Business file generation method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of business automation and artificial intelligence, and discloses a business file generation method and device, electronic equipment and a storage medium. The business file generation method comprises the following steps: receiving a plurality of documents of a to-be-evaluated object; generating a task instruction based on the plurality of documents and the target evaluation field; executing the task instruction, and performing information extraction on the plurality of documents to obtain key information; performing association processing on information which comes from different documents and aims at the same theme in the key information to obtain an association processing result; according to an association processing result, performing information matching processing based on the key information and / or the plurality of documents to obtain first target information matched with the target evaluation field; and generating a business file of the to-be-evaluated object based on the first target information and the target evaluation field. Through the method, multiple documents of the supplier can be automatically and intelligently analyzed, information association is established among different documents, the comprehensively evaluated supplier archive is generated, and the archive establishment efficiency is effectively improved.

Description

Technical Field

[0001] This application relates to the fields of business automation and artificial intelligence technology, and in particular to a business document generation method, apparatus, electronic device, and storage medium. Background Technology

[0002] Suppliers are a key resource for the success of a company's business projects. Before formal cooperation, companies need to conduct a comprehensive background and capability assessment of potential suppliers and enter their information into the company's internal system to form standardized supplier profiles for subsequent bidding invitations and procurement sourcing.

[0003] Currently, when processing supplier information, most companies rely on purchasing or bidding personnel to manually input various types of supplier documents into the company's internal system for manual review. This approach suffers from inefficiency, loss of some information value, and incomplete supplier evaluation profiles, thereby affecting the level of supply chain management. Summary of the Invention

[0004] The embodiments of this application aim to at least partially address one of the technical problems in the related art. To this end, embodiments of this application propose a business profile generation method, apparatus, electronic device, and storage medium.

[0005] This application provides a business file generation method, which includes: receiving multiple documents of an object to be evaluated; generating task instructions based on the multiple documents and a target evaluation field; executing the task instructions to extract key information from the multiple documents; performing association processing on information from different documents that are related to the same topic in the key information to obtain association processing results; performing information matching processing based on the key information and / or multiple documents according to the association processing results to obtain first target information that matches the target evaluation field; and generating a business file of the object to be evaluated based on the first target information and the target evaluation field.

[0006] In some implementations, based on the association processing results, information matching processing is performed on key information and / or multiple documents to obtain first target information that matches the target evaluation field. This includes: processing key information and / or multiple documents based on the association processing results to obtain information processing results; and matching the information processing results with the target evaluation field to obtain the first target information.

[0007] In some implementations, information processing is performed on key information and / or multiple documents to obtain information processing results, including: integrating information on the same topic in the key information and / or multiple documents to obtain information integration results; understanding the key information and / or multiple documents to obtain profile information of the object to be evaluated; determining key indicators in the key information and / or multiple documents, and querying external reference information based on the key indicators to obtain risk information of the object to be evaluated; and obtaining information processing results based on at least one of the information integration results, profile information, and risk information.

[0008] In some implementations, the method further includes: in response to receiving a question-and-answer instruction for the object to be evaluated, querying business files to obtain answer data; and outputting the answer data.

[0009] In some implementations, the method further includes: periodically acquiring updated information about the object to be evaluated; and updating the business files based on the updated information.

[0010] In some implementations, the method further includes: receiving voice data; extracting second target information from the voice data that matches the target evaluation field; and supplementing the second target information into the business file.

[0011] In some implementations, the method further includes: receiving an audit operation on the business file and obtaining an audit result; receiving a rating operation on the object to be evaluated based on the business file and obtaining a rating result.

[0012] This application provides a business file generation apparatus, comprising: a receiving module for receiving multiple documents of an object to be evaluated; a first generation module for generating task instructions based on the multiple documents and a target evaluation field; an extraction module for executing the task instructions and extracting key information from the multiple documents; an association module for associating information from different documents on the same topic within the key information to obtain an association processing result; a matching module for performing information matching processing based on the key information and / or multiple documents according to the association processing result to obtain first target information matching the target evaluation field; and a second generation module for generating a business file of the object to be evaluated based on the first target information and the target evaluation field.

[0013] The present application provides an electronic device including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any of the above embodiments.

[0014] Embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method of any of the above embodiments. Attached Figure Description

[0015] Figure 1 A flowchart illustrating the business file generation method provided for embodiments of this application; Figure 2 An example of supplier profile generation based on an AI large model provided for implementation of this application; Figure 3 A schematic diagram of a business file generation apparatus provided for an embodiment of this application; Figure 4 A block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0016] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0017] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0018] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0019] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0020] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0021] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0022] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0023] Suppliers are a critical resource for the success of a company's business projects (such as real estate projects). Before formal cooperation, companies need to conduct a comprehensive background and capability assessment of potential suppliers and enter their information into the SRM system to create standardized supplier profiles for subsequent bidding invitations and procurement sourcing. This profile creation process is the starting point of supplier lifecycle management, and its efficiency and quality directly affect the level of subsequent supply chain management.

[0024] Currently, when processing supplier information, most companies rely on purchasing or bidding personnel to manually input various types of supplier documents into the SRM system for manual review. This approach suffers from inefficiency, loss of some information value, and incomplete supplier evaluation profiles, thereby affecting the level of supply chain management.

[0025] Specifically, real estate development companies have the following problems in the supplier access and file management process: 1. Extremely low information entry efficiency: When reviewing a new supplier, procurement or bidding personnel need to open a folder sent by the supplier via email or cloud storage, which contains various types of files (company introduction PPT, scanned copies of qualification certificates, financial statement PDF, project case Word, etc.), and then manually extract and enter the supplier information field by field in the SRM system. The process is tedious, time-consuming, and easily interrupted.

[0026] 2. Loss of Value from Unstructured Information: The most valuable information about suppliers, such as project experience, technical capabilities, and management team introductions, often exists in unstructured PPT or Word documents. When manually creating files, this in-depth information is difficult to effectively and structurally input into the system, resulting in a flat and incomplete supplier profile within the system, making subsequent effective retrieval and matching difficult.

[0027] 3. Fragmented workflow and poor user experience: The process of reviewers reading and approving supplier materials is completely separate from the process of entering data into the system. This fragmentation leads to a large amount of repetitive information processing work and makes it impossible to guarantee the consistency between the entered data and the original document information, resulting in an extremely poor overall user experience.

[0028] Some methods utilize online supplier portals that offer file upload functionality, allowing suppliers to fill in some basic information on a single webpage and upload the remaining detailed information as a separate attachment. However, this method has the following technical limitations: 1. Merely a "Document Collector," Not a "Smart Processer": The system acts only as a "document collection box." It stores all documents uploaded by suppliers as static attachments, but cannot deeply read or understand their content. Reviewers still need to download all the files, open and read them one by one, and then return to the system interface to manually fill out forms. The core inefficiency problem remains unresolved.

[0029] 2. Inability to handle interconnected information across multiple documents: Complete supplier profiles are scattered across multiple documents of different types. Existing technology cannot automatically connect and integrate this fragmented information to form a unified and comprehensive understanding. For example, it cannot link a team introduction in a PowerPoint presentation with a project manager's resume in a Word document.

[0030] 3. Lack of intelligent assessment support: The system cannot automatically assign capability tags, assess risk levels, or generate comprehensive evaluation summaries based on an understanding of supplier information. The entire assessment and rating process still relies entirely on manual analysis and subjective judgment by reviewers.

[0031] Therefore, this application provides a business profile generation method that can automatically and intelligently parse various documents of suppliers and establish information associations between different documents, thereby generating a comprehensive supplier profile for evaluation, effectively improving the efficiency of profile building and providing scientific and objective decision support information.

[0032] In the technical solution of this application embodiment, multiple documents of the object to be evaluated are first received. Then, based on the multiple documents and the target evaluation field, a task instruction is generated and executed to extract key information from the multiple documents. Next, information from different documents that are related to the same topic in the key information is associated to obtain the association processing result. Based on the association processing result, information matching processing is performed based on the key information or multiple documents to obtain the first target information that matches the target evaluation field. Finally, based on the first target information and the target evaluation field, a business file of the object to be evaluated is generated. This method can automatically and intelligently parse various documents of the supplier and establish information associations between different documents, thereby generating a comprehensive supplier file for evaluation, effectively improving the file building efficiency and providing scientific and objective decision support information.

[0033] Figure 1 A flowchart illustrating the business file generation method provided in this application embodiment.

[0034] like Figure 1 As shown, the business file generation method 100 provided in this application embodiment includes, for example, steps S110-S160.

[0035] Step S110: Receive multiple documents of the object to be evaluated.

[0036] For example, the object to be evaluated can be a potential partner in the company's related business, such as a potential supplier for a real estate project. The reviewer can drag and drop multiple documents from the supplier to a designated area in the SRM system to receive the documents. These documents can be in various formats, such as a ZIP archive or a folder containing various types of files (e.g., company introduction PPT, scanned copies of qualification certificates, PDF financial statements, Word documents for project cases, etc.).

[0037] Step S120: Generate task instructions based on multiple documents and target evaluation fields.

[0038] For example, the target evaluation fields could be a list of fields (Schema) for a supplier profile creation page based on multiple documents, such as structured information that needs to be recorded, including "Company Full Name," "Registered Capital," "List of Qualification Certificates," "Past Experience in Similar Projects," and "Key Management Personnel." For instance, based on multiple documents and the target evaluation fields, relevant task instructions for creating supplier profiles using a large AI model can be generated.

[0039] Step S130: Execute the task instruction to extract key information from multiple documents.

[0040] For example, by executing task instructions, the AI ​​model can read the text in multiple documents and understand the core content of each document. For instance, the AI ​​model can identify which document is a business license, which is a financial statement, and which is a project case study, and extract key information from these documents.

[0041] Step S140: Perform association processing on information from different documents that are on the same topic in the key information to obtain the association processing result.

[0042] For example, information about the same topic (relative topic) extracted from different documents can be associated in the extracted key information. For instance, the "team introduction" in the company introduction PPT and the "project manager's resume" in the project case can be associated to obtain the association processing result.

[0043] Step S150: Based on the association processing results, perform information matching processing based on key information and / or multiple documents to obtain the first target information that matches the target evaluation field.

[0044] For example, by associating cross-document information in the extracted key information, multiple sets of association processing results for the same topic can be obtained. These association processing results are used to comprehensively describe the information of the object to be evaluated (e.g., a supplier). Based on the association processing results, the information (key information or information in multiple documents) is matched with the target evaluation field to obtain the first target information. The first target information can represent the content information that matches each target evaluation field, that is, the first target information and the target evaluation field are mapped.

[0045] Step S160: Based on the first target information and the target evaluation field, generate the business file of the object to be evaluated.

[0046] For example, based on the mapping relationship between the first target information and the target evaluation field, a complete file containing the target evaluation field and the corresponding filled first target information can be generated, that is, the business file of the object to be evaluated, such as generating a complete supplier file.

[0047] In the technical solution of this application embodiment, multiple documents of the object to be evaluated are first received. Then, based on the multiple documents and the target evaluation field, a task instruction is generated and executed to extract key information from the multiple documents. Next, information from different documents that are related to the same topic in the key information is associated to obtain the association processing result. Based on the association processing result, information matching processing is performed based on the key information or multiple documents to obtain the first target information that matches the target evaluation field. Finally, based on the first target information and the target evaluation field, a business file of the object to be evaluated is generated. This method can automatically and intelligently parse various documents of the supplier and establish information associations between different documents, thereby generating a comprehensive supplier file for evaluation, effectively improving the file building efficiency and providing scientific and objective decision support information.

[0048] First, combined Figure 2 This describes an example of generating supplier profiles in an SRM system based on a large AI model.

[0049] Figure 2 An example of supplier profile generation based on an AI large model provided for implementation of this application.

[0050] like Figure 2 As shown, generating supplier profiles based on an AI large model includes the following steps: S201, the reviewer initiates supplier profile creation in the SRM system.

[0051] S202, Upload / drag and drop the folder or ZIP archive containing the supplier's complete set of information.

[0052] S203, Batch file processing, including decompression, sorting, and text extraction using OCR and file parsing technologies.

[0053] S204, The server retrieves a list of fields (Schema) for all text and document pages.

[0054] S205, the AI ​​big model performs multi-document content understanding and information extraction, cross-document information association and integration, supplier capability profiling and risk analysis, and intelligent mapping of integrated information to page fields.

[0055] S206, AI outputs a structured JSON file to be populated.

[0056] S207, The server calls the internal API to automatically populate the supplier profile.

[0057] S208, the front-end page displays automatically generated supplier profiles and evaluation reports.

[0058] S209, the reviewers conduct the final review and grading.

[0059] S210, after the reviewers confirm, the supplier file officially becomes effective.

[0060] Next, the process of generating business files will be described in detail.

[0061] First, reviewers can directly drag and drop a folder or ZIP archive containing the complete information of a supplier (the entity to be evaluated) into the designated upload area in the supplier admission module of the SRM system to initiate the filing process. Upon receiving the file package, the server automatically decompresses it and preprocesses the multiple files within. Using OCR and file parsing technology, it extracts the plain text content of all documents (multiple documents, such as PPT, Word, PDF, images, etc.) while retaining their original file type tags.

[0062] Then, the server aggregates the text content of all files, along with the field list from the supplier profile creation page (target evaluation fields), and sends it to the AI ​​model to generate task instructions. The target evaluation fields define the structured information the system needs to record, such as "Company Full Name," "Registered Capital," "List of Qualification Certificates," "Past Experience in Similar Projects," and "Key Management Personnel." The AI ​​model executes the task instructions to perform complex, cross-document processing tasks related to the instructions. The following details the processing of multiple documents.

[0063] For example, by executing task instructions, the AI ​​big data model can extract and analyze information from multiple documents, that is, process key information and / or multiple documents to obtain information processing results. For example, firstly, it integrates information on the same topic in the key information and / or multiple documents to obtain information integration results; then, it understands the key information and / or multiple documents to obtain profile information of the object to be evaluated; and determines the key indicators in the key information and / or multiple documents, and queries external reference information based on the key indicators to obtain risk information of the object to be evaluated; finally, it obtains information processing results based on at least one of the information integration results, profile information, and risk information.

[0064] Specifically, AI first correlates and integrates information (key information) on the same topic extracted from different documents. For example, it integrates the "team introduction" from a company introduction PPT with the "project manager's resume" from a project case study to obtain information integration results, thereby forming a comprehensive understanding of the supplier's team capabilities. Then, based on the extracted key information or information from multiple documents, such as unstructured content like project case studies and technical solutions, it obtains a capability profile of the supplier (profile information). For example, it labels the supplier's core capabilities (such as "high-end curtain wall construction" and "BIM detailed design"). At the same time, it identifies relevant key indicators of the supplier's capability profile in the key information or multiple documents and conducts risk analysis. For example, it analyzes key indicators in financial statements and calls external interfaces to query the supplier's legal litigation information (external reference information) to obtain risk information of the object to be evaluated for preliminary risk assessment. Based on the information integration results, profile information, and risk information, it obtains the information processing results for the supplier, forming a holistic and unified understanding of the supplier.

[0065] In the technical solution of this application embodiment, firstly, the interactive method of supplier file creation is revolutionaryly transformed from "manual entry" of each field to "one-click drag and drop of folders." Users only need to upload the complete set of supplier information files at once, realizing end-to-end automation from unstructured data packages to structured system files, greatly improving user experience and work efficiency. Then, key information or multiple documents are processed separately for information integration on the same topic to obtain information integration results. Key information or multiple documents are understood and processed to obtain the profile information of the object to be evaluated. Key information and / or key indicators in multiple documents are determined, and external reference information is queried based on key indicators to obtain the risk information of the object to be evaluated. Finally, based on at least one of the information integration results, profile information, and risk information, the information processing result is obtained to generate the business file of the object to be evaluated. By simultaneously understanding a complete data package containing multiple types of documents and intelligently establishing information associations between different documents, a holistic and unified understanding of the supplier is formed, rather than isolated information extraction, thereby automatically completing the creation of supplier files, profile generation, and preliminary evaluation.

[0066] For example, based on the association processing results, information processing is performed on key information or multiple documents to obtain information processing results. Then, information matching processing is performed based on the key information or multiple documents to obtain first target information that matches the target evaluation field, thereby generating a business file of the object to be evaluated. For example, firstly, based on the association processing results, information processing is performed on key information or multiple documents to obtain information processing results; then, the information processing results are matched with the target evaluation field to obtain the first target information.

[0067] Specifically, based on at least one of the information integration results, profile information, and risk information obtained above, an overall understanding of the supplier's information processing results is obtained. Then, all the integrated and analyzed information (information processing results, i.e., at least one of the information integration results, profile information, and risk information) is intelligently matched and mapped with the fields required by the system (target assessment fields). The AI ​​returns the mapping results (i.e., the target assessment fields and the first target information that matches each other) as a structured JSON object. The server calls the API to automatically create a complete and clearly defined supplier profile (the business profile of the object to be assessed) in the SRM system. The front-end page not only displays the automatically populated fields but also presents the AI-generated supplier capability profile and assessment report in a visual way, such as tag clouds, radar charts, and risk lists, for reviewers to view.

[0068] In the technical solution of this application embodiment, firstly, information processing is performed on key information or multiple documents based on the association processing result to obtain information processing result. Then, the information processing result is matched with the target evaluation field to obtain first target information. Based on the first target information and the target evaluation field, a business file of the object to be evaluated is generated. This not only solves the problem of data entry efficiency, but also provides highly valuable decision support information for reviewers while automatically building the file through the analysis and profiling capabilities of AI.

[0069] For example, this method also performs a final review of the generated business files to be evaluated. For instance, firstly, it receives a review operation on the business files and obtains the review result; then, it receives a rating operation on the object to be evaluated based on the business files and obtains the rating result.

[0070] Specifically, reviewers can conduct final review and supplementation of AI-generated files on a highly information-based interface, receive review operations on business files, obtain review results, and receive rating operations from reviewers based on business files for the evaluation object, thus completing the rating of the supplier (such as "qualified", "strategic", "elimination", i.e., obtaining the rating result), thereby completing the entire access process and making the supplier file officially effective.

[0071] In the technical solution of this application embodiment, the review operation for the business file is first received to obtain the review result, and then the rating operation for the object to be evaluated based on the business file is received to obtain the rating result, so that the supplier file officially takes effect, providing the reviewers with highly valuable decision support information and improving the scientificity and objectivity of the access review.

[0072] For example, after generating the business profile to be evaluated, a question-and-answer interaction can also be performed. For instance, firstly, in response to receiving a question-and-answer instruction for the object to be evaluated, the business profile is queried to obtain the answer data; then, the answer data is output.

[0073] Specifically, after generating a supplier profile, the system can automatically generate a question-and-answer robot based on the supplier's complete information. Any internal employee of a company who wants to know something about the supplier (such as "Which cities have they worked on for high-rise projects?") can ask the robot a question (i.e., input the question-and-answer command) and get a precise answer (the robot outputs the answer data).

[0074] In the technical solution of this application embodiment, in response to receiving a question-and-answer instruction for the object to be evaluated, the business file is queried to obtain the answer data, and then the answer data is output so that enterprise personnel can query supplier information in a targeted manner, which greatly improves user experience and work efficiency.

[0075] For example, for evaluation objects that have been included in the database, the file information can be updated. For instance, firstly, the updated information of the objects to be evaluated can be obtained periodically; then, the business files can be updated based on the updated information.

[0076] Specifically, for suppliers already in the database, the system can periodically and automatically retrieve their latest information (updated information, such as newly won projects, new lawsuits, etc.) from the Internet, and AI will determine whether the supplier's profile or risk rating needs to be updated. The system will then update the supplier profile based on the updated information and send a notification to the administrator.

[0077] In the technical solution of this application embodiment, the updated information of the object to be evaluated is obtained periodically first, and then the business file is updated based on the updated information to ensure the comprehensiveness and timeliness of the supplier file, ensure the quality of supplier lifecycle management, and greatly improve user experience and work efficiency.

[0078] For example, the document information of the object to be evaluated can also be received by the reviewer through voice input. For example, first, voice data is received; then, second target information matching the target evaluation field is extracted from the voice data; finally, the second target information is added to the business file.

[0079] Specifically, in addition to dragging and dropping files, the system can also provide a voice input entry point. Reviewers can send voice data to the system by speaking while reading paper documents. The system extracts key information related to the supplier from the voice data and matches it with the target evaluation fields to obtain secondary target information. The secondary target information is then added to specific fields in the supplier's profile.

[0080] In the technical solution of this application embodiment, firstly, voice data is received, then second target information matching the target evaluation field is extracted from the voice data, and finally the second target information is added to the business file, which greatly improves user experience and work efficiency.

[0081] Figure 3 A schematic diagram of a business file generation apparatus provided for an embodiment of this application.

[0082] like Figure 3 As shown, the business document generation device 300 includes: The receiving module 310 is used to receive multiple documents of the object to be evaluated.

[0083] The first generation module 320 is used to generate task instructions based on multiple documents and target evaluation fields.

[0084] The extraction module 330 is used to execute task instructions and extract key information from multiple documents.

[0085] The association module 340 is used to associate information from different documents that are on the same topic in the key information and obtain the association processing result.

[0086] The matching module 350 is used to perform information matching processing based on key information and / or multiple documents according to the association processing results, to obtain the first target information that matches the target evaluation field.

[0087] The second generation module 360 ​​is used to generate a business file of the object to be evaluated based on the first target information and the target evaluation field.

[0088] For example, the matching module 350 is further configured to: perform information processing on key information and / or multiple documents based on the association processing result to obtain information processing result; and match the information processing result with the target evaluation field to obtain first target information.

[0089] For example, information processing is performed on key information and / or multiple documents to obtain information processing results, including: integrating information on the same topic in the key information and / or multiple documents to obtain information integration results; understanding the key information and / or multiple documents to obtain profile information of the object to be evaluated; determining key indicators in the key information and / or multiple documents, and querying external reference information based on the key indicators to obtain risk information of the object to be evaluated; and obtaining information processing results based on at least one of the information integration results, profile information, and risk information.

[0090] For example, the business file generation apparatus 300 further includes a query module for: querying the business file to obtain answer data in response to receiving a question-and-answer instruction for the object to be evaluated; and outputting the answer data.

[0091] For example, the business file generation device 300 also includes an update module for: periodically acquiring update information of the object to be evaluated; and updating the business file based on the update information.

[0092] For example, the business file generation apparatus 300 further includes a supplementary module for: receiving voice data; extracting second target information that matches the target evaluation field from the voice data; and supplementing the second target information into the business file.

[0093] For example, the business document generation device 300 further includes a receiving module, configured to: receive an audit operation on the business document and obtain an audit result; receive a rating operation on the object to be evaluated based on the business document and obtain a rating result.

[0094] This application provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0095] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method in any of the above embodiments.

[0096] Figure 4 A block diagram of an electronic device provided in an embodiment of this application.

[0097] This application provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method in any of the above embodiments.

[0098] like Figure 4 As shown, for ease of understanding, embodiments of this application illustrate a specific electronic device 400.

[0099] Electronic device 400 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 400 may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0100] like Figure 4As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 402 or a computer program loaded from storage unit 408 into random access memory (RAM) 403. RAM 403 may also store various programs and data required for the operation of electronic device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output (I / O) interface 404 is also connected to bus 404.

[0101] Multiple components in electronic device 400 are connected to I / O interface 404. These components include: input unit 406, such as a keyboard or mouse; output unit 407, such as various types of displays or speakers; storage unit 408, such as a disk or optical disk; and communication unit 409, such as a network interface card (NIC), modem, or wireless transceiver. Communication unit 409 allows electronic device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0102] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods described above. For example, in some embodiments, any one or more of the methods described above can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of any one or more of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 401 can be configured to perform any one or more of the methods described above by any other suitable means (e.g., by means of firmware).

[0103] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this application, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0104] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0105] In the description of this application, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this application, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0106] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0107] Furthermore, the terms "first," "second," etc., used in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying relative importance, or implicitly specifying the number of technical features indicated in this embodiment. Therefore, features defined with terms such as "first" and "second" in the embodiments of this application can explicitly or implicitly indicate that the embodiment includes at least one of those features. In the description of this application, the word "multiple" means at least two or more, such as two, three, four, etc., unless otherwise explicitly and specifically defined in the embodiments.

[0108] In this application, unless otherwise explicitly specified or limited in the embodiments, the terms "installation," "connection," "joining," and "fixing" appearing in the embodiments should be interpreted broadly. For example, a connection can be a fixed connection, a detachable connection, or an integral part; it can also be a mechanical connection, an electrical connection, etc. Of course, it can also be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication between two components, or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific implementation.

[0109] In this application, unless otherwise expressly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "on top of," and "over" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

Claims

1. A method for generating business files, characterized in that, The method includes: Receive multiple documents for the object to be evaluated; Based on the multiple documents and target evaluation fields, generate task instructions; Execute the task instructions to extract key information from the multiple documents; The key information from different documents that are on the same topic is associated to obtain the association processing result; Based on the association processing result, information matching processing is performed on the key information and / or the multiple documents to obtain the first target information that matches the target evaluation field; Based on the first target information and the target evaluation field, a business file of the object to be evaluated is generated.

2. The method according to claim 1, characterized in that, The step of performing information matching processing based on the association processing result, the key information, and / or the multiple documents, to obtain first target information that matches the target evaluation field includes: Based on the association processing result, information processing is performed on the key information and / or the multiple documents to obtain the information processing result; The information processing result is matched with the target evaluation field to obtain the first target information.

3. The method according to claim 2, characterized in that, The information processing of the key information and / or the multiple documents to obtain the information processing result includes: The key information and / or information on the same topic in the multiple documents are integrated to obtain an information integration result. The key information and / or the multiple documents are processed to obtain the profile information of the object to be evaluated. Identify the key information and / or key indicators in the multiple documents, and query external reference information based on the key indicators to obtain the risk information of the object to be evaluated; The information processing result is obtained based on at least one of the information integration result, the profile information, and the risk information.

4. The method according to any one of claims 1-3, characterized in that, Also includes: In response to receiving a question-and-answer instruction for the object to be evaluated, the answer data is obtained by querying the business file; Output the answer data.

5. The method according to any one of claims 1-3, characterized in that, Also includes: Periodically obtain updated information about the object to be evaluated; The business file is updated based on the updated information.

6. The method according to any one of claims 1-3, characterized in that, Also includes: Receive voice data; Extract second target information that matches the target evaluation field from the speech data; The second target information is added to the business file.

7. The method according to any one of claims 1-3, characterized in that, Also includes: Receive the review operation for the business file and obtain the review result; Receive the rating operation of the object to be evaluated based on the business file, and obtain the rating result.

8. A business document generation device, characterized in that, The device includes: The receiving module is used to receive multiple documents of the object to be evaluated. The first generation module is used to generate task instructions based on the multiple documents and target evaluation fields; The extraction module is used to execute the task instructions and extract key information from the multiple documents. The association module is used to associate information from different documents that are on the same topic in the key information to obtain the association processing result. The matching module is used to perform information matching processing based on the key information and / or the multiple documents according to the association processing result, to obtain the first target information that matches the target evaluation field; The second generation module is used to generate the business file of the object to be evaluated based on the first target information and the target evaluation field.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-7.

Images