Self-service face checking method and device based on configurable product process

Abstract

The invention discloses a self-service face verification method based on a configurable loan product process. The method comprises the following steps: face verification process information is configured; distributing a video room according to the loan customer identity information; playing a face-to-face question according to the face-to-face process information, and capturing and identifying an answer of the loan customer; confirming a loan willingness result according to the answer content of the loan customer; if the loan willingness result is loan confirmation, verifying the loan person, the loan information and the loan willingness result; if the information is verified to be correct, guiding the loan customer to contract a contract and submit a credit application; and recording and storing data in the kernel process. The method has the advantages of high efficiency, high safety, high matching degree and low cost.

Description

Technical Field

[0001] The present invention belongs to the field of financial technology, and in particular to the customer identity verification and willingness verification links in online loan business, and provides a self-service face-to-face review video room system and method based on configurable product processes, aiming to improve loan approval efficiency and customer experience through automated and intelligent means. Background Art

[0002] With the rapid development of Internet finance, online loan services have become an important way to meet the financing needs of individuals and small and micro enterprises. The traditional offline verification method is not only time-consuming and laborious, but also limited by geography and time, and it is difficult to meet the requirements of modern financial services for immediacy and convenience.

[0003] The current Internet loan system screens customer information for a fixed loan product, recommending the loan product to those who meet the conditions of the loan product, and not recommending the loan product to those who do not meet the conditions of the loan product. Therefore, many loan demand resources that do not meet the conditions of the loan product but meet the conditions of other loan products are wasted, which leads to a waste of a lot of loan demand resources. In other words, it is difficult to match the target customers with suitable loan products in a targeted manner.

[0004] In addition, the existing face-to-face verification is inefficient and generally secure, and there is a possibility of fraud.

[0005] Therefore, there is an urgent need to develop an efficient, highly matched and secure online self-service interview method. Summary of the invention

[0006] To solve the above problems, the present invention proposes a self-service interview method and device based on a configurable product process. The method can quickly create a personalized video interview environment according to different loan product process requirements, analyze the loan customer's answers in real time through ASR (Automatic Speech Recognition) technology, judge their loan willingness, and automatically advance the credit application process accordingly.

[0007] The technical solution provided by the present invention is as follows:

[0008] First, a self-service review method based on a configurable loan product process is provided, including the following steps:

[0009] Configure the face-to-face verification process information;

[0010] Allocate video rooms based on loan customer identity information;

[0011] Play the interview questions based on the interview process information, and capture and identify the loan customer's answers;

[0012] Confirm the loan intention result based on the loan customer's answer;

[0013] If the loan intention result is to confirm the loan, the lender, loan information and loan intention result will be verified;

[0014] If the information is verified to be correct, the loan customer will be guided to sign the contract and submit the credit application;

[0015] Record and store data during the facial verification process.

[0016] In one possible implementation, the face-to-face verification process information includes: opening remarks, loan customer information verification, loan information verification, loan willingness verification, closing remarks, question bank script, automatic speech recognition model, recording method and video room layout.

[0017] In a possible implementation, the method for allocating a video room according to the lender identity information includes:

[0018] Match the corresponding loan product information according to the product ID and identity information submitted by the loan customer when calling the processing interface at the loan application portal during loan application;

[0019] Assign corresponding video rooms based on loan product information.

[0020] In a possible implementation, the method of playing the interview questions according to the interview process information and capturing and identifying the loan customer's answers includes:

[0021] Report the face-to-face verification process information in sequence; and perform facial recognition on loan customers and verify the authenticity of their identities during the reporting process;

[0022] Automatic speech recognition collection technology ASR is used to collect the answers given by loan customers to various questions during the face-to-face verification process; and the answers are converted into processable data to obtain customer answer data.

[0023] Furthermore, the method of confirming the loan intention result according to the loan customer's answer includes:

[0024] Based on the customer answer data, use the preset intent model template to match each of the customer answer data;

[0025] If the matching result of the current question is a positive answer, then proceed to the next question matching; otherwise, terminate;

[0026] If all questions are answered in the affirmative, the result of confirming the customer's loan willingness is to confirm the loan.

[0027] In one possible implementation, if the information is verified to be correct, the method of guiding the loan customer to sign the contract and submit a credit application includes:

[0028] If the loan customer information, loan information and loan intention are verified to be correct, the customer's identity information will be verified through facial recognition;

[0029] If the verification is correct, the loan customer will be guided to sign the contract and submit a credit application.

[0030] Secondly, we provide a self-service review device based on a configurable loan product process, including:

[0031] Configuration module, used to configure the face verification process information;

[0032] An allocation module, used for allocating video rooms according to loan customer identity information;

[0033] A recognition module, which is used to play the interview questions according to the interview process information, and capture and recognize the loan customer's answers;

[0034] The willingness confirmation module is used to confirm the loan willingness result according to the loan customer's answer;

[0035] The verification module is used to verify the lender, loan information and loan intention result if the loan intention result is to confirm the loan;

[0036] The signing module is used to guide the loan customer to sign the contract and submit the credit application if the information is verified to be correct;

[0037] The storage module is used to record and store data during the facial verification process.

[0038] According to a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the self-service review method based on the configurable loan product process as described in the first aspect is implemented.

[0039] In a fourth aspect, a non-transitory computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the self-service review method based on the configurable loan product process as described in the first aspect is implemented.

[0040] In a fifth aspect, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the self-service review method based on the configurable loan product process as described in the first aspect.

[0041] Beneficial effects of the present invention:

[0042] 1. Improve efficiency: The method of the present invention significantly shortens the loan approval cycle and improves customer service experience through automated processes.

[0043] 2. Enhanced security: The method of the present invention uses multi-factor identity authentication and video recording to effectively prevent fraud.

[0044] 3. High flexibility: The method of the present invention can support highly customized configuration and adapt to the personalized needs of different loan products.

[0045] 4. Intelligent decision-making: The method described in the present invention can combine ASR and NLP technologies to achieve accurate identification of loan intentions and reduce human misjudgment.

[0046] 5. Enhanced compliance: The method described in the present invention can meet the requirements of the personal loan management regulations, strictly abide by the relevant laws and regulations of the state on personal loan management, and ensure the compliance of the loan business.

[0047] 6. Reduce costs: The device described in the present invention realizes the online verification process, and banks can reduce their dependence on physical outlets, reduce operating costs, and improve service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the process of the method of the present invention;

[0049] Figure 2 is a schematic diagram of the device of the present invention;

[0050] Figure 3 This is a schematic structural diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0051] The content of the present invention is further described below in conjunction with specific embodiments, but the content of the present invention is not limited thereto. Figure 1 , which is a self-service review method based on a configurable loan product process, including the following steps:

[0052] S100, configuring face-to-face verification process information.

[0053] In one possible implementation, in step S100, the face-to-face verification process information includes: opening remarks, loan customer information verification, loan information verification, loan willingness verification, closing remarks, question bank script, automatic speech recognition model, recording method and video room layout.

[0054] Furthermore, the question bank includes: "Are you the legal person of XX company?", "Have you fully understood the terms of the contract, and promise that your loan application and contract signing intention are genuine and voluntary?", "The amount of the loan you use for production and operation this time is XX, the loan term is XX, and the interest rate is XX, is that correct?", etc.

[0055] Furthermore, the video room layout includes video background, seat avatars and interface element display positions.

[0056] It should be noted that the automatic speech recognition model can support functions such as speech recognition, enhancement, separation, speech log and microphone signal processing.

[0057] S200, allocating a video room according to the loan customer's identity information.

[0058] In a possible implementation, step S200 includes the following steps:

[0059] S210, matching corresponding loan product information according to the product ID and identity information sent by the loan customer when calling the processing interface at the loan application portal when applying for the loan;

[0060] S220, allocating a corresponding video room based on the loan product information.

[0061] Further, the step S220 includes the following steps:

[0062] Register the borrower's ID card information and the original ID card photo, and generate a processing link based on the corresponding product ID;

[0063] After the processing link is clicked, the authorization token is obtained through the C-end SDK, and the authorization token is called to create a video room.

[0064] The video room includes: audio and video service information, product information and process speech information.

[0065] For example, loan channel A integrates the C-end SDK, and in the previous step, loan product B has been configured for this loan channel A. Product B will generate a product ID number C. The borrower needs a loan, enters the APP of loan channel A, uploads the ID card information, and then clicks "I want a loan". The system calls the creation and processing interface, which will register the borrower's ID card information and the original ID card photo, and attach the product ID number C corresponding to product B. Based on the above steps, the loan customer can match the corresponding loan product and allocate the corresponding video room.

[0066] S300, playing the interview questions according to the interview process information, and capturing and identifying the loan customer's answers.

[0067] In a possible implementation, S300 includes the following steps:

[0068] S310, reporting the face-to-face verification process information in sequence; and during the reporting process, performing face recognition and online verification on the loan customer, and verifying the authenticity of the identity;

[0069] S320, using automatic speech recognition collection technology ASR, collects the answers given by loan customers to various questions during the face-to-face verification process; and converts the content of the answers into a processable data form to obtain customer answer data.

[0070] Furthermore, in S310, facial recognition is performed on the loan customer, and combined with the ID card information, the personal ID card verification and facial recognition service provided by the Ministry of Public Security is called to check the authenticity of the loan customer's identity to prevent loan fraud.

[0071] Furthermore, in S320, the customer answer data is in text format data or specific structured data to facilitate subsequent data matching.

[0072] S400: confirm the loan willingness result according to the loan customer's answer.

[0073] In one possible implementation, step S400 includes:

[0074] Based on the customer answer data, use the preset intent template to match each of the customer answer data;

[0075] If the matching result of the current question is a positive answer, then proceed to the next question matching; otherwise, terminate;

[0076] If all questions are answered in the affirmative, the result of confirming the customer's loan willingness is to confirm the loan.

[0077] For example, the preset intent template content is as follows:

[0078]

[0079]

[0080] Understandably, enough questions can be added to the preset intention template to confirm the customer's loan information, and the answers to the above questions only have two results: affirmative answers and negative answers, such as "yes", "confirmed", "I agree", "I am willing" and other similar answers, so as to match the customer's answer data with the intention template, and then judge the customer's loan intention and confirm the loan willingness result. If a negative answer is identified during the question-and-answer process, the face-to-face verification process is terminated.

[0081] S500: If the loan intention result is to confirm the loan, the lender, loan information and loan intention result are verified.

[0082] In one possible implementation, in S500, the method for verifying the lender, loan information and loan intention result includes: face in-frame monitoring, face recognition and identity card verification.

[0083] S600: If the information is verified to be correct, the loan customer is guided to sign the contract and submit a credit application.

[0084] In a possible implementation, S600 includes the following steps:

[0085] If the loan customer information, loan information and loan intention are verified to be correct, the customer's identity information will be verified through facial recognition;

[0086] If the verification is correct, the loan customer will be guided to sign the contract and submit a credit application.

[0087] S700, recording and storing data during the facial verification process.

[0088] It can be understood that the data of the face-to-face verification process recorded and stored in S700 is used for subsequent audit and analysis, and the signature information is sent back to the business system for retention.

[0089] The following is a description of the self-service interview device based on the configurable loan product process provided by the present invention. The self-service interview device based on the configurable loan product process described below and the self-service interview method based on the configurable loan product process described above can be referenced to each other.

[0090] Figure 2 FIG. 1 is a schematic diagram of a self-service face-to-face verification device based on a configurable loan product process provided by an embodiment of the present invention. Figure 2 As shown, it includes: a configuration module 21, an allocation module 22, an identification module 23, a willingness confirmation module 24, a verification module 25, a contract signing module 26 and a storage module 27, wherein:

[0091] Configuration module 21, used to configure face verification process information;

[0092] An allocation module 22, for allocating video rooms according to the identity information of loan customers;

[0093] The identification module 23 is used to play the interview questions according to the interview process information, and capture and identify the loan customer's answer;

[0094] The willingness confirmation module 24 is used to confirm the loan willingness result according to the loan customer's answer;

[0095] Verification module 25, for verifying the lender, loan information and loan willingness result if the loan willingness result is to confirm the loan;

[0096] The signing module 26 is used to guide the loan customer to sign the contract and submit the credit application if the information is verified to be correct;

[0097] The storage module 27 is used to record and store the data during the facial verification process.

[0098] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communications interface 320 and the memory 330 communicate with each other via the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the self-service review method based on the configurable loan product process.

[0099] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0100] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the self-service review method based on the configurable loan product process provided by the above methods.

[0101] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the self-service review method based on the configurable loan product process provided by the above-mentioned methods.

[0102] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0103] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A self-service audit method based on a configurable loan product process, characterized in that: The following steps are involved: Configure the face-to-face verification process information; Allocate video rooms based on loan customer identity information; Play the interview questions based on the interview process information, and capture and identify the loan customer's answers; Confirm the loan intention result based on the loan customer's answer; If the loan intention result is to confirm the loan, the lender, loan information and loan intention result will be verified; If the information is verified to be correct, the loan customer will be guided to sign the contract and submit the credit application; Record and store data during the facial verification process.

2. The self-service audit method based on configurable loan product process according to claim 1 is characterized in that: The face-to-face verification process information includes: opening remarks, loan customer information verification, loan information verification, loan willingness verification, closing remarks, question bank script, automatic speech recognition model, recording method and video room layout.

3. The self-service audit method based on configurable loan product process according to claim 1 is characterized in that: The method for allocating a video room according to the lender identity information includes: Match the corresponding loan product information according to the product ID and identity information submitted by the loan customer when calling the processing interface at the loan application portal during loan application; Assign corresponding video rooms based on loan product information.

4. The self-service audit method based on configurable loan product process according to claim 1 is characterized in that: The method of playing the interview questions according to the interview process information and capturing and identifying the loan customer's answer includes: Report the face-to-face verification process information in sequence; and perform facial recognition on loan customers and verify the authenticity of their identities during the reporting process; Automatic speech recognition collection technology ASR is used to collect the answers given by loan customers to various questions during the face-to-face verification process; and the answers are converted into processable data to obtain customer answer data.

5. The self-service audit method based on configurable loan product process according to claim 4 is characterized in that: Methods for confirming the loan intention results based on the loan customer's answers include: Based on the customer answer data, use the preset intent model template to match each of the customer answer data; If the matching result of the current question is a positive answer, then proceed to the next question matching; otherwise, terminate; If all questions are answered in the affirmative, the result of confirming the customer's loan willingness is to confirm the loan.

6. The self-service audit method based on configurable loan product process according to claim 1 is characterized in that: If the information is verified to be correct, the method of guiding the loan customer to sign the contract and submit the credit application includes: If the loan customer information, loan information and loan intention are verified to be correct, the customer identity information will be verified through facial recognition; If the verification is correct, the loan customer will be guided to sign the contract and submit a credit application.

7. A self-service verification device based on a configurable loan product process, characterized in that: include: Configuration module, used to configure the face verification process information; An allocation module, used for allocating video rooms according to loan customer identity information; A recognition module, which is used to play the interview questions according to the interview process information, and capture and recognize the loan customer's answers; The willingness confirmation module is used to confirm the loan willingness result according to the loan customer's answer; The verification module is used to verify the lender, loan information and loan intention result if the loan intention result is to confirm the loan; The signing module is used to guide the loan customer to sign the contract and submit the credit application if the information is verified to be correct; The storage module is used to record and store data during the facial verification process.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, it implements the self-service review method based on the configurable loan product process as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the self-service review method based on the configurable loan product process as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements the self-service review method based on the configurable loan product process as described in any one of claims 1 to 6.

Images