Intelligent contract drafting method, system, equipment, storage medium and program

Abstract

The invention discloses an intelligent contract drafting method, system and device, a storage medium and a program, and relates to the technical field of data identification, and the method comprises the steps: receiving a drafting instruction; analyzing the contract based on a preset contract identification rule; identifying the analyzed contract based on an identification record table to obtain an identification result; and according to the identification result, carrying out receipt backfilling. Through the processing scheme disclosed by the invention, the problems of non-standard field identification and picture identification during contract drafting are solved.

Description

Technical Field

[0001] This invention relates to the field of data recognition technology, and in particular to a method, system, device, storage medium, and program for intelligent contract drafting. Background Technology

[0002] Contract drafting is the first step in contract management and the starting point of the contract management system, so it is crucial to the entire process. Traditionally, contracts are drafted using "contract templates," "contract models," or "contract texts." These methods are all based on pre-made templates, template data, and pre-made contract text rules to complete the drafting process.

[0003] While the above-mentioned contract drafting methods can draft contracts to a certain extent, several shortcomings have been found in practical use, preventing them from achieving optimal results. These shortcomings can be summarized as follows:

[0004] (1) Poor scalability. Contract templates and sample documents support specific contract types well, but cannot meet the differentiated needs of users. Personalized user needs need to be developed separately.

[0005] (2) The maintenance workload is large and the requirements are constantly changing, so the prefabricated contract templates need to be updated frequently to meet the changing requirements.

[0006] (3) It does not support the recognition of scanned documents and non-standard fields. Traditional templates and sample documents use specific rules to extract fields, requiring 100% matching for recognition. When the contract is a scanned document or contains complex formats such as tables, it will lead to inaccurate extraction.

[0007] Therefore, it is evident that the existing contract drafting methods described above still have inconveniences and shortcomings in their use, and urgently need further improvement. Creating a new intelligent contract drafting method has become a pressing goal for the industry. Summary of the Invention

[0008] In view of this, the present disclosure provides a smart contract drafting method, which at least partially solves the problems existing in the prior art.

[0009] In a first aspect, embodiments of this disclosure provide a smart contract drafting method, the method comprising the following steps:

[0010] Receive drafting instructions;

[0011] The contract is parsed based on preset contract identification rules;

[0012] The parsed contract is identified based on the identification record table to obtain the identification result;

[0013] The form is filled back into the system based on the identification results.

[0014] According to a specific implementation of an embodiment of this disclosure, the method further includes:

[0015] Before parsing the contract, the extraction rules are selected through RAG, and a master and sub-tables of identification records are generated based on the preset mapping field information.

[0016] According to a specific implementation of an embodiment of this disclosure, the method further includes:

[0017] The system uses RAG to determine whether uploaded files contain unstructured data. When a file contains unstructured data, a multimodal large model is invoked to parse the unstructured data and recognize it as text. Unstructured data includes images and tables.

[0018] According to a specific implementation of an embodiment of this disclosure, the method further includes:

[0019] Users can complete the drafting and recognition adjustments by modifying the extraction field configuration in the built-in recognition rules.

[0020] According to a specific implementation of this disclosure, a preset contract identification rule is included, comprising: extracted field name, extracted field type, extracted field remarks, form filling mapping sub-entity, and form filling mapping field; wherein, the extracted field name includes: payment type, payment terms, contract amount, signing location, name of Party A, contract amount in words, customer, and supplier.

[0021] According to a specific implementation of an embodiment of this disclosure, the method further includes:

[0022] The identification record table is updated based on the field types of the identification results; wherein, the field types of the identification results include: reference translation type, basic type direct assignment and enumerated translation type.

[0023] Secondly, embodiments of this disclosure provide a smart contract drafting system, the system comprising:

[0024] The instruction receiving module is configured to receive drafting instructions;

[0025] The parsing module is configured to parse contracts based on preset contract identification rules;

[0026] The identification module is configured to identify the parsed contract based on the identification record table and obtain the identification result;

[0027] The backfill module is configured to backfill documents based on the identification results.

[0028] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising:

[0029] At least one processor; and,

[0030] A memory communicatively connected to the at least one processor; wherein,

[0031] The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to perform the contract intelligent drafting method as described in the first aspect or any implementation thereof.

[0032] Fourthly, embodiments of this disclosure also provide a non-transitory computer-readable storage medium storing computer instructions that, when executed by at least one processor, cause the at least one processor to perform the contract intelligent drafting method in the first aspect or any implementation thereof.

[0033] Fifthly, embodiments of this disclosure also provide a computer program product, the computer program product including a computing program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, which, when executed by a computer, cause the computer to execute the contract intelligent drafting method in the first aspect or any implementation thereof.

[0034] The intelligent contract drafting method in this embodiment solves the problem of non-standard field recognition during drafting by using user-defined contract recognition rules, RAG (Retrieval-Augmented Generation), and large model inference technology, thus meeting users' personalized customization needs. The use of a multimodal large model and RAG technology also solves the problem of recognizing tables in scanned documents and contract texts. Attached Figure Description

[0035] Figure 1 This is a schematic diagram of a smart contract drafting method provided in an embodiment of the present disclosure;

[0036] Figure 2 A flowchart of a smart contract drafting method provided in this embodiment of the disclosure;

[0037] Figure 3 This is a schematic diagram of a service deployment architecture provided in an embodiment of the present disclosure;

[0038] Figure 4 This is a schematic diagram of an operation interface for configuring identification rules provided in an embodiment of this disclosure;

[0039] Figure 5A schematic diagram of an identification rule field provided in an embodiment of this disclosure;

[0040] Figure 6 This is a schematic diagram of a contract type identification rule provided in an embodiment of the present disclosure;

[0041] Figure 7 This is a schematic diagram of a field extraction method provided in an embodiment of the present disclosure;

[0042] Figure 8 This is a schematic diagram of contract drafting operation provided in an embodiment of the present disclosure;

[0043] Figure 9 This is a schematic diagram of the structure of a smart contract drafting system provided in an embodiment of the present disclosure;

[0044] Figure 10 A schematic diagram of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0045] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0046] The following specific examples illustrate the implementation of this disclosure. Those skilled in the art can easily understand other advantages and effects of this disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. This disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this disclosure. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0047] It should be noted that the aspects described in this invention can be embodied in a wide variety of forms, and any specific structure and / or function described in this invention is merely illustrative. Based on this disclosure, those skilled in the art will understand that one aspect described in this invention can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. Furthermore, this device and / or method can be implemented using other structures and / or functionalities besides one or more of the aspects set forth in this invention.

[0048] Furthermore, specific details are provided in the following description to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the described aspects can be practiced without these specific details.

[0049] This invention provides an intelligent contract drafting method based on user rules, RAG technology, and large-scale model inference. By using large-scale models and RAG technology to process unstructured document data, the efficiency of the "contract drafting" process in the early stages of contract preparation in Contract Lifecycle Management (CLM) can be greatly improved. Furthermore, the use of multimodal large-scale models and RAG technology can solve the problems of scanned document recognition and table recognition in contract text. Users first configure contract document recognition rules, then upload the file. The large-scale model can automatically identify the information the user wants from the contract document according to the user-configured rules. The contract management backend service then automatically populates the documents with this information after data transformation.

[0050] The intelligent contract drafting process is divided into two business stages: rule configuration and intelligent drafting operation.

[0051] The recognition rule configuration allows users to configure the document field recognition rules for contract drafting according to their own needs. The document field recognition rules are a prerequisite for subsequent intelligent drafting.

[0052] The intelligent drafting process involves the user uploading a contract file, the contract backend service finding the user's configured rules based on the contract type, relying on RAG and large model inference to identify information in the contract text, and then filling the processed data back into the document.

[0053] Figure 1 This is a schematic diagram of the intelligent contract drafting method provided in this embodiment of the disclosure.

[0054] Figure 2 , Figure 8 To and Figure 1 The corresponding flowchart for the intelligent contract drafting method.

[0055] like Figure 1 As shown, at step S110, a drafting instruction is received.

[0056] More specifically, we now proceed to step S120.

[0057] In step S120, the contract is parsed based on preset contract identification rules.

[0058] In this embodiment of the invention, the method further includes: before parsing the contract, selecting extraction rules through RAG, and generating a master-sub-table of identification records based on preset mapping field information.

[0059] In this embodiment of the invention, the method further includes: determining whether the uploaded file contains unstructured data based on RAG; wherein, when the file contains unstructured data, a multimodal large model is invoked to parse the unstructured data and identify it as text; wherein, the unstructured data includes images and tables.

[0060] In this embodiment of the invention, the method further includes: the user completing the drafting and recognition adjustment by modifying the extraction field configuration in the built-in recognition rules.

[0061] like Figure 3 As shown, during the contract drafting initiation phase, the contract front-end system (browser) triggers the drafting process. Subsequently, the contract back-end system calls the RAG module to accurately extract rule configuration items at the rule configuration level and generates a master-sub-table data structure for identification records based on pre-defined mapping field information. After data generation is complete, the master-sub-table is sent back to the contract front-end (browser). At this point, the contract is in a "parsing" state, preparing for subsequent file parsing and other operations.

[0062] More specifically, the system has built-in recognition rules for commonly used contract types. Users can also copy these built-in rules and modify the extracted field configurations to meet their personalized document drafting and recognition needs. For example, if a user wants to convert the contract amount in uppercase letters to Arabic numerals for easier document backfilling, they can add "Convert contract amount from uppercase letters to number format" to the remarks section of the extracted field. During the large-scale model recognition stage of contract drafting, this conversion operation can be performed based on this description.

[0063] like Figure 4 As shown, the preset contract recognition rules include: extracted field names, extracted field types, extracted field remarks, form-filling mapping sub-entities, and form-filling mapping fields. The extracted field names include: payment type, payment terms, contract amount, signing location, client name, contract amount in words, customer, and supplier. Extracted field types include: string and numeric. Form-filling mapping sub-entities include: payment agreement, contract registration, and contract counterparty. Form-filling mapping fields include: payment type, payment terms, contract amount, signing location, contracting parties, contract amount in words, customer, and supplier. Extracted field remarks can be modified according to customer needs.

[0064] like Figure 5 As shown, the identification rule fields include contract type, transaction type, name, type, identification supplementary information, and mapping document fields.

[0065] The large model identification information includes name, type, and supplementary identification information, which is used for large model inference. It can extract the document fields that the user wants based on the modified information. The document mapping information is used in the contract management front-end and back-end services to accurately fill the identified information back into the specific document fields.

[0066] Users can create different identification rules for different contract types and transaction types. During the drafting process, a specific algorithm can be used to find the identification rules for the corresponding contract type. An algorithm illustration is shown below. Figure 6 As shown.

[0067] Furthermore, the RAG module initiates the file parsing process, performing in-depth processing on contract-related documents. Upon completion of the parsing task, it proactively sends a parsing completion event. The contract backend system captures this event message through an event listening mechanism, thereby updating the status of the identification record. At this point, the identification record status changes from the previous state to "parsing complete," signifying the end of the file parsing phase.

[0068] Next, proceed to step S130.

[0069] In step S130, the parsed contract is identified based on the identification record table to obtain the identification result.

[0070] In this embodiment of the invention, the method further includes: updating the identification record table based on the field type of the identification result; wherein, the field type of the identification result includes: reference translation type, basic type direct assignment and enumerated translation type.

[0071] More specifically, the accuracy of the extracted fields is ensured by interacting with the Prompt and the large model.

[0072] Prompt is the fundamental way for the program to interact with the large model. Each extraction rule corresponds to one or more Prompt templates (such as...). Figure 7 (As shown). The Prompt includes both basic contract field extraction descriptions and variables calculated in real-time based on the contract context. Different Prompt templates are generated based on the main and sub-tables of the business model to ensure the accuracy of the results. During contract execution, the Prompt associated with the extraction rules is executed.

[0073] Meanwhile, during contract drafting, the contract documents are pushed to the RAG service for parsing. During the parsing process, the algorithm automatically identifies whether the document is an image (scanned document). When the document is an image, the multimodal large model is called to parse the image and recognize it as text.

[0074] Furthermore, the contract backend system asynchronously calls the intelligent plugin to carry out the identification work based on the existing identification records, and updates the identification record table at the same time to ensure the real-time nature of the data.

[0075] Then, the recognition results are obtained through a scheduled task mechanism. After obtaining the recognition results and the corresponding status information, these parsing results are updated in the recognition details table.

[0076] Next, the identified record values ​​are updated according to the field type (e.g., reference translation type, direct assignment of basic types, enumerated translation types). After the value update is completed, the identification status is checked; if the identification work is completed, the process proceeds to the next step. During this stage, the contract is in the "Identifying" state, and the status is updated to "Identification Completed" after the identification is completed.

[0077] Next, proceed to step S140.

[0078] In step S140, the document is backfilled based on the identification result.

[0079] More specifically, once the identification process is complete, the contract backend system sends a message to the contract frontend system, notifying it that the identification task is finished. Subsequently, based on the identification results, the contract frontend system performs a backfilling operation on the documents, accurately filling the relevant data into the corresponding document positions, thus completing this crucial step in the entire contract processing flow.

[0080] The intelligent contract drafting method proposed in this invention solves problems such as non-standard field recognition and scanned document recognition during drafting by using user-defined contract recognition rules, RAG (Reference Aspects of Contract) and large model inference technology. It addresses issues such as the lack of flexibility and scalability of traditional drafting methods, the difficulty in maintaining contract templates and examples, the inability of traditional contract drafting to recognize images in scanned documents and contract text, the requirement for precise matching for recognition, the inability to recognize complex fields, and the inability to understand contract text.

[0081] Figure 9 The present invention illustrates a smart contract drafting system 900, which includes an instruction receiving module 910, a parsing module 920, an identification module 930, and a backfilling module 940.

[0082] The instruction receiving module 910 is used to receive drafting instructions;

[0083] The parsing module 920 is used to parse contracts based on preset contract identification rules;

[0084] The identification module 930 is used to identify the parsed contract based on the identification record table and obtain the identification result;

[0085] The backfill module 940 is used to backfill the document based on the identification result.

[0086] See Figure 10 This disclosure also provides an electronic device 100, which includes:

[0087] At least one processor; and,

[0088] The memory is communicatively connected to the at least one processor; wherein,

[0089] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the contract smart drafting method in the foregoing method embodiments.

[0090] This disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the contract intelligent drafting method in the foregoing method embodiments.

[0091] This disclosure also provides a computer program product, which includes a computing program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions that, when executed by a computer, cause the computer to perform the contract intelligent drafting method in the foregoing method embodiments.

[0092] The following is for reference. Figure 10 The diagram illustrates a structural schematic of an electronic device 100 suitable for implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 10 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0093] like Figure 10 As shown, the electronic device 100 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1008 into a random access memory (RAM) 1003. The RAM 1003 also stores various programs and data required for the operation of the electronic device 100. The processing unit 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0094] Typically, the following devices can be connected to I / O interface 1005: input devices 1006 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1007 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1008 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows electronic device 100 to communicate wirelessly or wiredly with other devices to exchange data. Although electronic device 100 with various devices is shown in the figure, it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0095] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 1009, or installed from storage device 1008, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of embodiments of this disclosure.

[0096] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0097] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0098] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: acquire at least two Internet Protocol (IP) addresses; send a node evaluation request including the at least two IP addresses to a node evaluation device, wherein the node evaluation device selects an IP address from the at least two IP addresses and returns it; and receive the IP address returned by the node evaluation device; wherein the acquired IP address indicates an edge node in a content delivery network.

[0099] Alternatively, the aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: receive a node evaluation request including at least two Internet Protocol (IP) addresses; select an IP address from the at least two IP addresses; and return the selected IP address; wherein the received IP address indicates an edge node in the content delivery network.

[0100] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0101] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0102] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The name of a unit does not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0103] It should be understood that the various parts of this disclosure can be implemented in hardware, software, firmware, or a combination thereof.

[0104] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for intelligent contract drafting, characterized in that, The method includes the following steps: Receive drafting instructions; The contract is parsed based on preset contract identification rules; The parsed contract is identified based on the identification record table to obtain the identification result; The form is filled back into the system based on the identification results.

2. The intelligent contract drafting method according to claim 1, characterized in that, The method further includes: Before parsing the contract, the extraction rules are selected through RAG, and a master and sub-tables of identification records are generated based on the preset mapping field information.

3. The intelligent contract drafting method according to claim 1, characterized in that, The method further includes: The system uses RAG to determine whether uploaded files contain unstructured data. When a file contains unstructured data, a multimodal large model is invoked to parse the unstructured data and recognize it as text. Unstructured data includes images and tables.

4. The intelligent contract drafting method according to claim 1, characterized in that, The method further includes: Users can complete the drafting and recognition adjustments by modifying the extraction field configuration in the built-in recognition rules.

5. The intelligent contract drafting method according to claim 1, characterized in that, The preset contract recognition rules include: extracted field names, extracted field types, extracted field remarks, form-filling mapping sub-entities, and form-filling mapping fields; among which, the extracted field names include: payment type, payment terms, contract amount, signing location, party A's name, contract amount in words, customer, and supplier.

6. The intelligent contract drafting method according to claim 1, characterized in that, The method further includes: The identification record table is updated based on the field types of the identification results; wherein, the field types of the identification results include: reference translation type, basic type direct assignment and enumerated translation type.

7. A smart contract drafting system, characterized in that, The system includes: The instruction receiving module is configured to receive drafting instructions; The parsing module is configured to parse contracts based on preset contract identification rules; The identification module is configured to identify the parsed contract based on the identification record table and obtain the identification result; The backfill module is configured to backfill documents based on the identification results.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, cause the at least one processor to perform the contract intelligent drafting method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions that, when executed by at least one processor, cause the at least one processor to perform the contract intelligent drafting method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computing program stored on a non-transitory computer-readable storage medium, the computer program including program instructions that, when executed by a computer, cause the computer to perform the intelligent contract drafting method as described in any one of claims 1 to 6.

Images