Document auditing method, device and equipment
Through identification and pre -processing document information and applied pre -configured audit strategies, the problem of low efficiency of existing documents review technology has been solved, and a more efficient and flexible document review process is achieved.
Patent Information
- Application Number
- CN202411350029.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-26
- Publication Date
- 2025-01-21
AI Technical Summary
The existing document review technology is inefficient, manual review is time-consuming and the rule engine is difficult to adjust dynamically, limiting the flexibility and response speed of audits.
By obtaining document information, identifying target information, and entering large models for pre -processing, getting the document to be processed. Based on the type of document type parameters, a pre -configured audit strategy is conducted to the processing documents for review, and the results of the documents are obtained.
The accuracy and speed of document review have been improved, artificial intervention has been reduced, and the flexibility and response capacity of the review has been enhanced.
Smart Images
Figure CN119337855A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of data processing technology, and in particular to a document review method, device and equipment. Background Art
[0002] In corporate financial management, the review of documents such as invoices and receipts is a tedious and time-consuming task that often requires a lot of human resources. In related technologies, existing products for reviewing documents, such as extracting key review elements through images and extracting review elements from text information, are very inefficient in manual review. Existing document review methods use rule engines for review, but the engine may need to process very complex business rules that may change over time and may require different interpretations and applications in different situations, which may make the writing and maintenance of rules difficult and expensive. Although the rule engine allows dynamic rule configuration, changes to the rules require the intervention of technical personnel, which limits the flexibility and response speed of the review. Summary of the invention
[0003] The present disclosure provides a document review method, device and equipment to at least solve the above technical problems existing in the prior art.
[0004] According to a first aspect of the present disclosure, a document review method is provided, the method comprising:
[0005] Acquiring document information, and identifying target information in the document information;
[0006] Input the target information into the large model for preprocessing to obtain the document to be processed;
[0007] The document to be processed is audited with a preconfigured audit strategy based on the document type parameter to obtain a document audit result.
[0008] In one possible implementation, the pre-configured audit strategy includes:
[0009] Get the text description of the type of input document;
[0010] The text description is matched with a preset text comparison symbol, and the input document is audited according to the audit policy corresponding to the successfully matched text comparison symbol.
[0011] In one possible implementation, it also includes:
[0012] Preset parsing template;
[0013] When the input document has an attachment, the attachment is parsed based on a preset parsing template to obtain a text description of the type of the input document.
[0014] In one possible implementation manner, the inputting the target information into the large model for preprocessing includes:
[0015] The target information is filtered, processed and refined.
[0016] In one possible implementation, the auditing of the to-be-processed document based on the document type parameter using a preconfigured audit strategy includes:
[0017] Determine a corresponding audit strategy based on the document type parameters;
[0018] The documents to be processed are audited according to the audit strategy.
[0019] In one possible implementation, the audit strategy includes multiple audit strategies; the determining of the corresponding audit strategy based on the document type parameter includes:
[0020] Based on the document type parameters, the audit strategies are matched from front to back in the set audit strategy sequence until a match is successful, thereby obtaining a corresponding audit strategy.
[0021] In one possible implementation manner, optical character recognition technology is used to recognize the target information in the document information.
[0022] In one possible implementation, it also includes:
[0023] Save the document review results.
[0024] According to a second aspect of the present disclosure, a document review device is provided, the device comprising:
[0025] An acquisition module, used to acquire document information and identify target information in the document information;
[0026] A processing module, used for inputting the target information into the large model for preprocessing to obtain a document to be processed;
[0027] The audit module is used to audit the to-be-processed document based on the document type parameters with a pre-configured audit strategy to obtain a document audit result.
[0028] According to a third aspect of the present disclosure, there is provided an electronic device, including:
[0029] at least one processor; and
[0030] a memory communicatively connected to the at least one processor; wherein,
[0031] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the present disclosure.
[0032] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method described in the present disclosure.
[0033] The document review method, device and equipment disclosed in the present invention review the documents obtained after identification and filtering, so that the obtained review results are more accurate; and the present application uses pre-configured review strategies for review, so the review speed is faster.
[0034] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, in which:
[0036] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts.
[0037] Figure 1 The schematic diagram shows the implementation process of the document review method of the embodiment of the present disclosure. Figure 1 ;
[0038] Figure 2 The schematic diagram shows the implementation process of the document review method of the embodiment of the present disclosure. Figure 2 ;
[0039] Figure 3 A schematic diagram of the structure of a document review device according to an embodiment of the present disclosure is shown;
[0040] Figure 4 A schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION
[0041] In order to make the purpose, features, and advantages of the present disclosure more obvious and easy to understand, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.
[0042] The following describes a document review method, device and equipment provided by the present application in conjunction with the accompanying drawings.
[0043] like Figure 1 As shown, the present application provides a document review method, the method comprising:
[0044] S101, acquiring document information, and identifying target information in the document information;
[0045] It is understandable that the document information in the present application may be a financial document, such as a financial document: a document directly used for the purpose of collecting payment, such as: bills of exchange, promissory notes, checks, etc.; a commercial document: a document other than financial documents, such as: invoices, transport documents, insurance documents, packing documents, etc.; it may also be a financial document: such as bills of exchange, promissory notes, checks. Commercial documents: mainly refers to documents prepared by exporters, such as: commercial invoices, packing lists, weight lists, size lists. Freight documents: refers to the certification documents issued by the carrier for the collection and transportation of goods when various modes or tools of transportation are used, including ocean bills of lading, air waybills, road, rail and inland waterway transport documents, special courier and postal receipts; insurance documents: refers to documents involved in international cargo transportation insurance, including insurance policies, advance insurance policies, and insurance certificates; official documents: refers to documents and certificates issued by the official, including customs invoices, certificates of origin, and commodity inspection certificates; ancillary documents: documents other than the above purposes, such as shipping notices, proof of mailing, beneficiary certificates, and sample mailing certificates.
[0046] This application uses optical character recognition (OCR) technology to identify the target information in the document information. OCR technology can realize automatic text recognition by converting the text in the picture or scanned copy into text. This is very helpful for tasks that require extracting data from a large number of paper documents, such as automatically identifying ID card numbers, license plate numbers, invoice numbers, etc.
[0047] In this application, the target information varies depending on the document. For example, the target information of a financial document may be the reimbursement type, reimbursement amount, etc. The target information of an express document may be the express number, shipping place, receiving place, etc.
[0048] S102, inputting the target information into the large model for preprocessing to obtain a document to be processed;
[0049] It is understandable that the big model in this application adopts an intelligent model, and may adopt a model that already exists or may be produced in the future. This application does not limit this. This application is based on the AI big model to understand the document information and perform effective data processing.
[0050] In some embodiments, the step of inputting the target information into a large model for preprocessing includes:
[0051] The target information is filtered, processed and refined.
[0052] Specifically, the AI big model provided in this application is mainly used to further filter, process and refine the input target information to obtain more accurate audit document information, so that the triggered audit strategy is more matched and the audit results are more accurate.
[0053] S103, auditing the document to be processed with a pre-configured audit strategy based on the document type parameter to obtain a document audit result.
[0054] It should be noted that the audit strategy in this application is pre-set, and each document type corresponds to a different audit strategy. When matching, the document type is matched according to the order of the audit strategy configuration until the match is successful. The corresponding audit strategy is used to audit the document to obtain the document audit result.
[0055] The document review method provided by the present application obtains the target information in the document information by identifying the document information, and then pre-processes the target information through a large model to filter out duplicate and erroneous target information, thereby obtaining the document to be processed, and finally matches the corresponding review strategy to the document to be processed, and uses the corresponding review strategy to review the document to be processed to obtain the document review result. The present application identifies the document information and processes it with a large model, identifies it multiple times to obtain the document to be processed, and then reviews the document to be processed, and finally uses the configured review strategy to review it, so that the document review result obtained has a higher accuracy rate and a faster review speed.
[0056] In some embodiments, the pre-configured audit policy includes:
[0057] Get the text description of the type of input document;
[0058] The text description is matched with a preset text comparison symbol, and the input document is audited according to the audit policy corresponding to the successfully matched text comparison symbol.
[0059] Specifically, in the embodiment of the present application, a Chinese comparison escape comparison symbol is first set, and then when the user needs to search for the audit policy corresponding to the document type, the user can enter the Chinese description, and according to the Chinese description, the text comparison symbol corresponding to the document type can be determined, and the text comparison symbol corresponds to the audit policy, thereby configuring the audit policy. The document audit method provided by the present application allows the user to match the required audit policy by entering the Chinese description, so that people who do not understand technology can also configure the audit policy, which is convenient to use and easy to implement.
[0060] After the audit strategy is completed, obtain the document information for audit.
[0061] In some embodiments, the document review method provided by the present application further includes:
[0062] Preset parsing template;
[0063] When the input document has an attachment, the attachment is parsed based on a preset parsing template to obtain a text description of the type of the input document.
[0064] It is understandable that if there are attachments in the uploaded documents, the attachments need to be parsed, otherwise the information of the attachments cannot be obtained. Therefore, a parsing template is pre-set in this application. The parsing template in this application can adopt the template type corresponding to Excel, so that when there are attachments in the uploaded documents, the parsing template can be used to parse the data in the attachments, and then the parsed data can be compared with the Chinese comparison operator to determine the corresponding audit strategy.
[0065] In some embodiments, the auditing of the to-be-processed document using a preconfigured audit strategy based on the document type parameter includes:
[0066] Determine a corresponding audit strategy based on the document type parameters;
[0067] The documents to be processed are audited according to the audit strategy.
[0068] It can be understood that in this application, the audit strategy is different according to the different document types. For example, when the document type is a bill of exchange, it is necessary to adopt the first audit strategy corresponding to the bill of exchange to audit the bill of exchange; when the document type is a check, it is necessary to adopt the second audit strategy corresponding to the check to audit the check in order to improve the accuracy of the audit.
[0069] In some embodiments, the audit strategy includes multiple audit strategies; the determining the corresponding audit strategy based on the document type parameter includes:
[0070] Based on the document type parameters, the audit strategies are matched from front to back in the set audit strategy sequence until a match is successful, thereby obtaining a corresponding audit strategy.
[0071] It is understandable that if Figure 2 As shown, for example, the present application includes a first audit strategy, a second audit strategy, a third audit strategy...an Nth audit strategy; they are set in sequence during configuration. After obtaining the data to be processed, the audit strategy is matched according to the configuration order based on the document type parameters until the match is successful, thereby obtaining a matching audit strategy.
[0072] In some embodiments, the document review method provided by the present application further includes:
[0073] Save the document review results.
[0074] Specifically, after the audit is completed, it will be recorded in the audit result management. The audit document results can also be pushed to a third-party system for subsequent payment and collection processing.
[0075] The document review method provided by this application builds a document review configuration based on Chinese description rules, so that people who do not understand technology can configure the review rules through Chinese descriptions. It also pre-embeds attachments through the import of Excel templates, and realizes dynamic recognition and extraction of Excel data. In addition, this application realizes more effective data filtering, processing, and refining through the combination of OCR and large model technologies, which further improves the review pass rate.
[0076] like Figure 3 As shown, an embodiment of the present application provides a document review device, the device comprising:
[0077] The acquisition module 301 is used to acquire document information and identify target information in the document information;
[0078] Processing module 302, used for inputting the target information into the large model for preprocessing to obtain a document to be processed;
[0079] The review module 303 is used to review the document to be processed based on the document type parameter with a pre-configured review strategy to obtain a document review result.
[0080] The document review device provided in the present application comprises an acquisition module 301 which acquires document information and identifies target information in the document information; a processing module 302 inputs the target information into a large model for preprocessing to obtain a document to be processed; and a review module 303 reviews the document to be processed based on a document type parameter with a preconfigured review strategy to obtain a document review result.
[0081] In some embodiments, the audit module 303 further includes:
[0082] An acquisition unit, used to acquire a text description of the type of input document;
[0083] The matching unit is used to match the text description with a preset text comparison symbol, and to review the input document according to the review strategy corresponding to the successfully matched text comparison symbol.
[0084] In some embodiments, it also includes:
[0085] Configuration unit, used to preset parsing templates;
[0086] When the input document has an attachment, the attachment is parsed based on a preset parsing template to obtain a text description of the type of the input document.
[0087] In some embodiments, the processing module 302 includes:
[0088] The processing unit is used to filter, process and refine the target information.
[0089] In some embodiments, the audit module 303 includes:
[0090] A determination unit, used to determine a corresponding audit strategy based on the document type parameter;
[0091] The audit unit is used to audit the to-be-processed documents according to the audit strategy.
[0092] In some embodiments, the audit strategy includes multiple audit strategies; the audit unit includes:
[0093] The audit subunit is used to match the audit policies in sequence from front to back according to the set audit policy sequence based on the document type parameters until a match is successful, thereby obtaining a corresponding audit policy.
[0094] In some embodiments, optical character recognition technology is used to recognize the target information in the document information.
[0095] In some embodiments, the document review device provided by the present application further includes:
[0096] The save module is used to save the document review results.
[0097] The present application also provides a document review system, including a document review device and a server; the server provides background function support for the intelligent review software, and provides the intelligent review software with application program interface, data conversion, business logic processing and other functions. In addition, a server database is provided to store the business model and data of "document information--rule engine--review result".
[0098] An embodiment of the present application provides an electronic device, including:
[0099] at least one processor; and
[0100] a memory communicatively connected to the at least one processor; wherein,
[0101] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any one of the above embodiments.
[0102] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.
[0103] Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement an embodiment of the present disclosure is shown. The electronic device 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. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.
[0104] like Figure 4 As shown, the device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.
[0105] A number of components in the device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0106] The computing unit 401 may be a variety of general and / or special 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 dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as the document review method. For example, in some embodiments, the document review method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the document review method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the document review method in any other appropriate manner (e.g., by means of firmware).
[0107] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0108] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0109] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0110] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).
[0111] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.
[0112] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.
[0113] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.
[0114] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.
[0115] The above is only a specific embodiment of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present disclosure, which should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.
Claims
1. A document review method, characterized in that: The method comprises: Acquiring document information, and identifying target information in the document information; Input the target information into the large model for preprocessing to obtain the document to be processed; The document to be processed is audited with a preconfigured audit strategy based on the document type parameter to obtain a document audit result.
2. The method according to claim 1, characterized in that The pre-configured audit policy includes: Get the text description of the type of input document; The text description is matched with a preset text comparison symbol, and the input document is audited according to the audit policy corresponding to the successfully matched text comparison symbol.
3. The method according to claim 2, characterized in that Also includes: Preset parsing template; When the input document has an attachment, the attachment is parsed based on a preset parsing template to obtain a text description of the type of the input document.
4. The method according to claim 1, characterized in that: The inputting of the target information into the large model for preprocessing comprises: The target information is filtered, processed and refined.
5. The method according to claim 1, characterized in that The step of reviewing the to-be-processed document based on the document type parameter using a preconfigured review strategy includes: Determine a corresponding audit strategy based on the document type parameters; The documents to be processed are audited according to the audit strategy.
6. The method according to claim 5, characterized in that The audit strategy includes multiple audit strategies; the corresponding audit strategy is determined based on the document type parameter, including: Based on the document type parameters, the audit strategies are matched from front to back in the set audit strategy sequence until a match is successful, thereby obtaining a corresponding audit strategy.
7. The method according to claim 1, characterized in that Optical character recognition technology is used to recognize the target information in the document information.
8. The method according to claim 1, characterized in that Also includes: Save the document review results.
9. A document review device, characterized in that: The device comprises: An acquisition module, used to acquire document information and identify target information in the document information; A processing module, used for inputting the target information into the large model for preprocessing to obtain a document to be processed; The audit module is used to audit the to-be-processed document based on the document type parameters with a pre-configured audit strategy to obtain a document audit result.
10. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.