardized file names can be generated. Users can view these automatically organized results on the user interface.

[0073] In the field of judicial case file organization, users can automate the organization of judicial case files. Users can upload a case file document, specifically a JPG image of "B. Confirmation of Sending Address". The system first uses a text processing model to extract the category "Confirmation of Sending Address", title "B. Confirmation of Sending Address", abstract, and keywords from the image. This multi-dimensional information is displayed on the user interface for confirmation. After the user confirms the target multi-dimensional information is correct, the system enters a matching process, comparing the extracted target multi-dimensional information with cases in a preset file library. In the preset file library, the system finds a case similar to the current file, such as a file previously correctly classified as "C. Confirmation of Sending Address", and displays it as the "target file" on the user interface. After confirming the target file, the system can automatically identify and display the file's "target type", i.e., "Confirmation of Sending Address", further confirming the correct classification. Finally, based on preset archiving rules and element extraction (such as region, date, etc.), the files can be automatically archived to the "Sending Address Confirmation" directory under the "General Directory" and renamed "B Sending Address Confirmation". The processing results are displayed on the operation interface in real time, and users can check the accuracy of the archiving. The whole process significantly improves the efficiency and standardization of judicial case file organization.

[0074] Through the above process, the system not only automatically classifies and names case file materials, but also ensures that materials are accurately archived in the corresponding directories, facilitating subsequent case processing and material retrieval, thereby improving judicial efficiency and standardizing data processing. By using a large model combined with RAG technology, the efficiency, accuracy, and consistency of automatic judicial case file organization are improved. Through few-sample learning, the reliance on data annotation is reduced, lowering operating costs.

[0075] In the above embodiments of this application, in response to a modification instruction applied to the target multidimensional information, the method further includes: displaying the modified multidimensional information on an operation interface in response to the modification instruction applied to the target multidimensional information; and displaying a new file on the operation interface in response to a confirmation instruction applied to the modified multidimensional information, and adjusting the text processing model using the modified multidimensional information, wherein the new file is a file determined from multiple preset files by comparing the modified multidimensional information with preset multidimensional information of multiple preset files.

[0076] The modified multidimensional information mentioned above can be obtained by adjusting or replacing the target multidimensional information displayed on the operation interface after the user has viewed it and deemed it necessary. The modified multidimensional information may include file type, title, abstract, keywords, date, signatory, etc.

[0077] In the user interface, modification commands typically refer to user-triggered operations that alter the system's displayed content or data status. These modification commands can be generated by touching relevant controls within the interface. In a judicial case file organization system, users may need to modify multi-dimensional information automatically extracted from a large model to more accurately reflect the true content of the materials or to meet specific cataloging rules.

[0078] The aforementioned confirmation instructions are the user's approval and acceptance of the system's displayed or suggested content, typically used to finalize a change in an operation or data state. Confirmation instructions involve the user's approval of the modified multidimensional information and confirmation that this information is correctly applied to the cataloging and classification of the target file.

[0079] In one optional embodiment, when the target multidimensional information extracted from the large model needs modification, the user can directly make the changes on the user interface. After the modification is completed, the user confirms the changes, and the system not only displays the modified file information but also uses this information to adjust the text processing model. This adjustment process is based on user feedback, allowing the model to learn more accurate cataloging rules and standards, thus performing more accurately and efficiently in future cataloging tasks.

[0080] By allowing users to directly modify and confirm multidimensional information on the user interface, the system can provide instant feedback on user corrections to the cataloging results. This not only improves the accuracy of the information but also enhances user engagement and control. Executing confirmation commands not only updates the display on the user interface but also triggers model adjustments based on user modifications. This allows the model to gradually learn richer cataloging rules and more accurate classification standards, reducing reliance on large amounts of labeled data and improving the model's generalization ability and adaptability. This user-feedback-based model adjustment mechanism significantly improves the accuracy, consistency, and efficiency of automated judicial file organization, reduces operating costs, and enhances the system's flexibility and scalability.

[0081] In the above embodiments of this application, the method further includes: displaying the modified target file on the operation interface in response to a modification instruction applied to the target file; and displaying a new type on the operation interface in response to a confirmation instruction applied to the modified target file, wherein the new type is the type of the modified target file.

[0082] The target file mentioned above can be a file obtained by matching the file to be processed. In the field of judicial case file organization, the target file can be pre-confirmed judicial case file materials, such as mailing address confirmation letters, delivery summary details, and other vouchers.

[0083] The aforementioned modification commands are user-issued commands to edit or modify the target file, such as correcting information in the file, adjusting the file format, or adjusting the content layout.

[0084] The above confirmation command is an operation command for the user to approve the modification results after the system has completed the modification. After confirmation, the system will perform further operations, such as displaying the file type and saving the modification results.

[0085] The aforementioned new type refers to the classification to which the target file belongs after modification, such as a confirmation of sending address or a summary of delivery details. This new type reflects the filing and retrieval categories of the file in the field of judicial case file organization.

[0086] In one optional embodiment, when a user modifies a target file (e.g., adjusts the material category or modifies elements in the file name), the system responds to the modification command and displays a preview of the modified file on the user interface. After the user confirms that the modification is correct, the system further displays the file's "target type," which is intelligently categorized based on the modified file content and elements to ensure that the modified file can be accurately cataloged and archived.

[0087] In the field of judicial case file organization, target files encompass a wide range of judicial documents, from judgments and indictments to evidence photographs, in various formats and types. Modification and confirmation instructions are crucial steps in the user-system interaction; the former instructs the system to modify specific parts of the file, while the latter confirms whether the modified content meets requirements. Target types are the results of automatic identification and classification by the system based on file content and cataloging rules, guiding file storage and retrieval. By leveraging the intelligent processing capabilities of large-scale models and the efficient retrieval and generation capabilities of RAG technology, not only is the speed of file cataloging significantly improved, but accuracy and consistency during modification and confirmation processes are also ensured. The use of few-shot learning techniques reduces reliance on large amounts of labeled data, lowering system operating costs.

[0088] In the above embodiments of this application, in response to a confirmation instruction applied to target multidimensional information, displaying a target file matching the file to be processed on the operation interface includes: displaying at least one candidate file on the operation interface, wherein the at least one candidate file is a file determined by recalling multiple preset files stored in the file database based on the target multidimensional information; and displaying a target file on the operation interface in response to a confirmation instruction applied to at least one candidate file, wherein the target file is a file determined from at least one first sorted file, and the at least one first sorted file is obtained by sorting at least one candidate file using a text processing model.

[0089] The aforementioned file database stores a large number of preset files, which can be historically processed judicial case files used for system learning and recalling similar files.

[0090] The aforementioned candidate files are files recalled from the file database by the system using target multidimensional information. The candidate files are similar to the input files in some aspects and are candidates for further refinement.

[0091] The aforementioned ranking refers to the process of arranging candidate files from highest to lowest relevance to the target file based on the analysis results of the text processing model. It should be noted that this ranking process can be refined. Refined ranking refers to further refining the ranking results after initially ranking at least one candidate file using the text processing model, in order to more accurately determine the category and relevance of the target file, reduce misjudgments, and improve accuracy.

[0092] By using a text processing model to refine at least one candidate document, cases with a high degree of category matching with the current document to be processed can be accurately selected from the recalled similar case materials. The refinement process can be implemented using a refinement model. This model can be a deep learning model that evaluates the relevance and similarity between the query document and the example documents by calculating and analyzing various text and vector similarity features, thereby determining whether they belong to the same category.

[0093] The aforementioned fine-ranking model is a key component for determining the target type of the text to be processed. This fine-ranking model is based on large models and RAG technology, and combines multiple text and vector similarity features to improve the accuracy of case file material classification.

[0094] The features of the fine-ranking model include various similarity measures between the query document and the sample document, which may include, but are not limited to, text similarity features and vector similarity features.

[0095] Text similarity features can include text similarity scores for categories, titles, summaries, and keywords, as well as a composite ranking score calculated based on these similarities. Text similarity measures the closeness of two documents in terms of text content. Vector similarity features can include vector similarity scores for categories, titles, summaries, and keywords, as well as a composite vector similarity score, providing another method for measuring document similarity from the perspective of semantic vector space. Vector similarity considers the semantic relationships between words and can capture semantic details that might be missed in text similarity features.

[0096] The fine-ranking model employs a linear network structure with input and output layers. The input layer receives similarity scores calculated from the feature components, which form a fixed-size vector that serves as the model's input. The output layer outputs predicted values ​​(logits) to determine the class consistency between the input material and the recalled cases.

[0097] The fine-grained ranking model uses a contrastive loss function (Circle Loss) as its prediction objective function. This loss function aims to optimize the distance between similar and dissimilar cases, making it suitable for retrieval tasks. Through Circle Loss, the model can learn how to more accurately rank the recalled cases, ensuring that cases consistent with the input file category are ranked higher.

[0098] By integrating multiple text and vector similarity features, the refined ranking model can more comprehensively understand the content and context of the input text, thereby improving classification accuracy. Even in the field of judicial case file organization, facing complex and diverse case file materials, it can ensure that the materials are correctly classified and archived. The refined ranking model based on RAG technology relies heavily on a sample library and rule library, rather than a large amount of labeled data, which reduces the dependence on manual annotation. Maintaining the sample library is simpler than retraining traditional machine learning models, saving significant manpower and time costs. Since the refined ranking model can adapt to new material types or rule changes by configuring the case library and cataloging rule library, the system can quickly adapt to changes in the needs of judicial projects without frequent model retraining, improving the system's flexibility and scalability.

[0099] By using multidimensional target information for retrieval and refinement, the efficiency and accuracy of judicial case file organization can be significantly improved. Compared to traditional manual organization, this method reduces substantial labor costs and increases processing speed. Furthermore, due to the generalization and flexibility of the large model, it can quickly adapt to new document types or changes in cataloging rules through fine-tuning, maintaining high efficiency.

[0100] In the above embodiments of this application, the method further includes: displaying at least one modified candidate file on an operation interface in response to a modification instruction applied to at least one candidate file; and displaying a target file on the operation interface in response to a confirmation instruction applied to at least one modified candidate file, wherein the target file is a file determined from at least one second sorting file, and the at least one second sorting file is a file determined by sorting at least one modified candidate file using a text processing model.

[0101] The aforementioned modification instructions can be requests from users or the system to modify candidate files that have been initially identified or classified. If a user believes that the results are inaccurate or need to be adjusted, they can modify at least one candidate file according to the modification instructions to obtain at least one modified candidate file.

[0102] The above confirmation command can be generated after the user confirms that at least one candidate file has been modified and is correct.

[0103] In one optional embodiment, when a user or the system needs to modify the preliminary processing results, a modification command is issued. The system responds to these modification commands, reprocesses the relevant candidate files, and displays the modified files to the user on the "operation interface." After the user confirms the modifications are correct, they notify the system via a confirmation command. At this point, the text processing model performs final sorting and classification on the confirmed files, generates target files, and displays them on the operation interface for subsequent archiving and management. Users can directly modify the files on the operation interface without complex procedures, improving the convenience of interaction.

[0104] In the field of judicial case file organization, the above modifications to candidate documents not only improve the accuracy of document classification but also simplify user operations, ensuring the standardization and consistency of documents in the judicial case file management system, and effectively improving the efficiency and quality of judicial work.

[0105] In the above embodiments of this application, displaying a target file on an operation interface in response to a determination instruction applied to at least one candidate file includes: displaying at least one first sorted file on the operation interface, wherein the at least one first sorted file is the result of sorting at least one candidate file using the matching scores of at least one candidate file, and the matching scores of at least one candidate file are obtained by comparing the target multidimensional information and the candidate multidimensional information of at least one candidate file using a text processing model, and the matching scores are used to characterize the probability that the file to be processed is of the same category as the corresponding candidate file; and displaying a target file on the operation interface in response to a confirmation instruction applied to at least one first sorted file, wherein the target file is the first file in the at least one first sorted file.

[0106] The first sorted file mentioned above can be a list of files sorted according to their similarity to examples in the case library after processing by a large model. After sorting, files that are more likely to belong to the same category as the file currently being processed will be ranked first.

[0107] The matching score mentioned above can be used as a quantitative indicator to measure the similarity between the file to be processed and the candidate files. In the judicial case file organization system, the matching score is calculated by a large model based on the multidimensional information of the file (such as type, title, summary, keywords, etc.), reflecting the consistency probability of file categories.

[0108] The aforementioned candidate multidimensional information can be the feature information of candidate files, including type, title, abstract, keywords, etc., which are used to compare with the multidimensional information of the file to be processed.

[0109] The candidate files mentioned above can be files of known classification stored in the system, used as reference samples to help identify the category of the file to be processed.

[0110] The user issues commands through the interface. The confirmation command is used to select candidate files for fine sorting and comparison, while the confirmation command is used to confirm the sorting result and use the first item of the first sorted file as the target file for subsequent operations.

[0111] In one optional embodiment, when a user selects a candidate file on the user interface, the system responds with a confirmation command and initiates a large-scale model for more in-depth ranking and comparison. The large-scale model can calculate the matching score between the file to be processed and the candidate files, sort the candidate files according to their scores, and display the results on the user interface. A deep comparison can be performed between the retrieved samples and the file to be processed. After the user confirms the sorting results, the system responds with a confirmation command and automatically selects the first file in the sorted list as the target file, i.e., the file with the highest matching degree, for subsequent confirmation operations. The system displays the confirmed best-matching file to the user as the basis for the next step, such as information extraction and archiving.

[0112] By inputting the target's multidimensional information (such as the material's category, title, abstract, and keywords) and the candidate's multidimensional information into the text processing module, a pre-trained text processing model is used for comparison and matching. The resulting matching score accurately reflects the probability that the file to be processed and the candidate file belong to the same category. This is more accurate than traditional manual or rule-based classification methods because the large model can understand complex semantic relationships and text patterns, thereby reducing classification errors and improving overall classification accuracy.

[0113] Candidate files can be sorted based on their matching scores, with the files most likely to match the file to be processed appearing first. When the user confirms the sorting results on the interface, the system will prioritize displaying the first file in the first sorted list, i.e., the file with the highest matching score. This design improves the efficiency of users viewing and confirming files, reduces the time and effort required for manual screening of a large number of files, and enhances the user experience of organizing judicial case files.

[0114] Utilizing large-scale models and RAG technology for document matching and sorting significantly improves processing speed, enabling rapid classification results even with massive amounts of judicial case files. This avoids the problems of manual comparison or excessive computational resource consumption inherent in traditional methods, allowing the system to efficiently handle the large volume of judicial documents added daily. Through intelligent sorting and high-precision matching, the system reduces the need for manual classification and verification. Users can complete document classification and archiving with simple confirmation on the user interface, greatly reducing the complexity and workload of manual operations. When new document types need to be processed in the judicial process, the system can quickly adapt by updating the case library and cataloging rule library without retraining the model, thus maintaining the system's scalability and flexibility.

[0115] In the above embodiments of this application, the method further includes: in response to a modification instruction applied to at least one first sorting file, displaying at least one modified sorting file on an operation interface; in response to a confirmation instruction applied to at least one modified sorting file, adjusting the text processing model based on at least one modified sorting file, wherein the target file is the first file among at least one modified sorting file.

[0116] The above modification commands can be used by users to reclassify or rename one or more files in a sorting file.

[0117] The aforementioned confirmation command allows the user to acknowledge the modified sorting file and confirm that the file classification and naming are correct. This is the step for the user to make the final approval of the automated system's output.

[0118] In one optional embodiment, after a user modifies the dossier materials automatically organized and sorted by the large model on the user interface, the system displays an updated list of sorted files. After the user confirms the changes, the system automatically displays the detailed content of the first file selected by the user (the target file). Simultaneously, the system adjusts the text processing model based on the user's feedback on the sorted files. The purpose of adjusting the model is to better adapt it to the user's classification rules and needs, improving the accuracy and efficiency of future file processing. Users can intuitively see the modification results and confirm whether the classification and naming meet the requirements, which is crucial for improving the accuracy and standardization of dossier organization. Furthermore, adjusting the model based on user feedback reduces reliance on large amounts of labeled data, lowers operating costs, and improves the model's generalization ability, enabling it to better cope with future changes in material types or cataloging rules.

[0119] In the above embodiments of this application, the processing rules include: naming rules and storage rules. Responding to processing instructions applied to the operation interface, the method further includes: displaying naming element information matching the naming rules in the file to be processed on the operation interface, and displaying the target directory corresponding to the file to be processed, wherein the naming element information is information extracted from the file to be processed using a text processing model, and the target directory is a directory determined based on storage rules; responding to confirmation instructions applied to the naming element information and the target directory, displaying the processing result on the operation interface, wherein the processing result is used to indicate that, based on the naming element information and naming rules, the file to be processed has been successfully named, and the file to be processed has been successfully stored in the target directory.

[0120] In file management, the aforementioned processing rules can serve as specific guidelines for file naming and storage, including naming rules and storage rules. Naming rules define how files are named, while storage rules determine the directory structure and location where files are stored.

[0121] The aforementioned naming element information can be key information extracted from the file by the text processing model based on naming rules to generate filenames, such as case number, date, and party name.

[0122] The target directory mentioned above can be the storage location determined by the system for the file according to storage rules. The selection of the directory is based on the file type, extracted naming element information, etc.

[0123] The above processing result represents the final state after the system performs naming and storage operations, resulting in a file being assigned a new name that conforms to the naming rules and stored in the target directory.

[0124] In one optional embodiment, the file to be processed can be parsed according to processing rules. On the user interface, the system displays naming element information matching the naming rules, as well as the target directory determined according to the storage rules. The user can confirm the accuracy of this information on the user interface. Once the user confirms, the system will automatically generate a new name for the file to be processed based on the confirmed naming element information and naming rules, and store it in the corresponding target directory according to the storage rules. Finally, the user interface will display the processing result, i.e., the new name and storage location of the file, for the user to check and confirm.

[0125] In the context of judicial case file organization, processing rules (naming and storage rules) are the core of an automated organization system based on large-scale model technology. The user interface is used to interact with and control the file organization process. In this scenario, the text processing model specifically refers to an intelligent model based on large-scale model and few-shot learning techniques, used to parse and understand the semantics of case file materials and extract key naming elements. Determining the target directory and naming elements ensures that case file materials are classified and stored according to a standardized process. The processing results demonstrate the system's automated organization capabilities, ensuring efficient and accurate management of case file materials.

[0126] In the above embodiments of this application, the method further includes: responding to a modification instruction applied to the naming element information and displaying the modified element information on the operation interface; responding to a confirmation instruction applied to the modified element information, displaying the processing result on the operation interface, and adjusting the text processing model based on the modified element information, wherein the processing result is used to characterize that the file to be processed has been successfully named based on the modified element information and naming rules, and the file to be processed has been successfully stored in the target directory based on the storage rules.

[0127] The aforementioned naming element information can be key information or features used to determine the components of a filename, such as the file category, date, case number, etc.

[0128] The aforementioned modification commands can be commands issued by the user or the system to change naming element information.

[0129] The aforementioned confirmation command allows users to verify the validity of the modified feature information. After confirmation, the system will name and store the file based on this feature information.

[0130] The above processing results are obtained by naming and archiving the files to be processed based on the modified element information and the defined naming and storage rules.

[0131] The target directory mentioned above can be the storage location that the system assigns to files based on file type and elements, so as to achieve effective classification and management of files.

[0132] In one optional embodiment, after the large model extracts named feature information from the content of the file to be processed, the user or system administrator can check and modify it through the user interface. Once the feature information is modified, the user interface will display the modified information in real time for user confirmation. After the user confirms the modification, the system will generate a new filename based on the updated feature information and preset naming rules, and store the file in the corresponding target directory according to the storage rules. In addition, user modifications to the feature information can be recorded and used to adjust the text processing model, enabling the model to more accurately identify and extract this information in the future, thereby improving the accuracy and efficiency of automated cataloging.

[0133] In the embodiments of this application, users can directly modify naming element information, which not only enhances the intuitiveness and convenience of the operation but also ensures the accuracy and standardization of case file cataloging. For example, users can immediately correct information such as dates and case numbers that have been misidentified by the model. The system will immediately respond and display the modified information. After the user confirms that it is correct, the system will automatically rename and correctly archive the file according to the modified information and preset rules. This dynamic adjustment mechanism based on user feedback can not only effectively avoid human error but also continuously optimize the text processing model, making it more intelligent and reducing the need for future manual intervention. Ultimately, this process not only improves the efficiency of judicial case file organization but also reduces the error rate, ensuring the rigor and consistency of case file management.

[0134] In the above embodiments of this application, in response to a modification instruction applied to the target directory, the method further includes: displaying the modified directory on the operation interface; in response to a confirmation instruction applied to the modified directory, displaying the processing result on the operation interface, and adjusting the storage rules based on the modified directory, wherein the processing result is the result obtained by naming the file to be processed based on naming element information and naming rules, and storing the file to be processed in the modified directory based on the storage rules.

[0135] The aforementioned modification commands can be issued by users or system operators through the user interface, and are intended to change the target catalog or cataloging rules. These modification commands can include adjustments to the catalog structure, reassignment of material classifications, etc.

[0136] The above confirmation command allows the user to confirm the modified directory, indicating that the user approves the new directory allocation or cataloging rule adjustment. The system will then execute subsequent file naming and archiving operations based on the confirmation command.

[0137] In one optional embodiment, users or system operators can submit modification instructions for the initially formed directory structure or cataloging rules. Once received by the system, these modification instructions are immediately reflected in the user interface, allowing users to visually view the changes. If the user confirms the modification, the user interface displays the processing results, including file renaming and archiving status. The system adjusts the storage rules based on the confirmed modification instructions to ensure that subsequent files are stored according to the new directory structure and naming rules.

[0138] Through direct user interaction with the system, this solution significantly improves the flexibility and user satisfaction of judicial case file organization. Specifically, users can modify the case file directory and cataloging rules according to actual needs. This means that case file organization can more accurately match the specific needs of judicial practice, improving material retrieval efficiency and classification accuracy. Once the user confirms the modification, the system automatically adjusts the storage rules to ensure that all files to be processed are renamed based on the latest naming element information and naming rules, and stored in the modified directory. This process not only avoids errors caused by human operation but also greatly improves the system's responsiveness and adaptability to changing needs, reduces the operating costs of case file organization, and improves the efficiency and standardization of judicial work.

[0139] Figure 3 This is a schematic diagram illustrating the cataloging function of a sending address confirmation form according to an embodiment of this application, such as... Figure 3 As shown, the left side displays the documents to be processed, which can be images of delivery address confirmation forms containing multiple fields for information such as recipient, sender, and contact details. The last section displays the date and signature field. The right side displays the cataloging results, divided into three sections: first-level directory, second-level directory, and document name.

[0140] The first-level directory can include delivery address confirmation, delivery receipt, or other delivery vouchers. The second-level directory can include delivery address confirmation, and the document name can be "xxx delivery address confirmation".

[0141] Figure 4 This is a schematic diagram illustrating the classification and storage method of a mailing address confirmation form in a court document management system according to an embodiment of this application. The file to be processed can be case file materials, the text processing model can be an intelligent document processing system, the target multidimensional information can be the category, title, summary, and category keywords of the case file materials, and the target file can be a case file example, such as... Figure 4As shown, case file materials can be input into an intelligent document processing system. This system parses the content of the case file materials and extracts the information, transferring it to a case file index and a case file cataloging rule base to retrieve similar case file examples. When retrieving similar examples, a large-scale model can be used to refine the case file materials, generating categories, titles, abstracts, and category keywords. Based on the extracted information, similar case file examples can be found in the case file example base. The large-scale model can then be used to refine the retrieved cases, determining the target type of the case file materials based on the top-ranked examples. Processing rules corresponding to the target type can be retrieved from the cataloging rule base. These processing rules can include naming rules and storage rules. A text processing model can be used to extract naming element information from the case file materials. Based on storage rules, the target directory of the case file materials can be determined. Finally, the case file materials can be categorized into the target directory based on the naming element information and the target directory, and then renamed. It should be noted that samples can be manually added to the dossier sample library, and rules can be manually defined in the cataloging rule library. This diagram clearly illustrates the entire cataloging process, from inputting documents in various formats to intelligent parsing, classification indexing, and finally searching and archiving. The entire process fully utilizes IDP's multimodal material parsing capabilities and LLM's content extraction and similar dossier recall functions, ensuring accurate cataloging, classification, and effective storage of materials.

[0142] In the judicial field, judicial cataloging has significant project value, specifically reflected in the following aspects:

[0143] Improving judicial efficiency: By introducing large-scale modeling technology for judicial cataloging, the speed of classifying, archiving, and retrieving legal documents and evidence materials can be significantly improved, thereby greatly reducing manual processing time and increasing judicial efficiency. Case handlers can quickly retrieve the materials they need, accelerating the case processing process.

[0144] Improving accuracy and consistency: With its powerful semantic understanding and generalization capabilities, the large model can accurately identify and classify various types of legal materials. Even when faced with different naming conventions of different courts, it can maintain high consistency and accuracy, avoid human labeling errors, and ensure the rigor and standardization of judicial data.

[0145] Reduced operating costs: By employing few-shot learning and fine-tuning techniques, the reliance on large amounts of labeled data is significantly reduced, thereby lowering the costs of data acquisition and processing. This saves substantial human resources and time, improving overall operational efficiency.

[0146] Enhanced flexibility and scalability: The large model is highly flexible and scalable, and can flexibly respond to new material types and cataloging rule changes as needed. This reduces the frequent redevelopment and retraining work in traditional methods, and can quickly adapt to changes in the needs of judicial projects, thereby enhancing the long-term usability of the system.

[0147] Standardizing processes and increasing transparency: By using an intelligent cataloging system and standardizing trial procedures, the transparency and standardization of judicial work can be improved, making the handling of cases more scientific and transparent, which helps to enhance public trust in the judicial system.

[0148] This application combines the retrieval and generation processes, enabling the large model to handle various types and forms of materials, thus addressing complex requirements for multiple different material types. Through few-shot learning techniques, the training sample data can be reduced to a much smaller amount, significantly decreasing the cost of data acquisition and annotation. By configuring a case library and a cataloging rule library, it can flexibly respond to new project requirements such as adding new material types and changing cataloging rules, reducing the workload of redevelopment and training.

[0149] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0150] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0151] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0152] According to an embodiment of this application, a text processing method is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here. Figure 5 This is a flowchart of a text processing method according to an embodiment of this application. Figure 5 As shown, the method includes:

[0153] Step S502: Obtain the file to be processed.

[0154] In one alternative embodiment, the file to be processed can be received from an input source or uploaded manually. The file can be in formats such as Word, PDF, or JPG, and its source can be an electronic file system, submitted materials, or documents from other judicial authorities. At this stage, the system does not parse the file content; it simply retrieves the file for subsequent processing.

[0155] Step S504: Parse the text to be processed to obtain the text to be processed contained in the file to be processed.

[0156] After receiving the text to be processed, it can be parsed to extract the text content. The parsing process is not limited to plain text, but can also parse non-text information such as charts, tables, and signatures, converting this information into a processable text format.

[0157] Step S506: Compare the text to be processed with the preset text contained in multiple preset files to determine the target type of the text to be processed.

[0158] The different preset files are of different types.

[0159] The parsed text is input into a large model. By comparing the text to be processed with sample texts in a pre-defined sample library, the category of the file to be processed is determined. The pre-defined files are files that have been defined and labeled in the system; they constitute the sample library and are used to train and validate the model. The model finds the pre-defined file type that is most similar to the text to be processed by calculating text similarity, keyword matching, and other methods, thereby determining the target type of the file to be processed.

[0160] Step S508: Name and store the file to be processed based on the processing rules corresponding to the target type.

[0161] After determining the target type of the file to be processed, the system names and archives the file according to the rules stored in the dossier cataloging rule base. The rule base defines the naming format for each file type and the directory in which it should be stored.

[0162] In the field of judicial case file organization, the entire process utilizes the powerful semantic understanding and generalization capabilities of large models to achieve automated classification and archiving of judicial case files, significantly improving processing speed, reducing error rates, reducing reliance on manual labor, and enhancing the system's flexibility and scalability.

[0163] Through the above steps, the file to be processed is obtained; the text to be processed is parsed to obtain the text to be processed contained in the file; the text to be processed is compared with the preset text contained in multiple preset files to determine the target type of the file to be processed, wherein different preset files have different types; based on the processing rules corresponding to the target type, the file to be processed is named and stored, thereby improving the accuracy of file processing. It is worth noting that for the text to be processed containing at least one modality, the target type of the text to be processed can be determined by comparing the text to be processed with the preset text contained in multiple preset files and determining the type of the preset text similar to the text to be processed. Thus, based on the processing rules corresponding to the target type of the file to be processed, the file is automatically named and stored appropriately, reducing manual intervention, improving processing speed and accuracy, and thus solving the technical problem of low file processing accuracy in related technologies.

[0164] According to an embodiment of this application, a text processing method is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here. Figure 6 This is a flowchart of a text processing method according to an embodiment of this application. Figure 6 As shown, the method includes:

[0165] Step S602: Receive judicial case file files sent by the client.

[0166] In one alternative embodiment, judicial case files may be received from the client first. These files may include, but are not limited to, legal documents and evidentiary materials, and are typically provided in formats such as Word, PDF, or JPG.

[0167] Step S604: Parse the judicial case file to obtain the judicial case file text contained in the judicial case file.

[0168] Upon receiving judicial case files, intelligent document processing (IDP) technology can be used to parse the documents and extract the text information. IDP technology can handle multimodal materials, accurately extracting text content even if the document contains images or tables.

[0169] Step S606: Compare the judicial case file text with the preset case file text contained in multiple preset case file files to determine the target type of the judicial case file file.

[0170] The types of preset file types are different.

[0171] The extracted text information can be passed to a large model, which compares it with text in a pre-defined dossier (sample library) to determine the type of the current file. The key here is that the large model combines RAG technology, utilizing its retrieval and generation capabilities to find the most similar file type from the sample library, ensuring the accuracy and consistency of the classification.

[0172] Step S608: Based on the processing rules corresponding to the target type, the judicial case file is named and stored to obtain the processing result.

[0173] After determining the target type of the judicial case file, the corresponding processing rules can be retrieved from the case file cataloging rule base, and the judicial case file can be renamed and archived according to these processing rules. The processing rules define how the file should be named, in which directory it should be archived, and which key elements may need to be extracted.

[0174] Step S610: Send the processing result to the client.

[0175] The processing results (including file classification, naming, and storage location) can be sent back to the client to complete the entire automatic organization process of judicial case files.

[0176] The method described in this application can improve the efficiency, accuracy, and consistency of judicial case file organization, while reducing reliance on large amounts of labeled data, lowering operating costs, and improving the system's flexibility and scalability. It is an innovative solution in the field of automated judicial case file organization.

[0177] Through the above steps, the system receives judicial case files sent by the client; parses the judicial case files to obtain the judicial case file text contained within them; compares the judicial case file text with preset case file texts contained in multiple preset case files to determine the target type of the judicial case file, where different preset case file texts have different types; names and stores the judicial case file based on the processing rules corresponding to the target type, obtaining the processing result; and sends the processing result to the client, thus achieving the goal of improving the accuracy of file processing. It is worth noting that for the text to be processed containing at least one modality, the target type of the text to be processed can be determined by comparing the text to be processed with preset texts contained in multiple preset files and determining the type of preset texts similar to the text to be processed. This effectively and automatically names and stores the file appropriately based on the processing rules corresponding to the target type of the text to be processed, reducing manual intervention, improving processing speed and accuracy, and thus solving the technical problem of low file processing accuracy in related technologies.

[0178] According to an embodiment of this application, a text processing method is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here. Figure 7 This is a flowchart of a text processing method according to an embodiment of this application. Figure 7 As shown, the method includes:

[0179] Step S702: Obtain the file to be processed by calling the first interface.

[0180] The first interface includes a first parameter, and the value of the first parameter includes the file to be processed.

[0181] The aforementioned first interface can be an interface for data interaction between the cloud server and the client. The client can pass the file to be processed into the interface function as the first parameter of the interface function to achieve the purpose of uploading the file to be processed to the cloud server.

[0182] Step S704: Parse the text to be processed to obtain the text to be processed contained in the file to be processed.

[0183] Step S706: Compare the text to be processed with the preset text contained in multiple preset files to determine the target type of the text to be processed.

[0184] The different preset files are of different types.

[0185] Step S708: Based on the processing rules corresponding to the target type, name and store the file to be processed to obtain the processing result.

[0186] Step S710: Output the processing result by calling the second interface.

[0187] The second interface includes a second parameter, the value of which includes the processing result.

[0188] The aforementioned second interface can be an interface for data interaction between the cloud server and the client. The cloud server can pass the processing result into the interface function as the second parameter of the interface function, thereby achieving the purpose of sending the processing result to the client.

[0189] Through the above steps, the file to be processed is obtained by calling the first interface, where the first interface includes a first parameter whose value includes the file to be processed; the text to be processed is parsed to obtain the text to be processed contained in the file to be processed; the text to be processed is compared with the preset text contained in multiple preset files to determine the target type of the file to be processed, where different preset files have different types; based on the processing rules corresponding to the target type, the file to be processed is named and stored to obtain the processing result; the processing result is output by calling the second interface, where the second interface includes a second parameter whose value includes the processing result, thus achieving the goal of improving the accuracy of file processing. It is worth noting that for the text to be processed containing at least one modality, the target type of the text to be processed can be determined by comparing the text to be processed with the preset text contained in multiple preset files and determining the type of the preset text similar to the text to be processed. This effectively and automatically names and stores the file appropriately based on the processing rules corresponding to the target type of the file to be processed, reducing manual intervention, improving processing speed and accuracy, and thus solving the technical problem of low accuracy in file processing in related technologies.

[0190] According to an embodiment of this application, a text processing apparatus for implementing the above-described text processing method is also provided. Figure 8 This is a schematic diagram of a text processing device according to an embodiment of this application, such as... Figure 8 As shown, the device 800 includes: a first display device 802 and a second display device 804.

[0191] A first display device is used to respond to an input command applied to an operation interface and display a file to be processed on the operation interface, wherein the file to be processed contains at least one modality of text to be processed; a second display device is used to respond to a processing command applied to the operation interface and display a processing result on the operation interface, wherein the processing result is used to characterize the successful naming and storage of the file to be processed based on a target processing rule, the target processing rule being a processing rule corresponding to the target type of the file to be processed, the target type being determined by comparing the text to be processed with preset text contained in multiple preset files, and different preset files having different types.

[0192] It should be noted that the first display device 802 and the second display device 804 mentioned above correspond to steps S202 to S204 in the above embodiments. The two modules and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules or units can be hardware components or software components stored in memory and processed by one or more processors. The above modules can also run as part of the device in the server 10 provided in the above embodiments.

[0193] It should be noted that the preferred embodiments involved in the above embodiments of this application are the same as the solutions, application scenarios and implementation processes provided in the above embodiments, but are not limited to the solutions provided in the above embodiments.

[0194] According to an embodiment of this application, a text processing apparatus for implementing the above-described text processing method is also provided. Figure 9 This is a schematic diagram of a text processing device according to an embodiment of this application, such as... Figure 9 As shown, the device 900 includes: an acquisition module 902, a parsing module 904, a comparison module 906, and a processing module 908.

[0195] The module consists of: an acquisition module for acquiring the file to be processed; a parsing module for parsing the text to be processed to obtain the text to be processed contained in the file; a comparison module for comparing the text to be processed with preset text contained in multiple preset files to determine the target type of the file to be processed, wherein different preset files have different types; and a processing module for naming and storing the file to be processed based on the processing rules corresponding to the target type.

[0196] It should be noted that the acquisition module 902, parsing module 904, comparison module 906, and processing module 908 mentioned above correspond to steps S502 to S508 in the above embodiments. The four modules and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules or units can be hardware or software components stored in memory and processed by one or more processors. The above modules can also run as part of the device in the server 10 provided in the above embodiments.

[0197] According to an embodiment of this application, a text processing apparatus for implementing the above-described text processing method is also provided. Figure 10 This is a schematic diagram of a text processing device according to an embodiment of this application, such as... Figure 10 As shown, the device 1000 includes: a receiving module 1002, a parsing module 1004, a comparison module 1006, a processing module 1008, and a sending module 1010.

[0198] The system comprises the following modules: a receiving module for receiving judicial case files sent by the client; a parsing module for parsing the judicial case files to obtain the judicial case file text; a comparison module for comparing the judicial case file text with preset case file texts contained in multiple preset case files to determine the target type of the judicial case file, wherein different preset case files have different types; a processing module for naming and storing the judicial case file based on the processing rules corresponding to the target type to obtain the processing result; and a sending module for sending the processing result to the client.

[0199] It should be noted that the receiving module 1002, parsing module 1004, comparison module 1006, processing module 1008, and sending module 1010 correspond to steps S602 to S610 in the above embodiments. The five modules and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments. It should also be noted that the above modules or units can be hardware or software components stored in memory and processed by one or more processors. These modules can also run as part of a device within the server 10 provided in the above embodiments.

[0200] According to an embodiment of this application, a text processing apparatus for implementing the above-described text processing method is also provided. Figure 11 This is a schematic diagram of a text processing device according to an embodiment of this application, such as... Figure 11 As shown, the device 1100 includes: an acquisition module 1102, a parsing module 1104, a comparison module 1106, a processing module 1108, and an output module 1110.

[0201] The system comprises the following modules: an acquisition module for acquiring a file to be processed by calling a first interface, wherein the first interface includes a first parameter whose value includes the file to be processed; a parsing module for parsing the text to be processed to obtain the text to be processed contained in the file to be processed; a comparison module for comparing the text to be processed with preset text contained in multiple preset files to determine the target type of the file to be processed, wherein different preset files have different types; a processing module for naming and storing the file to be processed based on the processing rules corresponding to the target type to obtain the processing result; and an output module for outputting the processing result by calling a second interface, wherein the second interface includes a second parameter whose value includes the processing result.

[0202] It should be noted that the acquisition module 1102, parsing module 1104, comparison module 1106, processing module 1108, and output module 1110 mentioned above correspond to steps S702 to S710 in the above embodiments. The five modules and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules or units can be hardware or software components stored in memory and processed by one or more processors. The above modules can also run as part of the device in the server 10 provided in the above embodiments.

[0203] Embodiments of this application may provide an electronic device, which may be any one of a group of electronic devices. Optionally, in this embodiment, the aforementioned electronic device may also be replaced by a terminal device such as a mobile terminal.

[0204] Optionally, in this embodiment, the aforementioned electronic device may be located in at least one of a plurality of network devices in a computer network.

[0205] In this embodiment, the computer terminal described above can execute the program code in the method.

[0206] Optionally, Figure 12 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 12 As shown, the electronic device A may include: one or more ( Figure 12 (Only one is shown) processor 102, memory 104, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0207] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the methods in the above embodiments. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to terminal A via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0208] The processor can invoke information and application programs stored in memory via a transmission device to perform the following steps: responding to an input command applied to an operation interface, displaying a file to be processed on the operation interface, wherein the file to be processed contains at least one modality of text to be processed; responding to a processing command applied to the operation interface, displaying a processing result on the operation interface, wherein the processing result is used to characterize the result obtained by naming and storing the file to be processed based on the processing rules corresponding to the target type of the file to be processed, and the target type is the result determined by comparing the text to be processed with preset texts contained in multiple preset files, and different preset files have different types.

[0209] Those skilled in the art will understand that, Figure 12 The structure shown is for illustrative purposes only; the electronic device can also be a smartphone (such as an Android phone, iOS phone, etc.), tablet computer, PDA, mobile internet device (MID), PAD, and other terminal devices. Figure 12 This does not limit the structure of the aforementioned electronic device. For example, electronic device A may also include components that are more advanced than those described above. Figure 12 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same as the Figure 12 The different configurations shown.

[0210] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0211] Embodiments of this application also provide a computer-readable storage medium. Optionally, in this embodiment, the computer-readable storage medium can be used to store program code executed by the method provided in the above embodiments.

[0212] Optionally, in this embodiment, the storage medium may be located in any one of the electronic devices in the group of electronic devices in the computer network, or in any one of the mobile terminals in the group of mobile terminals.

[0213] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: in response to an input instruction applied to the operation interface, displaying a file to be processed on the operation interface, wherein the file to be processed contains at least one modality of text to be processed; in response to a processing instruction applied to the operation interface, displaying a processing result on the operation interface, wherein the processing result is used to characterize the result obtained by naming and storing the file to be processed based on the processing rules corresponding to the target type of the file to be processed, the target type being the result determined by comparing the text to be processed with preset text contained in multiple preset files, and different preset files having different types.

[0214] Embodiments of this application also provide a computer program product. Optionally, in this embodiment, the computer program product may include a computer program that, when executed by a processor, implements the methods provided in the embodiments described above.

[0215] Embodiments of this application also provide a computer program product. Optionally, the computer program product may include a non-volatile computer-readable storage medium, which can be used to store a computer program that, when executed by a processor, implements the method provided in the above embodiments.

[0216] Embodiments of this application also provide a computer program. Optionally, in this embodiment, when the computer program is executed by a processor, it implements the method provided in the above embodiments.

[0217] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0218] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0219] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0220] Furthermore, the functional units in the various embodiments of this application 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 as a software functional unit.

[0221] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0222] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A file processing method, characterized in that, include: In response to an input command applied to the operation interface, a file to be processed is displayed on the operation interface, wherein the file to be processed contains at least one modality of text to be processed; In response to the processing instructions applied to the operation interface, the processing result is displayed on the operation interface. The processing result is used to indicate that the file to be processed has been successfully named and stored based on the target processing rule. The target processing rule is a processing rule corresponding to the target type of the file to be processed. The target type is determined by comparing the text to be processed with preset text contained in multiple preset files. Different preset files have different types.

2. The method according to claim 1, characterized in that, In response to a processing instruction applied to the user interface, the method further includes: The target multidimensional information of the file to be processed is displayed on the operation interface. The target multidimensional information is information extracted from the text to be processed using a text processing model. In response to a confirmation command applied to the target multidimensional information, a target file matching the file to be processed is displayed on the operation interface, wherein the target file is a file determined from the plurality of preset files by comparing the target multidimensional information with preset multidimensional information of the plurality of preset files; In response to a confirmation command applied to the target file, the target type of the file to be processed is displayed on the operation interface, wherein the target type is the type of the target file; In response to a confirmation command applied to the target type, the processing result is displayed on the operation interface.

3. The method according to claim 2, characterized in that, The method further includes: In response to a modification command applied to the target multidimensional information, the modified multidimensional information is displayed on the operation interface; In response to a confirmation command applied to the modified multidimensional information, a new file is displayed on the operation interface, and the text processing model is adjusted using the modified multidimensional information. The new file is determined from the plurality of preset files by comparing the modified multidimensional information with preset multidimensional information of the plurality of preset files.

4. The method according to claim 2, characterized in that, The method further includes: In response to a modification command applied to the target file, the modified target file is displayed on the operation interface; In response to a confirmation command applied to the modified target file, a new type is displayed on the operation interface, wherein the new type is the type of the modified target file.

5. The method according to claim 2, characterized in that, The response acts on the confirmation command of the target multidimensional information, and displays the target file matching the file to be processed on the operation interface, including: At least one candidate file is displayed on the operation interface, wherein the at least one candidate file is a file determined by recalling the plurality of preset files stored in the file database based on the target multidimensional information; In response to a determination instruction applied to the at least one candidate file, the target file is displayed on the operation interface, wherein the target file is a file determined from at least one first sorting file, the at least one first sorting file being obtained by sorting the at least one candidate file using the text processing model.

6. The method according to claim 5, characterized in that, The method further includes: In response to a modification instruction applied to the at least one candidate file, at least one modified candidate file is displayed on the user interface; In response to a confirmation command applied to the at least one modified candidate file, the target file is displayed on the operation interface, wherein the target file is a file determined from at least one second sorting file, the at least one second sorting file being a file determined by sorting the at least one modified candidate file using the text processing model.

7. The method according to claim 5, characterized in that, The response acts on the determination instruction of the at least one candidate file, and displays the target file on the operation interface, including: The operation interface displays at least one first sorted file, wherein the at least one first sorted file is the result of sorting at least one candidate file using the matching score of at least one candidate file. The matching score of at least one candidate file is obtained by comparing the target multidimensional information and the candidate multidimensional information of at least one candidate file using the text processing model. The matching score is used to characterize the probability that the file to be processed is of the same category as the corresponding candidate file. In response to a confirmation command applied to the at least one first sorted file, the target file is displayed on the operation interface, wherein the target file is the first file among the at least one first sorted files.

8. The method according to claim 7, characterized in that, The method further includes: In response to a modification instruction applied to the at least one first sorting file, at least one modified sorting file is displayed on the operation interface; In response to a confirmation instruction applied to the at least one modified sorted file, the text processing model is adjusted based on the at least one modified sorted file, wherein the target file is the first file in the at least one modified sorted file.

9. The method according to claim 1, characterized in that, The processing rules include naming rules and storage rules, and the method further includes responding to processing instructions applied to the user interface. The operation interface displays the naming element information of the file to be processed that matches the naming rule, and displays the target directory corresponding to the file to be processed. The naming element information is information extracted from the file to be processed using a text processing model, and the target directory is a directory determined based on the storage rule. In response to the confirmation command applied to the naming element information and the target directory, the processing result is displayed on the operation interface, wherein the processing result is used to indicate that the file to be processed has been successfully named based on the naming element information and the naming rules, and the file to be processed has been successfully stored in the target directory.

10. The method according to claim 9, characterized in that, The method further includes: In response to the modification command applied to the named element information, the modified element information is displayed on the operation interface; In response to the confirmation command applied to the modified feature information, the processing result is displayed on the operation interface, and the text processing model is adjusted based on the modified feature information. The processing result is used to indicate that the file to be processed has been successfully named based on the modified feature information and the naming rules, and the file to be processed has been successfully stored in the target directory based on the storage rules.

11. The method according to claim 9, characterized in that, In response to a modification command applied to the target directory, the method further includes: The modified directory is displayed on the user interface; In response to the confirmation command applied to the modified directory, the processing result is displayed on the operation interface, and the storage rules are adjusted based on the modified directory. The processing result is obtained by naming the file to be processed based on the naming element information and the naming rules, and storing the file to be processed in the modified directory based on the storage rules.

12. A file processing method, characterized in that, include: Get the file to be processed; The text to be processed is parsed to obtain the text to be processed contained in the file to be processed; The text to be processed is compared with preset texts contained in multiple preset files to determine the target type of the text to be processed, wherein different preset files have different types; Based on the processing rules corresponding to the target type, the files to be processed are named and stored.

13. A file processing method, characterized in that, include: Receive judicial case files sent by the client; The judicial case file is parsed to obtain the judicial case file text contained in the judicial case file; The judicial case file text is compared with the preset case file text contained in multiple preset case file files to determine the target type of the judicial case file file, wherein the types of different preset case file files are different; Based on the processing rules corresponding to the target type, the judicial case file is named and stored to obtain the processing result; The processing result is sent to the client.

14. A file processing method, characterized in that, include: The file to be processed is obtained by calling a first interface, wherein the first interface includes a first parameter, and the value of the first parameter includes the file to be processed; The text to be processed is parsed to obtain the text to be processed contained in the file to be processed; The text to be processed is compared with preset texts contained in multiple preset files to determine the target type of the text to be processed, wherein different preset files have different types; Based on the processing rules corresponding to the target type, the file to be processed is named and stored to obtain the processing result; The processing result is output by calling a second interface, wherein the second interface includes a second parameter, and the parameter value of the second parameter includes the processing result.

15. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method according to any one of claims 1 to 14.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 14.

17. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1 to 14.

Images