Element self-matching intelligent invoicing method and device based on large model technology

Abstract

The invention discloses an element self-matching intelligent invoicing method and device based on a large model technology. The method comprises the following steps: learning and training a large model by utilizing file data of different file types, and generating analysis modules corresponding to the different file types; automatically selecting a corresponding analysis module according to a file type of a to-be-processed file uploaded or selected by a user, and identifying or reading the to-be-processed file according to the selected analysis module to obtain text invoicing information required by invoicing in the to-be-processed file; performing structured conversion on the character invoicing information to generate structured character invoicing information, and performing invoice issuing by combining the structured character invoicing information with an enterprise knowledge graph and a commodity coding service to generate a preview invoice; and sending the preview invoice to a client of the user, and issuing invoice data corresponding to the to-be-processed file according to an issuing request confirmed by the client.

Description

Technical Field

[0001] The present invention relates to the technical field of invoice issuance, and more specifically, to an element self-matching intelligent invoicing method and device based on large model technology. Background Art

[0002] Invoicing is the core of corporate tax management and is also a business that must be carried out for corporate compliance operations. Invoicing information can have different carriers, including text, voice, pictures and files, and its content can be described in different ways, including formatted or semi-formatted data and natural language descriptions. For example, a client of an accounting company may send a message to an accounting accountant saying "Issue an 800 yuan meal invoice for Company A". In this case, the invoicing information is in the form of text and described in natural language; a company business person may send a business contract to an invoicer and ask the invoicer to issue an invoice based on the contract. In this case, the invoicing information is in the form of a file, and the contract contains formatted purchaser information and other invoicing information described in natural language. The invoicing scenario seems simple, but in reality it faces problems of inefficiency and error.

[0003] The inefficiency is due to the large amount of information that needs to be filled in when issuing an invoice. When the invoicer enters each item during the invoicing process, he needs to first check the original invoicing information sent by the business personnel or the accounting company's client, and then manually enter the invoicing data on the invoicing page. The face information of an invoice can be as few as a dozen or as many as dozens or even hundreds of items, which means that when issuing an invoice, the invoicer needs to repeat the process of checking and entering dozens of times, resulting in a long process and low invoicing efficiency.

[0004] Errors are a common problem in all manual operations. The results of manual operations will be affected by factors such as the operator's skills, concentration, and the complexity of the operation process. It is impossible to ensure that the results are as accurate as the program running results, and the more complex the operation process, the higher the probability of error.

[0005] Invoicing service providers have always been committed to avoiding the above problems by automating the process. The process of entering the confirmed invoice data into the page has been automated. However, before the access to the big model capability, there are still obstacles in the process of automatically breaking down the original invoicing information into individual invoice data. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a method and device for intelligent invoicing with self-matching of elements based on large model technology.

[0007] According to one aspect of the present invention, a method for intelligent invoicing based on self-matching of elements based on a large model technology is provided, comprising:

[0008] The large model is used to learn and train file data of different file types to generate parsing modules corresponding to different file types;

[0009] Automatically select the corresponding parsing module according to the file type of the file to be processed uploaded or selected by the user, and perform identification or reading operations on the file to be processed according to the selected parsing module to obtain the text invoicing information required by the invoicing file to be processed;

[0010] Convert text invoicing information into structured form to generate structured text invoicing information, and combine the structured text invoicing information with the enterprise knowledge graph and product coding service to issue invoices and generate preview invoices;

[0011] The previewed invoice is sent to the user's client, and based on the client's request for confirmation of issuance, the invoice data corresponding to the pending file is issued.

[0012] Optionally, the file types of the files to be processed include voice, image and Excel table.

[0013] Optionally, the large model is learned and trained using file data of different file types to generate parsing modules corresponding to different file types, including:

[0014] The large model is used to learn and annotate data through different invoicing formats to generate an OCR recognition module for the large model to identify invoicing information of different invoicing formats;

[0015] The big model is used to learn and annotate different invoicing voice data to generate an AI voice recognition module for the big model to identify the invoicing information of different invoicing voices;

[0016] The big model is learned and data annotated through different Excel tables to generate an Excel form reading module for the big model to identify the invoicing information of different Excel tables.

[0017] Optionally, a corresponding parsing module is automatically selected according to the file type of the file to be processed uploaded or selected by the user, and the file to be processed is identified or read according to the selected parsing module to obtain text invoicing information of the invoicing requirement in the file to be processed, including:

[0018] When the file type of the file to be processed is voice, select the AI ​​voice recognition module to perform voice recognition on the file to be processed and convert the file to be processed into text invoicing information required for invoicing;

[0019] When the file type of the to-be-processed file is an image, an OCR recognition module is selected to extract text information from the to-be-processed file to obtain text invoicing information required by the invoicing file;

[0020] When the file type of the file to be processed is an Excel table, select the Excel table reading module to traverse the cells of the file to be processed, extract the key data required for invoicing, and obtain the text invoicing information required for invoicing in the file to be processed.

[0021] According to another aspect of the present invention, there is provided an element self-matching intelligent invoicing device based on a large model technology, comprising:

[0022] The first generation module is used to learn and train the large model using file data of different file types to generate parsing modules corresponding to different file types;

[0023] The acquisition module is used to automatically select a corresponding parsing module according to the file type of the file to be processed uploaded or selected by the user, and to identify or read the file to be processed according to the selected parsing module to obtain the text invoicing information required by the invoicing file to be processed;

[0024] The second generation module is used to perform structured conversion on the text invoicing information to generate structured text invoicing information, and combine the structured text invoicing information with the enterprise knowledge graph and the commodity coding service to issue an invoice and generate a preview invoice;

[0025] The issuing module is used to send the previewed invoice to the user's client, and issue the invoice data corresponding to the pending file based on the client's request for confirmation of issuance.

[0026] Optionally, the file types of the files to be processed include voice, image and Excel table.

[0027] Optionally, the first generating module includes:

[0028] The first generation submodule is used to learn and annotate the data of the large model through different invoicing formats, and generate an OCR recognition module for the large model to recognize the invoicing information of different invoicing formats;

[0029] The second generation submodule is used to learn and annotate the large model through different invoicing voice data, and generate an AI voice recognition module for the large model to recognize the invoicing information of different invoicing voices;

[0030] The third generation submodule is used to learn and annotate the data of the large model through different Excel tables, and generate an Excel form reading module for the large model to identify the invoicing information of different Excel tables.

[0031] Optionally, obtain a module, including:

[0032] The recognition submodule is used to select the AI ​​voice recognition module to perform voice recognition on the file to be processed when the file type of the file to be processed is voice, and convert the file to be processed into text invoicing information required for invoicing;

[0033] The first extraction submodule is used to select the OCR recognition module to extract text information from the to-be-processed file when the file type of the to-be-processed file is an image, and obtain the text invoicing information required by the invoicing file;

[0034] The second extraction submodule is used to select the Excel form reading module to traverse the cells of the file to be processed when the file type of the file to be processed is an Excel table, extract the key data required for invoicing, and obtain the text invoicing information required for invoicing in the file to be processed.

[0035] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute the method described in any one of the above aspects of the present invention.

[0036] According to another aspect of the present invention, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of the above aspects of the present invention.

[0037] Therefore, the present invention innovates the invoicing process, transforming the original process of manual identification and filling in invoicing information into a process that utilizes large model information extraction, reading comprehension and other capabilities, identifies and extracts the corresponding invoice data based on the original invoicing information provided by business personnel and accounting company customers, and then the system automatically completes the filling work, thereby replacing the manual entry process, which can effectively improve the work efficiency of the invoicer and reduce the probability of error. The invention of this method greatly reduces the invoicing time, which can be reduced from the traditional 5 minutes to 1 minute. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] A more complete understanding of exemplary embodiments of the present invention may be obtained by referring to the following drawings:

[0039] Figure 1 It is a flowchart of an element self-matching intelligent invoicing method based on a large model technology provided by an exemplary embodiment of the present invention;

[0040] Figure 2 It is another flow chart of the method for intelligent invoicing based on self-matching of elements and large model technology provided by an exemplary embodiment of the present invention;

[0041] Figure 3It is a structural schematic diagram of an element self-matching intelligent invoicing device based on a large model technology provided by an exemplary embodiment of the present invention;

[0042] Figure 4 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0043] Below, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described here.

[0044] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0045] Those skilled in the art can understand that the terms "first" and "second" in the embodiments of the present invention are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0046] It should also be understood that, in the embodiments of the present invention, “plurality” may refer to two or more than two, and “at least one” may refer to one, two or more than two.

[0047] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0048] In addition, the term "and / or" in the present invention is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects before and after are in an "or" relationship.

[0049] It should also be understood that the description of the various embodiments of the present invention focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced to each other, and for the sake of brevity, they will not be described one by one.

[0050] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0051] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0052] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0053] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0054] Embodiments of the present invention can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems, etc.

[0055] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system executable instructions (such as program modules) executed by computer systems. Generally, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in a distributed cloud computing environment, where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0056] Exemplary Methods

[0057] Figure 1 1 is a flow chart of a method for self-matching intelligent invoicing based on a large model technology provided by an exemplary embodiment of the present invention. This embodiment can be applied to electronic devices, such as Figure 1 As shown, the factor self-matching intelligent invoicing method 100 based on the big model technology includes the following steps:

[0058] Step 101, using file data of different file types to learn and train the large model, and generating parsing modules corresponding to different file types;

[0059] Step 102, automatically selecting a corresponding parsing module according to the file type of the to-be-processed file uploaded or selected by the user, and performing identification or reading operations on the to-be-processed file according to the selected parsing module to obtain text invoicing information required by the invoicing file;

[0060] Step 103, convert the text invoicing information into a structured form to generate structured text invoicing information, and combine the structured text invoicing information with the enterprise knowledge graph and the commodity coding service to issue an invoice and generate a preview invoice;

[0061] Step 104, the previewed invoice is sent to the user's client, and invoice data corresponding to the to-be-processed file is issued according to the client's request for confirmation of issuance.

[0062] Specifically, the present invention proposes the following solutions to the technical problems existing in the prior art: innovation in the invoicing process, transforming the original process of manual identification and filling in invoicing information into the use of large model information extraction, reading comprehension and other capabilities, based on the original invoicing information (in the form of text and voice) provided by business personnel and accounting company customers, to identify and extract the corresponding invoice data, and then the system automatically completes the filling work, thereby replacing the manual input process, which can effectively improve the work efficiency of the invoicer and reduce the probability of error. Figure 2 As shown, the modules of this solution are as follows:

[0063] 1. Source data entry module. The source data entry module is divided into AI speech recognition unit, OCR recognition unit, and EXCEL form reading module.

[0064] The AI ​​voice recognition module is responsible for receiving user voice commands, using deep learning algorithms for voice recognition, and converting voice into text-based invoicing requirements.

[0065] The OCR recognition module extracts text information from image files (such as scans, photos, etc.) through OCR technology, and supports recognition of multiple languages ​​and complex layouts.

[0066] The Excel form reading module specializes in processing Excel spreadsheet files. It can automatically traverse the cells in the table and extract the key data required for invoicing, such as product information, quantity, unit price, etc.

[0067] After the user uploads or selects the file to be processed (voice, image or Excel table), the system automatically selects the corresponding parsing module for processing according to the file type. The parsing module performs the corresponding recognition or reading operation to convert the invoicing requirements in the file into text invoicing information. The converted text information is stored in the system for use by the subsequent large model key information extraction module.

[0068] Large model invoicing information extraction module. Since the invoicing formats of different companies are different, it is difficult to identify them. The large model analyzes and processes bills of different formats through learning and data annotation of a large number of samples. At the same time, in order to improve the accuracy of information extraction, the large model uses a variety of loss functions and optimization algorithms during the training process. It can perform layout analysis on invoicing sources of different formats, identify and segment different information areas, such as the purchaser, product, amount, etc., to facilitate subsequent information extraction. In the process of extracting invoicing information, the invoicer can have multiple rounds of conversations to supplement or adjust the invoicing information. The large model will confirm and extract the invoicing information based on the content of multiple rounds of conversations, and finally complete the key invoicing information such as invoicing date, purchaser information, seller information, product details, amount, etc.

[0069] Output invoicing information module. The extracted invoicing information is output in a structured form, such as JSON, XML and other formats, combined with the knowledge graph of corporate business cards and product coding services to achieve rapid invoicing, greatly improving the efficiency and accuracy of information entry in the invoicing process of corporate invoicers or accounting companies, and reducing corporate costs.

[0070] 4. Invoice preview and confirmation invoicing module. Fill in the invoice information into the invoice template according to different tax forms, and provide users with preview. After the user confirms, connect to the invoicing system for invoicing.

[0071] The key points of this invention patent are as follows:

[0072] (1) Optimization of the invoicing process. The traditional invoicing process requires manual extraction of key information from various transaction documents such as supermarket shopping receipts, handwritten orders, contracts, natural language voice, tables, WeChat chat text, etc. After the introduction of the big model, the system can automatically identify and extract key data such as product information, transaction information, transaction time, etc. from documents such as contracts, orders, and receipts, greatly reducing manual intervention and improving the automation level of the process. At the same time, the big model based on deep learning can quickly judge the user's invoicing intention based on the extracted information, and intelligently match or generate invoice templates that comply with tax regulations. This process is not only fast and efficient, but can also be flexibly adjusted according to different scenarios and needs, improving the accuracy and compliance of invoices and greatly simplifying the invoicing process.

[0073] (2) High-precision invoicing information extraction. A variety of loss functions and optimization algorithms are used to ensure accurate extraction of key information from invoicing sources in different formats, such as invoicing date, buyer and seller information, product details, and amount.

[0074] (3) Combining the big model with knowledge graph and coding services. Combining the knowledge graph of corporate business cards and product coding services can achieve fast invoicing and improve the efficiency and accuracy of the overall invoicing process.

[0075] (4) Seamless connection with the invoicing system. Seamless connection with the existing electronic invoicing system simplifies the invoicing process and reduces enterprise costs.

[0076] Beneficial effects of the present invention: The present invention greatly reduces the time required for invoicing, which can be reduced from the traditional 5 minutes to within 1 minute.

[0077] Exemplary Devices

[0078] Figure 3 Schematic diagram of the structure of an element self-matching intelligent invoicing device based on a large model technology provided by an exemplary embodiment of the present invention. Figure 3 As shown, the device 300 includes:

[0079] A generation module 310 is used to learn and train the large model using file data of different file types to generate parsing modules corresponding to different file types;

[0080] The acquisition module 320 is used to automatically select a corresponding parsing module according to the file type of the to-be-processed file uploaded or selected by the user, and to perform identification or reading operations on the to-be-processed file according to the selected parsing module to obtain the text invoicing information of the invoicing requirement in the to-be-processed file;

[0081] The generation module 330 is used to perform structured conversion on the text invoicing information to generate structured text invoicing information, and combine the structured text invoicing information with the enterprise knowledge graph and the commodity coding service to issue an invoice and generate a preview invoice;

[0082] The issuing module 340 is used to send the previewed invoice to the user's client, and issue the invoice data corresponding to the to-be-processed file according to the client's request for confirmation of issuance.

[0083] Optionally, the file types of the files to be processed include voice, image and Excel table.

[0084] Optionally, the generating module 310 includes:

[0085] The first generation submodule is used to learn and annotate the data of the large model through different invoicing formats, and generate an OCR recognition module for the large model to recognize the invoicing information of different invoicing formats;

[0086] The second generation submodule is used to learn and annotate the large model through different invoicing voice data, and generate an AI voice recognition module for the large model to recognize the invoicing information of different invoicing voices;

[0087] The third generation submodule is used to learn and annotate the data of the large model through different Excel tables, and generate an Excel form reading module for the large model to identify the invoicing information of different Excel tables.

[0088] Optionally, the acquisition module 320 includes:

[0089] The recognition submodule is used to select the AI ​​voice recognition module to perform voice recognition on the file to be processed when the file type of the file to be processed is voice, and convert the file to be processed into text invoicing information required for invoicing;

[0090] The first extraction submodule is used to select the OCR recognition module to extract text information from the to-be-processed file when the file type of the to-be-processed file is an image, and obtain the text invoicing information required by the invoicing file;

[0091] The second extraction submodule is used to select the Excel form reading module to traverse the cells of the file to be processed when the file type of the file to be processed is an Excel table, extract the key data required for invoicing, and obtain the text invoicing information required for invoicing in the file to be processed.

[0092] Exemplary Electronic Devices

[0093] Figure 4 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. Figure 4 As shown, the electronic device 40 includes one or more processors 41 and a memory 42 .

[0094] The processor 41 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0095] The memory 42 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 41 may run the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above and / or other desired functions. In one example, the electronic device may also include: an input device 43 and an output device 44, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0096] In addition, the input device 43 may also include, for example, a keyboard, a mouse, etc.

[0097] The output device 44 can output various information to the outside, and can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto.

[0098] Of course, to simplify, Figure 4 Only some of the components related to the present invention in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, the electronic device may further include any other appropriate components according to specific application conditions.

[0099] Exemplary computer program products and computer-readable storage media

[0100] In addition to the above-mentioned methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present invention described in the above-mentioned "Exemplary Method" section of this specification.

[0101] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the embodiments of the present invention, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0102] In addition, an embodiment of the present invention may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0103] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, system or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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 above.

[0104] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details disclosed above are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0105] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0106] The block diagrams of the devices, systems, equipment, and systems involved in the present invention are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, systems, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The word "such as" used here refers to the phrase "such as but not limited to", and can be used interchangeably with it.

[0107] The method and system of the present invention may be implemented in many ways. For example, the method and system of the present invention may be implemented by software, hardware, firmware or any combination of software, hardware, firmware. The above order of steps for the method is only for illustration, and the steps of the method of the present invention are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present invention may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present invention. Thus, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0108] It should also be noted that in the system, device and method of the present invention, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. The above description of the disclosed aspects is provided to enable any technician in the field to make or use the present invention. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined here can be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown here, but in accordance with the widest range consistent with the principles and novel features disclosed here.

[0109] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present invention to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for intelligent invoicing based on self-matching of elements based on large model technology, characterized in that: include: The large model is used to learn and train file data of different file types to generate parsing modules corresponding to different file types; Automatically select a corresponding parsing module according to the file type of the file to be processed uploaded or selected by the user, and perform identification or reading operations on the file to be processed according to the selected parsing module to obtain text invoicing information of the invoicing requirement in the file to be processed; The text invoicing information is structured and converted to generate structured text invoicing information, and the structured text invoicing information is combined with the enterprise knowledge graph and the commodity coding service to issue an invoice and generate a preview invoice; The previewed invoice is sent to the client of the user, and invoice data corresponding to the to-be-processed file is issued according to the request for confirmation of issuance by the client.

2. The method according to claim 1, characterized in that The file types of the files to be processed include voice, image and Excel table.

3. The method according to claim 1, characterized in that The large model is learned and trained using file data of different file types to generate parsing modules corresponding to different file types, including: The large model is used to learn and annotate data through different invoicing formats, and an OCR recognition module for the large model to recognize invoicing information of different invoicing formats is generated; The large model is used to learn and annotate different invoicing voice data to generate an AI voice recognition module for the large model to recognize invoicing information of different invoicing voices; The large model is learned and data annotated through different Excel tables to generate an Excel form reading module for the large model to identify the invoicing information of different Excel tables.

4. The method according to claim 3, characterized in that Automatically select a corresponding parsing module according to the file type of the file to be processed uploaded or selected by the user, and perform identification or reading operations on the file to be processed according to the selected parsing module to obtain text invoicing information of the invoicing requirements in the file to be processed, including: When the file type of the to-be-processed file is voice, an AI voice recognition module is selected to perform voice recognition on the to-be-processed file, and convert the to-be-processed file into text invoicing information required for invoicing; When the file type of the to-be-processed file is an image, an OCR recognition module is selected to extract text information from the to-be-processed file to obtain text invoicing information of the invoicing requirement in the to-be-processed file; When the file type of the file to be processed is an Excel table, an Excel table reading module is selected to traverse the cells of the file to be processed, extract key data required for invoicing, and obtain text invoicing information required for invoicing in the file to be processed.

5. An element self-matching intelligent invoicing device based on large model technology, characterized in that: include: The first generation module is used to learn and train the large model using file data of different file types to generate parsing modules corresponding to different file types; An acquisition module is used to automatically select a corresponding parsing module according to the file type of the to-be-processed file uploaded or selected by the user, and to identify or read the to-be-processed file according to the selected parsing module to obtain the text invoicing information of the invoicing requirement in the to-be-processed file; The second generation module is used to perform structured conversion on the text invoicing information to generate structured text invoicing information, and combine the structured text invoicing information with the enterprise knowledge graph and the commodity coding service to issue an invoice and generate a preview invoice; The issuing module is used to send the previewed invoice to the user's client and issue the invoice data corresponding to the to-be-processed file according to the request for confirmation of the issuance by the client.

6. The device according to claim 5, characterized in that The file types of the files to be processed include voice, image and Excel table.

7. The device according to claim 5, characterized in that The first generation module includes: The first generation submodule is used to learn and annotate the big model through different invoicing formats, and generate an OCR recognition module for the big model to recognize invoicing information of different invoicing formats; The second generation submodule is used to learn and annotate the large model through different invoicing voice data, and generate an AI voice recognition module for the large model to recognize invoicing information of different invoicing voices; The third generation submodule is used to learn and annotate the data of the large model through different Excel tables, and generate an Excel form reading module for the large model to identify the invoicing information of different Excel tables.

8. The device according to claim 7, characterized in that Get modules, including: The recognition submodule is used for selecting an AI voice recognition module to perform voice recognition on the file to be processed when the file type of the file to be processed is voice, and converting the file to be processed into text invoicing information required for invoicing; A first extraction submodule is used for selecting an OCR recognition module to extract text information from the file to be processed when the file type of the file to be processed is an image, so as to obtain text invoicing information of the invoicing requirement in the file to be processed; The second extraction submodule is used to select an Excel form reading module to traverse the cells of the file to be processed when the file type of the file to be processed is an Excel table, extract key data required for invoicing, and obtain text invoicing information required for invoicing in the file to be processed.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 4.

10. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1 to 4.

Images