Unstructured trade contract element extraction system, method and device, medium and product

Abstract

The invention discloses an unstructured trade contract element extraction system, method and device, a medium and a product, and relates to the field of trade contract management, the system comprises a trade contract information acquisition module, a data processing module, an OCR module, an AI analysis module, a comparison module and a result adjustment module which are connected in sequence; the comparison module is also connected with the trade contract information acquisition module; and the result adjustment module is also connected with the trade contract information acquisition module. According to the method, the optical character recognition technology and the large model AI technology are integrated, so that the efficiency and the accuracy of unstructured trade contract processing are improved.

Description

Technical Field

[0001] The present application relates to the field of trade contract management, and in particular to a system, method, device, medium and product for extracting elements of an unstructured trade contract. Background Art

[0002] Currently, the processing of unstructured trade contracts (images or PDF formats) mostly relies on manual visual review. Due to the non-uniform file formats and different clarity, manual processing is inefficient and prone to errors. With the development of optical character recognition (OCR) technology and large-model artificial intelligence (AI) technology, new solutions have been provided. OCR technology can convert text in image files into editable formats, while AI technology, especially the application of large models, can conduct in-depth analysis and understanding of text content, providing a technical basis for automated extraction and deduplication. Summary of the invention

[0003] The purpose of this application is to provide a system, method, device, medium and product for extracting elements of unstructured trade contracts to improve the management efficiency and audit accuracy of unstructured trade contracts.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides an unstructured trade contract element extraction system, comprising: a trade contract information acquisition module, a data processing module, an OCR module, an AI analysis module, a comparison module and a result adjustment module connected in sequence; the comparison module is also connected to the trade contract information acquisition module; the result adjustment module is also connected to the trade contract information acquisition module;

[0006] The trade contract information acquisition module is used to acquire key element information of the unstructured trade contract to be compared and historical unstructured trade contracts; the key element information includes company name, trade contract number, invoice number, invoice date and invoice amount; the historical unstructured trade contract is in the form of picture or PDF;

[0007] The data processing module is used to convert the historical unstructured trade contract into a binary stream format to obtain a processed historical unstructured trade contract;

[0008] The OCR module is used to extract text information of the processed historical unstructured trade contract using optical character recognition technology;

[0009] The AI ​​analysis module is used to extract information corresponding to key elements based on the text information and use the AI ​​big model to obtain key element information of the historical unstructured trade contract;

[0010] The comparison module is used to compare the key element information of the unstructured trade contract to be compared with the key element information of the historical unstructured trade contract to obtain a comparison result; the comparison result is that there is repeated key element information in the unstructured trade contract to be compared and the historical unstructured trade contract, or there is no repeated key element information in the unstructured trade contract to be compared and the historical unstructured trade contract;

[0011] The result adjustment module is used to adjust key elements according to the comparison result and return to the "trade contract information acquisition module".

[0012] Optionally, it further comprises: an element information configuration module; the element information configuration module is connected to the trade contract information acquisition module;

[0013] The element information configuration module is used to determine the key elements of the unstructured trade contract.

[0014] Optionally, it further includes: a result display module; the result display module is connected to the AI ​​analysis module and the comparison module respectively;

[0015] The result display module is used to display the key element information and comparison results of the historical unstructured trade contract.

[0016] In a second aspect, the present application further provides a method for extracting elements of an unstructured trade contract, which is applied to the unstructured trade contract element extraction system mentioned above, and the method for extracting elements of an unstructured trade contract includes:

[0017] Obtain key element information of the unstructured trade contract to be compared and historical unstructured trade contracts; the key element information includes company name, trade contract number, name, invoice number, invoice date and invoice amount; the historical unstructured trade contract is in the form of picture or PDF;

[0018] Converting the historical unstructured trade contract into a binary stream format to obtain a processed historical unstructured trade contract;

[0019] Extracting text information of the processed historical unstructured trade contract using optical character recognition technology;

[0020] According to the text information, using the AI ​​big model, extract the information corresponding to the key elements to obtain the key element information of the historical unstructured trade contract;

[0021] Comparing the key element information of the unstructured trade contract to be compared with the key element information of the historical unstructured trade contract to obtain a comparison result; the comparison result is that there is repeated key element information in the unstructured trade contract to be compared and the historical unstructured trade contract, or there is no repeated key element information in the unstructured trade contract to be compared and the historical unstructured trade contract;

[0022] If the comparison result is that there is duplicate key element information in the unstructured trade contract to be compared and the historical unstructured trade contract, the key elements are adjusted and the "get key element information of the unstructured trade contract to be compared" is returned.

[0023] Optionally, it also includes:

[0024] Convert the key element information of the historical unstructured trade contract into a structured format.

[0025] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described methods for extracting elements of unstructured trade contracts.

[0026] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for extracting unstructured trade contract elements.

[0027] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for extracting unstructured trade contract elements.

[0028] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0029] The present application provides a system, method, device, medium and product for extracting elements of unstructured trade contracts, which improves the efficiency and accuracy of unstructured trade contract processing by integrating optical character recognition technology and large model AI technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0031] Figure 1 A structural block diagram of an unstructured trade contract element extraction system provided in an embodiment of the present application;

[0032] Figure 2 A flow chart of a method for extracting elements of an unstructured trade contract provided in one embodiment of the present application;

[0033] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0035] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0036] In an exemplary embodiment, Figure 1 As shown, a non-structured trade contract element extraction system is provided, comprising: a trade contract information acquisition module, a data processing module, an OCR module, an AI analysis module, a comparison module and a result adjustment module connected in sequence; the comparison module is also connected to the trade contract information acquisition module; the result adjustment module is also connected to the trade contract information acquisition module.

[0037] In practical applications, the unstructured trade contract element extraction system includes an element information configuration module, a trade contract information input module (trade contract information acquisition module), a data processing module, an OCR module, an AI analysis module, a result display and comparison module (comparison module and result display module), and a result adjustment and confirmation module (result adjustment module).

[0038] An element information configuration module; the element information configuration module is connected to the trade contract information acquisition module; the element information configuration module is used to determine the key elements of the unstructured trade contract.

[0039] In practical applications, the element information configuration module is used to extract key element information from a trade contract, including company name, trade contract number, invoice number, invoice date and invoice amount.

[0040] The trade contract information acquisition module is used to obtain key element information of the unstructured trade contract to be compared and the historical unstructured trade contract; the key element information includes company name, trade contract number, invoice number, invoice date and invoice amount; the historical unstructured trade contract is in the form of picture or PDF. In actual application, the contract newly uploaded by the user (unstructured trade contract to be compared) is compared with the contract in the historical database. If duplicate information is found, it means that the new contract violates the rules and may not be used for subsequent business.

[0041] In actual applications, the trade contract information input module is used to input the trade contract information to be compared, and the input trade contract information includes the element information extracted by the element information configuration module and its corresponding value (user input).

[0042] The data processing module is used to convert the historical unstructured trade contract into a binary stream format to obtain a processed historical unstructured trade contract.

[0043] In actual applications, the data processing module is used to process trade contract documents submitted in unstructured formats such as pictures or PDFs through OCR technology. The processing method is that the user submits the picture or PDF file to the data processing module, and the data processing module converts the file into a binary stream format and sends it to the OCR module.

[0044] The OCR module is used to extract text information of the processed historical unstructured trade contract using optical character recognition technology.

[0045] In practical applications, the OCR module is used to extract text information from images or PDF files uploaded by users through image analysis and submit all extracted text information to the AI ​​analysis module for processing.

[0046] The AI ​​analysis module is used to extract information corresponding to key elements based on the text information using the AI ​​big model to obtain key element information of the historical unstructured trade contract. The AI ​​big model is a pre-trained language model open sourced in China.

[0047] In actual applications, the AI ​​analysis module uses large model AI technology, with the key element information extracted by the element information configuration module as a prompt, to analyze and extract the corresponding value of each element.

[0048] The comparison module is used to compare the key element information of the unstructured trade contract to be compared with the key element information of the historical unstructured trade contract to obtain a comparison result; the comparison result is that there is repeated key element information in the unstructured trade contract to be compared and the historical unstructured trade contract, or there is no repeated key element information in the unstructured trade contract to be compared and the historical unstructured trade contract.

[0049] A result display module; the result display module is connected to the AI ​​analysis module and the comparison module respectively; the result display module is used to display the key element information and comparison results of the historical unstructured trade contract.

[0050] In actual applications, the result display and comparison module is used to display the extraction results of all element information from the AI ​​analysis module, and compare them with the values ​​corresponding to the element information input by the trade contract information input module. Based on the comparison results, users can quickly judge whether the contract they entered has duplicate content with the contract in the picture they uploaded.

[0051] The result adjustment module is used to adjust key elements according to the comparison result and return to the "trade contract information acquisition module".

[0052] The result adjustment and confirmation module is used to adjust the prompt words or element information according to the comparison result and the original document, and re-execute the extraction process until it is completed satisfactorily.

[0053] In an exemplary embodiment, the present application further provides a method for extracting unstructured trade contract elements, and the method for extracting unstructured trade contract elements is applied to the unstructured trade contract element extraction system described above, such as Figure 2 As shown, the unstructured trade contract element extraction method includes:

[0054] S1: Obtain key element information of the unstructured trade contract to be compared and historical unstructured trade contracts; the key element information includes company name, trade contract number, name, invoice number, invoice date and invoice amount; the historical unstructured trade contract is in picture or PDF format.

[0055] In practical applications, we first define the key elements that need to be extracted from the trade contract, such as company name, contract number, invoice number, invoice date and invoice amount.

[0056] Then input the trade contract information to be compared, including the element information defined above and its corresponding values.

[0057] S2: Convert the historical unstructured trade contract into a binary stream format to obtain a processed historical unstructured trade contract.

[0058] S3: Use optical character recognition technology to extract text information from the processed historical unstructured trade contracts. Use OCR technology to process trade contract documents submitted in unstructured formats such as images or PDFs, and batch process multiple files. Use OCR technology to parse all files into plain text, merge the results, and uniformly hand them over to the large model AI component for processing.

[0059] S4: Based on the text information, use the AI ​​big model to extract the information corresponding to the key elements to obtain the key element information of the historical unstructured trade contract.

[0060] In actual applications, the natural language processing capabilities of large-model AI are used to identify and extract corresponding content from the output text based on pre-configured element information (such as company name, contract number, etc.), and finally organize the extracted element information into a structured format to facilitate subsequent comparison and display.

[0061] Example: Configure prompt words: Find the following element information in the following text and output it in the form of <element information>:<element content>. The element information is company name, contract number, invoice number, invoice date, and invoice amount.

[0062] The text content output by S3 will contain a lot of irrelevant information and content containing essential information, such as contract descriptions and contract terms, which cannot be listed one by one. The output format after being extracted by the large model AI is:

[0063] Company name: xxxx Co., Ltd.

[0064] Contract number: SHDSS0981.

[0065] Invoice number: 01233215123123.

[0066] Ticketing date: January 1, 2023.

[0067] Invoice amount: 20000.50.

[0068] Compare the key element information of the unstructured trade contract to be compared with the key element information of the historical unstructured trade contract to obtain a comparison result; the comparison result is that there is repeated key element information in the unstructured trade contract to be compared and the historical unstructured trade contract, or there is no repeated key element information in the unstructured trade contract to be compared and the historical unstructured trade contract.

[0069] If the comparison result is that there is duplicate key element information in the unstructured trade contract to be compared and the historical unstructured trade contract, the key elements are adjusted and the "get key element information of the unstructured trade contract to be compared" is returned.

[0070] The extraction results of all element information are displayed and compared with the values ​​entered in S1 to identify duplicate values. The user can adjust the prompt words or element information based on the comparison results and the original document and re-execute the extraction process until it is completed satisfactorily.

[0071] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. 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. 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 unstructured trade contracts. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for extracting elements of an unstructured trade contract is implemented.

[0072] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above-mentioned method for extracting elements of unstructured trade contracts when executing the computer program.

[0073] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the above-mentioned method for extracting elements of unstructured trade contracts when executed by a processor.

[0074] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the above-mentioned unstructured trade contract element extraction method when executed by a processor.

[0075] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, 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 must comply with relevant regulations.

[0076] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile 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), magnetic 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 may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0077] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0078] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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, they should be considered to be within the scope of this specification.

[0079] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A non-structured trade contract element extraction system, characterized in that: include: A trade contract information acquisition module, a data processing module, an OCR module, an AI analysis module, a comparison module and a result adjustment module connected in sequence; the comparison module and the result adjustment module are also connected to the trade contract information acquisition module; The trade contract information acquisition module is used to acquire key element information of the unstructured trade contract to be compared and historical unstructured trade contracts; the key element information includes company name, trade contract number, invoice number, invoice date and invoice amount; the historical unstructured trade contract is in the form of picture or PDF; The data processing module is used to convert the historical unstructured trade contract into a binary stream format to obtain a processed historical unstructured trade contract; The OCR module is used to extract text information of the processed historical unstructured trade contract using optical character recognition technology; The AI ​​analysis module is used to extract information corresponding to key elements based on the text information and use the AI ​​big model to obtain key element information of the historical unstructured trade contract; The comparison module is used to compare the key element information of the unstructured trade contract to be compared with the key element information of the historical unstructured trade contract to obtain a comparison result; the comparison result is that there is repeated key element information in the unstructured trade contract to be compared and the historical unstructured trade contract, or there is no repeated key element information in the unstructured trade contract to be compared and the historical unstructured trade contract; The result adjustment module is used to adjust key elements according to the comparison result and return to the "trade contract information acquisition module".

2. The unstructured trade contract element extraction system according to claim 1 is characterized in that: Also includes: An element information configuration module; the element information configuration module is connected to the trade contract information acquisition module; The element information configuration module is used to determine the key elements of the unstructured trade contract.

3. The unstructured trade contract element extraction system according to claim 1 is characterized in that: It also includes: a result display module; the result display module is connected to the AI ​​analysis module and the comparison module respectively; The result display module is used to display the key element information and comparison results of the historical unstructured trade contract.

4. A method for extracting elements of unstructured trade contracts, characterized in that: The unstructured trade contract element extraction method is applied to the unstructured trade contract element extraction system according to any one of claims 1 to 3, and the unstructured trade contract element extraction method comprises: Obtain key element information of the unstructured trade contract to be compared and historical unstructured trade contracts; the key element information includes company name, trade contract number, name, invoice number, invoice date and invoice amount; the historical unstructured trade contract is in the form of picture or PDF; Converting the historical unstructured trade contract into a binary stream format to obtain a processed historical unstructured trade contract; Extracting text information of the processed historical unstructured trade contract using optical character recognition technology; According to the text information, using the AI ​​big model, extract the information corresponding to the key elements to obtain the key element information of the historical unstructured trade contract; Comparing the key element information of the unstructured trade contract to be compared with the key element information of the historical unstructured trade contract to obtain a comparison result; the comparison result is that there is repeated key element information in the unstructured trade contract to be compared and the historical unstructured trade contract, or there is no repeated key element information in the unstructured trade contract to be compared and the historical unstructured trade contract; If the comparison result is that there is duplicate key element information in the unstructured trade contract to be compared and the historical unstructured trade contract, the key elements are adjusted and "obtain key element information of the unstructured trade contract to be compared" is returned.

5. The method for extracting unstructured trade contract elements according to claim 4 is characterized in that: Also includes: Convert key element information of the historical unstructured trade contract into a structured format.

6. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for extracting elements of an unstructured trade contract as described in any one of claims 4-5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for extracting elements of an unstructured trade contract described in any one of claims 4 to 5 is implemented.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for extracting elements of an unstructured trade contract described in any one of claims 4 to 5 is implemented.

Images