Similar contract identification method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of contract management, and discloses a similar contract identification method and device, electronic equipment and a storage medium. The method comprises the following steps: screening a contract list to be compared from contract lists; identifying a target contract pair in the contract list to be compared, and obtaining a contract text of the target contract pair; based on the contract text of the target contract pair, extracting contract elements of each target contract in the target contract pair; and inputting the contract elements of the target contract pair into a contract comparison model to obtain a similarity comparison result of the target contract pair. According to the invention, the accuracy and processing speed of similar contract judgment are improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of contract management, and in particular, to a method, apparatus, electronic device, and storage medium for identifying similar contracts. Background Art

[0002] Large enterprises sign a huge number of contracts in their daily operations, and there may be situations where the contract contents are similar or even repeated. Similar or repeated contracts may bring the following problems: increasing audit complexity, wasting resources, causing information chaos, affecting contract execution, weakening internal control, increasing legal and compliance risks, being difficult to manage standardized, and hindering business data analysis. However, there is currently no efficient method for identifying similar contracts. Summary of the Invention

[0003] In view of the above situation, embodiments of the present application provide a method, apparatus, electronic device, and storage medium for identifying similar contracts, aiming to solve the above problems or at least partially solve the above problems.

[0004] In a first aspect, embodiments of the present application provide a method for identifying similar contracts, the method comprising: screening a list of contracts to be compared from a contract list; identifying target contract pairs in the list of contracts to be compared, and obtaining the contract texts of the target contract pairs; extracting contract elements of each target contract in the target contract pairs based on the contract texts of the target contract pairs; and inputting the contract elements of the target contract pairs into a contract comparison model to obtain a similarity comparison result of the target contract pairs.

[0005] In some embodiments, the screening a list of contracts to be compared from a contract list comprises: counting different contract counterparts in the contract list, and obtaining a contract set for each contract counterpart; traversing the contracts in the contract set of each contract counterpart pairwise; and taking the contract pairs that meet a preset condition as target contract pairs, and saving the contract information of the target contract pairs to the list of contracts to be compared.

[0006] In some embodiments, the taking the contract pairs that meet a preset condition as target contract pairs comprises: sorting the contracts of a target contract counterpart based on the application date; and if the difference between the application date of a first contract and the application date of a second contract in the target contract counterpart is within a preset time difference, and the application dates of the first contract and the second contract are adjacent, then taking the first contract and the second contract as target contract pairs.

[0007] In some embodiments, identifying the target contract pairs in the contract list to be compared and obtaining the contract texts of the target contract pairs includes: obtaining the scanned text of the target contract pairs based on the contract information in the contract list to be compared; and identifying the scanned text of the target contract pairs based on the OCR recognition technology to obtain the contract texts of the target contract pairs.

[0008] In some embodiments, extracting the contract elements of each target contract in the target contract pairs based on the contract texts of the target contract pairs includes: inputting the contract texts of the target contract pairs into a large language model respectively to obtain the contract elements of each target contract.

[0009] In some embodiments, the contract elements include at least one of the following: contract party information, contract subject matter, contract amount, payment time, payment method, liability for breach of contract, contract validity period, contract term number, confidentiality clause, contract modification and termination.

[0010] In some embodiments, the similarity comparison result includes at least one of the following: whether the target contract pairs are similar, the similarity degree of the target contract pairs, and the contract amount of the target contract pairs.

[0011] In a second aspect, an embodiment of the present application further provides a similar contract recognition device, and the device includes: a screening module, configured to screen a contract list to be compared from a contract list; an identification module, configured to identify target contract pairs in the contract list to be compared and obtain the contract texts of the target contract pairs; an extraction module, configured to extract the contract elements of each target contract in the target contract pairs; and a comparison module, configured to input the contract elements of the target contract pairs into a contract comparison model to obtain the similarity comparison result of the target contract pairs.

[0012] In some embodiments, the screening module is specifically configured to count different contract counterparties in the contract list, obtain the contract set of each contract counterparty; traverse the contracts in the contract set of each contract counterparty pairwise; use the contract pairs that meet the preset conditions as target contract pairs, and save the contract information of the target contract pairs to the contract list to be compared.

[0013] In some embodiments, the screening module is further specifically configured to sort the contracts of the target contract counterparties based on the application date; if the difference between the application date of the first contract and the application date of the second contract in the target contract counterparties is within a preset time difference and the application dates of the first contract and the second contract are adjacent, then use the first contract and the second contract as target contract pairs.

[0014] In some embodiments, the recognition module is specifically configured to obtain the scanned text of the target contract pair based on the contract information in the contract list to be compared; and recognize the scanned text of the target contract pair based on the OCR recognition technology to obtain the contract text of the target contract pair.

[0015] In some embodiments, the extraction module is specifically configured to input the contract text of the target contract pair into a large language model respectively to obtain the contract elements of each target contract.

[0016] In some embodiments, the contract elements include at least one of the following: information of both parties to the contract, subject matter of the contract, contract amount, payment time, payment method, liability for breach of contract, contract validity period, number of contract periods, confidentiality clause, modification and rescission of the contract.

[0017] In some embodiments, the similarity comparison result includes at least one of the following: whether the target contract pair is similar, the similarity degree of the target contract pair, the contract amount of the target contract pair.

[0018] In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor; and a memory arranged to store computer-executable instructions, the executable instructions when executed cause the processor to execute the steps of the first aspect above.

[0019] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device is caused to execute the steps of the first aspect above.

[0020] The above at least one technical solution adopted in the embodiments of the present application can achieve the following beneficial effects: By screening the contract list to be compared from the contract list, the scope of contracts to be compared is narrowed, and the comparison efficiency is improved; further, the target contract pair in the contract list to be compared is recognized to obtain the contract text of the target contract pair, and then the contract elements of each target contract in the target contract pair are extracted based on the contract text, avoiding the tediousness of manual screening and extracting more accurate information; finally, based on the contract elements of the target contract pair, input into the contract comparison model to obtain the similarity comparison result of the target contract pair, and the large model is used to judge the similarity of the extracted contract factors to determine whether two contracts are similar. This judgment is based on a comprehensive analysis of the contract content, rather than simply relying on simple matching or template comparison. Through the similar contract recognition method provided by the present application, the contracts are automatically screened and analyzed, combining the data analysis method with the large model, optimizing the contract screening and analysis process, and reducing manual intervention; at the same time, the large model is used to analyze similar contracts in a large amount of contract data, improving the accuracy and processing speed of the judgment. Description of the Drawings

[0021] The accompanying drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The schematic embodiments of the present application and the descriptions thereof are used to explain the present application and do not constitute an improper limitation to the present application. In the drawings:

[0022] Figure 1 The structural diagram of a similar contract recognition system provided by an embodiment of the present application is shown;

[0023] Figure 2 The flowchart of a similar contract recognition method provided by an embodiment of the present application is shown;

[0024] Figure 3 The flowchart of a similar contract recognition method provided by another embodiment of the present application is shown;

[0025] Figure 4 The structural diagram of a similar contract recognition device provided by an embodiment of the present application is shown;

[0026] Figure 5 The structural schematic diagram of an electronic device provided by an embodiment of the present application is shown. Detailed implementation manners

[0027] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments of the present application and the corresponding drawings. Apparently, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence. It should be understood that such use can be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the term "including" and its variants should be interpreted as an open-ended term meaning "including but not limited to".

[0029] As described in the background art, due to the large number of branches, large enterprises sign a huge number of contracts in their daily operations, and there may be situations where the contract contents are similar or even repeated. Similar or repeated contracts may bring the following problems:

[0030] 1) Increase the complexity of auditing

[0031] Duplicate contracts signed by branches can lead to redundant contract data, bringing greater workload and complexity to the audit work. Auditors need to spend more time checking for consistency, making it difficult to efficiently identify problematic contracts.

[0032] 2) Waste of resources

[0033] The signing of duplicate contracts wastes the enterprise's management resources, including manpower, time, and storage costs. Duplicate clauses and contracts take up space in the contract database, increasing maintenance costs and reducing management efficiency.

[0034] 3) Information chaos

[0035] Multiple contracts with similar or duplicate content may lead to information inconsistency. Especially when there are minor differences in the clause details, it is easy to cause data chaos and increase the difficulty of business management.

[0036] 4) Impact on contract execution

[0037] Duplicate contracts may cause confusion in the execution of contract clauses. Especially when the contract clauses of branches are inconsistent with the enterprise's standard contracts, it will affect the smoothness and controllability of the overall business process.

[0038] 5) Weakening of internal control

[0039] Duplicate contracts reflect the non-standardization of contract management by branches, which may expose loopholes in the enterprise's internal control and contract approval processes, weakening the effectiveness of the overall internal control system of the enterprise.

[0040] 6) Increase in legal and compliance risks

[0041] Duplicate contracts may hide unauthorized modifications, non-compliant clauses, or unclear responsibilities. If these contracts are not uniformly managed and audited, they are likely to lead to potential legal disputes or compliance risks.

[0042] 7) Difficulty in standardized management

[0043] The existence of a large number of duplicate contracts hinders the enterprise from forming a standardized contract template, resulting in the decentralization and inefficiency of the contract management process, making it difficult for the enterprise to achieve consistency and optimization in contract management.

[0044] 8) Hindrance to business data analysis

[0045] Duplicate contracts make contract data analysis more complex, increasing the difficulty of analyzing business trends or partner behavior patterns and reducing the quality and usability of data insights.

[0046] Therefore, in order to improve audit efficiency, optimize the contract management process, and reduce operational risks, it is particularly important to design an efficient method for identifying similar contracts.

[0047] Based on this, the present invention proposes a method for identifying similar contracts, which automatically screens and analyzes contracts, combines data analysis methods with large models, optimizes the contract screening and analysis process, and reduces manual intervention; at the same time, it uses large models to analyze similar contracts in large-scale contract data, improving the accuracy and processing speed of judgment.

[0048] The following describes the present application in detail through specific embodiments.

[0049] Figure 1 shows a schematic structural diagram of a similar contract identification system according to an embodiment provided by the present application. The method for identifying similar contracts provided by the embodiments of the present application can be implemented through a system such as Figure 1 and can be seen from Figure 1 The similar contract identification system includes a contract management system, a contract comparison service system, a text recognition system, and a large model system. Among them, the similar contract identification system is deployed with a similar contract identification system device ( Figure 4 ).

[0050] Specifically, the contract management system is used to manage various contracts of each branch (including the headquarters). The system includes information such as the name of the contract, document number, counterparty of the contract, application date, etc., as well as the contract PDF scan;

[0051] The contract comparison system: used to compare whether there is a possibility of similarity between two contract pairs. In this service, it is necessary to call the OCR recognition service and the large language model service, and provide a function to download the comparison result;

[0052] The OCR recognition system: extracts contract text from the contract PDF file;

[0053] The large model system: extracts key element information from the contract text content and judges whether the key element information of two contracts is similar and what the similarity is;

[0054] In some embodiments, the contract management system also includes contract business personnel, who manually check the contract pairs with high similarity in the contract similarity recognition results to avoid misjudgment by the system.

[0055] It should be noted that the present application is not limited to Figure 1 the shown similar contract identification system. Any system or device or framework that can implement the business logic of the present application is acceptable, Figure 1 which is only for exemplary illustration.

[0056] Figure 2 shows a schematic flowchart of a method for identifying similar contracts according to an embodiment provided by the present application. From Figure 2It can be seen that this method may include steps S1 to S4:

[0057] Step S1: Screen the contract list to be compared from the contract list.

[0058] Among them, the contract list is stored in the contract management system and includes various contracts of the target company and its respective branch companies. The contract list includes the application date, applicant, application department, document number, contract name, and contract counterparty of the contract, as shown in Table 1 for example.

[0059] Table 1

[0060] Application Date Applicant Application Department Application Number Contract Name Counterparty - Contract Counterparty

[0061] Generally, it is considered that under certain conditions, there is no possibility of similarity for contracts, such as contracts across branch companies or contracts that do not belong to the same contract counterparty, etc. Therefore, in order to save resources and time, the contract list to be compared is first screened out from the contract list.

[0062] Step S2: Identify the target contract pairs in the contract list to be compared and obtain the contract texts of the target contract pairs.

[0063] Specifically, read the contract list to be compared generated in the contract screening stage, traverse each row record in the contract list to be compared, and obtain contract number_contract name 1 and contract number_contract name 2; automatically obtain the specific contract 1 PDF scan file and contract 2 PDF scan file from the contract management system according to the contract number_contract name;

[0064] Since the large model cannot understand multi-page scanned PDF files well or even cannot understand them, it is necessary to first use the OCR recognition service to recognize the PDF files of contracts 1 and 2 to obtain the specific text content. The accuracy rate of OCR recognition in this stage reaches more than 99.9%, and it can ensure the relative relationship of the content, such as line breaks, spaces, etc.

[0065] Therefore, step S2 can be specifically implemented as: based on the contract information in the contract list to be compared, obtain the scanned text of the target contract pair; based on the OCR recognition technology, recognize the scanned text of the target contract pair to obtain the contract text of the target contract pair.

[0066] Step S3: Based on the contract texts of the target contract pairs, extract the contract elements of each target contract in the target contract pairs.

[0067] Since the contract has a large number of pages, directly inputting the original contract content of the target contract pair into the large model for comparison will cause the lengths of the two contracts to exceed the input range of the large model, or the overly long input length will affect the large model's understanding ability, thereby affecting the comparison effect. Therefore, the embodiments of this application adopt the method of extracting contract elements from the target contract to ensure the comparison effect.

[0068] In some embodiments, the contract elements include at least one of the following: information of both parties to the contract, subject matter of the contract, contract amount, payment time, payment method, liability for breach of contract, contract validity period, number of contract periods, confidentiality clause, modification and termination of the contract, etc.

[0069] Step S4: Input the contract elements of the target contract pair into the contract comparison model to obtain the similarity comparison result of the target contract pair.

[0070] Among them, the contract comparison model is a large language model. By training the large language model using a training set, a contract comparison model capable of determining whether two contracts are similar is obtained. Among them, the training set includes multiple contract pairs and the similarity comparison results of each contract pair.

[0071] Furthermore, save the contract number_name, contract similarity, and contract amount of the contract pairs with a high similarity comparison result in step S4 to a file and return them to the business personnel for analysis to avoid misjudgment. For example, a similarity greater than 90% is considered high similarity.

[0072] From Figure 2 As can be seen from the method shown, this application screens the contract list to be compared from the contract list, narrowing the scope of contracts to be compared and improving the comparison efficiency; further identifying the target contract pairs in the contract list to be compared, obtaining the contract texts of the target contract pairs, and then extracting the contract elements of each target contract in the target contract pairs based on the contract texts, avoiding the cumbersome manual screening and extracting more accurate information; finally, inputting the contract elements of the target contract pair into the contract comparison model to obtain the similarity comparison result of the target contract pair, and using the large model to judge the similarity of the extracted contract factors to determine whether two contracts are similar. This judgment is based on a comprehensive analysis of the contract content, rather than simply relying on simple matching or template comparison. Through the similar contract identification method provided by this application, contracts are automatically screened and analyzed, combining data analysis methods with the large model, optimizing the contract screening and analysis process, reducing manual intervention; at the same time, using the large model to analyze similar contracts in large-scale contract data, improving the accuracy and processing speed of judgment.

[0073] In some embodiments of this application, in the above method, in the above step S1, in the contract screening stage, screening the contract list to be compared from the contract list includes the following steps, as Figure 3 shown:

[0074] S11. Statistically analyze different counter-parties in the contract list to obtain the contract set of each counter-party.

[0075] S12. Traverse the contracts in the contract set of each counter-party pairwise.

[0076] S13. Use the contract pairs that meet the preset conditions as target contract pairs, and save the contract information of the target contract pairs to the contract list to be compared.

[0077] Specifically, sort the contracts of the target counter-party based on the application date; if the difference between the application date of the first contract and the second contract among the target counter-parties is within the preset time difference and the application dates of the first contract and the second contract are adjacent, then use the first contract and the second contract as the target contract pair.

[0078] Because it is considered in business that similar contracts only occur between the same counter-parties, therefore, statistically analyze different counter-parties Cs = {C1, C2, C3...} in the contract list. Traverse the counter-parties Cs. When traversing to C, retrieve all the contract records of C in the list. According to business experience, if the difference in the application dates of two contracts of the same counter-party is within half a year, then there is a possibility of similarity between the two contracts. Therefore, it is necessary to compare the application dates of the contracts of the same counter-party pairwise. To improve the comparison speed, first sort all the contracts of C in ascending order of the application date. After sorting, they are H = {h1, h2, h3...}. Traverse H. For example, for hi, then sequentially traverse the subsequent contracts h(i + n), where n > 1. If the difference in the application dates between h(i + n) and hi is within half a year, then add the contract pair information (hi, h(i + n)) to the contract pair list R to be compared, which specifically includes three fields: the counter-party, the contract hi number_contract hi name, and the contract h(i + n) number_contract h(i + n) name. At the same time, n = n + 1. If the difference in the application dates between h(i + n) and hi is outside half a year, then the traversal of contract hi terminates, and i = i + 1, that is, traverse the next contract until H is traversed. Save the contract pair list R to be compared. The contract pair list R to be compared is shown in Table 2 for example.

[0079] Table 2

[0080] Contract Counterparty Contract Number - Contract Name 1 Contract Number - Contract Name 2

[0081] In the embodiments of the present application, by combining data analysis methods with business experience, potential similar contract pairs that meet the business rules are first screened out from the contract list given by the branch. This step helps to narrow down the scope of contracts that need to be further compared, improves efficiency, and improves efficiency.

[0082] In some embodiments of the present application, in the above method, the similarity comparison results of the target contract pairs output by the large model in step S4 include at least one of the following: whether the target contract pairs are similar, the similarity degree of the target contract pairs, and the contract amounts of the target contract pairs.

[0083] For example, the similarity comparison results of the target contract pairs are as follows:

[0084] 202010016058_xx Group Fresh Food Store Sales Contract.pdf and 202008013023_xx Group Fresh Food Store Sales Contract.pdf

[0085] ```json

[0086] {

[0087] "Whether similar": "Yes",

[0088] "Similarity degree": 95%,

[0089] "Contract amount of Contract 1": "750,000 yuan",

[0090] "Contract amount of Contract 2": "750,000 yuan"

[0091] }

[0092] ```

[0093] 202105018905_xx Bank Purchase Contract.pdf and 202108027756_xx International Business Center Strategic Cooperation Tripartite Agreement.pdf

[0094] ```json

[0095] {

[0096] "Whether similar": "No",

[0097] "Similarity degree": "0%",

[0098] "Contract amount of Contract 1": "1,084,800.00 yuan",

[0099] "Contract amount of Contract 2": "3,000,000 yuan"

[0100] }

[0101] ```

[0102] In the embodiments of the present application, a large language model is used to judge the similarity of the extracted key contract factors to determine whether two contracts are similar. This judgment is based on a comprehensive analysis of the contract content, rather than simply relying on simple matching or template comparison, which improves the accuracy and processing speed of the judgment.

[0103] In some embodiments of the present application, a similar contract recognition device is provided, and the similar contract recognition device corresponds one-to-one with the similar contract recognition method in the above embodiments. As Figure 4 shown, the similar contract recognition device includes a screening module 201, an identification module 202, an extraction module 203, and a comparison module 204.

[0104] The screening module 201 is used to screen the contract list to be compared from the contract list;

[0105] The identification module 202 is used to identify the target contract pairs in the contract list to be compared and obtain the contract texts of the target contract pairs;

[0106] The extraction module 203 is used to extract the contract elements of each target contract in the target contract pair;

[0107] The comparison module 204 is used to input the contract elements of the target contract pair into the contract comparison model to obtain the similarity comparison result of the target contract pair.

[0108] In some embodiments of the present application, in the above device, the screening module 201 is specifically used to count the different contract counterparties in the contract list, obtain the contract set of each contract counterparty; traverse the contracts in the contract set of each contract counterparty pairwise; use the contract pairs that meet the preset conditions as the target contract pairs, and save the contract information of the target contract pairs to the contract list to be compared.

[0109] In some embodiments of the present application, in the above device, the screening module 201 is further specifically used to sort the contracts of the target contract counterparty based on the application date; if the difference between the application date of the first contract and the application date of the second contract in the target contract counterparty is within the preset time difference, and the application dates of the first contract and the second contract are adjacent, then use the first contract and the second contract as the target contract pair.

[0110] In some embodiments of the present application, in the above-mentioned device, the recognition module 202 is specifically configured to obtain the scanned text of the target contract pair based on the contract information in the contract list to be compared; and recognize the scanned text of the target contract pair based on the OCR recognition technology to obtain the contract text of the target contract pair.

[0111] In some embodiments of the present application, in the above-mentioned device, the extraction module 203 is specifically configured to input the contract text of the target contract pair into the large language model respectively to obtain the contract elements of each target contract.

[0112] In some embodiments of the present application, in the above-mentioned device, the contract elements include at least one of the following: contract party information, contract subject matter, contract amount, payment time, payment method, liability for breach of contract, contract validity period, contract term number, confidentiality clause, contract modification and cancellation.

[0113] In some embodiments of the present application, in the above-mentioned device, the similarity comparison result includes at least one of the following: whether the target contract pair is similar, the similarity degree of the target contract pair, the contract amount of the target contract pair.

[0114] It should be noted that any of the above-mentioned similar contract recognition devices can implement the foregoing similar contract recognition method one by one, which will not be elaborated here.

[0115] Figure 5 shows a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 5 shown, at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory, such as at least one disk memory, etc. Of course, the electronic device may also include other hardware required for other services.

[0116] The processor, network interface, and memory can be interconnected through the internal bus, and the internal bus can be an ISA (Industry Standard Architecture, industrial standard architecture) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus, or an EISA (Extended Industry Standard Architecture, extended industrial standard architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 5It is represented by only one bidirectional arrow, but it does not mean that there is only one bus or one type of bus.

[0117] A memory for storing programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0118] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a similar contract recognition device at the logical level. The processor executes the program stored in the memory and is specifically used to execute the foregoing method.

[0119] The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the foregoing method may be completed by the integrated logic circuit in the processor or the instructions in software form. The foregoing processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application may be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the foregoing method.

[0120] The electronic device can execute the similar contract recognition method provided by multiple embodiments of the present application and be implemented as a similar contract recognition device in Figure 4 the functions of the illustrated embodiments, which are not described herein again in the embodiments of the present application.

[0121] An embodiment of the present application also provides a computer-readable storage medium storing one or more programs, where the one or more programs include instructions that, when executed by an electronic device including multiple application programs, can enable the electronic device to execute the similar contract recognition method provided by multiple embodiments of the present application.

[0122] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0123] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0124] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0125] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0126] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0127] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0128] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0129] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity or device including the element.

[0130] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0131] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for identifying similar contracts, characterized in that, The method includes: Filter the contract list to be compared from the contract list; Identify the target contract pairs in the contract list to be compared, and obtain the contract texts of the target contract pairs; Based on the contract texts of the target contract pairs, extract the contract elements of each target contract in the target contract pairs; Input the contract elements of the target contract pairs into the contract comparison model to obtain the similarity comparison results of the target contract pairs.

2. The method according to claim 1, wherein The filtering the contract list to be compared from the contract list includes: Count the different contract counterparties in the contract list, and obtain the contract set of each contract counterparty; Traverse the contracts in the contract set of each contract counterparty pairwise; Take the contract pairs that meet the preset conditions as the target contract pairs, and save the contract information of the target contract pairs to the contract list to be compared.

3. The method according to claim 2, wherein The taking the contract pairs that meet the preset conditions as the target contract pairs includes: Sort the contracts of the target contract counterparty based on the application date; If the difference between the application date of the first contract and the second contract in the target contract counterparty is within the preset time difference, and the application dates of the first contract and the second contract are adjacent, then take the first contract and the second contract as the target contract pair.

4. The method according to any one of claims 1 to 3, characterized in that, The identifying the target contract pairs in the contract list to be compared and obtaining the contract texts of the target contract pairs includes: Based on the contract information in the contract list to be compared, obtain the scanned text of the target contract pairs; Based on the OCR recognition technology, recognize the scanned text of the target contract pairs to obtain the contract texts of the target contract pairs.

5. The method according to claim 1, wherein The extracting the contract elements of each target contract in the target contract pairs based on the contract texts of the target contract pairs includes: Input the contract texts of the target contract pairs into the large language model respectively to obtain the contract elements of each target contract.

6. The method according to claim 1, wherein The contract elements include at least one of the following: contract party information, contract subject matter, contract amount, payment time, payment method, liability for breach of contract, contract validity period, contract term number, confidentiality clause, contract modification and termination.

7. The method according to claim 1, wherein The similarity comparison results include at least one of the following: whether the target contract pairs are similar, the similarity degree of the target contract pairs, the contract amount of the target contract pairs.

8. A similar contract recognition device, characterized in that, The device includes: A screening module for filtering the contract list to be compared from the contract list; An identification module for identifying the target contract pairs in the contract list to be compared and obtaining the contract texts of the target contract pairs; An extraction module for extracting the contract elements of each target contract in the target contract pairs; A comparison module for inputting the contract elements of the target contract pairs into the contract comparison model to obtain the similarity comparison results of the target contract pairs.

9. An electronic device, including: A processor; And A memory arranged to store computer-executable instructions, characterized in that the executable instructions, when executed, cause the processor to execute the steps of the similar contract identification method according to any one of claims 1-7.

10. A computer-readable storage medium storing one or more programs, characterized in that, When the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device is caused to perform the steps of the similar contract recognition method as described in any one of claims 1-7.

Images