Voucher generation method and device, computer equipment and readable storage medium
By automatically identifying document information and generating vouchers, the problem of inefficient voucher generation caused by manual entry in the financial system is solved, and efficient automatic voucher generation is achieved.
Patent Information
- Application Number
- CN202510272329.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-07
- Publication Date
- 2025-06-27
AI Technical Summary
In the financial system, manual entry of document information leads to low efficiency in voucher generation, especially when the number of documents is large and the processing requirements are concentrated.
By obtaining the document information of the target document, the business type of the document is automatically identified and determined, the corresponding lending account template is determined based on the business type, and the corresponding vouchers are automatically generated.
It realizes automatic identification of document information and automatic generation of vouchers, improves the efficiency of voucher generation and reduces the time and cost of manual operation.
Smart Images
Figure CN120218034A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and particularly to a voucher generation method, apparatus, computer device, computer-readable storage medium, and computer program product. Background Art
[0002] With the development of computer technology, more and more enterprises process financial data through financial systems. Enterprises can convert documents into financial vouchers through an ERP (Enterprise Resource Planning) system for accounting and storage.
[0003] When accounting personnel receive documents such as invoices, they often generate corresponding vouchers by manually selecting debit and credit accounts and filling in information such as amounts. When the number of documents is large and the requirements for voucher processing are relatively concentrated, manually entering document information is likely to result in low voucher generation efficiency. Summary of the Invention
[0004] Based on this, it is necessary to provide a voucher generation method, apparatus, computer device, computer-readable storage medium, and computer program product that can improve the efficiency of voucher generation for the above technical problems.
[0005] In a first aspect, the present application provides a voucher generation method, including:
[0006] Obtain a target document and identify the document information of the target document;
[0007] Determine a target business type corresponding to the target document according to the document information of the target document;
[0008] Determine a target debit and credit account template corresponding to the target business type;
[0009] Generate a target voucher corresponding to the target document according to the target debit and credit account template.
[0010] In one embodiment, the determining the target business type corresponding to the target document according to the document information of the target document includes:
[0011] If the document information of the target document includes hierarchical information corresponding to a preset reference table, determine a first-level classification name and a second-level classification name that match the document information according to the preset reference table; the classification range corresponding to the first-level classification name is larger than the classification range corresponding to the second-level classification name;
[0012] Determine the target business type corresponding to the target document according to the mapping relationship between the first-level classification name, the second-level classification name, and the business type.
[0013] In one embodiment, the method further includes:
[0014] If the secondary classification name matching the document information cannot be determined according to the preset reference table, a prompt word is constructed based on the document information, and the constructed prompt word is input into the artificial intelligence large model to obtain the secondary classification name matching the document information; the artificial intelligence large model is trained according to classification name samples, and the classification name samples include first-level classification name samples and corresponding second-level classification name samples.
[0015] In one embodiment, the method further includes:
[0016] If the document information of the target document does not include the hierarchical information corresponding to the preset reference table, the document information of the target document is input into the type recognition model to obtain the target business type corresponding to the target document.
[0017] In one embodiment, generating the target voucher corresponding to the target document according to the target debit and credit account template includes:
[0018] Obtain the business scenario type;
[0019] Determine the scenario debit and credit account template from the target debit and credit account template according to the business scenario type;
[0020] Generate the target voucher corresponding to the business scenario type according to the scenario debit and credit account template.
[0021] In one embodiment, there are multiple target business types; determining the target debit and credit account template corresponding to the target business type includes:
[0022] Determine the target debit and credit account template corresponding to each target business type respectively.
[0023] In a second aspect, the present application further provides a voucher generation device, including:
[0024] A document information recognition module, configured to obtain a target document and recognize the document information of the target document;
[0025] A business type determination module, configured to determine the target business type corresponding to the target document according to the document information of the target document;
[0026] A subject template determination module, configured to determine the target debit and credit account template corresponding to the target business type;
[0027] A voucher generation module, configured to generate the target voucher corresponding to the target document according to the target debit and credit account template.
[0028] In a third aspect, the present application further provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the voucher generation method provided in the first aspect are implemented.
[0029] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the voucher generation method provided in the first aspect are implemented.
[0030] In a fifth aspect, the present application further provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps of the voucher generation method provided in the first aspect are implemented.
[0031] For the above-mentioned voucher generation method, device, computer device, computer-readable storage medium, and computer program product, by obtaining a target document, identifying the document information of the target document, determining the target business type corresponding to the target document according to the document information of the target document, determining the target debit and credit account template corresponding to the target business type, and generating a target voucher corresponding to the target document according to the target debit and credit account template, it is possible to realize the automatic recognition of document information, and then automatically determine the business type of the document, and automatically generate the corresponding voucher according to the debit and credit account template corresponding to the business type, thereby improving the voucher generation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.
[0033] Figure 1 It is an application environment diagram of the voucher generation method in an embodiment;
[0034] Figure 2 It is a flowchart of the voucher generation method in an embodiment;
[0035] Figure 3 It is a flowchart of the voucher generation method in another embodiment;
[0036] Figure 4 It is a structural block diagram of the voucher generation device in an embodiment;
[0037] Figure 5 It is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0038] In order to make the objectives, technical solutions, and advantages of the present application clearer and more understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0039] The voucher generation method provided by the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or on other network servers. The server 104 obtains the target document sent by the terminal 102, the server 104 identifies the document information of the target document, determines the target business type corresponding to the target document according to the document information of the target document, determines the target debit and credit account template corresponding to the target business type, and generates the target voucher corresponding to the target document according to the target debit and credit account template.
[0040] Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. It should be noted that the voucher generation method provided by the embodiments of the present application is applicable not only to the application scenario where the above-mentioned server and terminal interact, but also to the application scenarios of a single terminal or a single server.
[0041] In an exemplary embodiment, as Figure 2 shown, a voucher generation method is provided. Taking the method applied to the Figure 1 server as an example, it includes the following steps 202 to step 208. Among them:
[0042] Step 202, obtain the target document and identify the document information of the target document.
[0043] Among them, the target document refers to the document to be processed for generating vouchers. In the financial field, a document refers to an original voucher used by an enterprise in economic business activities. It records the detailed content of the enterprise's economic business and serves as an important basis for financial reimbursement, bookkeeping, and accounting. A document can be, for example, any one of an invoice, receipt, check, payroll, inventory in-and-out form, borrowing form, statement of account, or bank settlement form, etc.
[0044] Exemplarily, the target document can be obtained from a cloud server, and the document information of the target document can be identified. Among them, the cloud server can be used to store all the documents uploaded by financial personnel. Among them, the way to identify the document information of the target document can be selected according to the actual application scenario. For example, OCR (Optical Character Recognition), machine learning method recognition, etc.
[0045] The document information includes the information required for generating vouchers, such as document type, tax classification name, tax code, item name, amount, specification, etc. The document information corresponding to different types of documents is different. For example, for a special VAT invoice, the document information may include purchaser information, seller information, invoice issue date, goods or service information, tax code, and tax rate, etc. For a document of the ticket type, the document information may include ticket number, passenger information, travel information, ticket price and expense information, validity period, etc.
[0046] Step 204, determine the target business type corresponding to the target document according to the document information of the target document.
[0047] Among them, the target business type is used to represent the business type to which the target document belongs. The target business type includes, for example, types such as purchasing inventory, office work, business trips, etc. The target business type can be defined and set according to the actual application scenario.
[0048] Optionally, the target business type corresponding to the target document can be determined according to the document type of the target document. The document type can include tax type documents and non-tax type documents. Tax type documents include, for example, ordinary VAT invoices, special VAT invoices, receipts, etc. Non-tax type documents include, for example, airplane tickets, train tickets, passenger tickets, taxi tickets, machine-printed invoices, fixed-amount invoices, or shopping receipts, etc. For example, if the target document is a train ticket, determine that the target business type corresponding to the target document is a business trip. If the target document is a special VAT invoice, then determine the target business type corresponding to the target document through the tax classification name in the document information.
[0049] In some application scenarios, a document may include various types of document information, corresponding to multiple business types. For example, the same document may include both catering information and accommodation information, and the corresponding target business types are catering and accommodation respectively. That is to say, according to the document information of the target document, the target business types corresponding to the target document may include multiple types.
[0050] Step 206: Determine the target debit-credit account template corresponding to the target business type.
[0051] Among them, the debit-credit account template is a template representing the corresponding debit and credit accounts in the generated voucher. In the actual application scenario, the mapping relationship between the business type and the debit-credit account template can be preset in advance, and according to this mapping relationship, the target debit-credit account template corresponding to the target business type can be determined. Usually, one business type corresponds to one debit-credit account template, that is, there is a one-to-one mapping relationship between the business type and the debit-credit account template.
[0052] Step 208: Generate the target voucher corresponding to the target document according to the target debit-credit account template.
[0053] In the actual application scenario, the template voucher corresponding to the target document can be generated according to all the target debit-credit account templates, or based on the business scenario type, a part of all the target debit-credit account templates can be selected to generate the target voucher corresponding to the target document and matching the scenario.
[0054] Exemplarily, if the determined target debit-credit account templates include Template A and Template B, then for Scenario Type A, it is determined to generate the corresponding target voucher based on Template A, and for Scenario Type B, it is determined to generate the corresponding target voucher based on Template B. In other words, for the same document, there may be multiple business types, that is, corresponding to multiple debit-credit account templates. Based on multiple debit-credit account templates, one or more vouchers can be generated, and the financial information corresponding to multiple documents can be summarized into the same voucher.
[0055] In the above voucher generation method, by identifying and obtaining the document information of the target document, according to the document information of the target document, the target business type corresponding to the target document is determined, and the target debit-credit account template corresponding to the target business type is determined. According to the target debit-credit account template, the target voucher corresponding to the target document is generated, which can realize automatically generating the corresponding voucher based on the uploaded document, thereby improving the voucher generation efficiency.
[0056] In some embodiments, step 204 of determining the target business type corresponding to the target document according to the document information of the target document includes:
[0057] If the document information of the target document includes the hierarchical information corresponding to the preset reference table, determine the first-level classification name and the second-level classification name that match the document information according to the preset reference table; wherein, the classification range corresponding to the first-level classification name is larger than the classification range corresponding to the second-level classification name; determine the target business type corresponding to the target document according to the mapping relationship between the first-level classification name, the second-level classification name and the business type.
[0058] Among them, the preset reference table includes the preset first-level classification name and the second-level classification name. The preset reference table can be set with reference to the officially released tax classification code table, or can also be set according to the actual application scenario. The first-level classification name is used to represent the major categories in goods or services, and the second-level classification name is further subdivided on the basis of the first-level classification name, which represents more specific types of goods or services. The classification range corresponding to the first-level classification name is larger than the classification range corresponding to the second-level classification name. For example, the first-level classification names include goods, labor services, services, intangible assets, immovable properties, etc. The second-level classification names corresponding to the first-level classification name "goods" include agricultural, forestry, animal husbandry and fishery products, mineral products, food, beverages, tobacco, alcoholic products, etc. The second-level classification names corresponding to the first-level classification name "labor services" include processing labor services, repair and replacement labor services, etc. Specific goods can be further subdivided under each second-level classification name. Among them, both the first-level classification name and the second-level classification name can have corresponding codes. Exemplarily, part of the information in the preset reference table is shown in Table 1 below. Among them, "merged code" represents the tax code, "name of goods and labor services" represents the second-level classification name, and "abbreviation of commodity and service classification" represents the first-level classification name.
[0059] Table 1
[0060]
[0061] Optionally, after obtaining the document information of the target document, identify whether the document information includes the hierarchical information corresponding to the preset reference table. If the document information of the target document includes the hierarchical information corresponding to the preset reference table, determine the first-level classification name and the second-level classification name that match the document information according to the preset reference table, and then determine the target business type corresponding to the target document according to the mapping relationship between the first-level classification name, the second-level classification name and the business type. Among them, the matching can be characterized by the similarity being greater than the similarity threshold, that is, if the similarity between the document information and the first-level classification name and the second-level classification name is greater than the similarity threshold, it means that the document information matches the first-level classification name and the second-level classification name. If the similarity between the document information and the first-level classification name or the second-level classification name is less than the similarity threshold, it means that the document information does not match the first-level classification name and the second-level classification name.
[0062] In actual application scenarios, if the document information of the target document includes the first-level classification name in the preset reference table, it indicates that the document information includes the hierarchical information corresponding to the preset reference table. Therefore, there may be a situation where the document information of the target document includes the first-level classification name and the second-level classification name in the preset reference table, or the document information of the target document includes the first-level classification name in the preset reference table but does not include the second-level classification name. If the document information does not include the second-level classification name in the preset reference table, the second-level classification name matching the document information can be generated by an artificial intelligence large model or added manually. Then, based on the first-level classification name and the second-level classification name, the target business type corresponding to the target document is determined.
[0063] In this embodiment, if the document information of the target document includes the hierarchical information corresponding to the preset reference table, the first-level classification name and the second-level classification name matching the document information are determined according to the preset reference table. Thus, based on the mapping relationship between the first-level classification name, the second-level classification name, and the business type, the target business type corresponding to the target document can be determined quickly and accurately.
[0064] In some embodiments, the above method further includes:
[0065] If the second-level classification name matching the document information cannot be determined according to the preset reference table, a prompt word is constructed based on the document information, and the constructed prompt word is input into the artificial intelligence large model to obtain the second-level classification name matching the document information; wherein, the artificial intelligence large model is trained according to classification name samples, and the classification name samples include first-level classification name samples and corresponding second-level classification name samples.
[0066] In this embodiment, if the preset reference table does not include the second-level classification name matching the document information, it means that the second-level classification name matching the document information cannot be determined according to the preset reference table. A prompt word can be constructed based on the document information. If the document information includes "AA service", the prompt word can be constructed, for example, as "Please output the second-level classification name corresponding to AA service", and inputting this prompt word into the artificial intelligence large model can obtain the answer corresponding to the prompt word, that is, "the second-level classification name corresponding to AA service".
[0067] Understandably, before using the large artificial intelligence model to output the secondary classification names that match the document information, the large artificial intelligence model needs to be trained. It can be trained based on classification name samples, which include primary classification samples and secondary classification samples corresponding to the primary classification samples. Among them, the secondary classification samples can include all the secondary classification names and their approximate names in the tax classification code table. By training the large artificial intelligence model with a large number of classification name samples, the large artificial intelligence model can learn the corresponding relationship between the primary classification samples and the secondary classification samples. In this way, even if a name that is not in the corresponding relationship samples is input, the trained large artificial intelligence model can output the secondary classification name that matches the name, as well as the corresponding primary classification name. Among them, the training method of the large artificial intelligence model is not specifically limited herein.
[0068] In this embodiment, if the secondary classification name that matches the document information cannot be determined according to the preset reference table, a prompt word is constructed according to the document information, and the constructed prompt word is input into the large artificial intelligence model to obtain the secondary classification name that matches the document information. It can be realized that in the case where the secondary classification name that matches cannot be determined according to the preset reference table, the secondary classification name that matches is determined through the large artificial intelligence model, and the secondary classification name that matches the document information can be quickly determined, improving the determination efficiency of the secondary classification name, and further improving the voucher generation efficiency.
[0069] In some embodiments, the above method further includes:
[0070] If the document information of the target document does not include the hierarchical information corresponding to the preset reference table, the document information of the target document is input into the type recognition model to obtain the target business type corresponding to the target document.
[0071] In this embodiment, if the document information of the target document does not include the hierarchical information corresponding to the preset reference table, that is, the document information neither includes the primary classification name nor the secondary classification name, the target business type corresponding to the target document can be determined according to the type recognition model. Understandably, if the document of the target document includes the hierarchical information corresponding to the preset reference table, the target document usually displays the corresponding primary classification name or / and secondary classification name in the preset format. If the target document does not display the corresponding primary classification name and / or secondary classification name in the preset format, it is determined that the document information of the target document does not include the hierarchical information corresponding to the preset reference table. Therefore, it is easy to determine whether the document information of the target document includes the hierarchical information corresponding to the preset reference table.
[0072] Among them, the type recognition model can be a model obtained through training. For example, a neural network model can be trained based on training samples, where the training samples include a large number of document samples, and each document sample includes a labeled business type. The training samples are sequentially input into the neural network model for prediction to obtain the predicted business type. Based on the difference between the predicted business type and the labeled business type, the parameters of the neural network model are trained to obtain the type recognition model, which can recognize the business type corresponding to the input document.
[0073] In this embodiment, when the document information of the target document does not include the classification information corresponding to the preset reference table, the document information of the target document is input into the type recognition model to obtain the target business type corresponding to the target document, which can quickly determine the target business type corresponding to the target document through artificial intelligence and improve the determination efficiency of the target business type.
[0074] In an exemplary embodiment, step 208 of generating the target voucher corresponding to the target document according to the target debit-credit subject template includes:
[0075] Obtain the business scenario type; determine the scenario debit-credit subject template from the target debit-credit subject template according to the business scenario type; generate the target voucher corresponding to the business scenario type according to the scenario debit-credit subject template.
[0076] Among them, the business scenario type refers to the scenario type to which the voucher applies. For example, for the collection business scenario, select the scenario debit-credit subject template that matches the collection business scenario from the target debit-credit subject template, and generate the target voucher corresponding to the collection business scenario according to the scenario debit-credit subject template. It is easy to understand that the scenario debit-credit subject template refers to the debit-credit subject template that matches the business scenario type, and the scenario debit-credit subject template that matches the business scenario type can be set according to the actual application scenario requirements.
[0077] Exemplarily, the business scenario type can be determined according to business requirements, and the scenario debit-credit subject template can be determined from the target debit-credit subject template according to the business scenario type, so as to generate the target voucher corresponding to the business scenario type based on the document information according to the scenario debit-credit subject template. It should be noted that the document information in the same document may include document information corresponding to different business types, different business types correspond to different debit-credit subject templates, and then different vouchers correspond to different debit-credit subject templates according to different business scenario types. However, different vouchers may also include the same debit-credit subject template. For example, voucher A may include debit-credit subjects A, B, and C, and voucher B may include debit-credit subjects B, C, and D.
[0078] In this embodiment, by determining the scenario debit and credit account template from the target debit and credit account template according to the business scenario type and generating the target voucher corresponding to the business type based on the scenario debit and credit account template, it is possible to generate a target voucher that matches the business scenario type, thereby improving the accuracy of voucher generation.
[0079] In some embodiments, there are multiple target business types; determining the target debit and credit account template corresponding to the target business type includes:
[0080] Determining the target debit and credit account template corresponding to each target business type respectively.
[0081] In an actual application scenario, the same document may include document information corresponding to multiple business types. For example, the same special VAT invoice may include catering information and accommodation information, and the catering information and accommodation information belong to document information of different business types. If there are multiple target business types, the target debit and credit account template corresponding to each target business type is determined respectively, and there is a one-to-one correspondence between the business type and the debit and credit account template. Exemplarily, it is also possible to determine the scenario debit and credit account template that matches the scenario business type from each target debit and credit account template, and then generate the target voucher corresponding to the business scenario type according to the scenario debit and credit account template.
[0082] In this embodiment, in the case where there are multiple target business types, determining the target debit and credit account template corresponding to each target business type respectively can accurately determine the target debit and credit account template and improve the accuracy of voucher generation.
[0083] In an exemplary embodiment, the voucher generation process is as Figure 3As shown, taking the invoice as an example of the document for illustration. The staff uploads the invoice to the invoice cloud server, and the invoice cloud server can save and identify the invoice information of the target invoice. If it is identified that the invoice information includes the corresponding classification information in the preset reference table, the first-level classification name and the second-level classification name that match the invoice information are determined according to the preset reference table, and according to the corresponding relationship between the first-level classification name, the second-level classification name and the business type, the target business type corresponding to the invoice is determined. If the second-level classification name that matches the document information cannot be determined from the preset reference table, a prompt word is constructed according to the invoice information, and the prompt word is input into the artificial intelligence large model to obtain the second-level classification name that matches the invoice information, and then the target business type is determined according to the first-level classification name and the second-level classification name. If the invoice information does not include the classification information corresponding to the preset reference table, the invoice information is input into the type recognition model to obtain the target business type corresponding to the invoice. According to the corresponding relationship between the business type and the debit-credit account template, the target debit-credit account template corresponding to the target business type is determined, and thus the target voucher corresponding to the target invoice is generated according to the target debit-credit account template. It can be realized that the staff only needs to upload the invoice to automatically and quickly generate the corresponding voucher, which can greatly improve the voucher generation efficiency.
[0084] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments, and the execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps or stages in other steps.
[0085] Based on the same inventive concept, the embodiment of the present application also provides a voucher generation device for implementing the voucher generation method involved above. The implementation solution provided by this device to solve the problem is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more embodiments of the voucher generation device provided below can refer to the limitations on the voucher generation method in the above text, and will not be repeated here.
[0086] In an exemplary embodiment, as Figure 4 shown, a voucher generation device is provided, including: a document information recognition module 402, a business type determination module 404, a subject template determination module 406, and a voucher generation module 408, where:
[0087] The document information recognition module 402 is used to obtain a target document and recognize the document information of the target document;
[0088] The business type determination module 404 is used to determine the target business type corresponding to the target document according to the document information of the target document;
[0089] The subject template determination module 406 is used to determine the target debit and credit subject template corresponding to the target business type;
[0090] The voucher generation module 408 is used to generate the target voucher corresponding to the target document according to the target debit and credit subject template.
[0091] In some embodiments, the business type determination module 404 is further configured to, if the document information of the target document includes the hierarchical information corresponding to the preset reference table, determine the first-level classification name and the second-level classification name that match the document information according to the preset reference table; the classification range corresponding to the first-level classification name is larger than the classification range corresponding to the second-level classification name; according to the mapping relationship between the first-level classification name and the second-level classification name and the business type, determine the target business type corresponding to the target document.
[0092] In some embodiments, the above device further includes a second-level classification name determination module, configured to, if the second-level classification name that matches the document information cannot be determined according to the preset reference table, construct a prompt word according to the document information, and input the constructed prompt word into the artificial intelligence large model to obtain the second-level classification name that matches the document information; the artificial intelligence large model is trained according to the classification name samples, and the classification name samples include the first-level classification name samples and the corresponding second-level classification name samples.
[0093] In some embodiments, the business type determination module 404 is further configured to, if the document information of the target document does not include the hierarchical information corresponding to the preset reference table, input the document information of the target document into the type recognition model to obtain the target business type corresponding to the target document.
[0094] In some embodiments, the voucher generation module 408 is further configured to obtain the business scenario type; according to the business scenario type, determine the scenario debit and credit subject template from the target debit and credit subject template; according to the scenario debit and credit subject template, generate the target voucher corresponding to the business scenario type.
[0095] In some embodiments, there are multiple target business types; the subject template determination module 406 is further configured to determine the target debit and credit subject template corresponding to each target business type respectively.
[0096] Each module in the above-mentioned voucher generation device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.
[0097] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 5 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store voucher data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a voucher generation method.
[0098] Those skilled in the art can understand that Figure 5 the structure shown in
[0099] is only a block diagram of a part of the structure related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.
[0100] In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps of the voucher generation method in the above embodiment.
[0101] In an embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, it implements the steps of the voucher generation method in the above embodiment.
[0102] 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 for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.
[0103] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.
[0104] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this application.
[0105] The above-described embodiments merely represent several implementation manners of this application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of this application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application should be subject to the appended claims.
Claims
1. A method for generating a voucher, characterized in that: The method comprises: Acquire a target document and identify document information of the target document; Determining a target business type corresponding to the target document according to the document information of the target document; Determine the target loan account template corresponding to the target business type; A target voucher corresponding to the target document is generated according to the target debit and credit account template.
2. The method according to claim 1, characterized in that The determining, according to the document information of the target document, the target business type corresponding to the target document includes: If the document information of the target document includes classification information corresponding to a preset reference table, a first-level classification name and a second-level classification name matching the document information are determined according to the preset reference table; the classification range corresponding to the first-level classification name is larger than the classification range corresponding to the second-level classification name; According to the mapping relationship between the first-level classification name and the second-level classification name and the business type, the target business type corresponding to the target document is determined.
3. The method according to claim 2, characterized in that The method further comprises: If the secondary classification name that matches the document information cannot be determined according to the preset reference table, a prompt word is constructed according to the document information, and the constructed prompt word is input into the artificial intelligence big model to obtain the secondary classification name that matches the document information; the artificial intelligence big model is trained based on the classification name samples, and the classification name samples include the primary classification name samples and the corresponding secondary classification name samples.
4. The method according to claim 2, characterized in that: The method further comprises: If the document information of the target document does not include the classification information corresponding to the preset reference table, the document information of the target document is input into the type recognition model to obtain the target business type corresponding to the target document.
5. The method according to any one of claims 1 to 4, characterized in that: Generating a target voucher corresponding to the target document according to the target debit and credit account template includes: Get the business scenario type; Determining a scenario loan account template from the target loan account template according to the business scenario type; According to the scenario loan account template, a target voucher corresponding to the business scenario type is generated.
6. The method according to claim 1, characterized in that The target business type includes multiple ones; the target loan account template corresponding to the target business type is determined, including: Determine the target debit and credit account templates corresponding to each target business type respectively.
7. A credential generating device, characterized in that: The device comprises: A document information identification module, used to obtain a target document and identify the document information of the target document; A business type determination module, used to determine a target business type corresponding to the target document according to the document information of the target document; An account template determination module, used to determine a target loan account template corresponding to the target business type; The voucher generation module is used to generate a target voucher corresponding to the target document according to the target debit and credit account template.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.