A contract database automatic matching method and system

Abstract

The present application relates to the technical field of contract examination and approval, in particular to a contract database automatic matching method and system, which comprises the following steps: receiving a to-be-examined-and-approved contract file; analyzing the to-be-examined-and-approved contract file to obtain a service matter; screening out service types with a preset matching degree from the contract database according to the service matter; selecting a service type with the most marked information from the screened-out service types with the preset matching degree as a key type; analyzing the to-be-examined-and-approved contract file according to a corresponding file analysis model selected according to the key type to obtain suggested examination information of the to-be-examined-and-approved contract file; and marking a corresponding position on the to-be-examined-and-approved contract file according to the suggested examination information. The present application has the effects of providing examination and approval reference for examination and approval personnel and improving examination and approval efficiency.

Description

Technical Field

[0001] This invention relates to the technical field of contract approval, and in particular to a method and system for automatic matching of contract databases. Background Technology

[0002] Contracts serve as guidelines for corporate economic activities, protecting the company's interests and clearly defining its responsibilities and obligations. They are legal norms that must be followed in corporate economic activities. After drafting, contracts require approval from relevant company departments, and are confirmed through stamping and signatures. Contract approval ensures that the contract content meets the requirements of national laws, regulations, and policies, adheres to the principles of equality, mutual benefit, consensus, and equitable compensation, and minimizes various risks for the company.

[0003] In existing technologies, people can use contract approval process systems to transmit electronic contracts to replace paper contracts. However, current contract approval process systems can only provide functions such as data interaction and document viewing and marking. Contracts often need to be approved by several people in succession. Therefore, they are often approved by less experienced personnel first, and then reviewed by experienced personnel. However, for some newly hired personnel, this process takes a long time and is prone to omissions, resulting in low efficiency. Summary of the Invention

[0004] To provide approval personnel with a reference for approval and improve approval efficiency, this application provides a method and system for automatic matching of contract databases.

[0005] The above-mentioned objective of this application is achieved through the following technical solution: An automatic contract database matching method, comprising: Receive contract documents awaiting approval; The service items are obtained by analyzing the contract documents to be approved; Based on the service items, service types with a higher than preset matching degree are filtered in the contract database. The contract database stores multiple historical contract files. Each historical contract file is associated with a historical service item. Each service type is associated with multiple historical service items. Each historical service item is associated with at least one tag information. Select the service type with the most tagging information from the filtered service types that exceed the preset matching degree as the key type; Based on the key type, select the corresponding document analysis model to analyze the contract document to be signed, so as to obtain the suggested review information of the contract document to be signed; The recommended review information is marked in the corresponding position on the contract document to be signed.

[0006] By adopting the above technical solution, when a contract awaiting approval is received, the system can analyze the contract document to obtain the service items in the contract, then obtain the service type described in the contract, and then use the corresponding document analysis model to analyze it to obtain the suggested review information for the contract, which is marked on the contract for the approval personnel to provide approval reference, thereby improving approval efficiency.

[0007] In a preferred example, this application can be further configured such that the document analysis model is trained in the following manner: Each historical contract document sample in the training set is labeled to identify its tagging information. The audio source type is associated with all or part of the information in the historical contract document sample. The neural network is then trained using the labeled historical contract document sample training set to obtain a document analysis model.

[0008] By adopting the above technical solution, the document analysis model trained can achieve higher prediction accuracy as the amount of sample data increases.

[0009] In a preferred embodiment, this application can be further configured such that: the step of filtering service types exceeding a preset matching degree in the contract database based on the service items includes: Calculate the matching degree between each service type and the service item; Filter out service types that exceed the preset matching degree; The matching degree between each service type and the service item is calculated as follows: The service items in the service type are compared with the service item to obtain the sub-matching degree between each historical service item and the service item. The matching degree of the service type is calculated based on the sub-matching degree of each historical service item.

[0010] By adopting the above technical solutions, the matching degree of each service type can be measured more accurately.

[0011] In a preferred embodiment, this application can be further configured as follows: comparing multiple historical service items in the service type with the service item to obtain a sub-matching degree between each historical service item and the service item includes: The historical service items and the service items are input into the comparison model, and the sub-matching degree is obtained through reasoning.

[0012] The second objective of this invention is achieved through the following technical solution: An automatic contract database matching system includes: The receiving module is used to receive contract documents awaiting approval. The analysis module is used to analyze the contract documents to be approved to obtain service items; The filtering module is used to filter service types that exceed a preset matching degree in the contract database based on the service items. The contract database stores multiple historical contract files. Each historical contract file is associated with a historical service item. Each service type is associated with multiple historical service items. Each historical service item is associated with at least one tag information. The selection module is used to select the service type with the most tagging information as the key type from the filtered service types that exceed the preset matching degree. The reasoning module is used to select the corresponding document analysis model based on the key type to analyze the contract document to be signed and obtain suggested review information for the contract document to be signed and approved. The annotation module is used to annotate the corresponding positions on the contract documents to be signed based on the suggested review information.

[0013] In a preferred example, this application can be further configured such that the document analysis model is trained in the following manner: Each historical contract document sample in the training set is labeled to identify its tagging information. The audio source type is associated with all or part of the information in the historical contract document sample. The neural network is then trained using the labeled historical contract document sample training set to obtain a document analysis model.

[0014] In a preferred example, this application can be further configured as a filtering module, including: A calculation unit is used to calculate the matching degree between each service type and the service item; The filtering unit is used to filter out service types that exceed a preset matching degree; The computing unit includes: The comparison sub-unit is used to compare multiple historical service items in the service type with the service item to obtain the sub-matching degree between each historical service item and the service item; The calculation unit is used to calculate the service type matching degree based on the sub-matching degree of each historical service item.

[0015] In a preferred embodiment, this application can be further configured such that the comparison sub-unit includes: The inference micro-unit is used to input the historical service item and the service item into the comparison model and infer the sub-matching degree.

[0016] In summary, this application includes at least one of the following beneficial technical effects: 1. Upon receiving a contract awaiting approval, the system can analyze the contract document to obtain the service items and service types described in the contract. Then, it uses the corresponding document analysis model to analyze the contract and obtain suggested review information, which is marked on the contract for approval personnel to use as a reference, thereby improving approval efficiency. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the implementation of an automatic contract database matching method in one embodiment of this application; Figure 2 This is a flowchart illustrating the implementation of the automatic contract database matching method in another embodiment of this application; Figure 3 This is a module connection diagram of an automatic contract database matching system in one embodiment of this application. Detailed Implementation

[0018] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0019] It should be noted that the terms "first," "second," etc., used in this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this disclosure.

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

[0021] Figure 1 This is a flowchart illustrating the implementation of an automatic contract database matching method in one embodiment of this application, as follows: Figure 1 As shown, the automatic matching method for the contract database includes: This method is based on an automatic contract database matching system, which is integrated with the contract approval process system or other office systems. The contract database within this system stores multiple historical contract files. These historical contract files refer to actual historical contract records within the domain in which the system is applied. Each historical contract file is associated with a historical service item, and a service type is associated with multiple historical service items. Each historical service item is associated with at least one tag, which indicates a problem in the contract corresponding to that historical service item. The service type also depends on the actual application domain of the system. For example, in the construction field, it can include the following service types based on the subject matter: engineering supervision entrustment, engineering survey and design, construction preparation for building installation, construction contracting for building installation, construction of building decoration projects, subcontracting of building decoration projects, material supply, finished product processing ordering, and semi-finished product processing ordering. A service item refers to a detailed item under a certain service type, such as a product processing contract belonging to the semi-finished product processing ordering service type.

[0022] S1. Receive contract documents pending approval.

[0023] Contract documents pending approval can include survey and design contracts, construction engineering contracts, equipment procurement contracts, equipment leasing contracts, loan contracts, technical cooperation contracts, insurance contracts, consulting (supervision) contracts, supply contracts (materials and equipment supply by the owner), engineering construction contracts, etc. for various construction projects.

[0024] S2. Analyze the contract documents to be signed to obtain service items.

[0025] Specifically, the process involves extracting specific cooperation or delegation details from the contract documents to be signed, analyzing the text within those sections, and then inputting this text into a task analysis model for inference, thereby deriving the corresponding service items. This task analysis model is trained using the following method: Each text segment in the training set is labeled to indicate the service items in each segment, which are associated with all or part of the information in the text segment. A neural network is then trained using the labeled text segment training set to obtain a service item analysis model. These text segment samples are excerpts of text content related to cooperation or entrusted matters extracted from historical contract records.

[0026] S3. Filter service types that exceed the preset matching degree in the contract database based on the service items.

[0027] Combination Figure 2 S3 specifically includes: S31. Calculate the matching degree between each service type and service item.

[0028] S32. Filter out service types that exceed the preset matching degree.

[0029] The preset matching degree is a pre-defined value, such as 70%. The matching degree between each service type and the service item is calculated as follows: S311. Compare multiple historical service items in the service type with the service item to obtain the sub-matching degree between each historical service item and the service item.

[0030] S312. Calculate the service type matching degree based on the sub-matching degree of each historical service item.

[0031] Specifically, multiple historical service items within the service type are compared with the service item to obtain the sub-matching degree between each historical service item and the service item, including: By inputting historical service items and service items into the comparison model, the sub-matching degree is obtained through reasoning.

[0032] Specifically, the comparison model is trained in the following way: Each comparison sample in the comparison sample training set is labeled to indicate the sub-match degree of each comparison sample. The sub-match degree is associated with all or part of the information in the comparison sample. The neural network is trained using the labeled comparison sample training set to obtain the comparison model. The comparison sample includes a historical service item sub-sample and a service item sub-sample. The sub-match degree represents the degree of similarity between the historical service item sub-sample and the service item sub-sample.

[0033] Then, the average of the sub-matching degrees of each historical service item within the service type is taken as the matching degree of that service type, thereby enabling the calculation of the matching degree between each service type and the service item.

[0034] S4. Select the service type with the most tagging information from the filtered service types that exceed the preset matching degree as the key type.

[0035] Specifically, each service type includes multiple historical service items, and each historical service item includes at least one tag information. This allows us to count the number of tag information items for each service type and thus obtain the service type with the most tag information as the key type.

[0036] S5. Select the corresponding document analysis model based on the key type to analyze the contract documents to be approved, so as to obtain the suggested review information for the contract documents to be approved.

[0037] The suggested review information obtained through the document analysis model is the aforementioned tagging information, which also characterizes the problems existing in the contract document awaiting approval. The document analysis model is trained in the following way: Each historical contract document sample in the training set is labeled to identify its unique identifiers. The audio source type is associated with all or part of the information in the historical contract document sample. A neural network is then trained using this labeled training set to obtain a document analysis model. The historical contract document samples refer to the historical contract documents within the aforementioned contract database, and the labeled information represents the problems existing in those historical contract documents. These problems include, for example, whether the contract stipulates clear, operable, and enforceable liabilities for breach of contract; whether the contract includes warranty or guarantee provisions for the quality of the project, etc., which can be determined by the approvers by referring to the corresponding labeled information in previous historical contract documents.

[0038] S6. Mark the corresponding positions on the contract documents to be signed based on the suggested review information.

[0039] Specifically, the contract database also pre-stores a keyword lookup table, which is a pre-set table used for searching keywords. That is, keywords are recorded in advance in the table as values ​​in key-value pairs, and subsequently, only the key in the key-value pair needs to be used to search for keywords.

[0040] In one embodiment, the keyword lookup table pre-records the correspondence between suggested review information and keywords, that is, the correspondence between tagging information and keywords. In this case, the suggested review information is the key in the key-value pair, and the keyword is the value in the key-value pair. Therefore, the keyword can be used as the key to find the corresponding keyword. Then, by finding the keyword corresponding to the suggested review information in the contract document to be signed, it is marked in the appropriate position with a box or highlight, making it easy for approvers to refer to.

[0041] This application also provides an automatic contract database matching system, referring to... Figure 3 ,include: The receiving module is used to receive contract documents awaiting approval.

[0042] The analysis module is used to analyze the contract documents to be signed to obtain service items.

[0043] The filtering module is used to filter service types that exceed the preset matching degree in the contract database based on the service items. The contract database stores multiple historical contract files. Each historical contract file is associated with a historical service item. A service type is associated with multiple historical service items. Each historical service item is associated with at least one tag information.

[0044] The selection module is used to select the service type with the most tagging information as the key type from the filtered service types that exceed the preset matching degree.

[0045] The reasoning module is used to select the corresponding document analysis model based on the key type to analyze the contract documents to be approved, so as to obtain suggested review information for the contract documents to be approved.

[0046] The annotation module is used to annotate the corresponding positions on the contract documents to be signed based on the suggested review information.

[0047] The document analysis model was trained in the following way: Each historical contract document sample in the training set is labeled to identify its tagging information. The audio source type is associated with all or part of the information in the historical contract document sample. The neural network is then trained using the labeled historical contract document sample training set to obtain a document analysis model.

[0048] In one embodiment, the filtering module includes: The calculation unit is used to calculate the matching degree between each service type and the service item.

[0049] The filtering unit is used to filter out service types that exceed the preset matching degree.

[0050] The computing unit includes: The comparison sub-unit is used to compare multiple historical service items in the service type with the service item to obtain the sub-matching degree between each historical service item and the service item.

[0051] The calculation unit is used to calculate the service type matching degree based on the sub-matching degree of each historical service item.

[0052] Specifically, the comparison sub-units include: The inference micro-unit is used to input historical service items and service items into the comparison model, and infer the sub-match degree.

[0053] Specific limitations regarding the automatic contract database matching system can be found in the limitations of the automatic contract database matching method described above, and will not be repeated here. Each step of the aforementioned automatic contract database matching method can be implemented entirely or partially through software, hardware, or a combination thereof.

[0054] Various implementations of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, application-specific integrated circuits (ASICs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0055] These computational programs (also referred to as programs, software, software applications, or code) include machine instructions for a programmable processor and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms “machine-readable medium” and “computer-readable medium” refer to any computer program product, device, and / or apparatus (e.g., disk, optical disk, memory, programmable logic device (PLD)) used to provide machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term “machine-readable signal” refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0056] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0057] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0058] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this application can be achieved, and this is not limited herein.

[0059] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for automatic matching of contract databases, characterized in that, include: Receive contract documents awaiting approval; The service items are obtained by analyzing the contract documents to be signed, including: The specific cooperation or delegation details are extracted from the contract document to be signed. The text input analysis model of these specific cooperation or delegation details is crawled and used for reasoning to obtain the service items. The analysis model is trained in the following way: Each text segment in the text segment training set is labeled to indicate the service items of each text segment. The service items are associated with all or part of the information in the text segment sample. The neural network is trained using a training set of labeled text paragraph samples to obtain a problem analysis model. Based on the service items, service types with a higher than preset matching degree are filtered in the contract database. The contract database stores multiple historical contract files. Each historical contract file is associated with a historical service item. Each service type is associated with multiple historical service items. Each historical service item is associated with at least one tag information. Among them, the service types that exceed the preset matching degree in the contract database based on the service items include: Calculate the matching degree between each service type and the service item, wherein the matching degree between each service type and the service item is calculated in the following manner: The historical service items and the service items are input into the comparison model, and the sub-matching degree between each historical service item and the service item is obtained through reasoning. The average of the sub-matching degrees of each historical service item is taken as the matching degree of the service type; Filter out service types that exceed the preset matching degree; select the service type with the most tag information from the filtered service types that exceed the preset matching degree as the key type; Based on the key type, the corresponding document analysis model is selected to analyze the contract document to be approved, so as to obtain the suggested review information of the contract document to be approved. The document analysis model is trained in the following way: Each historical contract document sample in the training set is labeled to identify the tagging information of each historical contract document. The audio source type is associated with all or part of the information in the historical contract document sample. The neural network is trained using the labeled historical contract document sample training set to obtain the document analysis model. The recommended review information is marked at the corresponding locations on the contract documents pending approval, including: In the pre-stored keyword lookup table, the suggested review information is used as the key in the key-value pair, and the corresponding keyword is used as the value. Find the keywords in the contract documents to be signed and mark them in the corresponding positions using annotation boxes or highlights.

2. A contract database automatic matching system, characterized in that, include: The receiving module is used to receive contract documents awaiting approval. The analysis module is used to analyze the contract documents to be approved to obtain service items; The filtering module is used to filter service types that exceed a preset matching degree within the contract database based on the service items. The contract database stores multiple historical contract files, each associated with a historical service item. A service type is associated with multiple historical service items, and each historical service item is associated with at least one tag, including: A calculation unit is used to calculate the matching degree between each service type and the service item; The filtering unit is used to filter out service types that exceed a preset matching degree; The computing unit includes: The comparison sub-unit is used to compare multiple historical service items in the service type with the service item to obtain the sub-matching degree between each historical service item and the service item; The calculation unit is used to calculate the service type matching degree based on the sub-matching degree of each historical service item; The comparison sub-units include: The reasoning micro-unit is used to input the historical service item and the service item into the comparison model and reason to obtain the sub-matching degree; The selection module is used to select the service type with the most tagging information as the key type from the filtered service types that exceed the preset matching degree. The inference module is used to select the corresponding document analysis model based on the key type to analyze the contract document to be approved, so as to obtain the suggested review information of the contract document to be approved. The document analysis model is trained in the following way: Each historical contract document sample in the training set is labeled to identify the tagging information of each historical contract document. The audio source type is associated with all or part of the information in the historical contract document sample. The neural network is trained using the labeled historical contract document sample training set to obtain the document analysis model. The annotation module is used to annotate the corresponding positions on the contract documents to be signed based on the suggested review information.

Images