TWI676145B - Online review method and system - Google Patents

Abstract

An online auditing system includes a first electronic device, a bank server, and a customer database. When the bank server receives a bid request from the first electronic device that includes image data related to a face and an identity information and is related to a bid for a financial commodity, it is based on the face of the person who has extracted the image data. One of the characteristic data and the identification data determines the target customer information, and when it is determined that the facial characteristic data and the identification data respectively match the reference identification information and reference facial characteristic data of the target customer information, A credit rating model generates a credit rating result based on the face of the image data, and executes the bid for the financial product when it is determined that the credit rating result is not less than a threshold level.

Description

Online auditing method and system

The invention relates to a method and system for soliciting and reviewing, in particular to an online method and system for soliciting and reviewing.

Existing online banks are available for customers to apply for financial products online. However, when the identity of the customer is fraudulently used by other users who are different from the customer (common fraudulent methods include, for example, the use of fake ID cards), The other user's application for financial commodity transactions, such as loans, may cause losses to the customer and the bank.

In addition, even if the identity of the customer is not fraudulent, when the customer's credit is poor, it may affect the performance of the transaction. Therefore, the bank still needs to conduct a credit evaluation of the customer. Banks usually make assessments based on the records corresponding to the customer that they have stored or provided by the Joint Collection Center. However, there is still room for improvement in the credibility of the evaluation results based on the records alone.

Therefore, an object of the present invention is to provide at least one online review method, which can overcome at least one disadvantage of the prior art.

Therefore, the online auditing method of the present invention is suitable for execution by an electronic system, which includes a first electronic device operated by a user, and a first electronic device provided by a bank that can be connected with the first electronic device. A bank server that communicates and stores a pre-trained credit rating model and a customer database connected to the bank server. The customer database stores multiple customer data corresponding to multiple customers of the bank. Each piece of customer data has reference identification data and reference facial feature data. The method includes:

(A) With the first electronic device, obtain the image data related to a face and an identity information through the user operation, and send a bid request containing the image data and related to a financial commodity application to the bank server;

(B) When the bank server receives the bid request from the first electronic device, the facial feature data of the human face and the identification information of the identity information are extracted from the image data, and One of the facial feature data and the identification data, and use one of the customer data as the target customer data;

(C) determining, by the bank server, whether the facial feature data and the identification data match the reference facial feature data and the reference identity data of the target customer data, respectively;

(D) when the bank server determines that the facial feature data and the identification data match the reference identity data and the reference facial feature data of the target customer data, respectively, by the credit rating A model that generates a credit rating result based on at least the face of the image data; and

(E) With the bank server, when it is determined that the credit rating result is not less than a threshold level, the bid for the financial commodity is executed.

In some implementation aspects, in step (B), the bank server determines whether the reference facial feature data of one of the facial feature data and the customer data stored in the customer database is the same. When the similarity between them is not less than a first threshold, the customer information is used as the target customer information.

In some implementation aspects, the bank server further stores a pre-trained face feature comparison model. In step (B), the bank server performs comparison by using the face feature comparison model. In order to obtain the similarity between the facial feature data and the reference facial feature data of the customer data.

In some implementation aspects, each piece of customer data stored in the customer database also has bid history record data, and the bid history record data has at least one financial commodity that the customer has applied for corresponding to the customer data. In step (C), the bank server not only determines whether the facial feature data and the identification data match the reference identity data and reference facial feature data of the target customer data, but also based on the target customer data. The bid history record data determines whether the financial commodity related to the bid request is the same as one of the financial commodities of the bid history record data of the target customer data. In step (D), the bank server is determining that the The facial feature data and the identification data respectively correspond to the reference identity data and the reference facial feature data of the target customer data, and the financial commodity related to the bid request does not correspond to the bid history of the target customer data. When one of the financial commodities in the data is the same, by using the credit rating model, at least The personal data of the face, resulting in the credit rating results.

In some implementations, the bank server can also communicate with a levy server belonging to the levy center. Step (D) further includes:

(d1) With the bank server, it is determined that the facial feature data and the identification data match the reference identity data and reference facial feature data of the target customer data, respectively, and that the bid request When the financial commodity is not the same as one of the financial commodities of the bid history data of the target customer data, sending a data request of the reference identification data including the target customer data to the levy server;

(d2) by using the affiliate server, upon receiving the data request from the bank server, transmitting associative data related to the credit history of the customer corresponding to the target customer data to the bank server; and

(d3) Using the bank server and the credit rating model to generate the credit rating result based on at least the face of the image data and the joint data.

In some implementation aspects, in step (d2), the joint data has at least one of a credit card payment record, a loan record, an education level, a job type, and a job title corresponding to the customer corresponding to the target customer information. .

In some implementation aspects, the bank server further stores an external environmental indicator, the external environmental indicator includes at least one of a current gross domestic product (GDP) and a boom signal. In step ( In d3), the bank server uses the credit rating model to generate the credit rating result not only based on the face of the image data and the joint data, but also based on the external environmental indicators.

In some embodiments, the system further includes a second electronic device capable of communicating with the bank server. In step (C), it is determined that the facial feature information and the identification information do not respectively match the reference identity information and the reference facial feature data of the target customer information, or the financial information related to the bid request When the commodity is the same as one of the financial commodities of the bid history data of the target customer information, a first notification message related to the manual note is sent to the second electronic device for display. In step (E), when the bank server determines that the credit rating result is less than the threshold level, it sends a second notification message related to the manual note to the second electronic device for display.

In some implementations, in step (A), the first electronic device obtains the image data by photographing a document containing the human face and the identity information.

In some implementation aspects, in step (A), the first electronic device obtains first image data related to the identity information by photographing a document containing the identity information and by photographing the user's The face to obtain second image data related to the human face, the image data including the first image data and the second image data.

Therefore, it is an object of the present invention to provide at least one online review system that can overcome at least one disadvantage of the prior art.

Therefore, the online auditing system of the present invention includes a first electronic device operated by a user, a bank server and a customer database. The bank server is provided by a bank and can communicate with the first electronic device and store a pre-trained credit rating model. The customer database is connected to the bank server. The customer database stores a plurality of customer data corresponding to a plurality of customers of the bank, and each customer data includes reference identification data and reference facial feature data.

The first electronic device obtains image data related to a face and an identity information through the operation of the user, and sends a bid request containing the image data and related to a financial commodity application to the bank server.

When the bank server receives the bid request from the first electronic device, it extracts the facial feature data of the face and the identification information of the identity information from the image data, and according to the facial feature data and the One of the identification data, the one of the customer data is used as the target customer data.

The bank server determines whether the facial feature data and the identification data match the reference facial feature data and the reference identity data of the target customer data, respectively.

When the bank server determines that the facial feature data and the identification data match the reference identity data and the reference facial feature data of the target customer data, respectively, by using the credit rating model, at least according to the image The face of the data produces a credit rating result.

When the bank server determines that the credit rating result is not less than a threshold level, it executes the bid for the financial commodity.

In some implementation aspects, the bank server determines that the similarity between the facial feature data and the reference facial feature data of one of the customer data stored in the customer database is not less than one. At the first threshold, the customer information is used as the target customer information.

In some implementation aspects, the bank server also stores a pre-trained face feature comparison model, and compares the face feature comparison model to obtain the face feature data and the Similarity between the reference facial feature data of the customer data.

In some implementation forms, each piece of customer data stored in the customer database also has bid history record data, and the bid history record data has at least one financial commodity that the customer has applied for corresponding to the customer data.

The bank server not only determines whether the facial feature data and the identification information match the reference identity information and reference facial feature data of the target customer data, but also based on the bid history data of the target customer data Determine whether the financial commodity related to the bid request is the same as one of the financial commodities of the bid history record data of the target customer data.

The bank server determines that the facial feature data and the identification data match the reference identity data and reference facial feature data of the target customer data, respectively, and that the financial commodity related to the bid request is not related to the When one of the financial commodities of the bid history data of the target customer data is the same, the credit rating model is used to generate the credit rating result based on at least the face of the image data.

In some implementations, the bank server may also communicate with a joint collection server belonging to the joint collection center. The bank server determines that the facial feature data and the identification data match the reference identity data and reference facial feature data of the target customer data, respectively, and that the financial commodity related to the bid request is not related to the When one of the financial commodities of the bid history data of the target customer data is the same, a data request including the reference identification data of the target customer data is transmitted to the levy server. When the joint server receives the data request from the bank server, the joint server sends to the bank server associated data of the customer's credit record corresponding to the target client data. The bank server uses the credit rating model to generate the credit rating result based on at least the face of the image data and the joint data.

In some implementation aspects, the joint data has at least one of a credit card payment record, a loan record, an education level, a job type, and a job title corresponding to the customer corresponding to the target customer information.

In some implementation forms, the bank server further stores an external environmental indicator, the external environmental indicator includes at least one of a current gross domestic product (GDP) and a boom signal. The bank server uses the credit rating model to generate the credit rating result not only based on the face and the joint data of the image data, but also based on the external environmental indicators.

In some embodiments, the system further includes a second electronic device capable of communicating with the bank server. The bank server determines that the facial feature data and the identification information do not match the reference identity information and the reference facial feature data of the target customer data, respectively, or the financial commodity related to the bid request and the When one of the financial commodities of the bid history record data of the target customer data is the same, a first notification message related to the artificial note is sent to the second electronic device for display. When the bank server determines that the credit rating result is less than the threshold level, it sends a second notification message related to the manual note to the second electronic device for display.

In some implementation forms, the first electronic device obtains the image data by photographing a document containing the human face and the identity information.

In some implementations, the first electronic device obtains first image data related to the identity information by photographing a document containing the identity information and obtains the image information related to the user by photographing the face of the user. Second image data of a human face, the image data including the first image data and the second image data.

The effect of the present invention is that the bank server can determine that the facial feature data and the identification data are consistent with the target customer data, and use the credit rating model based on the face data of the face data. Only when the more credible credit rating result is not less than the threshold level, the bidding of the financial commodity is allowed. In this way, not only can the possibility of being misused by the customer's identity be effectively reduced, but also the external appearance of the face There is a great chance that characteristics are related to economic characteristics, so it can also effectively reduce the risk of banks.

Before the present invention is described in detail, it should be noted that in the following description, similar elements are represented by the same numbers.

Referring to FIG. 1 and FIG. 2, the online auditing system of the present invention includes a bank server 1, a customer database 2, a first electronic device 3, and a second electronic device 4.

The bank server 1 is provided by a bank and can communicate with the first electronic device 3, the second electronic device 4 and a joint collection server 6 belonging to the joint collection center via a communication network 5. The bank server 1 stores a pre-trained credit rating model 11, a pre-trained face feature comparison model 12, and an external environmental indicator 13. The external environmental indicator 13 includes, for example, the current gross domestic product ( Gross Domestic Product (GDP) and boom lights.

The customer database 2 is connected to the bank server 1 and stores a plurality of customer data 21, 21 'corresponding to a plurality of customers of the bank, respectively. Each customer data 21 (21') has reference identification information 211, With reference to the facial feature data 212 and the bid history record data 213, the bid history record data 213 has at least one financial commodity that the customer has applied for corresponding to the customer data 21 (21 '). In this embodiment, the financial commodities are, for example, credit cards, loans, insurance, and the like.

The first electronic device 3 is held by a user, such as a customer of the bank. In this embodiment, the first electronic device 3 is, for example, a smart phone, and is not limited thereto. In other embodiments, it may also be a tablet computer, a notebook computer, or a personal computer.

In this embodiment, the second electronic device 4 is held by a staff member of the bank, for example. In this embodiment, the first electronic device 3 is, for example, a personal computer, and is not limited thereto. In other implementations, the first electronic device 3 may also be a tablet computer, a notebook computer, or a smart phone.

In the following description, in the case where the user holds the first electronic device 3 and an identity card in order to apply for a credit card online, an embodiment of how the above embodiment cooperates with the joint collection server 6 to implement the online review and examination method of the present invention .

First, as described in step S201, the first electronic device 3 obtains image data related to a face and an identity information through the user operation. In this embodiment, the identity information is, for example, an identity card number, and is not limited thereto.

In this embodiment, the first electronic device 3 obtains the image data by shooting a document containing the human face and the identity information, but is not limited thereto. For example, the first electronic device 3 captures the front side of the ID card (including a headshot and an ID card number) held by the user, and obtains image data related to the face and the ID card number. In other embodiments, the first electronic device 3 obtains the first image data related to the identity information by shooting a document containing the identity information, and obtains the related image information by shooting the user's face. The second image data of the human face, the image data including the first image data and the second image data, for example, the first electronic device 3 captures the front side of the identity card held by the user to obtain It is related to the first image data of the ID card number, and the second image data related to the human face is obtained by shooting the user's face. It is worth mentioning that because the image data obtained in this way is related The face of the user is the face of the user's proper face. Compared with the photo taken on the ID card, the result of steps S205 and S207 in this embodiment has relatively better accuracy.

Then, as described in step S202, the first electronic device 3 sends an application request containing the image data and related to a financial commodity application to the bank server 1. Continuing the previous example, the bid request is related to the credit card bid.

When the bank server 1 receives the bid request from the first electronic device 3, as described in step S203, the bank server 1 extracts facial feature data of the face and the identity information from the image data. Identification information.

Next, in step S204, the bank server 1 uses the one of the customer data 21 and 21 '(for example, the customer data 21') as the target customer data according to one of the facial feature data and the identification data. twenty one'. In this embodiment, the bank server 1 determines between the facial feature data and the reference facial feature data 211 of one of the customer data 21, 21 'stored in the customer database 2. When the similarity is not less than a first threshold, the customer information 21, 21 'is used as the target customer information (that is, the customer information 21'), and is not limited thereto. In other implementation aspects, the bank server 1 may also be designed to determine the identity identification information that is the same as the reference identity identification information 212 of one of the customer data 21, 21 ', to identify the customers. The data 21, 21 'is used as the target customer data (ie, the customer data 21').

It is worth noting that, in this embodiment, the bank server 1 compares the facial feature comparison model 12 in order to obtain the facial feature data and the customer data 21, 21 '. Reference to the similarity between face feature data 212 can effectively reduce the system's computing resources, but is not limited to this. In other implementations, the general face can be used instead of the face feature comparison model 12 The feature comparison software compares the facial feature data with all such reference facial feature data 212. It is worth noting that when the number of such reference facial feature data 212 is large, if the facial feature data is compared with the reference facial feature data 212 one by one, it will be very time-consuming and consume computing resources, and In this embodiment, the face feature comparison model 12 trained in advance is used for comparison, so there is no need to compare one by one, and it has the effect of saving time and saving computing resources.

In step S205, the bank server 1 determines whether the facial feature data and the identification data match the reference identity data 211 and reference facial feature data 212 of the target customer data (ie, customer data 21 '), respectively. . If the bank server 1 determines that the facial feature data and the identification data do not match the target identity data 211 and the reference facial feature data 212 of the target customer data (ie, the customer data 21 '), the process Proceed to step S206. On the contrary, if the bank server 1 determines that the facial feature data and the identification data respectively match the reference identification data 211 and the reference person of the target customer data (that is, the customer data 21 '). For the facial feature data 212, the flow proceeds to step S207.

In step S206, a first notification message related to the manual note is transmitted to the second electronic device 4 for display. In this way, the staff of the bank can be notified immediately that the credentials held by the user may be forged for subsequent processing, so that the risk of fraudulent identity of the customer can be reduced.

In step S207, the bank server 1 determines whether the financial commodity related to the bid request is related to the target customer information (i.e., customer information 21) based on the bid history data 213 of the target customer information (i.e., customer information 21 ') One of the financial commodities of the bid history record data 213 is the same. When the bank server 1 determines that the financial product related to the bid request is the same as one of the financial records of the bid history record data 213 of the target customer data (ie, customer data 21 '), the flow proceeds to step S206, otherwise The process proceeds to step S208. In this way, the staff of the bank can be notified immediately about the target customer profile (ie customer profile 21 ') corresponding to the customer's application for the same financial product to be repeated, so that subsequent processing can reduce The client's identity was compromised. If the previous example shows that when the user wants to apply for a credit card that is the same as the one indicated in the application history data, it is very likely that the user is a customer corresponding to the target customer data 21 ' If you immediately notify the bank's staff at this time, you can effectively reduce the chance of successful fraud.

Supplementally, in other embodiments, step S207 may also be omitted, that is, when the determination result of step S205 is YES, the flow directly proceeds to step S208.

In step S208, the bank server 1 sends a data request for the reference identification data 211 including the target customer data (i.e., the customer data 21 ') to the levy server 6.

Upon receiving the data request from the bank server 2, the levy server 6 transmits the data corresponding to the target customer data (ie, the customer data 21 ') as described in step S209. The association information of the customer's credit history is sent to the bank server 1. In this embodiment, the joint data has a credit card payment record, a loan record, an education level, a job type, and a job title corresponding to the customer corresponding to the target customer information (ie, customer information 21 ').

When the bank server 1 receives the association data from the association server 6, as described in step S210, with the credit rating model 11, according to the face and the association data of the image data, And the external environmental indicator 13 produces a credit rating result.

In step S211, the bank server 1 determines whether the credit rating result is not less than a threshold level. If the result is yes, the flow proceeds to step S212, otherwise, the flow proceeds to step S213.

In step S212, the bank server 1 executes the application for the financial commodity related to the application request. Following the previous example, the bank server 1 executes the application for the credit card.

In step S213, the bank server 1 sends a second notification message related to the manual note to the second electronic device 4 for display. In this way, the staff of the bank can be notified immediately that the user's credit rating is too low, so that subsequent processing can reduce the risk of the bank.

In summary, the bank server 1 determines the reference identity information 211 and the reference face feature data of the facial feature data and the identification information that respectively match the target customer profile (ie, customer profile 21 '). 212 and only when the credit rating model 11 is based on the face of the image data, the joint information and the external environmental indicator 13 and the credible credit rating result is not less than the threshold level, Allowing the application of the financial commodity, in this way, not only can effectively reduce the possibility of being misused by the identity of the customer, but also the external characteristics of the human face have a great chance to be related to economic characteristics, so it can also effectively reduce the risk of the bank .

However, the above are only examples of the present invention. When the scope of implementation of the present invention cannot be limited in this way, any simple equivalent changes and modifications made in accordance with the scope of the patent application and the content of the patent specification of the present invention are still Within the scope of the invention patent.

100‧‧‧online review system

1‧‧‧bank server

11‧‧‧Credit Rating Model

12‧‧‧Face feature comparison model

13‧‧‧ External environmental indicators

2‧‧‧Customer database

21, 21 ’‧‧‧ Customer Information

211‧‧‧Reference identification information

212‧‧‧Refer to facial feature data

213‧‧‧ bid history

3‧‧‧The first electronic device

4‧‧‧Second electronic device

5‧‧‧Communication Network

6‧‧‧Joining Server

S201 ~ S213‧‧‧step

Other features and effects of the present invention will be clearly presented in the embodiment with reference to the drawings, in which: FIG. 1 is a block diagram exemplarily illustrating an embodiment of the online auditing system of the present invention; A flowchart exemplarily illustrates an embodiment of the online auditing method of the present invention.

Claims (18)

An online auditing method suitable for execution by an electronic system including a first electronic device operated by a user and a bank provided by a bank that can communicate with and store the first electronic device There is a bank server with a pre-trained credit rating model and a customer database connected to the bank server. The customer database stores a plurality of customer data corresponding to multiple customers of the bank. Each customer The data includes reference identification data, reference facial feature data, and bid history record data. The bid history record data has at least one financial product that the customer has applied for corresponding to the customer data. The method includes: (A) Using the first electronic device to obtain image data related to a face and an identity information through the operation of the user, and transmitting a bid request containing the image data and related to a financial commodity application to the bank server; (B) With the bank server, when receiving the bid request from the first electronic device, retrieve from the image data The facial feature data of the face and the identification information of the identity information, and based on one of the facial feature data and the identification information, one of the customer data is used as the target customer data; (C) borrowing The bank server determines whether the facial feature data and the identification data match the reference facial feature data and the reference identity data of the target customer data, and also according to the bid history of the target customer data The data determines whether the financial product related to the bid request is the same as one of the financial records of the bid history data of the target customer data; (D) the bank server determines the facial feature data and the The identification information corresponds to the reference identity information and the reference facial feature data of the target customer information, and the financial commodity related to the bid request is not one of the financial commodities of the target customer data and the bid history record data At the same time, by using the credit rating model, a credit is generated based on at least the face of the image data. And other results; and (E) by the bank server, when it is determined that the result of the credit rating of not less than a threshold level, the implementation of the financial bid for commodities. The online review method according to claim 1, wherein in step (B), the bank server determines whether one of the facial feature data and the customer data stored in the customer database is When the similarity between the reference facial feature data is not less than a first threshold, the customer data is used as the target customer data. The online review method according to claim 2, wherein the bank server further stores a pre-trained face feature comparison model. In step (B), the bank server uses the face The feature comparison model is used to perform comparison to obtain the similarity between the facial feature data and the reference facial feature data of the customer data. The online levy review method according to claim 1, wherein the bank server can also communicate with a levy server belonging to the levy center, and step (D) further includes: (d1) using the bank server Device, when it is determined that the facial feature data and the identification data respectively match the reference identity information and the reference facial feature data of the target customer data, and that the financial commodity related to the bid request is not related to the target customer When one of the financial commodities of the bid history record data of the data is the same, a data request including the reference identification data of the target customer data is transmitted to the levy server; (d2) through the levy server, When receiving the data request from the bank server, send association data related to the credit history of the customer corresponding to the target customer data to the bank server; and (d3) through the bank server, borrow The credit rating model generates the credit rating result based on at least the face of the image data and the joint data. The online solicitation method according to claim 4, wherein, in step (d2), the joint solicitation data has a credit card payment record, a loan record, an education level, and a job corresponding to the customer corresponding to the target customer information At least one of a category and a title. The online auditing method according to claim 5, wherein the bank server further stores an external environmental indicator, the external environmental indicator includes a current gross domestic product (GDP) and a boom signal. At least one, in step (d3), the bank server uses the credit rating model to generate the credit rating not only based on the face and the joint data of the image data, but also based on the external environmental indicators. And so on. As described in claim 6, the system further comprises a second electronic device capable of communicating with the bank server, wherein: in step (C), the face feature data and the The identification information does not correspond to the reference identity information and the reference facial feature information of the target customer information, or one of the financial products of the bidding history record data related to the bidding request and the target customer data. At the same time, a first notification message related to the manual note is sent to the second electronic device for display; and in step (E), when the bank server determines that the credit rating result is less than the threshold level , Sending a second notification message related to the manual note to the second electronic device for display. The online review method according to claim 1, wherein in step (A), the first electronic device obtains the image data by photographing a document containing the face and the identity information. The online review method according to claim 1, wherein, in step (A), the first electronic device obtains first image data related to the identity information by shooting a document containing the identity information, and The second image data related to the human face is obtained by photographing the user's face, and the image data includes the first image data and the second image data. An online auditing system includes: a first electronic device operated by a user; a bank server provided by a bank and capable of communicating with the first electronic device and storing a pre-trained credit rating And other models; and a customer database connected to the bank server, the customer database stores multiple customer data corresponding to multiple customers of the bank, each of which has reference identity information and reference face features Data, and bid history record data, the bid history record data has at least one financial commodity that the customer has applied for corresponding to the customer data; wherein the first electronic device is obtained by the user's operation and related to a human face and An image of identity information, and sends a bid request containing the image data and a bid for a financial commodity to the bank server; wherein the bank server is receiving the bid request from the first electronic device The facial feature data of the face and the identification information of the identity information are extracted from the image data, and According to one of the facial feature data and the identification data, the one of the customer data is used as the target customer data; wherein, the bank server determines whether the facial feature data and the identification data respectively match the target data. The reference facial feature data of the target customer data and the reference identity identification data are further determined based on the bid history record data of the target customer data, and whether the financial commodity related to the bid request is related to the bid history of the target customer data. One of the financial commodities of the recorded data is the same; wherein, the bank server determines that the facial feature data and the identification data match the reference identity information and the reference facial feature data of the target customer data, respectively, and the When the financial commodity related to the bid request is not the same as one of the financial commodities of the bid history record data of the target customer information, a credit rating is generated by the credit rating model based on at least the face of the image data And other results; and, the bank server determines that the credit rating result is not At the time of a threshold level, the implementation of the financial bid for commodities. The online review system as described in claim 10, wherein the bank server determines whether the reference facial feature data of one of the face feature data and the customer data stored in the customer database is When the similarity between them is not less than a first threshold, the customer information is used as the target customer information. The online review system according to claim 11, wherein the bank server further stores a pre-trained face feature comparison model, and compares the face feature comparison model to obtain The similarity between the facial feature data and the reference facial feature data of the customer data. The online review system according to claim 10, wherein: the bank server can also communicate with a joint collection server belonging to the joint collection center; the bank server is determining the facial feature data and the identity The identification information respectively matches the reference identity identification information and the reference facial feature information of the target customer information, and the financial commodity related to the application request is not the same as one of the financial commodities of the application history record data of the target customer information When sending a data request containing the target customer's data to the reference identification information to the syndication server; when the syndication server receives the data request from the bank server, it transmits the information related to the target customer The association information of the customer's credit record corresponding to the data is sent to the bank server; and the bank server uses the credit rating model to generate the credit based on at least the face of the image data and the association information Rating results. The online review system according to claim 13, wherein the joint collection information has at least one of a credit card payment record, a loan record, an education level, a job type, and a job title corresponding to the customer corresponding to the target customer information . The online review system according to claim 14, wherein the bank server further stores an external environmental indicator, the external environmental indicator includes a current gross domestic product (GDP) and a boom signal At least one of them; and the bank server generates the credit rating result based on the credit rating model not only based on the face of the image data and the associated data, but also based on the external environmental indicators. The online review system according to claim 15, further comprising a second electronic device capable of communicating with the bank server, wherein: the bank server determines that the facial feature data and the identification data are not different When the reference identity information and the reference facial feature data corresponding to the target customer data, or one of the financial commodities related to the bid history record data of the target customer data is the same as the financial commodity related to the bid request, send a A first notification message related to a manual note to the second electronic device for display; and the bank server sends a second notification message related to a manual note when it determines that the credit rating result is less than the threshold level To the second electronic device for display. The online review system according to claim 10, wherein the first electronic device obtains the image data by photographing a document containing the face and the identity information. The online review system according to claim 10, wherein the first electronic device obtains first image data related to the identity information by photographing a document containing the identity information and by photographing the user's The face to obtain second image data related to the human face, the image data including the first image data and the second image data.