Online loan review method, review device, electronic device and storage medium

Through the online loan review method, biometric technology is used for remote verification, which solves the problems of high cost and time-consuming traditional loan review, and achieves fast and reliable loan review, meeting the rapid needs of small and micro financing businesses.

CN113112232BActive Publication Date: 2024-11-22INDUSTRIAL AND COMMERCIAL BANK OF CHINA
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110403224.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-04-14
Publication Date
2024-11-22
Estimated Expiration
2041-04-14

AI Technical Summary

Technical Problem

The traditional loan review model is costly and time-consuming, and cannot meet the needs of rapid development of loan business.

Method used

Using the online loan review method, by receiving loan requests submitted by the applicant, sending verification links to the company's shareholders, conducting the first and second rounds of biometrics, including face recognition, voiceprint recognition and micro-expression recognition, combined with online video Connect, verify shareholder identity and authorization document signatures, and realize remote online audit.

Benefits of technology

It reduces the cost and time of loan processing, improves audit reliability, meets the rapid demand of small and micro financing businesses, and improves financing efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113112232B_ABST
    Figure CN113112232B_ABST
Patent Text Reader

Abstract

The present disclosure provides an online loan review method, which relates to the field of artificial intelligence. The online loan review method includes: receiving a loan request submitted by an applicant, wherein the loan request includes information of N shareholders of the company to which the applicant belongs, and N is an integer greater than or equal to 2. Sending verification links to the N shareholders of the company respectively. Receive N loan verification materials, wherein each of the loan verification materials is uploaded by each shareholder of the company through the corresponding verification link. Perform a first round of biometric identification on each corresponding shareholder of the company based on each of the loan verification materials. And after the number of N shareholders of the company who pass the first round of biometric identification meets a first preset condition, the loan request is reviewed. The present disclosure also provides an online loan review device, as well as an electronic device and a storage medium.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure belongs to the field of artificial intelligence, and more specifically, relates to an online loan review method, review device, electronic device and storage medium. Background Art

[0002] In recent years, the demand for small and micro financing by individuals or enterprises has grown rapidly. For example, after an enterprise submits a loan application, the business personnel of a financial institution generally conduct "going to the enterprise" in a traditional way, that is, the business personnel go offline to the enterprise to review the business situation, enterprise qualifications, or handle the materials required for the business. For example, the enterprise may also need to convene relevant personnel to make a resolution on the financing business and form a resolution material for the business personnel to review.

[0003] In the process of implementing the concept of the present disclosure, the inventors found that there are at least the following problems in the prior art:

[0004] Traditional methods such as on-site investigations are costly and time-consuming, and in actual applications cannot meet the needs of the rapid development of loan business. Summary of the invention

[0005] In view of this, the embodiments of the present disclosure provide an online loan review method for investigating, reviewing or handling loan business online, as well as an online loan review device, electronic device and storage medium.

[0006] One aspect of an embodiment of the present disclosure provides an online loan review method. The online loan review method includes: receiving a loan request submitted by an applicant, wherein the loan request includes information of N shareholders of the company to which the applicant belongs, wherein N is an integer greater than or equal to 2. Sending verification links to the N shareholders of the company respectively. Receive N loan verification materials, wherein each of the loan verification materials is uploaded by each shareholder of the company through the corresponding verification link. Perform a first round of biometric identification on each corresponding shareholder of the company based on each of the loan verification materials. And after the number of N shareholders of the company who pass the first round of biometric identification meets a first preset condition, the loan request is reviewed.

[0007] According to an embodiment of the present disclosure, the review of the loan request includes: receiving a video review request initiated by the applicant and / or the N shareholders of the company. In response to the video review request, establishing an online video connection with the applicant and / or the N shareholders of the company at the same time. Acquiring multimedia information of the applicant and / or the N shareholders of the company based on the online video connection. Performing a second round of biometric identification on the applicant and / or the N shareholders of the company based on the multimedia information. And reviewing the loan request based on the results of the second round of biometric identification.

[0008] According to an embodiment of the present disclosure, the second round of biometric identification of the applicant and / or the N shareholders of the company based on the multimedia information includes: performing at least one of face recognition, voiceprint recognition and micro-expression recognition on the applicant and / or the N shareholders of the company based on the multimedia information.

[0009] According to an embodiment of the present disclosure, the performing micro-expression recognition on the applicant and / or the N shareholders of the company based on the multimedia information includes: obtaining the micro-expressions of the applicant and / or the N shareholders of the company based on the multimedia information. Scoring the micro-expressions of each of the applicant and / or the N shareholders of the company using a micro-expression recognition model. When the score is less than or equal to a preset value, confirming that the loan request is not approved.

[0010] According to an embodiment of the present disclosure, the voiceprint recognition of the applicant and / or the N shareholders of the company based on the multimedia information includes: obtaining a first voiceprint feature based on the multimedia information, and comparing the first voiceprint feature with a voiceprint feature in a black voiceprint library, wherein the black voiceprint library includes pre-stored voiceprint features of users with loan risks. When the first voiceprint feature is similar to the voiceprint feature in the black voiceprint library, it is confirmed that the loan request is not approved.

[0011] According to an embodiment of the present disclosure, the establishing of an online video connection with the applicant and / or the N shareholders of the company in response to the video review request includes: obtaining status information of M verification personnel, where M is an integer greater than or equal to 2. Sorting at least two verification personnel whose status information is in a ready state according to the ready time. And establishing an online video connection between the verification personnel with an earlier ready time and the applicant and / or the N shareholders of the company.

[0012] According to an embodiment of the present disclosure, before receiving the video review request initiated by the applicant and / or the N shareholders of the company, it also includes: sending loan authorization documents to the N shareholders of the company respectively, and the loan authorization documents include the loan information in the loan request. Receiving the loan authorization document signed online by the N shareholders of the company. After the number of shareholders of the company who have signed meets the second preset condition, allowing the applicant and / or the N shareholders of the company to initiate a video review request.

[0013] According to an embodiment of the present disclosure, the receiving N loan verification materials includes: receiving a video file uploaded by the company shareholder through the verification link, wherein the video file includes the content of the company shareholder reading verification information, wherein the verification information is used to verify the identity of the company shareholder.

[0014] According to an embodiment of the present disclosure, the first round of biometric identification of the company shareholder based on the loan verification materials includes: obtaining a face image of the company shareholder in the video file for face recognition. And / or obtaining voice information read by the company shareholder in the video file for identification, including: converting the voice information into text information, and comparing the text information with the verification information. And obtaining a second voiceprint feature based on the voice information, and comparing the second voiceprint feature with the voiceprint feature in the black voiceprint library, wherein the black voiceprint library includes pre-stored voiceprint features of users with loan risks.

[0015] According to an embodiment of the present disclosure, the first round of biometric identification includes: the facial image of the company shareholder matches the facial image in the information of the company shareholder, and / or the text information matches the verification information, and the voiceprint feature is not similar to the voiceprint feature in the black voiceprint library.

[0016] Another aspect of the disclosed embodiment provides an online loan review device. The online loan review device includes a request receiving module, a link sending module, a material receiving module\biometric module and a loan review module. The request receiving module is used to receive a loan request submitted by an applicant, wherein the loan request includes information of N shareholders of the company to which the applicant belongs, wherein N is an integer greater than or equal to 2. The link sending module is used to send verification links to the N shareholders of the company respectively. The material receiving module is used to receive N loan verification materials, wherein each of the loan verification materials is uploaded by each shareholder of the company through the corresponding verification link. The biometric module is used to perform a first round of biometric identification on each corresponding shareholder of the company based on each of the loan verification materials. And the loan review module is used to review the loan request after the number of N shareholders of the company who pass the first round of biometric identification meets a first preset condition.

[0017] Another aspect of the embodiment of the present disclosure provides an electronic device. The electronic device includes one or more memories and one or more processors. The memories store executable instructions. The processor executes the executable instructions to implement the above method.

[0018] Another aspect of an embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the method described above when executed.

[0019] Another aspect of the embodiments of the present disclosure provides a computer program product, including a computer program / instruction, which implements the above-mentioned method when executed by a processor.

[0020] One or more of the above-mentioned embodiments have the following advantages or beneficial effects: it can at least partially solve the problem of high cost and long time caused by on-site investigation of loan business, after receiving the loan request submitted by the applicant online, and sending a verification link to the company shareholders of the applicant's company, and then performing biometric identification on the company shareholders based on the received loan verification materials, it can realize remote online loan review, and combine biometric technology to verify multi-dimensional biometric data, thereby reducing the cost and time of loan processing and improving the reliability of the review. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0022] Figure 1 An exemplary system architecture to which an online loan review method can be applied according to an embodiment of the present disclosure is schematically shown;

[0023] Figure 2 A flowchart of an online loan review method according to an embodiment of the present disclosure is schematically shown;

[0024] Figure 3 The flowchart of performing the first round of biometric identification on each company shareholder according to an embodiment of the present disclosure is schematically shown;

[0025] Figure 4 The flowchart of recognizing the voice information read aloud by the shareholders of a company according to an embodiment of the present disclosure is schematically shown;

[0026] Figure 5A Schematically illustrates a flow chart of a first round of biometric identification according to an embodiment of the present disclosure;

[0027] Figure 5B Schematically shows a flow chart of a first round of biometric identification according to another embodiment of the present disclosure;

[0028] Figure 6 A flowchart of reviewing a loan request according to an embodiment of the present disclosure is schematically shown;

[0029] Figure 7 The flowchart of establishing an online video connection according to an embodiment of the present disclosure is schematically shown;

[0030] Figure 8 A flowchart of performing micro-expression recognition on an applicant and / or N company shareholders according to an embodiment of the present disclosure is schematically shown;

[0031] Fig. 9 The flowchart of performing voiceprint recognition on an applicant and / or N company shareholders according to an embodiment of the present disclosure is schematically shown;

[0032] Fig.10 A block diagram schematically shows an online loan review device according to an embodiment of the present disclosure;

[0033] Fig.11 The structure diagram of the biometric recognition module according to the embodiment of the present disclosure is schematically shown;

[0034] Fig.12 A block diagram of an online loan review device according to another embodiment of the present disclosure is schematically shown;

[0035] Fig.13 A block diagram of a computer system suitable for implementing an online loan review method and apparatus according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0036] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0037] An embodiment of the present disclosure provides an online loan review method. The online loan review method includes: receiving a loan request submitted by an applicant, wherein the loan request includes information of N shareholders of the company to which the applicant belongs, wherein N is an integer greater than or equal to 2. Sending verification links to the N shareholders of the company respectively. Receive N loan verification materials, wherein each loan verification material is uploaded by each shareholder of the company through a corresponding verification link. Perform a first round of biometric identification on each corresponding shareholder of the company based on each loan verification material. And after the number of N shareholders of the company who pass the first round of biometric identification meets a first preset condition, the loan request is reviewed.

[0038] According to the embodiments of the present disclosure, the applicant may be a legal person of an enterprise, or may be an authorized staff member within the company, for example, the staff member may submit materials with the seal of the legal person, etc. The present disclosure does not limit this, and the identity of the applicant may be determined according to financial institutions or relevant laws. In some embodiments of the present disclosure, the applicant may also be a shareholder of the company.

[0039] When a limited liability company or a joint stock company with multiple shareholders submits a loan application, it may be necessary to hold a shareholder meeting to vote on the loan application and form a shareholder meeting resolution. The shareholder meeting resolution can enable the financial institution to determine that the loan is an overall decision of the company and can avoid disputes between a shareholder and the financial institution on the grounds of ignorance. Usually, when a shareholder meeting is held to vote, all shareholders are called together for a meeting. After the vote is passed, the business personnel may also go to the company to review the relevant materials. In the above process, it is difficult to unify the free time of each shareholder, and it will also take a lot of time for each shareholder and business personnel to go to the company.

[0040] By utilizing the online loan review method of the disclosed embodiment, after receiving the loan request submitted by the applicant online, a verification link is sent to the shareholders of the company to which the applicant belongs, and then the biometrics of the company shareholders are performed based on the received loan verification materials. Remote online loan review can be performed, and multi-dimensional biometric data can be verified in combination with biometric technology, thereby reducing the cost and time of loan processing and improving the reliability of the review.

[0041] It should be noted that the online loan review method and device of the embodiments of the present disclosure can be used in the financial field, and can also be used in any field other than the financial field. The present disclosure does not limit the application field of the online loan review method and device.

[0042] Figure 1 The exemplary system architecture 100 to which the online loan review method according to the embodiment of the present disclosure can be applied is schematically shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0043] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0044] Users (such as applicants, company shareholders, or verification personnel of financial institutions) can use terminal devices 101, 102, and 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0045] The terminal devices 101 , 102 , and 103 may be various electronic devices having a camera, a display screen, and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, and the like.

[0046] The server 105 may be a server that provides various services, such as a background management server (only an example) that provides support for websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze and process received user requests, loan verification materials, multimedia information, and other data, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0047] According to the embodiments of the present disclosure, referring to Figure 1 First, the applicant can, for example, use the terminal device 101 to submit a loan application to the server 105 through the network 104. Then, after receiving the loan request, the server 105 sends a verification link to the terminal devices 102 and 103 used by the two company shareholders through the network 104. Next, the two company shareholders submit loan verification materials through the corresponding verification links respectively. Finally, the server 105 performs a first round of biometric identification on each corresponding company shareholder based on each loan verification material. And after the number of N company shareholders who pass the first round of biometric identification meets the first preset condition, the loan request is reviewed.

[0048] It should be noted that the online loan review method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the online loan review device provided in the embodiment of the present disclosure can generally be set in the server 105. The online loan review method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the online loan review device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0049] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0050] Figure 2 The flowchart of the online loan review method according to the embodiment of the present disclosure is schematically shown.

[0051] like Figure 2 As shown, the method includes operations S210 to S250.

[0052] In operation S210, a loan request submitted by an applicant is received, wherein the loan request includes information of N shareholders of the company to which the applicant belongs, wherein N is an integer greater than or equal to 2.

[0053] According to the embodiments of the present disclosure, the applicant can use the personal loan client provided by the financial institution (for example, installed on the terminal device 101) to supplement personal information, image materials, initiate loans, etc. For example, the applicant fills in and confirms personal information, uploads image materials such as business license, applicant's ID, spouse's ID and marriage certificate, and fills in the shareholder information of the applicant's company, such as mobile phone number, ID or other materials.

[0054] Then, in operation S220, verification links are sent to the N shareholders of the company respectively.

[0055] In operation S230, N loan verification materials are received, wherein each loan verification material is uploaded by each company shareholder through a corresponding verification link.

[0056] According to the embodiments of the present disclosure, referring to Figure 1 , the server 105 may send a text message or email including a verification link to each shareholder. After receiving the verification link, the shareholder clicks to enter, and can jump to the personal loan client\WeChat public account\webpage, etc., to enter the online shareholder meeting confirmation page. Among them, the online shareholder meeting confirmation page can be presented in the form of multiple-choice questions, allowing each shareholder to select the correct verification information. After the shareholder selects the verification information, the result of the shareholder's selection is returned to the server 105 and compared with the materials uploaded in advance by the applicant. In other embodiments of the present disclosure, shareholders can upload a video of reading the verification information. Among them, the verification information can be the name of the corporate legal person, or company-related business information.

[0057] In operation S240, a first round of biometric identification is performed on each corresponding company shareholder based on each loan verification material.

[0058] In operation S250, after the number of N shareholders of the company who pass the first round of biometric identification meets the first preset condition, the loan request is reviewed.

[0059] According to an embodiment of the present disclosure, the first preset condition may be that all shareholders of the company to which the applicant belongs need to pass the first round of biometric identification, and then the loan request can be reviewed. The number of shareholders who have passed the first round of biometric identification can also be determined based on the share quota. For example, if the shareholders who have passed the first round of biometric identification hold more than two-thirds of the shares in total, the loan request can continue to be reviewed.

[0060] By utilizing the online loan review method of the disclosed embodiment, the company's shareholders can be biometrically identified based on the received loan verification materials, thereby ensuring the authenticity of the company's shareholders' identities, reducing the cost and time of loan business processing, and improving the reliability of the review.

[0061] According to an embodiment of the present disclosure, receiving N loan verification materials includes receiving a video file uploaded by a company shareholder through a verification link, wherein the video file includes the content of the company shareholder reading aloud the verification information, wherein the verification information is used to verify the identity of the company shareholder. For example, each company shareholder may be required to read aloud the name of the company's legal person, the company's quarterly turnover, etc., and record the reading process as a video for uploading. It should be noted that the present disclosure does not limit the content of the verification information read aloud, and the verification information content sufficient to prove the identity of the shareholder can be determined according to actual conditions.

[0062] Combine the following Figure 3 ~ Figure 5 illustrates the process of conducting the first round of biometric identification on each corresponding company shareholder based on each loan verification material, and passing the first round of biometric identification.

[0063] Figure 3 The flowchart of performing the first round of biometric identification on each company shareholder in operation S240 according to an embodiment of the present disclosure is schematically shown. Figure 4 The flowchart of recognizing voice information read aloud by company shareholders according to an embodiment of the present disclosure is schematically shown.

[0064] like Figure 3 As shown, in operation 240, performing a first round of biometric identification on each corresponding company shareholder based on each loan verification material may include operations S310 to S320.

[0065] In operation S310, facial images of shareholders of a company in a video file are acquired for facial recognition.

[0066] According to an embodiment of the present disclosure, for example, a facial image of a major shareholder (holding the most shares) is obtained from a video file, and then compared with the photo on his ID card to determine whether it is the real person. In some embodiments, the name information on the ID card can also be extracted and compared with the retrieved business information to confirm that the identity of the major shareholder is real.

[0067] In operation S320, voice information read aloud by shareholders of the company in the video file is obtained for recognition.

[0068] like Figure 4 As shown, in operation 320, recognizing the voice information read aloud by the company's shareholders may include operations S410 to S420.

[0069] In operation S410, the voice information is converted into text information, and the text information is compared with the verification information.

[0070] According to an embodiment of the present disclosure, taking the name of the company legal person as an example, after receiving a video of each shareholder reading the name of the company legal person, the voice including the name of the company legal person can be converted into text form and compared with the materials uploaded by the applicant or the name of the company legal person in the query of business information.

[0071] In operation S420, a second voiceprint feature is obtained based on the voice information, and the second voiceprint feature is compared with a voiceprint feature in a black voiceprint library, wherein the black voiceprint library includes pre-stored voiceprint features of users with loan risks.

[0072] Figure 5A The flowchart of the first round of biometric identification according to an embodiment of the present disclosure is schematically shown. Figure 5B The flowchart of the first round of biometric identification according to another embodiment of the present disclosure is schematically shown.

[0073] like Figure 5A As shown, after obtaining the face image of the company shareholder in the video file for face recognition in operation 310, operation S510 may be performed. In operation S510, it may be determined whether the face image of the company shareholder matches the face image in the information of the company shareholder. If they match, it indicates that the identity of the company shareholder meets the requirements, and the face recognition passes. If they do not match, the person providing the verification materials is not a company shareholder, and the face recognition fails.

[0074] like Figure 5B As shown, after operation S420, operations S520 and S530 may also be included. In operation S520, it may be determined whether the text information matches the verification information. In operation S530, it may be determined whether the voiceprint feature is similar to the voiceprint feature in the black voiceprint library. When the text information provided by a shareholder matches the verification information, and the voiceprint feature is not similar to the voiceprint feature in the black voiceprint library (indicating that the shareholder has no loan risk), it indicates that the voiceprint recognition is passed.

[0075] Take the example of face recognition and voice information extraction for a company shareholder. If the face recognition fails, the first round of biometrics fails. If the face recognition passes, but the text information does not match the verification information, the first round of biometrics fails. If the face recognition passes, the text information matches the verification information, and the voiceprint features are not similar to those in the black voiceprint database, the first round of biometrics passes. If the face recognition passes, the text information matches the verification information, and the voiceprint features are similar to those in the black voiceprint database, the first round of biometrics can be determined based on the actual situation. For example, if a shareholder of a company has a personal loan that is overdue and has no connection with the company's finances, it can be confirmed to have passed.

[0076] According to the embodiments of the present disclosure, a shareholder of a company correctly provides verification information, which preliminarily shows that his shareholder identity has a certain degree of credibility. In addition, in the related technology, people with loan records can be collected voiceprint features when applying for loans. When a loan is overdue, the debtor's voiceprint features can be put into the black voiceprint library, and the debtor is a user with loan risks.

[0077] By using the online loan review method of the embodiment of the present disclosure, it is possible to determine whether a company's shareholders have ever had loan risks, and use this as a factor in reviewing the company's repayment ability, thereby improving the comprehensive review capability and reducing the risk of loan overdue.

[0078] In some embodiments, only operation S310 or operation S320 may be performed, or both operation S310 and operation S320 may be performed. Correspondingly, operations S510, S520, and S530 for determining whether the first round of biometric identification is passed may be flexibly selected for execution according to the situation of executing operation S310 and operation S320. Although the above describes the various operations of the method in a specific order, the embodiments of the present disclosure are not limited thereto, and the above operations may be performed in other orders as needed. For example, operation S310 may be performed after operation S320, or may be performed simultaneously.

[0079] According to an embodiment of the present disclosure, after the number of N company shareholders who pass the first round of biometric identification meets the first preset condition, it indicates that the company shareholders of the company in this loan request meet the conditions for forming a valid shareholders' meeting resolution, and the identity of each shareholder is true. Therefore, the loan request can be further reviewed. For example, each shareholder is convened online to make a shareholders' meeting resolution, and each shareholder is required to sign a loan authorization document to authorize this loan request. When the authorization results of each shareholder for this loan request meet the conditions, the applicant and / or N company shareholders can be allowed to initiate a video review request for an online video review.

[0080] Figure 6The flowchart of reviewing a loan request in operation S250 according to an embodiment of the present disclosure is schematically shown.

[0081] like Figure 6 As shown, in operation S250, after the number of N shareholders of the company who pass the first round of biometric identification meets the first preset condition, reviewing the loan request may include operations S610 to S680.

[0082] In operation S610, loan authorization documents are sent to N shareholders of the company respectively, where the loan authorization documents include loan information in the loan request.

[0083] According to an embodiment of the present disclosure, the loan authorization document may include information such as the loan amount, loan type, repayment period and interest rate in this loan request, as well as information such as the responsibilities and obligations that both parties should comply with.

[0084] In operation S620, a loan authorization document signed online by N shareholders of the company is received.

[0085] In operation S630, after the number of signed company shareholders meets the second preset condition, the applicant and / or N company shareholders are allowed to initiate a video review request.

[0086] According to an embodiment of the present disclosure, if each shareholder agrees with the content in the loan authorization document, they sign and confirm. For example, the second preset condition can be that all shareholders sign and confirm, or the number of company shareholders who sign the loan authorization document can be determined based on the shareholding ratio, for example, the shareholding ratio of shareholders who sign and confirm accounts for more than two-thirds of the company's shares.

[0087] Taking the second preset condition of all shareholders signing and confirming as an example, after the biometric recognition is successful, the authorization link can be sent to the shareholders again, and each shareholder enters the shareholders' meeting resolution to read the signature confirmation page. If a shareholder disagrees with the content of the shareholders' meeting resolution (that is, the content of the loan authorization document), the system will automatically send a reminder to other shareholders, terminate the authorization process of other shareholders, and send a notification to the applicant. If the shareholder agrees with the content of the shareholders' meeting resolution, select "Confirm Signature", enter the signature page, complete the signature with a handwritten signature, and save the image. After all shareholders have completed and agreed to sign, an electronic version of the shareholders' meeting resolution is generated and backed up.

[0088] In operation S640, a video review request initiated by the applicant and / or N company shareholders is received.

[0089] According to the embodiments of the present disclosure, a video audit can be conducted only on the applicant (for example, the applicant is a corporate legal person who has sufficient information about the company), or only on one or more of the N shareholders of the company (for example, the applicant is only a staff member who submits materials and lacks sufficient knowledge of the company), or on the applicant and N shareholders of the company at the same time. Then, according to the identity of the person being audited, the corresponding strategy is selected for inquiry.

[0090] In operation S650, in response to the video review request, an online video connection is established with the applicant and / or N company shareholders.

[0091] According to an embodiment of the present disclosure, after establishing an online video connection with the applicant, the applicant's location at this time can be determined by means of GPS positioning, IP address positioning, etc., and matched with the company's actual business address to ensure that the applicant initiated the video review request at the business address. Among them, when the applicant and N company shareholders participate in the video review together, only the applicant's address can be determined. If the applicant does not participate in the video review, it can be stipulated that at least one company shareholder should participate in the video review at the company's actual business address.

[0092] In operation S660, multimedia information of the applicant and / or N company shareholders is obtained based on the online video connection.

[0093] According to the embodiments of the present disclosure, the audio information and video picture information in the audit process can be collected through the terminal devices of the applicant and / or N shareholders of the company participating in the video audit. In some embodiments of the present disclosure, an interface including content requiring signature confirmation can also be popped up on the video interface, and the multimedia information can also include text information or text images.

[0094] In operation S670, a second round of biometric identification is performed on the applicant and / or the N shareholders of the company based on the multimedia information.

[0095] In operation S680, the loan request is reviewed based on the result of the second round of biometric identification.

[0096] The online loan review method of the disclosed embodiment utilizes biometric technology to assist verification personnel in conducting risk assessments for remote reviews, which can enable small and micro financing businesses to be handled fully online without leaving home, further improving the efficiency of online small and micro financing business handling, and better meeting the "short, frequent, and urgent" financing needs of small and micro customers.

[0097] Figure 7 The flowchart of establishing an online video connection in operation S650 according to an embodiment of the present disclosure is schematically shown.

[0098] like Figure 7As shown, in operation S650, establishing an online video connection with the applicant and / or N company shareholders in response to the video review request may include operations S710 to S730.

[0099] In operation S710, status information of M verification persons is obtained, where M is an integer greater than or equal to 2.

[0100] In operation S720, at least two verification personnel whose status information is a ready state are sorted according to the ready time.

[0101] In operation S730, the verification personnel who are ready earlier establish an online video connection with the applicant and / or N company shareholders.

[0102] According to the embodiments of the present disclosure, referring to Figure 1 , taking the applicant and company shareholders participating in the online video review as an example. First, the applicant can use the terminal device 101 to initiate a video review request. Then, after receiving the video review request, the server 105 orders the verification personnel using the terminal device 102 to be responsible for the online video review. Next, after the verification personnel establishes an online video connection with the applicant, the company shareholders using the terminal device 103 can join this online video and accept the verification personnel's inquiries at the same time as the applicant. In addition, other company shareholders or verification personnel can use other terminal devices to join this online video.

[0103] According to an embodiment of the present disclosure, the status of the verification personnel's video interview may include "ready" and "not ready", and only the "ready" verification personnel can access the online video. The "ready" status can be manually adjusted by the verification personnel, and the "not ready" status can be manually adjusted by the verification personnel, or the system can automatically adjust it to "not ready" after the video call is connected.

[0104] First, the verification personnel adjusted to the "ready" state are sorted according to the time when they were adjusted to the "ready" state to form a queue of verification personnel to be assigned, wherein the "ready" list is dynamically refreshed. Then, when responding to a video connection request, the "ready" one with the earliest video connection is established first and then removed from the "ready" list.

[0105] In some embodiments of the present disclosure, when responding to a video connection request, if the queue is empty for 30 seconds (for example only), the request initiator is prompted that "too many people are calling in at the moment, please wait a few minutes before calling in" (for example only), and after the request initiator clicks to confirm, the page for waiting for video interview is returned. At this time, the page is still in the "waiting for interview" state, and the "initiate interview (i.e. video review request)" can still be initiated. If the queue is not empty, the verification person with the first sequence number (i.e., the earliest ready time) is directly assigned.

[0106] If the allocation is successful, the verification personnel will receive the video call instruction and click to connect manually, and the video call will be carried out after success. If the request initiator has hung up before clicking to connect or the verification personnel did not click to connect in time, etc., resulting in the failure of the two parties to successfully connect the video, the original allocation will be cancelled, and the request initiator will be in the "waiting for interview" state, but can still "initiate an interview".

[0107] In some embodiments of the present disclosure, the duration for the requester to initiate a video can be 30 seconds (just an example). If the video cannot be connected within 30 seconds, the user will be returned to the waiting video interview page and will still be in the "waiting for video interview" state. The user can still "initiate a video interview".

[0108] According to an embodiment of the present disclosure, performing a second round of biometric identification on the applicant and / or N company shareholders based on multimedia information in operation 680 may include: performing at least one of facial recognition, voiceprint recognition, and micro-expression recognition on the applicant and / or N company shareholders based on multimedia information.

[0109] According to the embodiments of the present disclosure, referring to Figure 1 The server 105 can compare the on-site photos of the applicant and / or N company shareholders with the corresponding facial information uploaded by the applicant, and calculate the facial recognition score of the applicant and / or N company shareholders according to the matching degree of facial elements. If the score exceeds the threshold, the facial recognition comparison passes, otherwise the facial recognition fails. In the process of online video interview, multiple random facial recognitions can be performed to determine whether there is a change of person in the middle, reduce the possibility of fraud, and avoid problems such as business personnel failing to discover or colluding in time.

[0110] Utilizing the online loan review method of the disclosed embodiment, it is possible to use biometric recognition technologies such as micro-expression judgment, voiceprint recognition, and face recognition to verify the operating conditions of the applicant's company through online video, replacing the "going to the household" link of business personnel. Under the premise of ensuring that business risks are controllable, it improves business processing efficiency and the degree of intensive operation, and promotes economies of scale.

[0111] Figure 8 The flowchart of performing micro-expression recognition on the applicant and / or N company shareholders according to an embodiment of the present disclosure is schematically shown.

[0112] like Figure 8 As shown, micro-expression recognition of the applicant and / or N shareholders of the company can be implemented through operations S810 to S830.

[0113] In operation S810, micro-expressions of the applicant and / or N company shareholders are acquired based on the multimedia information.

[0114] In operation S820 , the micro-expression of each of the applicant and / or the N company shareholders is scored using a micro-expression recognition model.

[0115] In operation S830, when the score is less than or equal to a preset value, it is determined that the loan request is not approved.

[0116] According to an embodiment of the present disclosure, during the video review process, the verification personnel ask questions to the applicant and / or any one of the N company shareholders based on the scenario script library set up in advance, and record the answers and whether the answers are abnormal. Among them, the scenario script library can be configured according to products and regions. In the process of multiple people answering in a video review at the same time, when the verification personnel ask questions to a certain person, his answer may have an impact on other people, and the micro-expression changes of other shareholders can be recorded. Therefore, in the scenario where multiple people participate in the video review, combining micro-expression recognition technology can increase the possibility of discovering potential problems.

[0117] According to the embodiments of the present disclosure, the micro-expression anti-fraud model can be used to capture the subtle and abnormal facial expressions of the applicant and / or N company shareholders during the entire face-to-face interview from the current video data, thereby improving the accuracy of anti-fraud. Specifically, the micro-expression anti-fraud model can be trained using a micro-expression library formed by historical collection. For example, for facial expression changes, there can be 21 expression features such as pursing lips, frowning, and closing eyes, and for psychological emotional changes, there can be 7 basic emotional features such as sadness, joy, anger, and surprise.

[0118] Therefore, a micro-expression recognition scoring card can be established based on the micro-expression anti-fraud model, and a numerical value can be pre-set. If the score is lower than the minimum value, it is considered that there is a fraud risk and the loan request is confirmed to be rejected.

[0119] In some embodiments of the present disclosure, for example, when multiple people are conducting an online video interview, if one person's score is lower than a preset value, the loan request can be directly confirmed as not approved. In other embodiments, the micro-expression score of each person can be calculated first, and then all micro-expression scores can be comprehensively scored, and the approval of the loan request can be confirmed based on the comprehensive score.

[0120] Fig. 9 The flowchart of performing voiceprint recognition on an applicant and / or N company shareholders according to an embodiment of the present disclosure is schematically shown.

[0121] like Fig. 9 As shown, voiceprint recognition of the applicant and / or N shareholders of the company can be implemented through operations S910 to S920.

[0122] In operation S910, a first voiceprint feature is obtained based on multimedia information, and the first voiceprint feature is compared with a voiceprint feature in a black voiceprint library, wherein the black voiceprint library includes pre-stored voiceprint features of users with loan risks.

[0123] In operation S920, when the first voiceprint feature is similar to the voiceprint feature in the black voiceprint library, it is determined that the loan request is not approved.

[0124] According to the embodiments of the present disclosure, audio information can be recorded during the video interview, the voiceprint features of the auditee (such as the applicant and / N shareholders of the company) can be extracted, and matched with the existing black voiceprint library. If a match is found, the audit is rejected. In other embodiments of the present disclosure, the recent voiceprint features in the same area can be matched first to see if they are similar, thereby reducing the workload and improving the computing efficiency.

[0125] The online loan review method of the disclosed embodiment can solve the problem that the traditional model cannot meet the needs of small and micro financing business. The verification personnel can remotely contact the audited person through multimedia methods such as audio and video to verify the company information and understand the operating conditions of the company applying for the loan. The voiceprint features in the audio information are extracted and compared with the black voiceprint library, which reduces the workload of the verification personnel.

[0126] Fig.10 The block diagram of the online loan review device 1000 according to an embodiment of the present disclosure is schematically shown.

[0127] like Fig.10 As shown, the online loan review device 1000 may include a request receiving module 1010 , a link sending module 1020 , a material receiving module 1030 , a biometric recognition module 1040 and a loan review module 1050 .

[0128] The request receiving module 1010 may, for example, perform operation S210 to receive a loan request submitted by an applicant, wherein the loan request includes information of N shareholders of the company to which the applicant belongs, wherein N is an integer greater than or equal to 2.

[0129] The sending link module 1020 may, for example, perform operation S220 to send verification links to N shareholders of the company respectively.

[0130] The receiving material module 1030 may, for example, perform operation S230 to receive N loan verification materials, wherein each loan verification material is uploaded by each company shareholder through a corresponding verification link.

[0131] The biometric identification module 1040 may, for example, perform operation S240 for performing a first round of biometric identification on each corresponding company shareholder based on each loan verification material.

[0132] The loan review module 1050 may, for example, perform operation S250 to review the loan request after the number of N shareholders of the company who pass the first round of biometric identification meets a first preset condition.

[0133] According to an embodiment of the present disclosure, the biometric recognition module 1040 may also perform operations S310 to S320, and operations S410 to S420, for example. The method is used to obtain a face image of a company shareholder in a video file for face recognition; and / or obtain voice information read by a company shareholder in a video file for recognition, including: converting the voice information into text information, comparing the text information with the verification information; and obtaining a second voiceprint feature based on the voice information, and comparing the second voiceprint feature with the voiceprint feature in a black voiceprint library, wherein the black voiceprint library includes pre-stored voiceprint features of users with loan risks.

[0134] According to an embodiment of the present disclosure, the biometric identification module 1040 may also perform operations S510 to S520, for example, to determine that the first round of biometric identification is passed, including: the face image of the company shareholder matches the face image in the information of the company shareholder. And / or the text information matches the verification information, and the voiceprint feature is not similar to the voiceprint feature in the black voiceprint library.

[0135] According to an embodiment of the present disclosure, the loan review module 1050 can, for example, perform operations S610 to S680, and is used to send loan authorization documents to N company shareholders respectively, and the loan authorization documents include loan information in the loan request. Receive the loan authorization document signed online by N company shareholders. After the number of signed company shareholders meets the second preset condition, allow the applicant and / or the N company shareholders to initiate a video review request. The loan review module 1050 is also used to receive a video review request initiated by the applicant and / or the N company shareholders. In response to the video review request, establish an online video connection with the applicant and / or the N company shareholders. Obtain multimedia information of the applicant and / or the N company shareholders based on the online video connection. Perform a second round of biometric identification on the applicant and / or the N company shareholders based on the multimedia information. And based on the results of the second round of biometric identification, review the loan request.

[0136] According to an embodiment of the present disclosure, the online loan review device 1000 may further include a video connection module. The video connection module may, for example, perform operations S710 to S730 to obtain status information of M verification personnel, where M is an integer greater than or equal to 2. At least two verification personnel whose status information is ready are sorted according to the ready time. And the verification personnel with the earliest ready time establish an online video connection with the applicant and / or N company shareholders.

[0137] Fig.11The structural diagram of the biometric recognition module 1040 according to an embodiment of the present disclosure is schematically shown.

[0138] like Fig.11 As shown, the biometric recognition module 1040 may include a face recognition module 1141, a voiceprint recognition module 1142 and a micro-expression recognition module 1143, which may perform at least one of face recognition, voiceprint recognition and micro-expression recognition on the applicant and / or N company shareholders based on multimedia information.

[0139] According to an embodiment of the present disclosure, the micro-expression recognition module 1143 may, for example, perform operations S810 to S830 to obtain micro-expressions of the applicant and / or N shareholders of the company based on the multimedia information. The micro-expression recognition model is used to score the micro-expressions of each of the applicant and / or N shareholders of the company. When the score is less than or equal to a preset value, it is confirmed that the loan request is not approved.

[0140] According to an embodiment of the present disclosure, the voiceprint recognition module 1142 may, for example, perform operations S910 to S920 to obtain a first voiceprint feature based on multimedia information, and compare the first voiceprint feature with a voiceprint feature in a black voiceprint library, wherein the black voiceprint library includes pre-stored voiceprint features of users with loan risks. When the first voiceprint feature is similar to the voiceprint feature in the black voiceprint library, it is confirmed that the loan request is not approved.

[0141] Fig.12 A block diagram of an online loan review device 1200 according to another embodiment of the present disclosure is schematically shown.

[0142] like Fig.12 As shown, the online loan review device 1200 may include a system screening module 1210 , a supplementary information module 1220 , a shareholders' meeting initiation module 1230 , an online video verification module 1240 , a verification business processing module 1250 and a verification business review module 1260 .

[0143] The system screening module 1210 can choose whether to turn on the online loan review switch according to the product type, model type, and affiliated institution. For example, "Enterprise loan type-tobacco loan-A region bank branch" can be subject to online loan review, and "Personal loan type-entrepreneurship loan-B region bank" cannot be subject to online loan review. At this time, the salesperson can be asked to conduct on-site investigations and other operations according to the traditional mode. After the online loan review switch is turned on, it can be screened according to factors such as loan amount and risk factor. Users who meet all the screening conditions will be allowed to enter and the loan submitted by the user will be allowed to be reviewed online.

[0144] The supplementary information module 1220 can be used to remind the applicant to submit the business license, applicant's ID card, spouse's ID card and marriage certificate and other image materials, as well as the shareholder information of the applicant's company, etc. after the system screening module 1210 allows it. Then, the supplementary information module 1220 can automatically review the materials and remind the customer to upload them again if they do not meet the requirements.

[0145] The shareholder meeting initiating module 1230 may perform operations S220 to S230 and operations S610 to S630 to send a verification link or a loan authorization document to shareholders and receive verification materials or signed loan authorization documents.

[0146] The online video verification module 1240 may perform operations S640 to S660 and operations S710 to S730 to receive an online video request from an applicant and / or a shareholder of the company and establish an online video connection.

[0147] The verification business processing module 1250 can receive the company basic information verification, image data verification, video detail verification, applicant credit inquiry results, and verification suggestions submitted by the verification personnel, and process them according to the specific situation. Specifically, for example, if the verification suggestion is that the loan review is not passed, it can be directly rejected and a failure notice is sent to the applicant. For another example, if the verification suggestion is passed, it is confirmed to be passed and a pass notice is sent to the applicant. For another example, if the verification suggestion is pending, it is sent to the verification business review module 1260.

[0148] The business verification module 1260 can make judgments based on the information submitted by the customer, video records and system risk prompts, and notify the customer to withdraw money if the review is passed.

[0149] Compared with the traditional mode of "going to households", it is difficult for business personnel to "go to households" continuously, and the number of customers served per day is limited. By using the online loan review and loan device of the disclosed embodiment, the number of customers that verification personnel can serve can be greatly increased, and the business efficiency is significantly improved compared with the traditional mode.

[0150] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0151] For example, any multiple modules in the online loan review device 1000 or the online loan review device 1200 can be combined into one module, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one module in the online loan review device 1000 or the online loan review device 1200 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in any appropriate combination of any of them. Alternatively, at least one module in the online loan review device 1000 or the online loan review device 1200 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be executed.

[0152] Fig.13 A block diagram of a computer system suitable for implementing an online loan review method and apparatus according to an embodiment of the present disclosure is schematically shown. Fig.13 The computer system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0153] like Fig.13As shown, the computer system 1300 according to the embodiment of the present disclosure includes a processor 1301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1302 or the program loaded from the storage part 1308 to the random access memory (RAM) 1303. The processor 1301 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 1301 may also include an onboard memory for caching purposes. The processor 1301 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

[0154] In RAM 1303, various programs and data required for the operation of system 1300 are stored. Processor 1301, ROM 1302 and RAM 1303 are connected to each other through bus 1304. Processor 1301 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 1302 and / or RAM 1303. It should be noted that the program can also be stored in one or more memories other than ROM 1302 and RAM 1303. Processor 1301 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0155] According to an embodiment of the present disclosure, the system 1300 may further include an input / output (I / O) interface 1305, which is also connected to the bus 1304. The system 1300 may further include one or more of the following components connected to the I / O interface 1305: an input section 1306 including a keyboard, a mouse, etc.; an output section 1307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1308 including a hard disk, etc.; and a communication section 1309 including a network interface card such as a LAN card, a modem, etc. The communication section 1309 performs communication processing via a network such as the Internet. A drive 1310 is also connected to the I / O interface 1305 as needed. A removable medium 1311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1310 as needed, so that a computer program read therefrom is installed into the storage section 1308 as needed.

[0156] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1309, and / or installed from the removable medium 1311. When the computer program is executed by the processor 1301, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0157] An embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains a program code for executing the method provided by the embodiment of the present disclosure. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the online loan review method provided by the embodiment of the present disclosure.

[0158] When the computer program is executed by the processor 1301, the above functions defined in the system / device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0159] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 1309, and / or installed from the removable medium 1311. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0160] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0161] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0162] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Without departing from the scope of the present disclosure, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. An online loan review method, include: Receive a loan request submitted by an applicant, wherein the loan request includes information of N shareholders of the company to which the applicant belongs, wherein N is an integer greater than or equal to 2; Send verification links to each of the N shareholders of the company; Receiving N loan verification materials, wherein each of the loan verification materials is uploaded by each shareholder of the company through the corresponding verification link; Performing a first round of biometric identification on each corresponding shareholder of the company based on each of the loan verification materials; and After the number of N shareholders of the company who pass the first round of biometric identification meets the first preset condition, the loan request is reviewed, wherein the satisfaction of the first preset condition indicates that the shareholders of the company in this loan request meet the conditions for forming a valid shareholders' meeting resolution, and the identities of each shareholder are true; The review of the loan request includes: Conducting a second round of biometric identification and address matching on the applicant and / or N shareholders of the company, where the second round of biometric identification includes micro-expression recognition and voiceprint recognition; The micro-expression recognition includes recording the micro-expression changes of other shareholders when multiple people are answering questions to a certain person in a video review, specifically including scoring each person's micro-expression; and comprehensively scoring all micro-expression scores; The voiceprint recognition includes extracting the voiceprint features of the person under review and comparing them with the voiceprint features in the black voiceprint library, wherein the black voiceprint library includes pre-stored voiceprint features of users with loan risks; The address matching includes locating the location of the applicant or the location of at least one shareholder and matching it with the actual business address of the company.

2. The online loan review method according to claim 1, in, The review of the loan request includes: Receiving a video review request initiated by the applicant and / or N shareholders of the company; In response to the video review request, establish an online video connection with the applicant and / or N shareholders of the company; Acquiring multimedia information of the applicant and / or N shareholders of the company based on the online video connection; Performing a second round of biometric identification on the applicant and / or N shareholders of the company based on the multimedia information; and Based on the results of the second round of biometrics, the loan request is reviewed.

3. The online loan review method according to claim 2, in, The performing a second round of biometric identification on the applicant and / or the N shareholders of the company based on the multimedia information further includes: Perform facial recognition on the applicant and / or the N shareholders of the company based on the multimedia information.

4. The online loan review method according to claim 3, in, The performing micro-expression recognition on the applicant and / or the N shareholders of the company based on the multimedia information includes: Acquire micro-expressions of the applicant and / or N shareholders of the company based on the multimedia information; The micro-expression of each of the applicant and / or the N shareholders of the company is scored using a micro-expression recognition model.

5. The online loan review method according to claim 3, in, The voiceprint feature of the person under review includes a first voiceprint feature, and the voiceprint recognition of the applicant and / or the N shareholders of the company based on the multimedia information includes: Acquire the first voiceprint feature based on the multimedia information, and compare the first voiceprint feature with the voiceprint features in a black voiceprint library, wherein the black voiceprint library includes pre-stored voiceprint features of users with loan risks; When the first voiceprint feature is similar to the voiceprint feature in the black voiceprint library, it is confirmed that the loan request has not been approved.

6. The online loan review method according to claim 2, wherein the step of establishing an online video connection with the applicant and / or N shareholders of the company in response to the video review request. include: Obtaining status information of M verification personnel, where M is an integer greater than or equal to 2; sorting the at least two verification personnel whose status information is in the ready state according to the ready time; and The verification personnel who are ready earlier will establish an online video connection with the applicant and / or N shareholders of the company.

7. The online loan review method according to claim 2, in, Before receiving the video review request initiated by the applicant and / or N shareholders of the company, it also includes: Sending loan authorization documents to each of the N shareholders of the company, wherein the loan authorization documents include the loan information in the loan request; Receive the loan authorization document signed online by N shareholders of the company; After the number of the company shareholders who have signed meets the second preset condition, the applicant and / or N of the company shareholders are allowed to initiate a video review request.

8. The online loan review method according to claim 1, in, The receiving of N loan verification materials includes: A video file uploaded by the company shareholder through the verification link is received, wherein the video file includes content of the company shareholder reading verification information, wherein the verification information is used to verify the identity of the company shareholder.

9. The online loan review method according to claim 8, in, The first round of biometric identification of each corresponding shareholder of the company based on each loan verification material includes: Obtaining facial images of shareholders of the company in the video file for facial recognition; and / or Acquiring the voice information read aloud by the shareholder of the company in the video file for recognition, including: converting the voice information into text information, and comparing the text information with the verification information; and A second voiceprint feature is obtained based on the voice information, and the second voiceprint feature is compared with a voiceprint feature in a black voiceprint library, wherein the black voiceprint library includes pre-stored voiceprint features of users with loan risks.

10. The online loan review method according to claim 9, in, The first round of biometric verification includes: The facial image of the shareholder of the company matches the facial image in the information of the shareholder of the company; and / or The text information matches the verification information, and the voiceprint feature is not similar to the voiceprint features in the black voiceprint library.

11. An online loan review device, include: A request receiving module, configured to receive a loan request submitted by an applicant, wherein the loan request includes information of N shareholders of the company to which the applicant belongs, wherein N is an integer greater than or equal to 2; A link sending module, used for sending verification links to N shareholders of the company respectively; A material receiving module, used for receiving N loan verification materials, wherein each of the loan verification materials is uploaded by each shareholder of the company through the corresponding verification link; A biometric identification module, used for performing a first round of biometric identification on each corresponding shareholder of the company based on each of the loan verification materials; and A loan review module, configured to review the loan request after the number of N shareholders of the company who have passed the first round of biometric identification meets a first preset condition, wherein satisfying the first preset condition indicates that the shareholders of the company in this loan request meet the conditions for forming a valid shareholders' meeting resolution and the identities of the shareholders are true; Wherein, the biometric recognition module includes a micro-expression recognition module, and the review of the loan request includes: Conducting a second round of biometric identification and address matching on the applicant and / or N shareholders of the company, where the second round of biometric identification includes micro-expression recognition and voiceprint recognition; The micro-expression recognition module is used to record the micro-expression changes of other shareholders when multiple people ask questions to a certain person during a video review, including scoring each person's micro-expression; and comprehensively scoring all micro-expression scores; The voiceprint recognition includes extracting the voiceprint features of the person under review and comparing them with the voiceprint features in the black voiceprint library, wherein the black voiceprint library includes pre-stored voiceprint features of users with loan risks; The address matching includes locating the location of the applicant or the location of at least one shareholder and matching it with the actual business address of the company.

12. An electronic device, include: One or more memories storing executable instructions; as well as One or more processors execute the executable instructions to implement the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the method according to any one of claims 1 to 10.

14. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.