Intelligent factoring asset service platform, method and storage medium based on artificial intelligence

Abstract

The present application relates to artificial intelligence, and provides an intelligent factoring asset service platform, method and storage medium based on artificial intelligence, including: an enterprise audit module, which is used to identify enterprise files through optical character recognition technology, read enterprise data, and determine enterprise access results; an asset audit module, which is used to collect asset orders, query supplier registration information for each asset, obtain the corresponding registration information of the supplier, generate order review tasks, assign order review tasks to corresponding intelligent robot devices, complete the verification of the assets in the registration, obtain the verification results, complete the order review, and obtain the asset access results; a contract generation module, which is used to perform registration in the registration, trigger the generation of electronic contracts, push the online signing tasks corresponding to the electronic contracts to the terminal, and complete the online signing of the electronic contracts; a blockchain module, which is used to write electronic contracts into the contract sub-blockchain and write assets into the asset sub-blockchain, so as to improve the efficiency and quality of factoring business.

Description

Technical Field

[0001] The present application relates to artificial intelligence, and in particular to an artificial intelligence-based intelligent factoring asset service platform, method and storage medium. Background Art

[0002] Factoring business is the largest type of business in the supply chain finance market with potential scale. It is a receivables debt transfer business based on real trade background. That is, the factor provides commercial factoring financial solutions to the financing party, including investment and financing solutions, asset management solutions, risk management solutions, collection solutions, etc.

[0003] With the accelerated development of factoring business, the mode of large-scale manual operation and manual review has caused the asset service stage to have a long process, low efficiency, labor-intensive and high risk, which directly hinders the growth of business scale. For example, the traditional factoring asset service platform has the following problems: manual verification of the authenticity of enterprises and assets is time-consuming and easy to miss, and the efficiency of manual inspection and registration is low. Summary of the invention

[0004] Based on this, it is necessary to provide an artificial intelligence-based intelligent factoring asset service platform, method and storage medium to address the above-mentioned technical problems, which will overall reduce the factoring company's document review and manpower investment in factoring business, enhance the factoring asset management capabilities, and improve the efficiency and quality of factoring business.

[0005] An artificial intelligence-based intelligent factoring asset service platform, comprising:

[0006] An enterprise review module, used to identify enterprise documents through optical character recognition technology, read enterprise data, the enterprise data including enterprise litigation information, and determine the enterprise access result based on the enterprise data;

[0007] The asset review module is used to collect asset orders, query the supplier registration information for each asset, obtain the corresponding Zhongdeng registration information of the supplier, use the Zhongdeng registration information as a matching sample pool for machine learning, generate a corresponding order review task for each asset, and the order review task includes the Zhongdeng registration information corresponding to the asset. The order review task is assigned to the corresponding intelligent robot device. The intelligent robot device obtains the transfer information related to the asset by learning the Zhongdeng registration information in the order review task, completes the Zhongdeng registration asset verification according to the transfer information, and obtains the verification result. The order review is completed according to the verification result to obtain the asset access result;

[0008] The contract generation module is used to complete the enterprise access and asset access, and then register in the China Dictionary. After registration, it automatically triggers the generation of an electronic contract, pushes the online signing task corresponding to the electronic contract to the terminal, completes the online signing of the electronic contract, and enters the blockchain module;

[0009] The blockchain module is used to automatically trigger the writing of electronic contracts into the contract sub-blockchain after the online signing of the electronic contract is completed, and automatically trigger the writing of assets into the asset sub-blockchain after the registration is successful.

[0010] In one embodiment, the enterprise audit module includes:

[0011] The enterprise litigation information review unit is used to identify the litigation attribute status of the enterprise based on the enterprise litigation information, and when the litigation attribute status is the defendant status, obtain the association relationship between the enterprise in the plaintiff status and the preset contract type, and determine the enterprise access result based on the association relationship and the enterprise litigation information.

[0012] In one embodiment, the enterprise audit module includes:

[0013] The enterprise personnel review unit is used to identify the qualification certificates of enterprise personnel, read key information, send an identity recognition request carrying the key information to an authority, and obtain the review result of the enterprise personnel according to the recognition result corresponding to the identity recognition request.

[0014] In one embodiment, the asset audit module includes:

[0015] The invoice verification unit is used to identify the electronic invoice through optical character recognition technology, obtain the invoice element information, send an invoice verification request carrying the invoice element information to an authoritative agency, and obtain the corresponding asset access result according to the inspection result corresponding to the invoice verification request.

[0016] In one embodiment, the asset audit module includes:

[0017] The machine learning judgment unit is used to identify the invoice identification, contract identification, transaction contract name, and asset corresponding project company name in the registration information through optical character recognition technology, parse the recognition results in sequence according to the preset field order, obtain various sub-analysis results, and obtain the verification result according to the various sub-analysis results.

[0018] In one embodiment, the contract generation module includes:

[0019] The face recognition unit is used to receive the face recognition request for face signing sent by the terminal, identify the face according to the facial feature data carried in the face recognition request, and obtain the recognition result. When the recognition result is that the face recognition authentication is passed, a formal signing request is initiated to the corresponding terminal.

[0020] In one embodiment, the contract generation module includes:

[0021] The electronic signature unit is used to obtain characteristic information of the electronic signatory, produce proprietary identification data according to the characteristic information, and generate a signature carrying the proprietary identification data.

[0022] In one embodiment, the blockchain module includes:

[0023] The main chain sub-chain structural unit is used to provide global ledger maintenance through the main chain, select the corresponding consensus mechanism through the sub-chain according to the scenario identifier, and determine the association relationship between the main chain and other sub-chains according to the scenario identifier, and the association relationship includes cross-chain transactions and independent operation.

[0024] An artificial intelligence-based intelligent factoring asset service method based on the artificial intelligence-based intelligent factoring asset service platform described in any of the above embodiments, the method comprising:

[0025] Identify enterprise files through optical character recognition technology, read enterprise data, the enterprise data including enterprise litigation information, and determine enterprise access results based on the enterprise data;

[0026] Carry out asset collection, query the supplier registration information for each asset, obtain the corresponding Zhongdeng registration information of the supplier, use the Zhongdeng registration information as a matching sample pool for machine learning, generate a corresponding order review task for each asset, the order review task includes the Zhongdeng registration information corresponding to the asset, assign the order review task to the corresponding intelligent robot device, the intelligent robot device obtains the transfer information related to the asset by learning the Zhongdeng registration information in the order review task, completes the Zhongdeng registration asset verification according to the transfer information to obtain the verification result, completes the order review according to the verification result, and obtains the asset access result;

[0027] After completing enterprise access and asset access, the registration is carried out, and the electronic contract is automatically triggered after registration, and the online signing task corresponding to the electronic contract is pushed to the terminal to complete the online signing of the electronic contract;

[0028] After the online signing of the electronic contract is completed, it will automatically trigger the writing of the electronic contract into the contract sub-blockchain. After the registration in China Securities Depository and Clearing Corporation is successful, it will automatically trigger the writing of the assets into the asset sub-blockchain.

[0029] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0030] Identify enterprise files through optical character recognition technology, read enterprise data, the enterprise data including enterprise litigation information, and determine enterprise access results based on the enterprise data;

[0031] Carry out asset collection, query the supplier registration information for each asset, obtain the corresponding Zhongdeng registration information of the supplier, use the Zhongdeng registration information as a matching sample pool for machine learning, generate corresponding order review tasks for each asset, the order review tasks include the Zhongdeng registration information corresponding to the asset, assign the order review tasks to the corresponding intelligent robot devices, the intelligent robot devices obtain the transfer information related to the assets by learning the Zhongdeng registration information in the order review tasks, complete the Zhongdeng registration asset verification according to the transfer information to obtain the verification result, complete the order review according to the verification result, and obtain the asset access result;

[0032] After completing enterprise access and asset access, the registration is carried out, and the electronic contract is automatically triggered after registration, and the online signing task corresponding to the electronic contract is pushed to the terminal to complete the online signing of the electronic contract;

[0033] After the online signing of the electronic contract is completed, it will automatically trigger the writing of the electronic contract into the contract sub-blockchain. After the registration in China Securities Depository and Clearing Corporation is successful, it will automatically trigger the writing of the assets into the asset sub-blockchain.

[0034] The above-mentioned AI-based intelligent factoring asset service platform, method and storage medium use the enterprise audit module to identify enterprise documents through optical character recognition technology, read enterprise data, and the enterprise data includes litigation-related information. The enterprise access result is determined based on the enterprise data; the asset audit module is used to collect asset orders, query the supplier registration information for each asset, obtain the corresponding Zhongdeng registration information of the supplier, use the Zhongdeng registration information as a matching sample pool for machine learning, generate corresponding order review tasks for each asset, and the order review tasks include the Zhongdeng registration information corresponding to the asset. The order review tasks are assigned to the corresponding intelligent robot devices. The intelligent robot devices obtain asset-related transfer information by learning the Zhongdeng registration information in the order review tasks. The contract generation module is used to complete the enterprise access and asset access, and then conduct the registration in China. After the registration, the electronic contract is automatically triggered to be generated, and the online signing task corresponding to the electronic contract is pushed to the terminal to complete the online signing of the electronic contract and enter the blockchain module; the blockchain module is used to automatically trigger the writing of the electronic contract into the contract sub-blockchain after the online signing of the electronic contract is completed, and automatically trigger the writing of the asset into the asset sub-blockchain after the registration in China is successful. Through the cooperation of the enterprise review module, the asset review module, the contract generation module and the blockchain module, OCR (Optical Character Recognition) intelligent recognition, big data, intelligent inspection, etc. are applied to realize the intelligent review of enterprises and assets, realize intelligent review, machine learning intelligent judgment and automatic registration, and apply blockchain encryption and evidence storage technology to ensure security, which reduces the overall review and manpower investment of factoring companies in factoring business, improves the asset management capabilities of factoring, and improves the efficiency and quality of factoring business. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is an architecture diagram of an intelligent factoring asset service platform in one embodiment;

[0036] Figure 2 It is a diagram of an application environment in which an intelligent factoring asset service platform operates in one embodiment;

[0037] Figure 3 It is a structural block diagram of an intelligent factoring asset service platform in one embodiment;

[0038] Figure 4 An interactive diagram of the review process for enterprise access in an embodiment;

[0039] Figure 5 An interactive diagram of the review process for enterprise access in another embodiment;

[0040] Figure 6This is an architecture diagram of the combination of AI and RPA in one embodiment;

[0041] Figure 7 It is a flow chart of asset access review in one embodiment;

[0042] Figure 8 It is a process interaction diagram of invoice verification in one embodiment;

[0043] Fig. 9 A machine learning logic diagram in one embodiment;

[0044] Fig.10 This is a flowchart of blockchain on-chain in one embodiment;

[0045] Fig.11 A flowchart of an intelligent factoring asset service method based on artificial intelligence in one embodiment;

[0046] Fig.12 A schematic diagram of a process for implementing extremely fast loan disbursement in one embodiment;

[0047] Fig.13 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0049] The architecture of the AI-based smart factoring asset service platform provided in this application is as follows: Figure 1 As shown in the figure, the service platform can be entered through a unified entrance, which includes a computer entrance, a mobile app entrance and a standard docking entrance. The service platform is applied to multiple business scenarios. As shown in the figure, there are corresponding different functions for different objects. The entire service platform applies a variety of advanced technologies, including robots, artificial intelligence, blockchain, biometrics, OCR (Optical Character Recognition) technology, enterprise big data, electronic signing, invoice verification, etc. Figure 2 FIG. 1 is a diagram of an application environment in which an artificial intelligence-based intelligent factoring asset service platform operates in one embodiment. Figure 2As shown, the application environment includes a terminal 110, a server 120, and an organization center 130. The terminal, the server, and the organization center 130 communicate with each other through a network, and the communication network can be a wireless or wired communication network, such as an IP network, a cellular mobile communication network, etc., wherein the number of terminals, servers, and organization centers is not limited. The organization center may include, but is not limited to, an industrial and commercial big data center, a public security agency big data center, China Securities Depository and Clearing Corporation, a national tax big data center, etc.

[0050] The terminal 110 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The server may be implemented as an independent server or a server cluster consisting of multiple servers. The intelligent factoring asset service platform based on artificial intelligence may be deployed on one or more different servers.

[0051] In one embodiment, Figure 3 As shown, an artificial intelligence-based intelligent factoring asset service platform is provided, including an enterprise audit module 210, an asset audit module 220, a contract generation module 230 and a blockchain module 240.

[0052] The enterprise review module 210 is used to identify enterprise documents through optical character recognition technology, read enterprise data, and the enterprise data includes enterprise litigation information, and determine the enterprise access result based on the enterprise data.

[0053] Specifically, enterprise files are documents related to the qualifications of enterprises, such as electronic copies of business licenses, etc. Enterprise data includes but is not limited to enterprise name, enterprise type, enterprise legal representative, enterprise registration address, enterprise operation start and end dates, whether the enterprise is included in the list of abnormal operations, enterprise litigation information, etc. Among them, enterprise litigation information can be obtained from the service interface provided by external data service providers, and the specific information provided in the interface is identified by keywords to obtain enterprise litigation information.

[0054] Through OCR intelligent recognition of the company's qualification certificates and other electronic documents, key information is read, and combined with industrial and commercial, litigation-related, and blacklist big data, the company's intelligent review is completed, achieving zero manual entry and intervention review, and obtaining the company's access results. The specific steps are as follows Figure 4 As shown, the following steps are included:

[0055] Step 301: After entering the enterprise name and submitting the enterprise business license image at the terminal, a business license image recognition request is sent to the intelligent factoring asset service platform to start the enterprise access process;

[0056] Step 302: The enterprise review module in the intelligent factoring asset service platform performs OCR image recognition on the submitted business license, reads the certificate information, and verifies it with the entered enterprise name. If the two data match, proceed to the next step;

[0057] Steps 303-305: the enterprise review module uses technical means such as Qichacha to send an enterprise registration information query request to the Industrial and Commercial Big Data Center based on the enterprise name, calls the industrial and commercial big data to verify the enterprise's detailed information and business conditions, receives the enterprise registration information response message, saves and verifies the enterprise information, and proceeds to the next step if it meets the enterprise access conditions;

[0058] Steps 306-308, further query the enterprise's litigation information, send a request for querying the enterprise's litigation information to the Industrial and Commercial Big Data Center to provide data basis for enterprise access, receive a response message for the enterprise's litigation information, and parse the enterprise's litigation information. If there is too much litigation information or the litigation information contains transaction asset information, the enterprise's access will be rejected. Otherwise, the enterprise's access will be approved and the enterprise's litigation information will be saved.

[0059] In one embodiment, the enterprise audit module 210 includes:

[0060] The enterprise litigation information review unit 211 is used to identify the litigation attribute status of the enterprise based on the enterprise litigation information. When the litigation attribute status is the defendant status, the association relationship between the enterprise in the plaintiff status and the preset contract type is obtained, and the enterprise access result is determined based on the association relationship and the enterprise litigation information.

[0061] Specifically, the status of the litigation attribute includes the defendant status and the plaintiff status. For example, if Enterprise A has litigation information, it is identified whether Enterprise A is in the plaintiff status or the defendant status. If it is in the plaintiff status, the risk of breach of contract is low and the enterprise is allowed to enter. If it is in the defendant status, it is further determined whether the plaintiff is the project company corresponding to the trade contract. If the plaintiff is not the project company corresponding to the trade contract, there is no need to determine whether the dispute is caused by the contract. If the plaintiff is the project company corresponding to the trade contract, it is further determined that the contract, invoice and other elements are further determined to obtain the amount involved in the case and count the number of information involved in the case. When the amount involved in the case exceeds the preset threshold or the number of information involved in the case exceeds the preset threshold, it is determined that the enterprise access is not passed. In one embodiment, the identified valid information is displayed on the enterprise review information page.

[0062] In this embodiment, the association between the enterprise in the plaintiff status and the preset contract type is further obtained through the litigation attribute status, and the enterprise access result is determined based on the association relationship and the enterprise litigation information, which can improve the effectiveness of the enterprise access result judgment.

[0063] In one embodiment, the enterprise audit module 210 includes:

[0064] The enterprise personnel review unit 212 is used to identify the qualification certificates of enterprise personnel, read key information, send an identity recognition request carrying key information to an authority, and obtain the review result of the enterprise personnel according to the recognition result corresponding to the identity recognition request.

[0065] Specifically, through OCR intelligent recognition of personal qualification certificates and other electronic documents, key information is read, and combined with public security, litigation, and blacklist big data, the intelligent review of legal representatives and handlers is completed, achieving zero manual entry and intervention review. The specific steps are as follows Figure 5 As shown, the following steps are included:

[0066] Step 401: Submit the legal person ID card image at the terminal, send the legal person ID card identification request to the intelligent factoring asset service platform, and start the identification process;

[0067] Step 402, the enterprise personnel review unit in the enterprise review module in the intelligent factoring asset service platform uses OCR technology to recognize the submitted legal person ID card image;

[0068] In steps 403-405, the enterprise personnel review unit submits the identified information to the public security big data for real-name authentication through a legal person real-name authentication request, and obtains a real-name authentication response message. If the real-name authentication response message indicates that the authentication is successful, the review result is that the enterprise personnel review is successful, the enterprise is allowed to enter, and the legal person information is saved. Otherwise, the review result is that the enterprise personnel review has not passed and the enterprise access has not passed.

[0069] In this embodiment, by quickly identifying the qualifications and certificates of enterprise personnel, reading key information, sending an identity recognition request carrying the key information to an authoritative organization, and obtaining the review results of the enterprise personnel based on the recognition results corresponding to the identity recognition request, the review results of the enterprise personnel can be obtained quickly and efficiently, thereby determining the enterprise access pass result based on the review results of the enterprise personnel.

[0070] The asset review module 220 is used to collect asset orders and query the supplier registration information for each asset. The query obtains the corresponding Zhongdeng registration information of the supplier, and uses the Zhongdeng registration information as a matching sample pool for machine learning to generate a corresponding order review task for each asset. The order review task includes the Zhongdeng registration information corresponding to the asset. The order review task is assigned to the corresponding intelligent robot device. The intelligent robot device obtains the transfer information related to the asset by learning the Zhongdeng registration information in the order review task, completes the Zhongdeng registration asset verification based on the transfer information, and obtains the verification result. The order review is completed based on the verification result to obtain the asset access result.

[0071] Among them, there is no official standard filling example for the property transfer description in the asset registration document. It is completely different depending on the voice and context of the asset transferee. It is composed of some unstructured data and has no rules. It cannot be identified by conventional computer programming applications. Asset-related transfer information includes invoice number, transaction contract name, asset corresponding project company name, etc.

[0072] Specifically, the asset review module uses machine learning and natural language processing to enable AI robots to understand the various voices and contexts in registration, thereby helping the robot to accurately identify asset hit information during the review process, achieving intelligent review results, fully improving review and registration efficiency, and saving labor costs. In addition, the supplier's registration information will be used as a matching sample pool for machine learning and as a sample for subsequent machine learning to continuously improve the learning effect.

[0073] Among them, AI (Artificial Intelligence) is also called artificial intelligence, which is an advanced technology for studying and developing theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. RPA (Robotic Process Automation) is also called robotic process automation, which can simulate human operations and is the lowest cost and fastest solution to replace manual operations. It is suitable for data-intensive, repetitive operations and regular and fixed trigger processes.

[0074] Through cutting-edge AI technology, machine learning and natural language processing, RPA (Robotic Process Automation) is enabled, enabling RPA to optimize processes, not only replacing manual labor with machines, but also avoiding a lot of manual debugging work. In one embodiment, the architecture diagram of the combination of AI and RPA is as follows: Figure 6 As shown, this architecture is low-cost, safe and standardized, flexible to deploy, and independently developed.

[0075] In one embodiment, the specific steps of the asset audit module for asset access audit are as follows: Figure 7 As shown, the following steps are included:

[0076] Step 501: The asset review module in the intelligent factoring asset service platform collects assets through various channels;

[0077] Step 502: The asset audit module performs a supplier registration information query for each asset, and queries all the registration information of the supplier, which serves as a matching sample pool for subsequent machine learning;

[0078] Step 503: The asset review module generates a review task for each asset;

[0079] Step 504: The asset review module assigns the review task to the system according to the number of robots and the status of each robot. The task assignment can also be adjusted manually. During this process, the asset-related information, including the registration information, will be pushed to the intelligent robot simultaneously.

[0080] Step 505: After receiving the document review task, the intelligent robot starts working, learning each registration document of the supplier corresponding to the asset, and checking whether there is any transfer information related to the asset, such as the invoice number, the name of the transaction contract, the name of the project company corresponding to the asset, etc., so as to complete the document review action;

[0081] Step 5061-1: If the robot fails the document review, it generates corresponding result information and outputs it to the asset review module, and the asset review module generates corresponding document review follow-up tasks;

[0082] Step 5061-2: The asset review module dispatches the order to the customer service call center personnel based on the review results, and the customer service personnel complete the offline communication with the project company or supplier to supplement or replace the information;

[0083] Steps 5062-508: If the robot passes the review, the asset audit module generates a manual review task based on the review result, and the operator completes the asset access after review. This step is optional. As machine learning becomes more intelligent and its learning ability improves, the human review action can be gradually cancelled.

[0084] The contract generation module 230 is used to complete the enterprise access and asset access, and then perform the registration. After the registration, it automatically triggers the generation of an electronic contract, and pushes the online signing task corresponding to the electronic contract to the terminal to complete the online signing of the electronic contract and enter the blockchain module.

[0085] Specifically, after the electronic contract is generated, the online signing task can be pushed to the terminal, and online signing can be carried out with relevant factoring companies, core enterprises, project companies, and suppliers. Facial recognition can be performed before signing. The terminal sends an AI face-to-face facial recognition request to the contract generation module of the intelligent factoring asset service platform. The intelligent factoring asset service platform can initiate a formal signing action to the terminal after the facial recognition authentication is passed, thereby completing the online signing of the electronic contract.

[0086] Blockchain module 240 is used to automatically trigger the writing of electronic contracts into the contract sub-blockchain after the online signing of the electronic contract is completed, and automatically trigger the writing of assets into the asset sub-blockchain after the registration is successful.

[0087] Specifically, blockchain is a decentralized, distributed, shared ledger. Its value lies in the construction of a self-organizing network, using cryptography to generate a string of data blocks that are time-ordered and cannot be tampered with, thereby establishing a distributed consensus mechanism and realizing a decentralized trust system. The blockchain module of the smart factoring asset service platform electronically signs the electronic contracts signed by the factor and all parties, the various electronic documents finally archived by the factor, and even the collection records, and stores them through the alliance blockchain and writes them into the contract sub-blockchain, which has the advantages of anti-tampering and easy evidence collection. When the collection period exceeds the final litigation measures, blockchain technology can ensure that the chain of evidence is complete and effective. After the successful registration of the China Securities Depository and Clearing Corporation, the assets will be automatically triggered to be written into the asset sub-blockchain, which can also ensure the security of the assets. The contract sub-blockchain and the asset sub-blockchain can form cross-chain transactions or run independently. It should be emphasized that the above-mentioned electronic contracts are written into the contract sub-blockchain, and the assets are written into the asset sub-blockchain, which ensures the privacy and security of the above information and can be stored in the nodes of a blockchain.

[0088] In this embodiment, the enterprise audit module, asset audit module, contract generation module and blockchain module cooperate with each other to apply OCR intelligent recognition, big data, intelligent inspection, etc. to realize intelligent review of enterprises and assets, realize intelligent document review, machine learning intelligent judgment and automatic registration, and apply blockchain encryption and evidence storage technology to ensure security, which reduces the factoring company's overall document review and manpower investment in factoring business, improves the factoring asset management capabilities, and improves the efficiency and quality of factoring business.

[0089] In one embodiment, the asset audit module 220 includes:

[0090] The invoice verification unit 221 is used to identify the electronic invoice through optical character recognition technology, obtain invoice element information, send an invoice verification request carrying the invoice element information to an authority, and obtain the corresponding asset access result according to the verification result corresponding to the invoice verification request.

[0091] Specifically, through OCR intelligent recognition of invoices and other electronic documents, the invoice element information is identified, including the invoice number, invoice amount, invoice header information, etc., and the invoice is intelligently checked to obtain the tax bureau information to determine whether the invoice is authentic, whether it has been written off or expired. If there are such problems, it will be automatically reviewed and rejected without manual intervention. The specific steps are as follows Figure 8 As shown, the following steps are included:

[0092] Step 601, submit the invoice image at the terminal, send an invoice image recognition request to the intelligent factoring asset service platform, and start the recognition process;

[0093] Steps 602-603, the invoice inspection unit of the asset audit module in the intelligent factoring asset service platform recognizes the invoice information from the invoice image through OCR technology, eliminating the manual input process, and saves the recognized invoice information;

[0094] In step 604, the invoice verification unit submits the identified invoice element information to the national tax big data for verification through an invoice information query request, and uses the identified invoice element information, such as invoice number, code, tax-inclusive amount, tax-exclusive amount, invoice type, verification code, etc. to call the national tax big data to verify the authenticity of the invoice.

[0095] Steps 605-606, obtaining an invoice information response message. If the invoice information response message indicates that the invoice verification has passed, the recognition result is that the invoice verification has passed. Otherwise, the recognition result is that the invoice verification has not passed, and the invoice verification information is saved.

[0096] In one embodiment, the asset audit module 220 includes:

[0097] The machine learning judgment unit 222 is used to identify the invoice ID, contract ID, transaction contract name, and asset corresponding project company name in the registration information through optical character recognition technology, and parse the recognition results in sequence according to the preset field order to obtain each sub-analysis result, and obtain the verification result according to each sub-analysis result.

[0098] Specifically, if the query certificate of company A finds that the invoice number 00010001 to be transferred to the first company has already been transferred to institution B, it means that the rights transferred to the first company are defective, which is a type of hit. Machine learning is used to intelligently judge the underlying assets of the China Securities Depository and Clearing Corporation and accurately identify whether the asset information has been publicly registered or transferred. In the process of comparison, the invoice ID, contract ID, transaction contract name, and asset corresponding project company name information in the China Securities Depository and Clearing Corporation registration information are identified, and the information will be parsed in sequence according to the preset field order to obtain each sub-parsing result. The sub-parsing result includes the results obtained after the sequential comparison. The final verification result is determined based on the sub-parsing results obtained by the sequential comparison.

[0099] In one embodiment, the machine learning logic diagram is as follows Fig. 9 As shown, according to Fig. 9 The logical sequence shown obtains the comparison results in turn and finally obtains the verification result.

[0100] In this embodiment, by identifying the invoice ID, contract ID, transaction contract name, and asset corresponding project company name information in the registration information, they are parsed in sequence to obtain various sub-parsing results, and verification results are obtained based on the various sub-parsing results, thereby improving the reliability of the verification results.

[0101] In one embodiment, the contract generation module 230 includes:

[0102] The face recognition unit 231 is used to receive the face recognition request for face signing sent by the terminal, identify the face according to the facial feature data carried in the face recognition request, and obtain the recognition result. When the recognition result is that the face recognition authentication is passed, a formal signing request is initiated to the corresponding terminal.

[0103] Among them, face recognition is a biological liveness recognition technology that identifies people based on their facial features. Face recognition authentication is a technology that uses a camera or camera to collect images or video streams containing faces, and automatically detects and tracks faces in the images, accurately identifies the detected faces, and compares them with existing face data in the database to determine the identity.

[0104] Specifically, the intelligent factoring asset service platform uses facial recognition technology to perform liveness detection and identification on the legal representative and the person handling the business, ensuring that they are the ones who are performing the business operations and signing the contracts, thus avoiding the credit risk that the other party may later claim that the operations were not performed by them and therefore their actions are invalid.

[0105] In this embodiment, when the recognition result is that the face recognition authentication is passed, a formal contract signing request is initiated to the corresponding terminal, which further ensures the reliability of the contract signing.

[0106] In one embodiment, the contract generation module 230 includes:

[0107] The electronic signature unit 232 is used to obtain characteristic information of the electronic signatory, produce proprietary identification data according to the characteristic information, and generate a signature carrying the proprietary identification data.

[0108] Specifically, an electronic signature is a signature in the form of a proprietary data message produced by the electronic signatory based on the proprietary information provided by the electronic signatory under the authentication of true intention. It has four core elements: the data used to produce the electronic signature belongs to the signatory, the electronic signature production data is only controlled by the signatory when signing, any changes to the electronic signature after signing can be discovered, and any changes to the content and form of the data message after signing can be discovered.

[0109] The intelligent factoring asset service platform completes the real intention authentication by applying facial recognition authentication technology. Proprietary identification data is produced based on the characteristic information, and a signature carrying the proprietary identification data is generated. Through technical means such as hash algorithms and trusted timestamps, any changes to the electronic signature after signing can be discovered. In addition, the blockchain evidence storage technology is used in conjunction with third-party notary offices and judicial appraisal centers to ensure the integrity and authenticity of the evidence information.

[0110] The specific application scenarios are as follows: Through intelligent identity recognition and online electronic signature, the security, effectiveness and convenience of contract signing are ensured, and the electronic signature supports one-click stamping, flexible stamping, interline stamping, etc. The seal types cover corporate seals, legal representative seals, and agent seals, etc., fully meeting different business scenarios.

[0111] In one embodiment, the blockchain module 240 includes:

[0112] The main chain sub-chain structure unit 241 is used to provide global ledger maintenance through the main chain, select the corresponding consensus mechanism according to the scenario identifier through the sub-chain, and determine the association relationship between the main chain and other sub-chains according to the scenario identifier, and the association relationship includes cross-chain transactions and independent operation.

[0113] Specifically, the smart factoring alliance blockchain adopts a one-main-chain-multiple-sub-chain architecture. The main chain does not synchronize a large amount of data, but only provides global ledger maintenance functions to ensure security and decentralization. The sub-chain selects a suitable consensus mechanism based on the actual scenario, forms a two-way anchor with the main chain through cross-chain nodes, and can realize cross-chain transactions or independent operation with other sub-chains based on the actual business scenario, helping the sub-chain to obtain the final consistency provided by the main chain while improving performance. Through this hierarchical structure, security and stability are placed on the main chain, and efficiency is placed on the sub-chain to develop separate scenarios, thereby solving the impossible triangle contradiction between decentralization, security and efficiency.

[0114] The intelligent factoring asset service platform electronically signs the electronic contracts signed by the factor and all parties, the various electronic documents finally filed by the factor, and even the collection records, and stores them through the alliance blockchain, which has the advantages of anti-tampering and easy evidence collection. When the collection period has expired and the final litigation method can be taken, the blockchain technology can ensure that the chain of evidence is complete and effective.

[0115] In one embodiment, Fig.10 The specific interaction process example is as follows:

[0116] Step 701: After the intelligent document review completes the asset access, the registration is carried out, and the electronic contract is automatically generated after the registration;

[0117] Step 702: After the registration is successful, the asset will be automatically uploaded to the blockchain.

[0118] Step 703: After the electronic contract is generated and manually reviewed, the online signing task can be pushed to the terminal for online signing with the relevant factoring companies, core enterprises, project companies, and suppliers;

[0119] Step 704: Perform face recognition before signing the contract and send an AI face recognition request;

[0120] Step 705: After the face recognition authentication is passed, the formal signing operation is initiated;

[0121] Step 706, completing online signing of the electronic contract;

[0122] Step 707: After all parties to the contract have signed the contract, the transaction is completed and the contract is automatically uploaded to the blockchain.

[0123] In one embodiment, Fig.11 As shown, based on the artificial intelligence-based intelligent factoring asset service platform described in any of the above embodiments, an artificial intelligence-based intelligent factoring asset service method is provided, including:

[0124] Step 802, identifying enterprise files through optical character recognition technology, reading enterprise data, wherein the enterprise data includes enterprise litigation information, and determining the enterprise access result based on the enterprise data.

[0125] Step 804, perform asset collection, query the supplier registration information for each asset, query and obtain the corresponding Zhongdeng registration information of the supplier, use the Zhongdeng registration information as a matching sample pool for machine learning, generate corresponding order review tasks for each asset, and the order review tasks include the Zhongdeng registration information corresponding to the asset. The order review tasks are assigned to the corresponding intelligent robot devices, and the intelligent robot devices obtain the transfer information related to the assets by learning the Zhongdeng registration information in the order review tasks, complete the Zhongdeng registration asset verification according to the transfer information, and obtain the verification results, and complete the order review according to the verification results to obtain the asset access results.

[0126] Step 806, after completing enterprise access and asset access, perform registration in the central registration system. After registration, the electronic contract is automatically generated and the online signing task corresponding to the electronic contract is pushed to the terminal to complete the online signing of the electronic contract and enter step 808.

[0127] Step 808: After the online signing of the electronic contract is completed, it will automatically trigger the writing of the electronic contract into the contract sub-blockchain. After the registration in the China Securities Depository and Clearing Corporation is successful, it will automatically trigger the writing of the assets into the asset sub-blockchain.

[0128] like Fig.12 As shown, it is a flowchart of realizing extremely fast loan by using the above-mentioned intelligent factoring asset service method in a specific embodiment.

[0129] It should be understood that although Figure 4-5 , Figure 7-11 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 4-5 , Figure 7-11At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0130] For the specific definition of the intelligent factoring asset service method based on artificial intelligence, please refer to the definition of the intelligent factoring asset service platform based on artificial intelligence above, which will not be repeated here. Each module in the above-mentioned intelligent factoring asset service platform based on artificial intelligence can be implemented in whole or in part through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules, and can be distributed in multiple different servers.

[0131] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.13 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data tables. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an intelligent factoring asset service method based on artificial intelligence is implemented.

[0132] Those skilled in the art will understand that Fig.13 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0133] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: identifying enterprise files through optical character recognition technology, reading enterprise data, the enterprise data including enterprise litigation information, determining enterprise access results according to the enterprise data, performing asset collection, querying supplier registration information for each asset, querying and obtaining the corresponding Zhongdeng registration information of the supplier, using the Zhongdeng registration information as a matching sample pool for machine learning, generating corresponding order review tasks for each asset, the order review tasks including the Zhongdeng registration information corresponding to the asset, and assigning the order review tasks to corresponding intelligent robot devices, the intelligent robot devices obtain asset-related transfer information by learning the Zhongdeng registration information in the order review tasks, completing Zhongdeng registration asset verification according to the transfer information to obtain verification results, completing order review according to the verification results, obtaining asset access results, completing Zhongdeng registration after completing enterprise access and asset access, automatically triggering the generation of electronic contracts after registration, pushing the online signing tasks corresponding to the electronic contracts to the terminal to complete the online signing of the electronic contracts, automatically triggering the writing of the electronic contracts into the contract sub-blockchain after the online signing of the electronic contracts is completed, and automatically triggering the writing of the assets into the asset sub-blockchain after the Zhongdeng registration is successful.

[0134] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: identifying the litigation attribute status of the enterprise based on the litigation information of the enterprise, and when the litigation attribute status is the defendant status, obtaining the association relationship between the enterprise in the plaintiff status and the preset contract type, and determining the enterprise access result based on the association relationship and the litigation information of the enterprise.

[0135] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: identifying the qualification certificates of enterprise personnel, reading key information, sending an identity recognition request carrying the key information to an authority, and obtaining the review result of the enterprise personnel based on the recognition result corresponding to the identity recognition request.

[0136] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: identifying the electronic invoice through optical character recognition technology to obtain invoice element information, sending an invoice inspection request carrying the invoice element information to an authoritative agency, and obtaining a corresponding asset access result based on the inspection result corresponding to the invoice inspection request.

[0137] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the invoice identification, contract identification, transaction contract name, and asset corresponding project company name in the registration information are identified by optical character recognition technology, and the identification results are parsed in sequence according to the preset field order to obtain various sub-parsing results, and verification results are obtained based on the various sub-parsing results.

[0138] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: receiving a face recognition request for face-to-face signing sent by a terminal, identifying the face based on the facial feature data carried in the face-to-face signing request, and obtaining a recognition result; when the recognition result is that the facial recognition authentication is passed, initiating a formal signing request to the corresponding terminal.

[0139] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: acquiring characteristic information of the electronic signatory, producing proprietary identification data based on the characteristic information, and generating a signature carrying the proprietary identification data.

[0140] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: providing global ledger maintenance through the main chain, selecting the corresponding consensus mechanism through the sub-chain according to the scenario identifier, and determining the association relationship between the main chain and other sub-chains according to the scenario identifier, and the association relationship includes cross-chain transactions and independent operation.

[0141] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0142] This application can be applied to smart government affairs, thereby promoting the construction of smart cities.

[0143] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0144] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0145] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. An artificial intelligence-based intelligent factoring asset service platform, characterized in that: include: An enterprise audit module is used to identify enterprise files through optical character recognition technology, read enterprise data, the enterprise data includes enterprise litigation information, determine the enterprise access result according to the enterprise data, send an enterprise litigation information query request to the industrial and commercial big data center, receive the enterprise litigation information response message, parse the enterprise litigation information, if the litigation information contains transaction asset information, the enterprise access is not passed, otherwise the enterprise access is passed, and the enterprise litigation information is saved. The enterprise audit module includes: an enterprise litigation information audit unit, used to identify the enterprise's litigation attribute status according to the enterprise litigation information, when the litigation attribute status is the defendant status, obtain the association relationship between the enterprise in the plaintiff status and the preset contract type, and determine the enterprise access result according to the association relationship and the enterprise litigation information; The asset review module is used to collect asset orders, query the supplier registration information for each asset, obtain the corresponding Zhongdeng registration information of the supplier, use the Zhongdeng registration information as a matching sample pool for machine learning, generate a corresponding order review task for each asset, and the order review task includes the Zhongdeng registration information corresponding to the asset. The order review task is assigned to the corresponding intelligent robot device. The intelligent robot device obtains the transfer information related to the asset by learning the Zhongdeng registration information in the order review task, completes the Zhongdeng registration asset verification according to the transfer information, and obtains the verification result. The order review is completed according to the verification result to obtain the asset access result; The contract generation module is used to complete the enterprise access and asset access, and then register in the China Dictionary. After registration, it automatically triggers the generation of an electronic contract, pushes the online signing task corresponding to the electronic contract to the terminal, completes the online signing of the electronic contract, and enters the blockchain module; The blockchain module is used to automatically trigger the writing of the electronic contract into the contract sub-blockchain after the online signing of the electronic contract is completed, and automatically trigger the writing of the asset into the asset sub-blockchain after the registration is successful. The contract sub-blockchain and the asset sub-blockchain form a cross-chain transaction.

2. The platform according to claim 1, characterized in that The enterprise audit module is also used to display the identified valid information on the enterprise audit information page.

3. The platform according to claim 1, characterized in that: The enterprise audit module includes: The enterprise personnel review unit is used to identify the qualification certificates of enterprise personnel, read key information, send an identity recognition request carrying the key information to an authority, and obtain the review result of the enterprise personnel according to the recognition result corresponding to the identity recognition request.

4. The platform according to claim 1, characterized in that The asset audit module includes: The invoice verification unit is used to identify the electronic invoice through optical character recognition technology, obtain the invoice element information, send an invoice verification request carrying the invoice element information to an authoritative agency, and obtain the corresponding asset access result according to the inspection result corresponding to the invoice verification request.

5. The platform according to claim 1, characterized in that: The asset audit module includes: The machine learning judgment unit is used to identify the invoice identification, contract identification, transaction contract name, and asset corresponding project company name in the registration information through optical character recognition technology, parse the recognition results in sequence according to the preset field order, obtain various sub-analysis results, and obtain the verification result according to the various sub-analysis results.

6. The platform according to claim 1, characterized in that: The contract generation module includes: The face recognition unit is used to receive the face recognition request for face signing sent by the terminal, identify the face according to the facial feature data carried in the face recognition request, and obtain the recognition result. When the recognition result is that the face recognition authentication is passed, a formal signing request is initiated to the corresponding terminal.

7. The platform according to claim 1, characterized in that The contract generation module includes: The electronic signature unit is used to obtain characteristic information of the electronic signatory, produce proprietary identification data according to the characteristic information, and generate a signature carrying the proprietary identification data.

8. The platform according to claim 1, characterized in that The blockchain module includes: The main chain sub-chain structural unit is used to provide global ledger maintenance through the main chain, select the corresponding consensus mechanism through the sub-chain according to the scenario identifier, and determine the association relationship between the main chain and other sub-chains according to the scenario identifier, and the association relationship includes cross-chain transactions and independent operation.

9. An artificial intelligence-based intelligent factoring asset service method based on the artificial intelligence-based intelligent factoring asset service platform according to any one of claims 1 to 8, the method comprising: Identify enterprise files through optical character recognition technology, read enterprise data, the enterprise data includes enterprise litigation information, determine the enterprise access result according to the enterprise data, send an enterprise litigation information query request to the industrial and commercial big data center, receive the enterprise litigation information response message, parse the enterprise litigation information, if the litigation information contains transaction asset information, the enterprise access is not passed, otherwise the enterprise access is passed, and the enterprise litigation information is saved. The enterprise review module includes: an enterprise litigation information review unit, which is used to identify the enterprise's litigation attribute status according to the enterprise litigation information, when the litigation attribute status is the defendant status, obtain the association relationship between the enterprise in the plaintiff status and the preset contract type, and determine the enterprise access result according to the association relationship and the enterprise litigation information; Carry out asset collection, query the supplier registration information for each asset, obtain the corresponding Zhongdeng registration information of the supplier, use the Zhongdeng registration information as a matching sample pool for machine learning, generate a corresponding order review task for each asset, the order review task includes the Zhongdeng registration information corresponding to the asset, assign the order review task to the corresponding intelligent robot device, the intelligent robot device obtains the transfer information related to the asset by learning the Zhongdeng registration information in the order review task, completes the Zhongdeng registration asset verification according to the transfer information to obtain the verification result, completes the order review according to the verification result, and obtains the asset access result; After completing enterprise access and asset access, the registration is carried out, and the electronic contract is automatically triggered after registration, and the online signing task corresponding to the electronic contract is pushed to the terminal to complete the online signing of the electronic contract; After the online signing of the electronic contract is completed, it will automatically trigger the writing of the electronic contract into the contract sub-blockchain. After the registration in China Securities Depository and Clearing Corporation is successful, it will automatically trigger the writing of the assets into the asset sub-blockchain. The contract sub-blockchain and the asset sub-blockchain form a cross-chain transaction.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method described in claim 9 are implemented.

Images