Digital base contract intelligent identification management method and system based on AI large model

Abstract

The invention relates to the technical field of computer technology, and provides a digital base contract intelligent identification management method and system based on an AI large model, and the method comprises the following steps: obtaining the name of a signed subject in a target contract; the name of a seal main body in the target contract is recognized through an AI large model of a digital base, and the AI large model comprises a seal detection model, an arc character set detection model, a character detection model, a character processing unit and a character recognition model; judging whether the name of the sealing main body is consistent with the name of the signing main body or not; and if the name of the sealing main body is not consistent with the name of the signing main body, the target contract is classified into an invalid contract library. According to the method, the name of the seal main body in the contract can be effectively identified, so that whether the contract is an invalid contract or not is judged conveniently, and screening of the invalid contract is facilitated.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a digital base contract intelligent identification management method based on an AI big model, a digital base contract intelligent identification management system based on an AI big model, a computer device and a non-temporary computer-readable storage medium. Background Art

[0002] Digital base is a digital infrastructure based on modern technology architecture, which usually includes key components such as data platform, cloud platform, IoT platform, artificial intelligence platform, and security, monitoring and control tools. These components are interrelated and integrated to form a complete digital infrastructure system. At present, digital base is widely used in various fields such as government, enterprises, and cities. With the popularization of digital base applications, the functions and advantages of digital base in contract management have also been gradually discovered.

[0003] The management of contracts is inseparable from the identification of contract contents. Whether the original contract is in electronic or paper form, it is mostly presented in electronic document format or image format when entering the database of the digital base. Therefore, it is necessary to use technologies such as OCR (Optical Character Recognition) to identify the characters in the contract. In some contract management scenarios, in addition to recognizing the characters in the body of the contract, it is also necessary to recognize the characters in the seal. For example, when it is necessary to verify whether the company name in the seal is consistent with the company name that signed the contract, it is necessary to accurately identify the characters in the seal. However, the characters to be recognized on the seal are different from the characters that can be easily recognized by conventional OCR technology. The company name on the seal is generally arranged and rotated along an arc to adapt to the shape of the seal, rather than the conventional text arranged in a straight line and in a uniform direction. Therefore, conventional OCR and other technologies are difficult to directly recognize the characters in the seal. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a digital base contract intelligent identification management method and system based on an AI large model, which can effectively identify the name of the stamping entity in the contract, thereby facilitating the judgment of whether the contract is an invalid contract and helping to screen invalid contracts.

[0005] The technical solution adopted by the present invention is as follows: A digital base contract intelligent recognition and management method based on AI big model, comprising the following steps: obtaining the name of the signing entity in the target contract; recognizing the name of the stamping entity in the target contract through the AI ​​big model of the digital base, wherein the AI ​​big model includes a seal detection model, an arc character group detection model, a character detection model, a character processing unit and a character recognition model; judging whether the name of the stamping entity is consistent with the name of the signing entity; if the name of the stamping entity is inconsistent with the name of the signing entity, the target contract is classified into an invalid contract library.

[0006] Furthermore, the name of the stamped body in the target contract is identified through the AI ​​large model of the digital base, specifically including: detecting the seal in the target contract through the seal detection model; detecting the arc character group in the seal through the arc character group detection model; detecting each character in the arc character group through the character detection model, and determining the center point of each character; rotating each character in the arc character group to a uniform angle and arranging them along a straight line according to the center point of each character in the arc character group through the character processing unit; identifying each character arranged along a straight line and at a uniform angle through the character recognition model to obtain the name of the stamped body.

[0007] Furthermore, the character detection model is a Gliding Vertex model.

[0008] Furthermore, the character processing unit is specifically used to: fit the center point of each character in the arc-shaped character group into a corresponding arc, and determine the midpoint of the arc and the center of the circle in which the arc is located; determine the radian value between the center point of each character in the arc-shaped character group and the midpoint of the arc according to the midpoint of the arc and the center of the circle in which the arc is located; rotate each character in the arc-shaped character group according to the radian value between its center point and the midpoint of the arc to rotate to a uniform angle, and translate the center point of each character in the arc-shaped character group to a tangent passing through the midpoint of the arc.

[0009] A digital base contract intelligent recognition and management system based on an AI big model, comprising: an acquisition module, the acquisition module is used to acquire the name of the signing entity in a target contract; an identification module, the identification module is used to identify the name of the stamping entity in the target contract through the AI ​​big model of the digital base, wherein the AI ​​big model includes a seal detection model, an arc character group detection model, a character detection model, a character processing unit and a character recognition model; a judgment module, the judgment module is used to judge whether the name of the stamping entity is consistent with the name of the signing entity; a classification module, the classification module is used to classify the target contract into an invalid contract library when the name of the stamping entity is inconsistent with the name of the signing entity.

[0010] Furthermore, the recognition module is specifically used to: detect the seal in the target contract through the seal detection model; detect the arc character group in the seal through the arc character group detection model; detect each character in the arc character group through the character detection model, and determine the center point of each character; rotate each character in the arc character group to a uniform angle and arrange them along a straight line according to the center point of each character in the arc character group through the character processing unit; recognize each character arranged along a horizontal straight line and at a uniform angle through the character recognition model to obtain the name of the stamp body.

[0011] Furthermore, the character detection model is a Gliding Vertex model.

[0012] Furthermore, the character processing unit is specifically used to: fit the center point of each character in the arc-shaped character group into a corresponding arc, and determine the midpoint of the arc and the center of the circle in which the arc is located; determine the radian value between the center point of each character in the arc-shaped character group and the midpoint of the arc according to the midpoint of the arc and the center of the circle in which the arc is located; rotate each character in the arc-shaped character group according to the radian value between its center point and the midpoint of the arc to rotate to a uniform angle, and translate the center point of each character in the arc-shaped character group to a tangent passing through the midpoint of the arc.

[0013] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for intelligent identification and management of digital base contracts based on an AI big model is implemented.

[0014] A non-temporary computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the digital base contract intelligent identification and management method based on an AI big model.

[0015] Beneficial effects of the present invention: The present invention can effectively identify the name of the stamping entity in the contract through a digital base AI large model including a seal detection model, an arc character group detection model, a character detection model, a character processing unit and a character recognition model, thereby facilitating the judgment of whether the contract is an invalid contract and facilitating the screening of invalid contracts. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of a digital base contract intelligent identification and management method based on an AI big model according to an embodiment of the present invention; Figure 2A schematic diagram of an arc fitted by the center point of a character in an arc-shaped character group according to an embodiment of the present invention; Figure 3 It is a block diagram of a digital base contract intelligent identification and management system based on an AI big model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] like Figure 1 As shown, the digital base contract intelligent identification management method based on the AI ​​big model of the embodiment of the present invention includes the following steps: S1, obtain the name of the signing entity in the target contract.

[0019] In an embodiment of the present invention, the contracts to be managed can be pre-imported into the digital base, which can store the imported contracts in image format or electronic document format and intelligently identify and manage each contract. The currently identified contract is called the target contract.

[0020] In one embodiment of the present invention, the name of the signing entity in the target contract can be automatically identified from the contract text. In another embodiment of the present invention, the name of the signing entity in the target contract can also be attached to the storage information and retrieved from the storage information in this step. For example, when identifying the target contract, the signing entity information of the corresponding contract is retrieved from the storage information according to the number or sequence number of the target contract.

[0021] S2, identifying the name of the stamping entity in the target contract through the AI ​​big model of the digital base, wherein the AI ​​big model includes a seal detection model, an arc character group detection model, a character detection model, a character processing unit and a character recognition model.

[0022] Specifically, the seal in the target contract can be first detected by the seal detection model, and then the arc character group detection model can be used to detect the arc character group in the seal. Then, each character in the arc character group can be detected by the character detection model, and the center point of each character can be determined. Then, the character processing unit can be used to rotate each character in the arc character group to a uniform angle and arrange them along a straight line according to the center point of each character in the arc character group. Finally, the character recognition model can be used to identify each character arranged along a horizontal straight line and at a uniform angle to obtain the name of the stamped body.

[0023] Usually, the arc character group in the seal contains the name of the seal subject. If the seal detection model does not detect the seal in the target contract, or the arc character group detection model does not detect the arc character group in the seal, or the character detection model does not detect the characters in the arc character group, and the character recognition model does not recognize the name of the seal subject, the target contract will be directly classified into the invalid contract library.

[0024] In one embodiment of the present invention, the seal detection model and the arc character group detection model can adopt a conventional target detection model, such as a target detection model based on deep learning, such as YOLO, etc. In other embodiments of the present invention, the functions of the seal detection model and the arc character group detection model can also be implemented by template matching.

[0025] In one embodiment of the present invention, the character detection model is a Gliding Vertex model, which can accurately detect and locate each character rotated at different angles, and the center point of the detection frame is the center point of the corresponding character.

[0026] After the character detection model obtains the center point of each character, the character processing unit can fit the center point of each character in the arc-shaped character group into a corresponding arc, and determine the midpoint of the arc and the center point of the circle in which the arc is located. Then, based on the midpoint of the arc and the center point of the circle in which the arc is located, determine the radian value between the center point of each character in the arc-shaped character group and the midpoint of the arc. Then, each character in the arc-shaped character group is rotated according to the radian value between its center point and the midpoint of the arc to rotate to a uniform angle, and the center point of each character in the arc-shaped character group is translated to a tangent passing through the midpoint of the arc.

[0027] Assume that there are 9 characters in a certain arc character group, and the center points a~i of each character are fitted into Figure 2 The arc of the arc, the midpoint p of the arc is exactly point e. According to any three points in the arc, the center o of the arc (the intersection of the perpendicular bisectors of the line segments between the two points) can be determined. The radian value of the angle between the straight lines ox and op is the radian value between the center point x of the character and the midpoint of the arc, where x is a~i. After obtaining the radian value, rotate each character in the counterclockwise direction of the arc midpoint p clockwise by the corresponding radian value, and rotate each character in the clockwise direction of the arc midpoint p counterclockwise by the corresponding radian value, so that each character can be rotated to a uniform angle. After the rotation is completed, translate the center point of each character in the arc character group to the tangent line passing through the midpoint p of the arc, so that each character can be arranged along a straight line and at a uniform angle.

[0028] In one embodiment of the present invention, the character recognition model may adopt a conventional neural network model, a support vector machine model, etc.

[0029] S3, determining whether the name of the stamping entity is consistent with the name of the signing entity.

[0030] S4. If the name of the stamping entity is inconsistent with the name of the signing entity, the target contract will be included in the invalid contract database.

[0031] It should be understood that the target contracts in the invalid contract library are not confirmed invalid contracts, but are initially automatically screened contracts with a high probability of being invalid. Therefore, the contracts in the invalid contract library of the embodiment of the present invention may be further manually reviewed and confirmed later.

[0032] It should be noted that when there are multiple seals in a target contract, the name of the stamping entity corresponding to each seal can be identified separately through step S2, and the name of each stamping entity can be compared with the names of multiple signing entities of the target contract one by one. If the name of a stamping entity is consistent with the name of any signing entity, the target contract is considered to be a valid contract. When the name of any stamping entity is inconsistent with the name of each signing entity, the target contract is classified into the invalid contract library.

[0033] According to the digital base contract intelligent recognition and management method based on AI big model in the embodiment of the present invention, the name of the stamping entity in the contract can be effectively identified through the digital base AI big model including the seal detection model, the arc character group detection model, the character detection model, the character processing unit and the character recognition model, thereby facilitating the judgment of whether the contract is an invalid contract and helping to screen invalid contracts.

[0034] Corresponding to the digital base contract intelligent identification and management method based on the AI ​​big model in the above-mentioned embodiment, the present invention also proposes a digital base contract intelligent identification and management system based on the AI ​​big model.

[0035] like Figure 3 As shown, the digital base contract intelligent identification and management system based on the AI ​​big model of the embodiment of the present invention includes: an acquisition module 10, an identification module 20, a judgment module 30 and a division module 40. Among them, the acquisition module 10 is used to obtain the name of the signing subject in the target contract; the identification module 20 is used to identify the name of the stamping subject in the target contract through the AI ​​big model of the digital base, wherein the AI ​​big model includes a seal detection model, an arc character group detection model, a character detection model, a character processing unit and a character recognition model; the judgment module 30 is used to determine whether the name of the stamping subject is consistent with the name of the signing subject; the division module 40 is used to classify the target contract into the invalid contract library when the name of the stamping subject is inconsistent with the name of the signing subject.

[0036] In an embodiment of the present invention, the contracts to be managed can be pre-imported into the digital base, which can store the imported contracts in image format or electronic document format and intelligently identify and manage each contract. The currently identified contract is called the target contract.

[0037] In one embodiment of the present invention, the name of the signing entity in the target contract can be automatically identified from the contract text by the acquisition module 10. In another embodiment of the present invention, the name of the signing entity in the target contract can also be attached to the storage information, and the acquisition module 10 can retrieve it from the storage information. For example, when identifying the target contract, the acquisition module 10 retrieves the signing entity information of the corresponding contract from the storage information according to the number or serial number of the target contract.

[0038] The recognition module 20 can first detect the seal in the target contract through the seal detection model, and then detect the arc character group in the seal through the arc character group detection model, and then detect each character in the arc character group through the character detection model, and determine the center point of each character, and then through the character processing unit according to the center point of each character in the arc character group, each character in the arc character group is rotated to a uniform angle and arranged along a straight line, and finally, each character arranged along a horizontal straight line and at a uniform angle is identified through the character recognition model to obtain the name of the stamped body.

[0039] Generally, the arc character group in the seal contains the name of the seal subject. If the seal detection model does not detect the seal in the target contract, or the arc character group detection model does not detect the arc character group in the seal, or the character detection model does not detect the characters in the arc character group, and the character recognition model does not recognize the name of the seal subject, the classification module 40 directly classifies the target contract into the invalid contract library.

[0040] In one embodiment of the present invention, the seal detection model and the arc character group detection model can adopt a conventional target detection model, such as a target detection model based on deep learning, such as YOLO, etc. In other embodiments of the present invention, the functions of the seal detection model and the arc character group detection model can also be implemented by template matching.

[0041] In one embodiment of the present invention, the character detection model is a Gliding Vertex model, which can accurately detect and locate each character rotated at different angles, and the center point of the detection frame is the center point of the corresponding character.

[0042] After the character detection model obtains the center point of each character, the character processing unit can fit the center point of each character in the arc-shaped character group into a corresponding arc, and determine the midpoint of the arc and the center point of the circle in which the arc is located. Then, based on the midpoint of the arc and the center point of the circle in which the arc is located, determine the radian value between the center point of each character in the arc-shaped character group and the midpoint of the arc. Then, each character in the arc-shaped character group is rotated according to the radian value between its center point and the midpoint of the arc to rotate to a uniform angle, and the center point of each character in the arc-shaped character group is translated to a tangent passing through the midpoint of the arc.

[0043] Assume that there are 9 characters in a certain arc character group, and the center points a~i of each character are fitted into Figure 2 The arc of the arc, the midpoint p of the arc is exactly point e. According to any three points in the arc, the center o of the arc (the intersection of the perpendicular bisectors of the line segments between the two points) can be determined. The radian value of the angle between the straight lines ox and op is the radian value between the center point x of the character and the midpoint of the arc, where x is a~i. After obtaining the radian value, rotate each character in the counterclockwise direction of the arc midpoint p clockwise by the corresponding radian value, and rotate each character in the clockwise direction of the arc midpoint p counterclockwise by the corresponding radian value, so that each character can be rotated to a uniform angle. After the rotation is completed, translate the center point of each character in the arc character group to the tangent line passing through the midpoint p of the arc, so that each character can be arranged along a straight line and at a uniform angle.

[0044] In one embodiment of the present invention, the character recognition model may adopt a conventional neural network model, a support vector machine model, etc.

[0045] It should be understood that the target contracts in the invalid contract library are not confirmed invalid contracts, but are initially automatically screened contracts with a high probability of being invalid. Therefore, the contracts in the invalid contract library of the embodiment of the present invention may be further manually reviewed and confirmed later.

[0046] It should be noted that when there are multiple seals in a target contract, the name of the stamping body corresponding to each seal can be identified separately by the identification module 20, and the name of each stamping body can be compared with the names of multiple signing bodies of the target contract one by one by the judgment module 30. If the name of a stamping body is consistent with the name of any signing body, the target contract is considered to be a valid contract. When the name of any stamping body is inconsistent with the name of each signing body, the classification module 40 classifies the target contract into the invalid contract library.

[0047] According to the digital base contract intelligent recognition and management system based on the AI ​​big model of the embodiment of the present invention, the name of the stamping entity in the contract can be effectively identified through the digital base AI big model including the seal detection model, the arc character group detection model, the character detection model, the character processing unit and the character recognition model, thereby facilitating the judgment of whether the contract is an invalid contract and helping to screen invalid contracts.

[0048] Corresponding to the above embodiment, the present invention also provides a computer device.

[0049] The computer device of an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for intelligent identification and management of digital base contracts based on the AI ​​big model described in the above embodiment of the present invention can be implemented.

[0050] According to the computer device of the embodiment of the present invention, when the processor executes the computer program stored in the memory, it can effectively identify the name of the stamping entity in the contract, thereby facilitating the judgment of whether the contract is an invalid contract and facilitating the screening of invalid contracts.

[0051] Corresponding to the above embodiment, the present invention also proposes a non-transitory computer-readable storage medium.

[0052] The non-temporary computer-readable storage medium of an embodiment of the present invention stores a computer program thereon, which, when executed by a processor, can implement the digital base contract intelligent identification and management method based on the AI ​​big model according to the above embodiment of the present invention.

[0053] According to the non-temporary computer-readable storage medium of an embodiment of the present invention, when the processor executes the computer program stored thereon, it can effectively identify the name of the stamping entity in the contract, thereby facilitating the judgment of whether the contract is an invalid contract and helping to screen invalid contracts.

[0054] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0055] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0056] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0057] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0058] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0059] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0060] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0061] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0062] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0063] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A digital base contract intelligent identification and management method based on AI big model, characterized in that: The following steps are involved: Get the name of the signing entity in the target contract; Identify the name of the stamping subject in the target contract through the AI ​​big model of the digital base, wherein the AI ​​big model includes a seal detection model, an arc character group detection model, a character detection model, a character processing unit and a character recognition model; Determine whether the name of the stamping entity is consistent with the name of the signing entity; If the name of the stamping entity is inconsistent with the name of the signing entity, the target contract will be included in the invalid contract library.

2. According to claim 1, the method for intelligent identification and management of digital base contracts based on AI big model is characterized in that: The name of the stamping entity in the target contract is identified through the AI ​​big model of the digital base, including: Detecting the seal in the target contract by using the seal detection model; Detecting the arc-shaped character group in the seal by using the arc-shaped character group detection model; Detecting each character in the arc-shaped character group by using the character detection model, and determining the center point of each character; By means of the character processing unit, each character in the arc-shaped character group is rotated to a uniform angle according to the center point of each character in the arc-shaped character group and arranged along a straight line; Each character arranged along a straight line and at a uniform angle is recognized by the character recognition model to obtain the name of the stamp body.

3. The method for intelligent identification and management of digital base contracts based on AI big model according to claim 2 is characterized in that: The character detection model is a Gliding Vertex model.

4. The method for intelligent identification and management of digital base contracts based on AI big model according to claim 2 is characterized in that: The character processing unit is specifically used for: Fitting the center point of each character in the arc-shaped character group into a corresponding arc, and determining the midpoint of the arc and the center of the circle where the arc lies; Determine the arc value between the center point of each character in the arc-shaped character group and the midpoint of the arc according to the midpoint of the arc and the center point of the circle where the arc is located; Each character in the arc-shaped character group is rotated according to the arc value between its center point and the midpoint of the arc to rotate to a uniform angle, and the center point of each character in the arc-shaped character group is translated to a tangent line passing through the midpoint of the arc.

5. A digital base contract intelligent identification and management system based on AI big model, characterized in that: include: An acquisition module, the acquisition module is used to acquire the name of the signing entity in the target contract; A recognition module, the recognition module is used to recognize the name of the stamping subject in the target contract through the AI ​​large model of the digital base, wherein the AI ​​large model includes a seal detection model, an arc character group detection model, a character detection model, a character processing unit and a character recognition model; A judgment module, the judgment module is used to judge whether the name of the stamping entity is consistent with the name of the signing entity; A classification module is used to classify the target contract into an invalid contract library when the name of the stamping entity is inconsistent with the name of the signing entity.

6. The digital base contract intelligent identification and management system based on AI big model according to claim 5 is characterized in that: The identification module is specifically used for: Detecting the seal in the target contract by using the seal detection model; Detecting the arc-shaped character group in the seal by using the arc-shaped character group detection model; Detecting each character in the arc-shaped character group by using the character detection model, and determining the center point of each character; By means of the character processing unit, each character in the arc-shaped character group is rotated to a uniform angle according to the center point of each character in the arc-shaped character group and arranged along a straight line; Each character arranged along a horizontal straight line and at a uniform angle is recognized by the character recognition model to obtain the name of the stamp body.

7. The digital base contract intelligent identification and management system based on AI big model according to claim 6 is characterized in that: The character detection model is a Gliding Vertex model.

8. The digital base contract intelligent identification and management system based on AI big model according to claim 6 is characterized in that: The character processing unit is specifically used for: Fitting the center point of each character in the arc-shaped character group into a corresponding arc, and determining the midpoint of the arc and the center of the circle where the arc lies; Determine the arc value between the center point of each character in the arc-shaped character group and the midpoint of the arc according to the midpoint of the arc and the center point of the circle where the arc is located; Each character in the arc-shaped character group is rotated according to the arc value between its center point and the midpoint of the arc to rotate to a uniform angle, and the center point of each character in the arc-shaped character group is translated to a tangent line passing through the midpoint of the arc.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the digital base contract intelligent identification and management method based on the AI ​​big model according to any one of claims 1-4.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the digital base contract intelligent identification and management method based on the AI ​​big model according to any one of claims 1-4.

Images