TW202009838A - Online application method and system for accurately determining a credit rating result based on which an application for financial commodity is executed - Google Patents
Online application method and system for accurately determining a credit rating result based on which an application for financial commodity is executed Download PDFInfo
- Publication number
- TW202009838A TW202009838A TW107127726A TW107127726A TW202009838A TW 202009838 A TW202009838 A TW 202009838A TW 107127726 A TW107127726 A TW 107127726A TW 107127726 A TW107127726 A TW 107127726A TW 202009838 A TW202009838 A TW 202009838A
- Authority
- TW
- Taiwan
- Prior art keywords
- data
- bank server
- customer
- facial feature
- face
- Prior art date
Links
Images
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
Description
本發明是有關於一種徵審方法及系統,特別是指一種線上徵審方法及系統。The present invention relates to a method and system for solicitation and examination, in particular to an online method and system for solicitation.
現有的網路銀行可供其客戶於線上申辦金融商品,然而,當客戶之身分被相異於該客戶之其他使用者冒用(常見的冒用的方式包含例如利用偽造身份證),若允許該其他使用者申辦金融商品之交易,譬如貸款,則恐造成該客戶及該銀行之損失。Existing online banks can be used by their customers to apply for financial products online. However, when the customer's identity is used by other users different from the customer (common methods of counterfeiting include, for example, the use of fake ID cards), if allowed The other user's bid for a financial commodity transaction, such as a loan, may cause losses to the customer and the bank.
此外,即便該客戶之身份未被冒用,當該客戶之信用不佳,也可能影響交易之履行,因此,銀行仍需要對該客戶進行信用評估。銀行通常是根據其所儲存的或者聯徵中心所提供的對應於該客戶的紀錄來進行評估,然而,僅根據所述紀錄所做出的評估結果之可信度仍有提升的空間。In addition, even if the customer's identity is not used fraudulently, when the customer's credit is not good, 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 they have stored or provided by the Lianzheng Center corresponding to the customer. However, there is still room for improvement in the credibility of the assessment results based on the records alone.
因此,本發明之目的,即在提供一種線上徵審方法,能克服現有技術的至少一缺點。Therefore, the purpose of the present invention is to provide an online examination method, which can overcome at least one of the disadvantages of the prior art.
於是,本發明線上徵審方法,適於藉由一電子系統執行,該電子系統包含一由一使用者所操作的第一電子裝置,以及由一銀行所提供的一個可與該第一電子裝置通訊且儲存有一個預先訓練出的信用評等模型的銀行伺服器及一連接該銀行伺服器的客戶資料庫,該客戶資料庫儲存有多筆分別對應於該銀行的多個客戶的客戶資料,每筆客戶資料具有參考身分識別資料及參考人臉特徵資料,該方法包含:Therefore, the online review method of the present invention is suitable to be executed by an electronic system including a first electronic device operated by a user and a first electronic device provided by a bank Communicate and store a bank server with 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 customer profile has reference identification data and reference facial feature data. The method includes:
(A)藉由該第一電子裝置,經該使用者操作獲得相關於一人臉及一身份資訊的影像資料,並傳送一個包含該影像資料且相關於一金融商品之申辦的申辦請求至該銀行伺服器;(A) Through the first electronic device, obtain image data related to a face and identity information through the operation of the user, and send a bid request containing the image data and related to a bid for a financial product to the bank server;
(B)藉由該銀行伺服器,在接收到來自該第一電子裝置的該申辦請求時,自該影像資料擷取出該人臉的人臉特徵資料及該身份資訊的身份識別資料,並根據人臉特徵資料及該身份識別資料其中一者,將該等筆客戶資料其中一者作為目標客戶資料;(B) Through the bank server, when receiving the bid request from the first electronic device, extract the facial feature data of the face and the identification information of the identification information from the image data, and according to One of the face feature data and the identification data, one of the customer data is used as the target customer data;
(C) 藉由該銀行伺服器,判定該人臉特徵資料及該身份識別資料是否分別相符於該目標客戶資料的該參考人臉特徵資料及該參考身分識別資料;(C) through the bank server, determine whether the facial feature data and the identification data are consistent with the reference facial feature data and the reference identification data of the target customer data, respectively;
(D) 藉由該銀行伺服器,在判定出該人臉特徵資料及該身份識別資料分別相符於該目標客戶資料的該參考身分識別資料及參考人臉特徵資料時,藉由該信用評等模型,至少根據該影像資料的該人臉,產生一信用評等結果;及(D) With the bank server, when it is determined that the facial feature data and the identification data are consistent with the reference identity data and reference facial feature data of the target customer data, respectively, by the credit rating The model, based at least on the face of the image data, produces a credit rating result; and
(E) 藉由該銀行伺服器,在判定出該信用評等結果不小於一門檻等級時,執行該金融商品之申辦。(E) Through the bank server, when it is determined that the credit rating result is not less than a threshold level, execute the bid for the financial product.
在一些實施態樣中,在步驟(B)中,該銀行伺服器在判定出該人臉特徵資料與該客戶資料庫所儲存的該等筆客戶資料其中一者的該參考人臉特徵資料之間的相似度不小於一第一門檻值時,將該等筆客戶資料其中該者作為該目標客戶資料。In some implementation aspects, in step (B), the bank server determines the reference facial feature data of one of the facial feature data and the customer data stored in the customer database When the similarity between the two is not less than a first threshold value, the one of the customer data is used as the target customer data.
在一些實施態樣中,該銀行伺服器還儲存有一個預先訓練出的人臉特徵比對模型,在步驟(B)中,該銀行伺服器是藉由該人臉特徵比對模型來進行比對以便獲得該人臉特徵資料與該等筆客戶資料的該等參考人臉特徵資料之間的相似度。In some implementations, the bank server also stores a pre-trained face feature comparison model. In step (B), the bank server compares 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.
在一些實施態樣中,該客戶資料庫所儲存的每筆客戶資料還具有申辦歷史紀錄資料,該申辦歷史紀錄資料具有該筆客戶資料所對應的該客戶所申辦過的至少一個金融商品,在步驟(C)中,該銀行伺服器不僅判定該人臉特徵資料及該身份識別資料是否分別相符於該目標客戶資料的該參考身分識別資料及參考人臉特徵資料,還更根據該目標客戶資料的該申辦歷史紀錄資料判定該申辦請求所相關的該金融商品是否與該目標客戶資料的該申辦歷史紀錄資料的其中一金融商品相同,在步驟(D)中,該銀行伺服器在判定出該人臉特徵資料及該身份識別資料分別相符於該目標客戶資料的該參考身分識別資料及參考人臉特徵資料,且該申辦請求所相關的該金融商品未與該目標客戶資料的該申辦歷史紀錄資料的其中一金融商品相同時,藉由該信用評等模型,至少根據該影像資料的該人臉,產生該信用評等結果。In some implementation forms, each customer data stored in the customer database also has application history record data, and the application history record data has at least one financial commodity that the customer corresponding to the customer data has applied for, in 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 data of the bid determines whether the financial commodity related to the bid request is the same as one of the financial commodities of the bid history data of the target customer data. In step (D), the bank server determines the The facial feature data and the identification data respectively match the reference identification data and the reference facial feature data of the target customer data, and the financial product related to the bid request does not match the bid history of the target customer data When one of the financial products in the 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.
在一些實施態樣中,該銀行伺服器還可與一歸屬於聯徵中心的聯徵伺服器相互通訊,步驟(D)還包含:In some implementation forms, the bank server can also communicate with a Lianzheng server belonging to the Lianzheng center. Step (D) further includes:
(d1)藉由該銀行伺服器,在判定出該人臉特徵資料及該身份識別資料分別相符於該目標客戶資料的該參考身分識別資料及參考人臉特徵資料,且該申辦請求所相關的該金融商品未與該目標客戶資料的該申辦歷史紀錄資料的其中一金融商品相同時,傳送一包含該目標客戶資料的該參考身份識別資料的資料請求至該聯徵伺服器;(d1) Through the bank server, the reference identity data and reference face feature data that determine that the facial feature data and the identification data respectively match the target customer data, and the relevant bid request When the financial product is not the same as one of the financial products in the bid history data of the target customer data, send a data request containing the reference identification data of the target customer data to the Lianzheng server;
(d2)藉由該聯徵伺服器,在接收到來自該銀行伺服器的該資料請求時,傳送相關於該目標客戶資料所對應的該客戶的信用紀錄的聯徵資料至該銀行伺服器;及(d2) Through the Lianzheng server, upon receiving the data request from the bank server, send the Lianzheng data related to the customer's credit record corresponding to the target customer data to the bank server; and
(d3)藉由該銀行伺服器,藉由該信用評等模型,至少根據該影像資料的該人臉及該聯徵資料,產生該信用評等結果。(d3) Using the bank server and the credit rating model, the credit rating result is generated based at least on the face and the joint data of the image data.
在一些實施態樣中,在步驟(d2)中,該聯徵資料具有對應於該目標客戶資料所對應的該客戶的信用卡繳款紀錄、貸款紀錄、教育程度、工作類別以及職稱其中至少一者。In some implementation aspects, in step (d2), the joint levy data has at least one of the credit card payment record, loan record, education level, job type, and job title of the customer corresponding to the target customer data .
在一些實施態樣中,該銀行伺服器還儲存一外部環境指標,該外部環境指標包含一當前的國內生產總值(Gross Domestic Product,GDP)及一景氣燈號其中至少一者,在步驟(d3)中,該銀行伺服器藉由該信用評等模型,不僅根據該影像資料的該人臉及該聯徵資料,還更根據該外部環境指標,產生該信用評等結果。In some implementations, the bank server also stores an external environmental indicator that includes at least one of a current gross domestic product (Gross Domestic Product, GDP) and a prosperity indicator. In the step ( In d3), 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.
在一些實施態樣中,該系統還包含一可與該銀行伺服器相互通訊的第二電子裝置。在步驟(C)中,在判定出該人臉特徵資料及該身份識別資料未分別相符於該目標客戶資料的該參考身分識別資料及參考人臉特徵資料,或該申辦請求所相關的該金融商品與該目標客戶資料的該申辦歷史紀錄資料的其中一金融商品相同時,傳送一相關於人工照會的第一通知訊息至該第二電子裝置以供其顯示。在步驟(E)中,該銀行伺服器在判定出該信用評等結果小於該門檻等級時,傳送一個相關於人工照會的第二通知訊息至該第二電子裝置以供其顯示。In some embodiments, the system further includes a second electronic device that can communicate with the bank server. In step (C), when it is determined that the facial feature data and the identification data do not respectively match the reference identity data and reference facial feature data of the target customer data, or the financial related to the bid request When the commodity is the same as one of the financial commodities in the bid history data of the target customer data, a first notification message related to the manual note is sent to the second electronic device for display. In step (E), when determining that the credit rating result is less than the threshold level, the bank server sends a second notification message related to the manual note to the second electronic device for display.
在一些實施態樣中,在步驟(A)中,該第一電子裝置是藉由拍攝一包含該人臉及該身份資訊的證件來獲得該影像資料。In some implementation aspects, in step (A), the first electronic device obtains the image data by photographing a certificate containing the face and the identity information.
在一些實施態樣中,在步驟(A)中,該第一電子裝置是藉由拍攝一包含該身份資訊的證件來獲得相關於該身分資訊的第一影像資料且藉由拍攝該使用者的臉部來獲得相關於該人臉的第二影像資料,該影像資料包含該第一影像資料及該第二影像資料。In some embodiments, in step (A), the first electronic device obtains the first image data related to the identity information by shooting a certificate containing the identity information and by shooting the user's The face obtains second image data related to the human face, and the image data includes the first image data and the second image data.
因此,本發明之目的,即在提供一種線上徵審系統,能克服現有技術的至少一缺點。Therefore, the purpose of the present invention is to provide an online examination system that can overcome at least one of the shortcomings of the prior art.
於是,本發明線上徵審系統包含一由一使用者操作的第一電子裝置、一銀行伺服器及一客戶資料庫。該銀行伺服器由一銀行所提供,並可與該第一電子裝置通訊且儲存有一個預先訓練出的信用評等模型。該客戶資料庫連接該銀行伺服器,該客戶資料庫儲存有多筆分別對應於該銀行的多個客戶的客戶資料,每筆客戶資料具有參考身分識別資料及參考人臉特徵資料。Therefore, the online review 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 stores a pre-trained credit rating model. The customer database is connected to the bank server, and the customer database stores a plurality of customer data corresponding to the customers of the bank, and each customer data has reference identification data and reference facial feature data.
該第一電子裝置經該使用者操作獲得相關於一人臉及一身份資訊的影像資料,並傳送一個包含該影像資料且相關於一金融商品之申辦的申辦請求至該銀行伺服器。The first electronic device obtains image data related to a face and identity information through the operation of the user, and transmits a bid request containing the image data and related to the bid of a financial commodity to the bank server.
該銀行伺服器在接收到來自該第一電子裝置的該申辦請求時,自該影像資料擷取出該人臉的人臉特徵資料及該身份資訊的身份識別資料,並根據人臉特徵資料及該身份識別資料其中一者,將該等筆客戶資料其中一者作為目標客戶資料。When receiving the bid request from the first electronic device, the bank server 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 will use one of these customer data as the target customer data.
該銀行伺服器判定該人臉特徵資料、該身份識別資料是否分別相符於該目標客戶資料的該參考人臉特徵資料及該參考身分識別資料。The bank server determines whether the facial feature data and the identification data are consistent with the reference facial feature data and the reference identity identification data of the target customer data, respectively.
該銀行伺服器在判定出該人臉特徵資料及該身份識別資料分別相符於該目標客戶資料的該參考身分識別資料及參考人臉特徵資料時,藉由該信用評等模型,至少根據該影像資料的該人臉,產生一信用評等結果。When the bank server determines that the facial feature data and the identification data are consistent with the reference identification data and the reference facial feature data of the target customer data, using the credit rating model, at least according to the image The face of the data produces a credit rating result.
該銀行伺服器在判定出該信用評等結果不小於一門檻等級時,執行該金融商品之申辦。The bank server executes the bid for the financial product when it determines that the credit rating result is not less than a threshold level.
在一些實施態樣中,該銀行伺服器在判定出該人臉特徵資料與該客戶資料庫所儲存的該等筆客戶資料其中一者的該參考人臉特徵資料之間的相似度不小於一第一門檻值時,將該等筆客戶資料其中該者作為該目標客戶資料。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, one of these customer profiles is used as the target customer profile.
在一些實施態樣中,該銀行伺服器還儲存有一個預先訓練出的人臉特徵比對模型,並且是藉由該人臉特徵比對模型來進行比對以便獲得該人臉特徵資料與該等筆客戶資料的該等參考人臉特徵資料之間的相似度。In some implementations, the bank server also stores a pre-trained face feature comparison model, and the face feature comparison model is used for comparison to obtain the face feature data and the The similarity between the reference facial feature data of equal customer data.
在一些實施態樣中,該客戶資料庫所儲存的每筆客戶資料還具有申辦歷史紀錄資料,該申辦歷史紀錄資料具有該筆客戶資料所對應的該客戶所申辦過的至少一個金融商品。In some implementation forms, each piece of customer data stored in the customer database also has application history record data, and the application history record data has at least one financial commodity that the customer corresponding to the customer data has applied for.
該銀行伺服器不僅判定該人臉特徵資料及該身份識別資料是否分別相符於該目標客戶資料的該參考身分識別資料及參考人臉特徵資料,還更根據該目標客戶資料的該申辦歷史紀錄資料判定該申辦請求所相關的該金融商品是否與該目標客戶資料的該申辦歷史紀錄資料的其中一金融商品相同。The bank server not only determines whether the facial feature data and the identification data are consistent with the reference identification data 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 product related to the bidding request is the same as one of the financial products in the bidding history data of the target customer data.
該銀行伺服器在判定出該人臉特徵資料及該身份識別資料分別相符於該目標客戶資料的該參考身分識別資料及參考人臉特徵資料,且該申辦請求所相關的該金融商品未與該目標客戶資料的該申辦歷史紀錄資料的其中一金融商品相同時,藉由該信用評等模型,至少根據該影像資料的該人臉,產生該信用評等結果。The bank server determines that the face identification data and the identification data respectively match the reference identification data and reference face characteristic data of the target customer data, and the financial product related to the bid request does not When one of the financial products in 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 at least on the face of the image data.
在一些實施態樣中,該銀行伺服器還可與歸屬於聯徵中心的一聯徵伺服器相互通訊。該銀行伺服器在判定出該人臉特徵資料及該身份識別資料分別相符於該目標客戶資料的該參考身分識別資料及參考人臉特徵資料,且該申辦請求所相關的該金融商品未與該目標客戶資料的該申辦歷史紀錄資料的其中一金融商品相同時,傳送一包含該目標客戶資料的該參考身份識別資料的資料請求至該聯徵伺服器。該聯徵伺服器在接收到來自該銀行伺服器的該資料請求時,傳送相關於該目標客戶資料所對應的該客戶的信用紀錄的聯徵資料至該銀行伺服器。該銀行伺服器藉由該信用評等模型,至少根據該影像資料的該人臉及該聯徵資料,產生該信用評等結果。In some embodiments, the bank server can also communicate with a Lianzheng server belonging to the Lianzheng center. The bank server determines that the face identification data and the identification data respectively match the reference identification data and reference face characteristic data of the target customer data, and the financial product related to the bid request does not When one of the financial products of the bid history data of the target customer data is the same, a data request containing the reference identification data of the target customer data is sent to the Lianzheng server. When receiving the data request from the bank server, the levy server sends the levy data related to the customer's credit record corresponding to the target customer data to the bank server. The bank server uses the credit rating model to generate the credit rating result based on at least the face and the joint data of the image data.
在一些實施態樣中,該聯徵資料具有對應於該目標客戶資料所對應的該客戶的信用卡繳款紀錄、貸款紀錄、教育程度、工作類別以及職稱其中至少一者。In some implementation forms, the joint levy data has at least one of the customer's credit card payment record, loan record, education level, job type, and job title corresponding to the target customer data.
在一些實施態樣中,該銀行伺服器還儲存一外部環境指標,該外部環境指標包含一當前的國內生產總值(Gross Domestic Product,GDP)及一景氣燈號其中至少一者。該銀行伺服器藉由該信用評等模型,不僅根據該影像資料的該人臉及該聯徵資料,還更根據該外部環境指標,產生該信用評等結果。In some implementations, the bank server also stores an external environmental indicator, which includes at least one of a current gross domestic product (GDP) and a boom indicator. 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 environment indicators.
在一些實施態樣中,該系統還包含一可與該銀行伺服器相互通訊的第二電子裝置。該銀行伺服器在判定出該人臉特徵資料及該身份識別資料未分別相符於該目標客戶資料的該參考身分識別資料及參考人臉特徵資料,或該申辦請求所相關的該金融商品與該目標客戶資料的該申辦歷史紀錄資料的其中一金融商品相同時,傳送一相關於人工照會的第一通知訊息至該第二電子裝置以供其顯示。該銀行伺服器在判定出該信用評等結果小於該門檻等級時,傳送一個相關於人工照會的第二通知訊息至該第二電子裝置以供其顯示。In some embodiments, the system further includes a second electronic device that can communicate with the bank server. The bank server determines that the face identification data and the identification data do not respectively match the reference identification data and reference face characteristic data of the target customer data, or the financial product related to the bid request and the financial When one of the financial commodities in the bid history data of the target customer data is the same, a first notification message related to the manual note is sent to the second electronic device for display. When determining that the credit rating result is less than the threshold level, the bank server sends a second notification message related to the manual note to the second electronic device for display.
在一些實施態樣中,該第一電子裝置是藉由拍攝一包含該人臉及該身份資訊的證件來獲得該影像資料。In some implementations, the first electronic device obtains the image data by photographing a certificate containing the face and the identity information.
在一些實施態樣中,該第一電子裝置是藉由拍攝一包含該身份資訊的證件來獲得相關於該身分資訊的第一影像資料且藉由拍攝該使用者的臉部來獲得相關於該人臉的第二影像資料,該影像資料包含該第一影像資料及該第二影像資料。In some embodiments, the first electronic device obtains the first image data related to the identity information by photographing a certificate containing the identity information and obtains the related image data by photographing the user's face The second image data of the face, the image data includes the first image data and the second image data.
本發明之功效在於:該銀行伺服器能藉由在判定出該人臉特徵資料及該身份識別資料皆相符於該目標客戶資料且藉由該信用評等模型根據該影像資料的該人臉所產生的更為可信的信用評等結果不小於該門檻等級時,才允許該金融商品之申辦,如此,不僅能有效降低被該客戶身分被冒用之可能,且人臉所呈現的外在特徵有很大的機會與經濟特徵有關,故還能有效降低銀行之風險。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 the credit rating model based on the facial data of the image data. Only when the result of a more credible credit rating is not less than the threshold level, the bidding of the financial product is allowed, which not only can effectively reduce the possibility of fraudulent use of the customer's identity, but also the external appearance of the face There is a great chance that the characteristics are related to the economic characteristics, so it can effectively reduce the risks of the bank.
在本發明被詳細描述之前,應當注意在以下的說明內容中,類似的元件是以相同的編號來表示。Before the present invention is described in detail, it should be noted that in the following description, similar elements are denoted by the same numbers.
參閱圖1與圖2,本發明線上徵審系統包含、一銀行伺服器1、一客戶資料庫2、一第一電子裝置3、及一第二電子裝置4。1 and 2, the online review system of the present invention includes a bank server 1, a
該銀行伺服器1由一銀行所提供,並可經由一通訊網路5與該第一電子裝置3、該第二電子裝置4以及歸屬於聯徵中心的一聯徵伺服器6相互通訊。該銀行伺服器1儲存有一個預先訓練出的信用評等模型11、一個預先訓練出的人臉特徵比對模型12以及外部環境指標13,該外部環境指標13例如包含當前的國內生產總值(Gross Domestic Product,GDP)及景氣燈號。The bank server 1 is provided by a bank and can communicate with the first
該客戶資料庫2連接該銀行伺服器1,並儲存有多筆分別對應於該銀行的多個客戶的客戶資料21、21’,每筆客戶資料21(21’)具有參考身分識別資料211、參考人臉特徵資料212及申辦歷史紀錄資料213,該申辦歷史紀錄資料213具有該筆客戶資料21(21’)所對應的該客戶所申辦過的至少一個金融商品。在本實施例中,該金融商品例如為信用卡、貸款及保險等等。The
該第一電子裝置3由一使用者所持有,該使用者例如為該銀行之客戶。在本實施例中,該第一電子裝置3例如為一智慧型電話,並不以此為限,在其他實施態樣中亦可為平板電腦、筆記型電腦或者個人電腦等等。The first
在本實施例中,該第二電子裝置4例如由該銀行之工作人員所持有。在本實施例中,該第一電子裝置3例如為一個人電腦,並不以此為限,在其他實施態樣中亦可為平板電腦、筆記型電腦或智慧型電話等等。In this embodiment, the second electronic device 4 is held by a bank staff, for example. In this embodiment, the first
以下說明在該使用者持有該第一電子裝置3及一身分證以便於線上申辦一信用卡的情況下,上述實施例如何配合該聯徵伺服器6執行本發明線上徵審方法的一實施例。The following describes how the above embodiment cooperates with the
首先,如步驟S201所述,該第一電子裝置3經該使用者操作獲得相關於一人臉及一身份資訊的影像資料。在本實施例中,該身份資訊例如為身分證字號,並不以此為限。First, as described in step S201, the first
在本實施例中,該第一電子裝置3是藉由拍攝一包含該人臉及該身份資訊的證件來獲得該影像資料,但不以此為限。舉例來說,該第一電子裝置3拍攝該使用者所持有的該身分證的正面(包含大頭照及身分證字號),即可獲得相關於該人臉及身分證字號的影像資料。在其他實施態樣中,該第一電子裝置3是藉由拍攝一包含該身份資訊的證件來獲得相關於該身分資訊的第一影像資料且藉由拍攝該使用者的臉部來獲得相關於該人臉的第二影像資料,該影像資料包含該第一影像資料及該第二影像資料,舉例來說,該第一電子裝置3拍攝該使用者所持有的該身分證的正面來獲得相關於該身分證字號第一影像資料,並藉由拍攝該使用者的臉部來獲得相關於該人臉的第二影像資料,值得一提的是,由於以此方式獲得的影像資料所相關的該人臉是該使用者適當前的臉部樣貌,相較於身分證上的大頭照,能使得本實施例後續步驟S205及S207所產生的結果具有相對較佳的準確性。In this embodiment, the first
接著,如步驟S202所述,該第一電子裝置3傳送一個包含該影像資料且相關於一金融商品之申辦的申辦請求至該銀行伺服器1。延續前例,該申辦請求相關於該信用卡之申辦。Next, as described in step S202, the first
該銀行伺服器1在接收到來自該第一電子裝置3的該申辦請求時,如步驟S203所述,該銀行伺服器1自該影像資料擷取出該人臉的人臉特徵資料及該身份資訊的身份識別資料。When the bank server 1 receives the bid request from the first
接著,在步驟S204中,該銀行伺服器1根據人臉特徵資料及該身份識別資料其中一者,將該等筆客戶資料21、21’其中一者(例如客戶資料21’)作為目標客戶資料21’。在本實施例中,該銀行伺服器1在判定出該人臉特徵資料與該客戶資料庫2所儲存的該等筆客戶資料21、21’其中一者的該參考人臉特徵資料211之間的相似度不小於一第一門檻值時,將該等筆客戶資料21、21’其中該者作為該目標客戶資料(即客戶資料21’),並不以此為限。在其他實施態樣中,該銀行伺服器1也可被設計為在判定出該身分識別資料相同於該等客戶資料21、21’其中一者的該參考身分識別資訊212時,將該等客戶資料21、21’其中該者作為該目標客戶資料(即客戶資料21’)。Next, in step S204, the bank server 1 uses one of the
值得說明的是,在本實施例中,該銀行伺服器1是藉由該人臉特徵比對模型12來進行比對以便獲得該人臉特徵資料與該等筆客戶資料21、21’的該等參考人臉特徵資料212之間的相似度,如此能有效降低系統的運算資源,但不以此為限,在其他實施態樣中,可不利用人臉特徵比對模型12而利用一般的臉部特徵比對軟體將該人臉特徵資料與所有該等參考人臉特徵資料212進行比對。值得注意的是,在該等參考人臉特徵資料212的數量龐大時,若將該人臉特徵資料逐一地與該等參考人臉特徵資料212比對,將十分耗時且消耗運算資源,而本實施例利用預先訓練的該人臉特徵比對模型12來進行比對,則不需逐一地比對而具有省時且節省運算資源的效果。It is worth noting that in this embodiment, the bank server 1 compares the facial
在步驟S205中,該銀行伺服器1判定該人臉特徵資料及該身份識別資料是否分別相符於該目標客戶資料(即客戶資料21’)的該參考身分識別資料211及參考人臉特徵資料212。若該銀行伺服器1在判定出該人臉特徵資料及該身份識別資料未分別相符於該目標客戶資料(即客戶資料21’)的該參考身分識別資料211及參考人臉特徵資料212,流程進行至步驟S206,反之,若該銀行伺服器1在判定出該人臉特徵資料及該身份識別資料分別相符於該目標客戶資料(即客戶資料21’)的該參考身分識別資料211及參考人臉特徵資料212,流程進行至步驟S207。In step S205, the bank server 1 determines whether the facial feature data and the identification data respectively match the
在步驟S206中,傳送一相關於人工照會的第一通知訊息至該第二電子裝置4以供其顯示。如此,可即時通知該銀行的工作人員該使用者所持有的證件可能是偽造的,以便進行後續處理,如此,能降低該客戶身分被冒用之風險。In step S206, a first notification message related to manual notes is sent to the second electronic device 4 for display. In this way, the staff of the bank can be notified immediately that the document held by the user may be forged for subsequent processing, so that the risk of the customer's identity being used can be reduced.
在步驟S207中,該銀行伺服器1根據該目標客戶資料(即客戶資料21’)的該申辦歷史紀錄資料213判定該申辦請求所相關的該金融商品是否與該目標客戶資料(即客戶資料21’)的該申辦歷史紀錄資料213的其中一金融商品相同。該銀行伺服器1在判定出該申辦請求所相關的該金融商品與該目標客戶資料(即客戶資料21’)的該申辦歷史紀錄資料213的其中一金融商品相同時,流程進入步驟S206,否則,流程進入步驟S208,如此,可即時通知該銀行的工作人員關於該目標客戶資料(即客戶資料21’)所對應的該客戶即將重覆的申辦相同的金融產品,以便後續的處理,能降低該客戶身分被冒用之風險。若以前例說明,當該使用者所欲申辦的信用卡相同於該申辦歷史資料中所指示出的以申辦信用卡,有很大的可能該使用者是冒用該目標客戶資料21’所對應之客戶的身份,此時若即時通知該銀行的工作人員,能有效降低冒用成功之機會。In step S207, the bank server 1 determines whether the financial product related to the bid request is in accordance with the
補充說明,在其他實施態樣中,也可省略步驟S207,亦即,當步驟S205的判定結果為是,流程直接進行至步驟S208。In addition, in other implementations, step S207 may also be omitted, that is, when the determination result of step S205 is yes, the flow directly proceeds to step S208.
在步驟S208中,該銀行伺服器1傳送一包含該目標客戶資料(即客戶資料21’)的該參考身份識別資料211的資料請求至該聯徵伺服器6。In step S208, the bank server 1 transmits a data request of the
該聯徵伺服器6在接收到來自該銀行伺服器2的該資料請求時,如步驟S209所述,該聯徵伺服器6傳送相關於該目標客戶資料(即客戶資料21’)所對應的該客戶的信用紀錄的聯徵資料至該銀行伺服器1。在本實施例中,該聯徵資料具有對應於該目標客戶資料(即客戶資料21’)所對應的該客戶的信用卡繳款紀錄、貸款紀錄、教育程度、工作類別以及職稱。When the
該銀行伺服器1在接收到來自該聯徵伺服器6的該聯徵資料時,如步驟S210所述,藉由該信用評等模型11,根據該影像資料的該人臉、該聯徵資料及該外部環境指標13,產生一信用評等結果。When the bank server 1 receives the joint levy data from the
在步驟S211中,該銀行伺服器1判定該信用評等結果是否不小於一門檻等級,若結果為是,流程進行至步驟S212,否則,流程進行至步驟S213。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 process proceeds to step S212, otherwise, the process proceeds to step S213.
步驟S212,該銀行伺服器1執行該申辦請求所相關的該金融商品之申辦。沿用前例,該銀行伺服器1執行該信用卡之申辦。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.
步驟S213,該銀行伺服器1傳送一個相關於人工照會的第二通知訊息至該第二電子裝置4以供其顯示。如此,可即時通知該銀行的工作人員關於該使用者的信用評等過低,以便後續的處理,能降低該銀行之風險。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 bank’s staff can be notified immediately that the user’s credit rating is too low for subsequent processing, which can reduce the bank’s risk.
綜上所述,該銀行伺服器1在判定出該人臉特徵資料及該身份識別資料分別相符於該目標客戶資料(即客戶資料21’)的該參考身分識別資料211及參考人臉特徵資料212且藉由該信用評等模型11根據該影像資料的該人臉、該聯徵資料及該外部環境指標13所產生的更為可信的該信用評等結果不小於該門檻等級時,才允許該金融商品之申辦,如此,不僅能有效降低被該客戶身分被冒用之可能,且人臉所呈現的外在特徵有很大的機會與經濟特徵有關,故還能有效降低銀行之風險。In summary, the bank server 1 determines that the facial feature data and the identification data respectively match the
惟以上所述者,僅為本發明之實施例而已,當不能以此限定本發明實施之範圍,凡是依本發明申請專利範圍及專利說明書內容所作之簡單的等效變化與修飾,皆仍屬本發明專利涵蓋之範圍內。However, the above are only examples of the present invention, and should not be used to limit the scope of the present invention. Any simple equivalent changes and modifications made according to the scope of the patent application of the present invention and the content of the patent specification are still classified as This invention covers the patent.
100‧‧‧線上徵審系統1‧‧‧銀行伺服器11‧‧‧信用評等模型12‧‧‧人臉特徵比對模型13‧‧‧外部環境指標2‧‧‧客戶資料庫21,21’‧‧‧客戶資料211‧‧‧參考身份識別資料212‧‧‧參考人臉特徵資料213‧‧‧申辦歷史紀錄3‧‧‧第一電子裝置4‧‧‧第二電子裝置5‧‧‧通訊網路6‧‧‧聯徵伺服器S201 ~S213‧‧‧步驟
100‧‧‧ Online review system 1‧‧‧
本發明之其他的特徵及功效,將於參照圖式的實施方式中清楚地呈現,其中: 圖1是一方塊圖,示例性地說明本發明線上徵審系統的一實施例;及 圖2是一流程圖,示例性地說明本發明線上徵審方法的一實施例。Other features and functions 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 review system of the present invention; and FIG. 2 is A flow chart exemplarily illustrates an embodiment of the online review method of the present invention.
100‧‧‧線上徵審系統 100‧‧‧ Online collection system
1‧‧‧銀行伺服器 1‧‧‧Bank server
11‧‧‧信用評等模型 11‧‧‧ Credit Rating Model
12‧‧‧人臉特徵比對模型 12‧‧‧ facial feature comparison model
13‧‧‧外部環境指標 13‧‧‧External environmental indicators
2‧‧‧客戶資料庫 2‧‧‧Customer database
21,21’‧‧‧客戶資料 21, 21’‧‧‧ Customer Information
211‧‧‧參考身份識別資料 211‧‧‧Reference identification data
212‧‧‧參考人臉特徵資料 212‧‧‧Reference to face feature data
213‧‧‧申辦歷史紀錄 213‧‧‧ Bid history
3‧‧‧第一電子裝置 3‧‧‧ First electronic device
4‧‧‧第二電子裝置 4‧‧‧Second electronic device
5‧‧‧通訊網路 5‧‧‧Communication network
6‧‧‧聯徵伺服器 6‧‧‧Lianzheng Server
Claims (20)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW107127726A TWI676145B (en) | 2018-08-09 | 2018-08-09 | Online review method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW107127726A TWI676145B (en) | 2018-08-09 | 2018-08-09 | Online review method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
TWI676145B TWI676145B (en) | 2019-11-01 |
TW202009838A true TW202009838A (en) | 2020-03-01 |
Family
ID=69188635
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW107127726A TWI676145B (en) | 2018-08-09 | 2018-08-09 | Online review method and system |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI676145B (en) |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8458074B2 (en) * | 2010-04-30 | 2013-06-04 | Corelogic Solutions, Llc. | Data analytics models for loan treatment |
CN107657525A (en) * | 2017-08-29 | 2018-02-02 | 深圳市佰仟金融服务有限公司 | One kind loan measures and procedures for the examination and approval and server |
TWM554597U (en) * | 2017-09-11 | 2018-01-21 | 臺灣土地銀行股份有限公司 | Batch loan application data processing system |
TWM557407U (en) * | 2017-11-23 | 2018-03-21 | Ctbc Bank Co Ltd | Credit review system |
CN108335193A (en) * | 2018-01-12 | 2018-07-27 | 深圳壹账通智能科技有限公司 | Whole process credit methods, device, equipment and readable storage medium storing program for executing |
TWM569027U (en) * | 2018-08-09 | 2018-10-21 | 中國信託商業銀行股份有限公司 | Online review system |
-
2018
- 2018-08-09 TW TW107127726A patent/TWI676145B/en active
Also Published As
Publication number | Publication date |
---|---|
TWI676145B (en) | 2019-11-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US12026716B1 (en) | Document-based fraud detection | |
US11023889B2 (en) | Enhanced merchant identification using transaction data | |
WO2018103456A1 (en) | Method and apparatus for grouping communities on the basis of feature matching network, and electronic device | |
CN108293054A (en) | System and method for the biometric authentication for using social networks | |
CN113989019A (en) | Method, device, equipment and storage medium for identifying risks | |
KR102110266B1 (en) | Method, apparatus and computer program for determining cryptocurrency tax evasion using artificial intelligence | |
CN109271415B (en) | Data processing method and device for credit investigation database | |
CN112053244B (en) | Information processing method, device and server | |
US20240202743A1 (en) | Learning model evaluation system, learning model evaluation method, and program | |
US20240211574A1 (en) | Learning model creating system, learning model creating method, and program | |
TWI676145B (en) | Online review method and system | |
CN113706258B (en) | Product recommendation method, device, equipment and storage medium based on combined model | |
TWM569027U (en) | Online review system | |
US20220114592A1 (en) | Printer for selectively printing symbolic information on a medium | |
US20220027916A1 (en) | Self Learning Machine Learning Pipeline for Enabling Binary Decision Making | |
CN114331463A (en) | Risk identification method based on linear regression model and related equipment thereof | |
JP7302107B1 (en) | LEARNING SYSTEMS, LEARNING METHODS AND PROGRAMS | |
CN112116356B (en) | Asset characteristic information processing method and device | |
CN116882998B (en) | Virtual currency fund analysis method | |
Rohilla et al. | Credit card frauds: an Indian perspective | |
TW202044077A (en) | Identity verification system and method for financial transactions | |
CN117853227A (en) | Risk assessment method, risk assessment device, computer equipment and storage medium | |
CN117035876A (en) | Data object exchange method, device and server | |
CN117273889A (en) | Service information acquisition method, device, equipment and medium | |
CN117974297A (en) | Service processing method, device, electronic equipment and computer readable medium |