Electronic creditor's right certificate intelligent issuing method, system and device and storage medium

Abstract

The invention discloses an electronic creditor's right certificate intelligent issuing method, which comprises the steps of S1, enhanced data collection and preprocessing: constructing an intelligent human-computer interaction interface, realizing efficient collection of specified data, and automatically analyzing uploaded document content; s2, deep data verification and intelligent analysis: analyzing the data by using a machine learning model to ensure accuracy, and verifying the logic consistency of the creditor and debt relationship; s3, self-adaptive creditor's right voucher generation: dynamically generating an electronic creditor's right voucher meeting legal requirements and industry standards by the system; s4, security enhancement and block chain evidence storage: endowing each electronic creditor's right certificate with a unique digital signature and a unique timestamp by adopting an encryption technology and a distributed account book mechanism; and S5, integrating and optimizing an automatic process, wherein the system design is compatible with various financial ecosystems. According to the invention, full-chain intellectualization from data acquisition and analysis to automatic voucher generation can be realized, and the issuing efficiency of the electronic creditor's right voucher is greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence applications, and in particular to a method, system, device and storage medium for intelligently issuing electronic debt certificates. Background Art

[0002] Digital transformation has become a hot topic across industries, and its influence has penetrated widely into multiple fields such as high-tech, retail, finance, manufacturing, and energy. This transformation process goes deep into the core levels of information, processes, and businesses. By transforming physical operations into digital forms, it uses advanced information technology to optimize resource allocation, accelerate process efficiency, and reshape business models. Especially in asset management, the voucher circulation mechanism of digital resources has greatly improved the liquidity and management efficiency of resources, and is a key link in promoting the digitalization of businesses.

[0003] As an effective way to activate the capital flow of private enterprises and small and medium-sized enterprises and alleviate financing difficulties, the importance of debt circulation is becoming increasingly prominent. Although this model has effectively promoted the effective use of accounts receivable, the existing system still shows limitations in the issuance and circulation of vouchers, and there are still some problems, including but not limited to cumbersome application materials, time-consuming and error-prone manual review, etc. These problems seriously restrict the effective use and circulation efficiency of electronic debt certificates.

[0004] To this end, this application specifically proposes a method and system for intelligently issuing electronic debt certificates to solve the above-mentioned technical problems. Summary of the invention

[0005] The main purpose of the present invention is to provide a method and system for intelligently issuing electronic debt certificates, which can achieve fast, accurate and high-security certificate issuance by integrating advanced artificial intelligence technology, blockchain and automated workflow, so as to solve the technical problems raised in the background technology.

[0006] The present invention adopts the following technical solutions to solve the above technical problems:

[0007] A method for intelligently issuing an electronic debt certificate includes the following specific steps:

[0008] S1. Enhanced data collection and preprocessing:

[0009] Build an intelligent human-computer interaction interface, combine the API interface with the real-time connection of the financial institution database, realize the efficient collection of specified data, and automatically parse the uploaded document content by integrating OCR optical character recognition and NLP natural language processing algorithms, and use the enterprise credit information platform to automatically verify the credit status of both parties of the debt;

[0010] S2. In-depth data verification and intelligent analysis:

[0011] Using machine learning models, we can deeply analyze submitted data, automatically compare contract terms, identify potential risk points, ensure data accuracy, and verify the logical consistency of creditor-debtor relationships to prevent fraud.

[0012] S3. Adaptive creditor's rights certificate generation:

[0013] Based on the verified data, the system dynamically generates electronic debt certificates that meet legal requirements and industry standards;

[0014] S4. Security Enhancement and Blockchain Evidence Storage:

[0015] Using encryption technology and distributed ledger mechanism, each electronic debt certificate is given a unique digital signature and timestamp to ensure that the certificate cannot be tampered with and is fully traceable;

[0016] S5.Automated process integration and optimization:

[0017] The system design is compatible with various financial ecosystems and supports seamless integration with external systems.

[0018] Preferably, the electronic debt certificate generated in the step S3 supports personalized customization to meet the debt proof needs in different scenarios.

[0019] An electronic debt certificate intelligent issuance system, used to execute any of the above-mentioned electronic debt certificate intelligent issuance methods, comprising:

[0020] A front-end human-computer interaction interface is used for user operation and display of feedback information. The front-end human-computer interaction interface integrates user-friendly interaction design and supports a variety of data input methods;

[0021] The back-end processing center is equipped with a data processing module, AI analysis module, credential generation module, security evidence storage module and system integration module to achieve closed-loop management from data collection to credential application.

[0022] Preferably, the front-end human-computer interaction interface is integrated with a composite interface device for accessing the data source and completing data capture and identification.

[0023] Preferably, the front-end human-computer interaction interface is provided with:

[0024] Login and authentication module, supporting multiple login methods;

[0025] Navigation and menu bar module, through the navigation structure, quickly query the entry of debt certificate issuance, as well as help, settings, and contact customer service functions;

[0026] Intelligent form filling module, which allows users to quickly and automatically fill in forms and automatically perform verification and adjustment;

[0027] The file upload and management area module supports batch upload, allowing users to upload multiple documents at a time, and provides instant preview after uploading to ensure that the upload is correct. It can also automatically identify and mark the type and purpose of uploaded files for easy management and retrieval;

[0028] The progress tracking and status notification module provides a visual progress bar to let users know the progress of debt certificate issuance at any time, and push important notifications to users in a timely manner through in-site messages, emails or SMS when the specified progress is reached;

[0029] The help and support module is connected to the online help center and user feedback portal, providing detailed graphic tutorials and FAQs to facilitate users to make suggestions or report problems. It also supports real-time chat and integrates online customer service functions for quick manual help.

[0030] The personalized settings module allows users to customize interface themes, language preferences, and notification methods according to their own habits to enhance the personalized experience.

[0031] Preferably, the intelligent form filling module integrates dynamic form function, automatic filling function and real-time verification and prompt function, wherein:

[0032] The dynamic form function is used to automatically adjust the fields required to be filled in according to the type of claim selected by the user, thereby reducing unnecessary input;

[0033] The auto-fill function uses optical character recognition and natural language processing algorithms to automatically capture and fill in relevant information after the user uploads the file, reducing the workload of manual input;

[0034] The real-time verification and prompt function is used to instantly check the input information, and immediately provide clear feedback and guidance for incorrect or incomplete input to help users correct it quickly.

[0035] Preferably, the back-end processing center is provided with:

[0036] The data processing module realizes data collection by receiving data submitted by the front end and automatically collecting original data related to the debt certificate as needed; making full use of optical character recognition and natural language processing algorithms to format and deduplicate the collected original data, identify the content on the acquired media carrier, ensure data quality, and extract and construct key features that are helpful for subsequent analysis.

[0037] The AI ​​analysis module uses machine learning and deep learning algorithms to train historical data, build prediction models, analyze new data based on the trained models, and generate decision-making recommendations for debt certificate issuance, including providing key elements in debt certificates;

[0038] The voucher generation module is used to submit a standard debt voucher template that meets legal requirements, and cooperate with the front end to personalize the template, and finally generate a specific debt voucher based on the AI ​​analysis results and user configuration;

[0039] The secure evidence storage module uses an encryption algorithm to encrypt the debt certificate data, uses blockchain technology to store the debt certificate data on the chain, and uses digital signature technology to ensure the authenticity and integrity of the debt certificate.

[0040] The system integration module provides an open API internally to facilitate docking with other systems, expand the application scenarios of the system, and achieve data sharing and service collaboration through integration with other systems, thereby realizing the intelligent issuance of debt certificates.

[0041] Preferably, the specific operation process of using the deep learning model in the A1 analysis module to automatically identify and extract key information from the debt basis text includes:

[0042] L1. Preprocessing operations:

[0043] Use the pre-trained language model to convert the input debt basis text into a semantic vector representation:

[0044] H=BERT(T)

[0045] Where T represents the input text, H is the embedded representation of the text, H = [h1, h2, ..., h n ],h i Represents the embedding vector of the i-th character;

[0046] L2. Encoding operation:

[0047] (1) An improved position encoding mechanism is introduced to enhance the model’s ability to perceive vocabulary boundaries. The position encoding vector P ij The method to obtain is:

[0048] P ij =Concatenate(Sin(f(pos i )), Cos(f(pos j )))

[0049] Here, f(·) is a mapping function from a position to an embedding space, pos i and pos j Represent the positions of vocabulary i and j respectively;

[0050] (2) Position encoding vector P ij is added to the text embedding vector to form an enhanced vector representation:

[0051] H'=H+P

[0052] Among them, P is a matrix, each row of which corresponds to the position code of the corresponding character in the text;

[0053] (3) Use the self-attention mechanism to enhance the degree of association between entities and enhance information sharing between relationships and entities:

[0054]

[0055] Among them, Q, K, and V represent query, key, and value matrices, respectively;

[0056] Q=WQH'

[0057] K=WKH'

[0058] V=WVH'

[0059] WQ, WK, WV are weight matrices and dk is the dimension of the key vector.

[0060] (4) The output A of the attention mechanism is added to the enhanced text embedding vector to form the final encoded representation: H” = H’ + A:

[0061] L3.Decoding operation:

[0062] Use conditional random fields to obtain label predictions for the input sequence by maximizing the following formula:

[0063]

[0064] in, Indicates that from label y t-1 to the weight of yt, is the label y t The eigenvector of t from the final encoded representation H".

[0065] On the other hand, the present invention further discloses a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the above method.

[0066] On the other hand, the present invention further discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above method.

[0067] It can be seen from the above technical solution that the present invention provides a method for intelligently issuing electronic debt certificates.

[0068] Compared with the prior art, the present invention has the following advantages:

[0069] 1. The method of the present invention deeply integrates artificial intelligence and financial technology, and utilizes the integrated application of artificial intelligence algorithms, machine learning, natural language processing and big data analysis technologies to realize the intelligence of the entire chain from data collection and analysis to the automatic generation of vouchers, thereby greatly improving the efficiency of issuing electronic debt certificates.

[0070] 2. The system of the present invention integrates diversified data input and composite interface devices by setting up a human-computer interaction interface at the front end, which can realize user-friendly operation and efficient data collection, thereby achieving preliminary intelligent and efficient data processing. Combined with the AI ​​analysis module at the back end, it can deeply mine and analyze the submitted data, effectively identify risks and ensure data accuracy, enhance the rigor of the verification of creditor-debtor relationships, prevent fraud, and improve transaction security.

[0071] 3. The system of the present invention uses an adaptive debt certificate generation module to dynamically output electronic certificates that comply with regulations based on verification results, thereby achieving personalization and standardization of debt certificate issuance, greatly improving business flexibility and compliance. In addition, with the help of security enhancement and blockchain evidence storage technology, each certificate is given a digital signature and timestamp to ensure its non-tamperability and full traceability, thereby consolidating the legal effect and trust basis of electronic certificates.

[0072] 4. Through automated process integration and optimized design, the present invention achieves broad compatibility with the financial ecosystem, promotes seamless connection of payment, clearing and other links, and improves the overall consistency and response speed of financial services. It not only simplifies the debt processing process, but also significantly enhances the transparency of the financial market and transaction efficiency.

[0073] 5. The AI ​​analysis module of the present invention uses a deep learning model to automatically identify and extract key information from the debt basis text, and introduces an improved position encoding mechanism through preprocessing, encoding and decoding operations to enhance the model's perception of vocabulary boundaries, which can improve the accuracy and efficiency of the system in automatically identifying and extracting key information from the debt basis text.

[0074] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become easy to understand through the following description. Of course, it is not necessary to achieve all of the advantages described above simultaneously for any product implementing the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] The drawings constituting a part of the present application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0076] Figure 1 It is a schematic diagram of the process of the present invention;

[0077] Figure 2 It is a schematic diagram of the structural framework of the system of the present invention. DETAILED DESCRIPTION

[0078] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. In the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0079] In the embodiment, see Figure 1 to Figure 2 .

[0080] like Figure 1 The method for intelligently issuing electronic debt certificates proposed in the embodiment of the present invention aims to achieve fast, accurate and high security of certificate issuance by integrating advanced artificial intelligence technology, blockchain and automated workflow, and includes the following specific operation steps:

[0081] S1. Enhanced data collection and preprocessing:

[0082] Build an intelligent human-computer interaction interface, combine the API interface with the real-time connection of the financial institution database, and realize the efficient collection of key data such as creditor information and debt details. By integrating OCR technology (optical character recognition) and NLP (natural language processing) algorithm, the uploaded document content can be automatically parsed, greatly reducing the burden of manual input. At the same time, with the help of the authoritative corporate credit information platform, the credit status of both parties of the debt can be automatically verified;

[0083] S2. In-depth data verification and intelligent analysis:

[0084] Using machine learning models, we can deeply analyze submitted data, automatically compare contract terms, identify potential risk points, ensure data accuracy, and verify the logical consistency of creditor-debtor relationships to prevent fraud.

[0085] S3. Adaptive creditor's rights certificate generation:

[0086] Based on the verified data, the system dynamically generates electronic debt certificates that meet legal requirements and industry standards. The generated electronic debt certificates support personalized customization to meet the debt proof needs in different scenarios;

[0087] S4. Security Enhancement and Blockchain Evidence Storage:

[0088] Using encryption technology and distributed ledger mechanism, each electronic debt certificate is given a unique digital signature and timestamp to ensure that the certificate cannot be tampered with and is fully traceable, significantly improving the legal effect and credibility of the certificate;

[0089] S5.Automated process integration and optimization:

[0090] The system design is compatible with various financial ecosystems, supports seamless integration with external systems such as payment, clearing, and auditing, achieves broad compatibility with the financial ecosystem, promotes seamless connection of payment, clearing and other links, and improves the overall consistency and responsiveness of financial services. It not only simplifies the debt processing process, but also significantly enhances financial market transparency and transaction efficiency, and realizes full-chain automation from voucher issuance to execution and settlement, greatly improving processing speed and reducing operating costs.

[0091] This method deeply integrates artificial intelligence and financial technology, and utilizes the integrated application of artificial intelligence algorithms, machine learning, natural language processing and big data analysis technologies. It can realize the intelligence of the entire chain from data collection and analysis to the automatic generation of certificates, greatly improving the efficiency of issuing electronic debt certificates.

[0092] On the other hand, Figure 2 As shown, the present invention also discloses an electronic debt certificate intelligent issuance system, which uses cutting-edge artificial intelligence algorithms, machine learning, natural language processing and big data analysis technologies to achieve full-chain intelligence from data collection, analysis to automatic voucher generation, innovates the issuance mode of debt certificates, and is used to execute any of the above-mentioned electronic debt certificate intelligent issuance methods, including:

[0093] The front-end human-computer interaction interface integrates user-friendly interactive design and supports a variety of data input methods for user operation and display feedback information. The front-end human-computer interaction interface integrates user-friendly interactive design and supports a variety of data input methods;

[0094] The back-end processing center is equipped with multiple functional modules, including data processing module, AI analysis module, credential generation module, security evidence module and system integration module, to achieve closed-loop management from data collection to credential application.

[0095] Furthermore, the front-end human-computer interaction interface is integrated with a composite interface device to provide a system front-end interface that is convenient for user operation and display of feedback information, and is used to access the data source and complete data capture and identification.

[0096] Furthermore, the human-computer interaction interface front end provided can also be accessed through a browser on various computers, mobile phones and other tools, and can also be used to integrate into the self-service voucher issuance machine display interaction. The front-end human-computer interaction interface is set up with:

[0097] The login and authentication module supports a variety of safe and convenient login methods, such as account password, mobile phone verification code, biometric authentication, etc., ensuring the security of user accounts while providing a quick way to enter the system;

[0098] The navigation and menu bar module has a clear navigation structure and functions of help, settings, and contacting customer service. Through the navigation structure, you can quickly find the entry point for issuing debt certificates;

[0099] The intelligent form filling module is used for users to quickly and automatically fill in forms and automatically verify and adjust them. It integrates dynamic form function, automatic filling function and real-time verification and prompt function. Among them: the dynamic form function is used to automatically adjust the fields required to be filled in according to the type of debt selected by the user, reducing unnecessary input; the automatic filling function uses optical character recognition and natural language processing algorithms to automatically capture and fill in relevant information after the user uploads documents such as identity cards and contracts, reducing the workload of manual input; the real-time verification and prompt function is used to instantly verify the input information, and immediately give clear feedback and guidance for incorrect or incomplete input to help users quickly correct it;

[0100] The file upload and management area module supports batch upload, allowing users to upload multiple documents at one time, such as scanned contracts, financial statements, etc. It also provides a file preview function, providing an instant preview after uploading to ensure that the upload is correct, and can automatically identify and mark the type and purpose of the uploaded file for easy management and search;

[0101] The progress tracking and status notification module provides a visual progress bar, allowing users to understand the progress of debt voucher issuance at any time, including the status of each stage such as data verification, review, and generation. When the specified progress is reached, important notifications such as review results, completion of voucher generation, etc. are pushed to users in a timely manner through in-site messages, emails, or SMS;

[0102] The Help and Support module is connected to the online help center and user feedback portal. The online help center is used to provide detailed graphic tutorials and FAQs, and the user feedback portal is used to encourage users to make suggestions or report problems to continuously optimize services. In addition, this module also supports real-time chat and integrates online customer service functions to enable users to quickly obtain manual help when they encounter problems.

[0103] The personalized settings module allows users to customize interface themes, language preferences, notification methods, etc. according to their own habits to enhance the personalized experience.

[0104] In summary, by setting up a human-computer interaction interface at the front end to integrate diversified data input and composite interface devices, user-friendly operation and efficient data collection can be achieved, thereby achieving preliminary intelligent and efficient data processing.

[0105] Furthermore, the backend processing center is provided with:

[0106] The data processing module realizes data collection, receives data submitted by the front end through API interface, file upload and other methods, and automatically collects original data related to debt certificates as needed; makes full use of optical character recognition and natural language processing algorithms to format and deduplicate the collected original data, identifies the content on various media carriers such as text and pictures, ensures data quality, and extracts and constructs key features that are helpful for subsequent analysis.

[0107] The AI ​​analysis module uses machine learning and deep learning algorithms to train historical data and establish a prediction model. Based on the trained model, it analyzes new data and generates decision-making recommendations for the issuance of debt certificates, including providing key elements of debt certificates, such as creditor and debtor information, debt amount, term, interest, repurchase method, etc. This module can deeply mine and analyze submitted data, effectively identify risks and ensure data accuracy, enhance the rigor of creditor-debtor relationship verification, prevent fraud, and improve transaction security by combining user-friendly operation and efficient data collection achieved by the front-end human-computer interaction interface setting.

[0108] The voucher generation module is used to submit a standard debt voucher template that meets legal requirements, and cooperate with the front end to personalize the template, such as adding specific terms, adjusting the style, etc. Finally, a specific debt voucher is generated based on the AI ​​analysis results and user configuration. At this time, the adaptive debt voucher generation module can dynamically output electronic vouchers that comply with regulations based on the verification results, realizing the personalization and standardization of debt voucher issuance, greatly improving business flexibility and compliance. In addition, with the help of security enhancement and blockchain evidence storage technology, each voucher is given a digital signature and timestamp to ensure its tamper-proof and full traceability, consolidating the legal effect and trust foundation of electronic vouchers;

[0109] The secure evidence storage module uses encryption algorithms to encrypt the debt certificate data to ensure the security of data transmission and storage, uses blockchain technology to store the debt certificate data on the chain to enhance the credibility of the certificate, and ensures the authenticity and integrity of the debt certificate through digital signature technology.

[0110] The system integration module is mainly used for the intelligent issuance of debt certificates. It provides an open API internally to facilitate docking with other systems, expand the application scenarios of the system, and realize data sharing and service collaboration through integration with other systems (such as debt circulation system, etc.).

[0111] The design of the entire backend system follows the principle of closed-loop management, that is, starting from data collection, through processing, analysis, and voucher generation, to voucher storage and application, a complete business process closed loop is formed. This process ensures that each link can be completed efficiently and accurately, and also facilitates subsequent tracking and auditing.

[0112] In summary, the intelligent issuance system of electronic debt certificates of the present invention, through deep integration of artificial intelligence and financial technology, has created a new era of efficient, secure and automated debt certificate processing. Through the implementation of the present invention, the issuance process of electronic debt certificates has been completely innovated, which not only greatly improves the processing efficiency and accuracy, but also significantly enhances the security and legal effect of the certificates, bringing more convenient, efficient and reliable debt management solutions to the financial market, and promoting the comprehensive digital upgrade of financial business processes.

[0113] Furthermore, the AI ​​analysis module uses a deep learning model to automatically identify and extract key information from the debt basis text, such as the creditor, debtor, amount, etc. The specific operation process includes:

[0114] L1. Preprocessing operations:

[0115] Use the pre-trained language model (BEBR) to convert the input debt text into a semantic vector representation:

[0116] H=BERT(T)

[0117] Where T represents the input text, H is the embedded representation of the text, H = [h1, h2, ..., h n ],h i Represents the embedding vector of the i-th character;

[0118] L2. Encoding operation:

[0119] (1) An improved position encoding mechanism is introduced to enhance the model’s ability to perceive vocabulary boundaries. The position encoding vector P ij The method to obtain is:

[0120] P ij =Concatenate(Sin(f(pos i )), Cos(f(pos j )))

[0121] Here, f(·) is a mapping function from a position to an embedding space, pos i and pos j Represent the positions of vocabulary i and j respectively;

[0122] (2) Position encoding vector P ij is added to the text embedding vector to form an enhanced vector representation:

[0123] H'=H+P

[0124] Among them, P is a matrix, each row of which corresponds to the position code of the corresponding character in the text;

[0125] (3) Use the self-attention mechanism to enhance the degree of association between entities and enhance information sharing between relationships and entities:

[0126]

[0127] Among them, Q, K, and V represent query, key, and value matrices, respectively;

[0128] Q=WQH'

[0129] K=WKH'

[0130] V=WVH'

[0131] WQ, WK, WV are weight matrices and dk is the dimension of the key vector.

[0132] (4) The output A of the attention mechanism is added to the enhanced text embedding vector to form the final encoding representation: H” = H’ + A;

[0133] L3.Decoding operation:

[0134] Use conditional random fields to obtain label predictions for the input sequence by maximizing the following formula:

[0135]

[0136] in, Indicates that from label y t-1 to y t The weight of is the label y t The eigenvector of t from the final encoded representation H".

[0137] Through the above steps, a deep learning model is used to automatically identify and extract key information from the debt basis text, and through preprocessing, encoding and decoding operations in sequence, an improved positional encoding mechanism is introduced to enhance the model's perception of vocabulary boundaries, which can improve the accuracy and efficiency of the system in automatically identifying and extracting key information from the debt basis text.

[0138] Furthermore, the specific operation process of generating a specific debt certificate according to the AI ​​analysis results and user configuration in the certificate generation module can be expressed in pseudo code, including:

[0139] enter:

[0140] templates (voucher template collection),

[0141] debt_info (debt information),

[0142] customization_requirements (customization requirements),

[0143] user_expectations (user expectations),

[0144] adaptive_threshold (adaptive threshold),

[0145] max_fitness_evaluations (maximum number of fitness function evaluations),

[0146] legal_requirements (legal and regulatory requirements)

[0147] Output:

[0148] optimal_certificate (optimal certificate)

[0149] 1. Clean debt information debt_info and extract key information;

[0150] 2. Automatically classify creditor's rights information according to legal requirements;

[0151] 3. Identify keywords related to creditor's rights and laws and regulations;

[0152] 4. Initialize the Q table;

[0153] 5.FOR i=1 TOmax_fitness_evaluations DO

[0154] 5.1 Select state and action;

[0155] 5.2 Update Q table:

[0156] Q'(st,at)=(1-α)·Q(st,at)+α·[r+γ·maxaQ(st+1,a)];

[0157] 6.END FOR

[0158] 7. Select the best action and generate preliminary debt certificate;

[0159] 8.IF fit(initial debt certificate)>=fit(current best certificate) THEN

[0160] 8.1 Update the best creditor's rights certificate to the preliminary creditor's rights certificate;

[0161] 9.ELSE

[0162] 8.2 Maintain the existing best credentials;

[0163] 9.END IF

[0164] 10. Obtain user feedback and modify the debt certificate;

[0165] 11. Repeat the training model and optimize the analysis model;

[0166] 12. Return optimal_certificate;

[0167] #Specific steps to expand

[0168] 1. Clean debt information debt_info and extract key information;

[0169] -Use NLP technology to extract information such as creditors, debtors, debt amounts, repayment periods, etc. from debt_info.

[0170] 2. Automatically classify creditor's rights information according to legal requirements;

[0171] -Classify debt_info using predefined rules and machine learning models.

[0172] 3. Identify keywords related to creditor's rights and laws and regulations;

[0173] -Use NLP technology to identify key debt relationships and legal and regulatory provisions from classified debt information.

[0174] 4. Initialize the Q table;

[0175] -Create a two-dimensional array Q table to store the expected cumulative rewards for all possible state and action combinations.

[0176] 5.FOR i=1 TO max_fitness_evaluations DO

[0177] 5.1 Select state and action;

[0178] -Select an action based on the current state.

[0179] 5.2 Update Q table:

[0180] -Update the Q table based on the selected action and state, the formula is as follows:

[0181] Q'(st,at)=(1-α)·Q(st,at)+α·[r+γ·maxaQ(st+1,a)]

[0182] Among them, α is the learning rate, γ is the discount factor, and r is the immediate reward.

[0183] 6. Select the best action and generate preliminary debt certificate;

[0184] -Select the action with the highest Q value in the Q table and generate a preliminary debt certificate.

[0185] 8.IF fit(initial debt certificate)>=fit(current best certificate) THEN

[0186] 8.1 Update the best creditor's rights certificate to the preliminary creditor's rights certificate;

[0187] -If the fitness of the newly generated debt certificate is better than the existing optimal certificate, the optimal certificate will be updated.

[0188] 9.ELSE

[0189] 8.2 Maintain the existing best credentials;

[0190] -Otherwise keep the existing best credential unchanged.

[0191] 10. Obtain user feedback and modify the debt certificate;

[0192] -Collect user feedback on the generated debt certificate and adjust the certificate content accordingly.

[0193] 11. Repeat the training model and optimize the analysis model;

[0194] -Retrain the model using new feedback data to optimize its performance.

[0195] In addition, in the specific implementation process, the specific use method of the electronic debt certificate intelligent issuance system includes:

[0196] The first step is intelligent data capture and preprocessing: using advanced OCR technology (optical character recognition) and NLP (natural language processing) algorithms, the system can automatically identify and extract debt-related information in various formats such as paper documents and electronic documents, greatly reducing manual input work. It can also achieve intelligent data cleaning and standardization, automatically correct recognition errors, and ensure data accuracy and completeness.

[0197] Analyze the acquired debt pre-processing data using a deep learning-driven intelligent analysis engine: Integrate deep learning models to conduct multi-dimensional analysis of the collected data, including verification of the legalization of debt relationships, risk assessment, and predictive analysis to effectively identify potential fraud; continuously optimize analysis models by learning from historical cases and regulatory updates to ensure accuracy and compliance in decision-making.

[0198] The second step is adaptive template generation and personalized configuration: For eligible creditor-debtor relationships, the system can automatically generate standardized electronic debt certificate templates based on different types of creditor-debtor relationships and legal and regulatory requirements; it supports users to customize the certificate content according to specific needs through a simple interactive interface, such as adding special terms or adjusting the format, to achieve flexibility and personalization in certificate issuance.

[0199] The third step is security and privacy protection: further provide security guarantees for the issued electronic debt certificates. Combined with blockchain technology, a unique identifier is assigned to each electronic debt certificate, and its hash value is stored in the distributed ledger to ensure the immutability and transparency of the certificate; the Advanced Encryption Standard (AES) and Transport Layer Security (TLS) protocols are used to ensure the security and privacy of data transmission and storage.

[0200] The fourth step is the subsequent processing of electronic debt certificates: the system design is compatible with various financial systems, supports seamless integration with external systems such as payment, clearing, and auditing, and realizes subsequent functions such as circulation, pledge, offset, and redemption of electronic debt certificates.

[0201] Furthermore, smart contract technology can be introduced to encode the key terms of the debt certificate to achieve automatic execution and conditional triggering of the certificate; ensuring that once the preset conditions are met (such as the repayment date arrives), the system can automatically start the corresponding reminder or payment process, thereby improving execution efficiency and certainty of contract performance.

[0202] In summary, through the implementation of this system, the process of issuing electronic debt certificates will achieve an unprecedented level of intelligence, greatly improve efficiency, reduce human errors, and at the same time enhance the security and legal effect of the certificates.

[0203] This not only simplifies the debt management process for enterprises and individuals, promotes the transparency and trust of financial transactions, but also provides strong technical support for the efficient operation and risk management of the financial market, and promotes profound changes in the field of financial technology.

[0204] On the other hand, the present invention further discloses a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the above method.

[0205] On the other hand, the present invention further discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above method.

[0206] In another embodiment provided in the present application, a computer program product containing instructions is also provided. When the computer is run on a computer, the computer executes any of the electronic debt certificate intelligent issuance methods in the above embodiments based on any of the electronic debt certificate intelligent issuance systems in the above embodiments.

[0207] It is understandable that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts in the above method.

[0208] The embodiment of the present application also provides an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus.

[0209] Memory, used to store computer programs;

[0210] The processor is used to implement the above-mentioned method for intelligent issuance of electronic debt certificates based on the above-mentioned system for intelligent issuance of electronic debt certificates when executing the program stored in the memory.

[0211] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0212] The communication interface is used for communication between the above electronic device and other devices.

[0213] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0214] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.

[0215] It should also be noted that electronic devices also include terminal devices, which can also be called terminals, user equipment (UE), mobile stations (MS), mobile terminals (MT), etc. Terminal devices can be mobile phones, smart TVs, wearable devices, tablet computers (Pad), computers with wireless transceiver functions, virtual reality (VR) terminal devices, augmented reality (AR) terminal devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, etc. The embodiments of the present application do not limit the specific technology and specific device form adopted by the terminal devices.

[0216] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive Solid State Disk (SSD)), etc.

[0217] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

[0218] In addition, it should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly.

[0219] In addition, the meaning of "and / or" appearing in the full text includes three parallel solutions. Taking "A and / or B" as an example, it includes solution A, solution B, or solutions that satisfy both A and B. In addition, in the embodiments of the present invention, "multiple" refers to more than two. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the protection scope required by the present invention.

Claims

1. A method for intelligently issuing electronic debt certificates, characterized in that: The specific steps are as follows: S1. Enhanced data collection and preprocessing: Build an intelligent human-computer interaction interface, combine the API interface with the real-time connection of the financial institution database, realize the efficient collection of specified data, and automatically parse the uploaded document content through the integration of optical character recognition and natural language processing algorithms, and use the enterprise credit information platform to automatically verify the credit status of both parties of the debt; S2. In-depth data verification and intelligent analysis: Using machine learning models, we can deeply analyze submitted data, automatically compare contract terms, identify potential risk points, ensure data accuracy, and verify the logical consistency of creditor-debtor relationships to prevent fraud. S3. Adaptive creditor's rights certificate generation: Based on the verified data, the system dynamically generates electronic debt certificates that meet legal requirements and industry standards; S4. Security Enhancement and Blockchain Evidence Storage: Using encryption technology and distributed ledger mechanism, each electronic debt certificate is given a unique digital signature and timestamp to ensure that the certificate cannot be tampered with and is fully traceable; S5.Automated process integration and optimization: The system design is compatible with various financial ecosystems and supports seamless integration with external systems.

2. The method for intelligently issuing electronic debt certificates as claimed in claim 1, characterized in that: The electronic debt certificate generated in the S3 step supports personalized customization to meet the debt proof needs in different scenarios.

3. An intelligent issuance system for electronic debt certificates, characterized in that: The method for intelligently issuing an electronic debt certificate according to any one of claims 1 to 2 above comprises: A front-end human-computer interaction interface is used for user operation and display of feedback information. The front-end human-computer interaction interface integrates user-friendly interaction design and supports a variety of data input methods; The back-end processing center is equipped with a data processing module, AI analysis module, credential generation module, security evidence storage module and system integration module to achieve closed-loop management from data collection to credential application.

4. The electronic debt certificate intelligent issuance system as claimed in claim 3, characterized in that: The front-end human-computer interaction interface is integrated with a composite interface device for realizing the access of data sources and completing data capture and identification.

5. The electronic debt certificate intelligent issuance system as claimed in claim 3, characterized in that: The front-end human-computer interaction interface is provided with: Login and authentication module, supporting multiple login methods; Navigation and menu bar module, through the navigation structure, quickly query the entry of debt certificate issuance, as well as help, settings, and contact customer service functions; Intelligent form filling module, which allows users to quickly and automatically fill in forms and automatically perform verification and adjustment; The file upload and management area module supports batch upload, allowing users to upload multiple documents at a time, and provides instant preview after uploading to ensure that the upload is correct. It can also automatically identify and mark the type and purpose of uploaded files for easy management and retrieval; The progress tracking and status notification module provides a visual progress bar to let users know the progress of debt certificate issuance at any time, and push important notifications to users in a timely manner through in-site messages, emails or SMS when the specified progress is reached; The help and support module is connected to the online help center and user feedback portal, providing detailed graphic tutorials and FAQs to facilitate users to make suggestions or report problems. It also supports real-time chat and integrates online customer service functions for quick manual help. The personalized settings module allows users to customize interface themes, language preferences, and notification methods according to their own habits to enhance the personalized experience.

6. The electronic debt certificate intelligent issuance system as claimed in claim 5, characterized in that: The intelligent form filling module integrates dynamic form function, automatic filling function and real-time verification and prompt function, among which: The dynamic form function is used to automatically adjust the fields required to be filled in according to the type of claim selected by the user, thereby reducing unnecessary input; The auto-fill function uses optical character recognition and natural language processing algorithms to automatically capture and fill in relevant information after the user uploads the file, reducing the workload of manual input; The real-time verification and prompt function is used to instantly check the input information, and immediately provide clear feedback and guidance for incorrect or incomplete input to help users correct it quickly.

7. The electronic debt certificate intelligent issuance system as claimed in claim 3, characterized in that: The back-end processing center is provided with: The data processing module realizes data collection by receiving data submitted by the front end and automatically collecting original data related to the debt certificate as needed; making full use of optical character recognition and natural language processing algorithms to format and deduplicate the collected original data, identify the content on the acquired media carrier, ensure data quality, and extract and construct key features that are helpful for subsequent analysis. The AI ​​analysis module uses machine learning and deep learning algorithms to train historical data, build prediction models, analyze new data based on the trained models, and generate decision-making recommendations for debt certificate issuance, including providing key elements in debt certificates; The voucher generation module is used to submit a standard debt voucher template that meets legal requirements, and cooperate with the front end to personalize the template, and finally generate a specific debt voucher based on the AI ​​analysis results and user configuration; The secure evidence storage module uses an encryption algorithm to encrypt the debt certificate data, uses blockchain technology to store the debt certificate data on the chain, and uses digital signature technology to ensure the authenticity and integrity of the debt certificate. The system integration module provides an open API internally to facilitate docking with other systems and expand the application scenarios of the system. It also realizes data sharing and service collaboration through integration with other systems, thereby realizing the intelligent issuance of debt certificates.

8. The electronic debt certificate intelligent issuance system as claimed in claim 7, characterized in that: The specific operation process of using the deep learning model in the AI ​​analysis module to automatically identify and extract key information from the debt basis text includes: L1. Preprocessing operations: Use the pre-trained language model to convert the input debt basis text into a semantic vector representation: H=BERT(T) Where T represents the input text, H is the embedded representation of the text, H = [h1, h2, ..., h n ],h i Represents the embedding vector of the i-th character; L2. Encoding operation: (1) An improved position encoding mechanism is introduced to enhance the model’s ability to perceive vocabulary boundaries. The position encoding vector P ij The method to obtain is: P ij =Concatenate(Sin(f(pos i )),Cos(f(pos j ))) Here, f(·) is a mapping function from a position to an embedding space, pos i and pos j Represent the positions of vocabulary i and j respectively; (2) Position encoding vector P ij is added to the text embedding vector to form an enhanced vector representation: H'=H+P Among them, P is a matrix, each row of which corresponds to the position code of the corresponding character in the text; (3) Use the self-attention mechanism to enhance the degree of association between entities and enhance information sharing between relationships and entities: Among them, Q, K, and V represent query, key, and value matrices, respectively; Q=WQH' K=WKH' V=WVH' WQ, WK, WV are weight matrices and dk is the dimension of the key vector. (4) The output A of the attention mechanism is added to the enhanced text embedding vector to form the final encoding representation: H” = H’ + A; L3.Decoding operation: Use conditional random fields to obtain label predictions for the input sequence by maximizing the following formula: in, Indicates that from label y t-1 to y t The weight of is the label y t The eigenvector of t from the final encoded representation H".

9. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 2.

10. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method according to any one of claims 1 to 2.

Images