A bank customer identity detection method, device and system

Abstract

The present invention relates to a method, device, and system for detecting bank customer identities. The method comprises: determining an identifiable identity area using a camera corresponding to a call machine, collecting facial image information, cropping the collected facial image information, and transmitting the cropped facial image information to a controller; the controller receiving the cropped facial image information, identifying it, and matching it with customer identity information; the customer inputting the type of business to be handled through the call machine, and the call machine matching the customer identity information with the type of business to be handled based on the risk category of the business type to form a business handling mode; and bank staff handling business according to the business handling mode matched with the customer identity information. The present invention fully meets the use case of bank customer identity detection and has the beneficial effect of improving bank office efficiency and intelligence.

Description

Technical Field

[0001] The present invention belongs to the technical field of smart banking, and in particular relates to a method, device and system for detecting the identity of a bank customer. Background Art

[0002] With the continuous improvement of people's living standards and the rapid development of the commerce, transportation, and tourism sectors, the development of the intelligent field is also gradually improving. At the same time, electronic contracting is rapidly penetrating into various industries. Companies in industries such as retail, manufacturing, and logistics are leveraging electronic contracts to upgrade their supply chains and enhance their competitiveness in the new infrastructure era. When conducting banking transactions, improving efficiency and enhancing the customer experience are particularly important. When conducting banking transactions, customers must queue up or sign for a number at the bank. Facial recognition is performed to verify the customer's identity. Transactions at smart ATMs trigger facial recognition, which is then triggered. Once triggered, bank staff will assist and guide the customer. Existing customer identity verification systems repeatedly require customers to undergo facial recognition, input information, and fill out written forms. This significantly wastes time, reduces banking efficiency, and provides a poor customer experience. Summary of the Invention

[0003] The purpose of the present invention is to provide a bank customer identity detection method, device and system to solve the above technical problems.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions:

[0005] An embodiment of the present invention provides a method for detecting a bank customer's identity, the method comprising:

[0006] Determine the identifiable identity area through the camera corresponding to the calling machine, collect facial image information, crop the collected facial image information, and send the cropped facial image information to the controller;

[0007] The controller receives the cropped facial image information for recognition and matches the customer identity information;

[0008] The customer enters the type of business they need to handle through the call machine. The call machine matches the customer's identity information with the type of business they need to handle based on the risk category of the business type, forming a business handling model;

[0009] Bank staff handles business in accordance with the business handling model that matches the customer's identity information.

[0010] Preferably, the method of determining the identifiable identity area by a camera corresponding to the calling machine, collecting facial image information, cropping the collected facial image information, and sending the cropped facial image information to the controller further includes the steps of:

[0011] Identify whether there is face information in the scene, if so, proceed to the next step;

[0012] Determine whether there is anyone entering or exiting; if yes, play a voice prompt; if not, proceed to the next step

[0013] Determining the number of faces in the collected facial image information;

[0014] If the number of faces in the face image information is greater than 1, a voice prompt will be played;

[0015] If the number of faces in the image is equal to 1, proceed to the next step;

[0016] If the number of faces in the image is equal to 0, then proceed to the step of identifying whether there is face information in the scene, and if so, proceed to the next step;

[0017] The collected facial image information is cropped and the cropped facial image information is sent to the controller.

[0018] Preferably, the controller receives the cropped facial image information for identification and matches the customer identity information, further comprising the steps of:

[0019] Send the facial image information collected by the camera to the face recognition module for identification;

[0020] The calling machine and the face recognition camera interact with each other to determine whether the collected face information meets the requirements. If yes, proceed to the next step. If not, replace the face image information and send the face image information collected by the camera to the face recognition module for recognition;

[0021] A mapping relationship is formed between the stored facial features and the collected customer facial images to match customers with identities, allowing customers to determine their unique identification.

[0022] Preferably, the customer inputs the type of business to be handled through the call machine, and the call machine matches the customer identity information with the type of business to be handled according to the risk category of the business type to form a business handling mode, which also includes the steps of:

[0023] If the type of business entered by the customer is not a high-risk business, the facial image information will be automatically verified after the initial facial image verification;

[0024] If the type of business the customer enters is a high-risk business, the ticket machine will initiate a request for manual verification of the facial image information;

[0025] If the facial image information is manually verified, the ticket machine sends an instruction to the camera to track the customer's movement trajectory in the business hall. The camera tracks the customer according to the instruction and saves the customer's movement trajectory data in real time;

[0026] If the customer applies for high-risk services again, the ticket calling machine determines whether the customer has left the camera monitoring area by calling the real-time stored customer movement trajectory data;

[0027] If yes, if the business type entered by the customer is a high-risk business type, the calling machine initiates a request for manual verification of the facial image information;

[0028] If no, proceed to the next step;

[0029] There is no need to manually verify facial image information, and you can directly start processing the high-risk business that you are applying for again.

[0030] Preferably, the step of forming a mapping relationship between the stored facial features and the collected customer facial images to match the customer with the identity so that the customer can determine the unique identification further includes the following steps:

[0031] Determine whether the customer in the transmitted facial image information is wearing a mask; if so, restrict the types of business that the customer wearing a mask can handle;

[0032] If the type of business to be handled input by the customer is a high-risk business type, before the ticket calling machine initiates a request for manual verification of the facial image information, the following steps are also included:

[0033] If the type of business that the customer inputs is a high-risk business type, the calling machine prompts the customer to take off the mask and proceed again. The camera corresponding to the calling machine determines the recognizable identity area, collects facial image information, crops the collected facial image information, and sends the cropped facial image information to the controller; the prompt is in the form of voice and / or text.

[0034] Preferably, the bank staff handles the business according to the business handling mode matching the customer identity information, further comprising the steps of:

[0035] Automatically matching the customer's identity information and the customer's facial recognition image information with the type of business that the customer needs to handle through the calling machine to form the business handling mode;

[0036] The bank staff makes inquiries when the customer inputs the type of business to be handled through the calling machine;

[0037] Data is sent and received in the bank's customer identity detection system through the customer information monitoring interface, and the normal customer information business processing status is fed back to the customer in real time through the normal customer information business processing status interface.

[0038] An embodiment of the present invention also provides a bank customer identity detection system, the system comprising: a camera, a calling machine, a controller, and a background management unit;

[0039] The camera includes a collection unit; the camera corresponds to the calling machine;

[0040] The camera is used to determine the identifiable area, collect facial image information, crop the collected facial image information, and send the cropped facial image information to the controller;

[0041] The acquisition unit includes:

[0042] A face acquisition module, used to acquire face image information;

[0043] A cropping module, used to crop the collected facial image information;

[0044] An interaction module, used to send the cropped facial image information to a controller;

[0045] The controller is configured to receive the cropped facial image information for recognition and match the cropped facial image information with the customer's identity information;

[0046] The calling machine is used for customers to input the type of business they need to handle, and matches the customer's identity information with the business handling mode according to the risk category of the business type;

[0047] The backend management unit is used for bank staff to handle business according to the business handling model that matches the customer identity information.

[0048] Preferably, the controller further includes a verification unit; the verification unit includes:

[0049] A facial recognition module is used to identify and match facial image information captured by a camera device; the facial image information captured by the camera device is matched by mapping the stored facial features with the captured customer facial image to match the customer with the customer's identity, thereby allowing the customer to determine a unique identification;

[0050] Face feature library module, used to store face image information;

[0051] A face comparison module is used to identify whether there is any face information in the scene, determine whether there are people entering or leaving, and determine the number of faces in the collected face image information;

[0052] A face calling module is used to encode and call the stored face image information;

[0053] The automatic verification module is used to automatically verify non-high-risk businesses based on the customer's identity information, without the need for the customer to confirm again.

[0054] Preferably, the controller further comprises: an identity detection unit; the identity detection unit comprises:

[0055] Identity information detection module, used to match customer identity information with business processing mode;

[0056] Identity information calling module, used to call customer identity information;

[0057] Preferably, the controller further includes:

[0058] Tracking module, used to obtain and save customer movement trajectory data in real time;

[0059] Risk classification module, used to classify business types or set risk categories;

[0060] Information sorting module, used to sort input and output data information;

[0061] A mask recognition module is used to determine whether the customer in the transmitted facial image information is wearing a mask;

[0062] The processing module is used to enable bank staff to handle business according to the business handling model that matches the customer identity information.

[0063] Preferably, the system further includes a background management unit; the background management unit includes:

[0064] A query module, used by the bank staff to query when the customer inputs the type of business to be handled through the call machine;

[0065] The customer information module is used to automatically match the customer's identity information and the customer's facial recognition image information with the type of business that the customer needs to handle input through the calling machine to form the business handling mode;

[0066] The information interaction module is used to send and receive data in the bank's customer identity detection system through the customer information monitoring interface, and also to provide real-time feedback of the normal customer information business processing status to the customer through the normal customer information business processing status interface.

[0067] An embodiment of the present invention further provides an electronic device, which is used to implement the bank customer identity detection method described in any embodiment of the present invention.

[0068] An embodiment of the present invention further provides a storage medium storing a computer program, wherein the computer program, when executed by a controller, implements the bank customer identity detection method described in any embodiment of the present invention.

[0069] Preferably, the electronic device further includes at least one LED display screen.

[0070] The present invention provides a method, device, and system for detecting bank customer identities, which have the following beneficial effects: After the customer performs an initial verification, the bank determines whether to automatically or manually verify their identity information based on the risk of the business to be handled, which can greatly reduce the bank's repetitive work. For high-risk businesses, only a single manual review is required to verify the identity of all bank businesses handled by the customer, provided that the customer does not leave the camera coverage area. This reduces the bank's business processing procedures, facilitates customer business processing, significantly improves the bank's intelligence level, reduces the probability of bank staff errors, and improves bank operating efficiency. At the same time, the system can automatically record customer data and automatically match it to the business the customer needs to handle, improving customer convenience and having the beneficial effect of improving the bank's intelligence level. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 A schematic diagram of a bank customer identity detection method according to an embodiment of the present invention;

[0072] Figure 2 The present invention applies to an embodiment of the method of determining an identifiable identity area by using a camera corresponding to a calling machine, collecting facial image information, cropping the collected facial image information, and sending the cropped facial image information to a controller, which also includes a flowchart of the steps;

[0073] Figure 3 The controller of one embodiment of the present invention receives the cropped facial image information for recognition and matches the customer identity information, and further includes a flowchart of the steps;

[0074] Figure 4 In one embodiment of the present invention, the customer inputs the type of business to be handled through the call machine. The call machine matches the customer's identity information with the type of business to be handled based on the risk category of the business type to form a business handling model, which also includes a flowchart of specific steps;

[0075] Figure 5This is a flowchart of the specific steps of the bank staff handling business according to the business handling mode matching the customer identity information in an embodiment of the present invention;

[0076] Figure 6 A schematic diagram of a collection unit of a bank customer identity detection system according to an embodiment of the present invention;

[0077] Figure 7 A schematic diagram of a controller of the bank customer identity detection system according to an embodiment of the present invention;

[0078] Figure 8 This is a schematic diagram of the background management unit of the bank customer identity detection system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0079] In order to be able to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the case of no conflict, the features in the embodiments of the present application and the embodiments can be combined with each other. Unless otherwise defined, all technical and scientific terms used herein are the same as those generally understood by those skilled in the art of the present invention. The terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0080] See also Figure 1 , Figure 1 This is a schematic diagram of a bank customer identity detection method according to an embodiment of the present invention; the method comprises:

[0081] Step S110: Determine the identifiable area through the camera corresponding to the number calling machine, collect facial image information, crop the collected facial image information, and send the cropped facial image information to the controller;

[0082] Step S120: The controller receives the cropped facial image information for recognition and matches the customer identity information;

[0083] Step S130: The customer inputs the type of service to be handled through the call machine. The call machine matches the customer's identity information with the type of service to be handled based on the risk category of the service to form a service handling mode.

[0084] Step S140: The bank staff handles the business according to the business handling mode that matches the customer identity information.

[0085] Specifically, this embodiment matches customer identity information with recognized facial image information to form a business processing model, which runs through the entire process of the business that the customer needs to handle. Bank staff can view customer identity information in real time and call customer identity information data according to business needs;

[0086] The beneficial effects of the method described in the embodiment of the present invention application are as follows: the face recognition module works in conjunction with the calling machine. When the face recognition module detects that a face has entered, it will simultaneously transmit the image to the background management unit. The controller processing module will process the acquired customer identity information to obtain standardized customer identity information that can be used in the bank, for example, a unified format for recording customer identity information. The verification unit, identity detection unit and processing module rely on the controller to work, and are integrated and coordinated for processing, without the need for additional docking or connection to an external controller. After completing the type of business selected by the customer, the processing module automatically records the customer data, eliminating the cost of manual record management. When the customer handles the same and / or other types of business again without leaving the bank's office area, the controller automatically performs identity verification through the automatic verification module, thereby optimizing the customer experience, saving time for the bank and the customer, and improving work efficiency.

[0087] like Figure 2 As shown, Figure 2 The present invention applies to an embodiment of the method of determining an identifiable identity area by a camera corresponding to a calling machine, collecting facial image information, cropping the collected facial image information, and sending the cropped facial image information to a controller, which also includes a flowchart of the steps, wherein the steps include:

[0088] Step S1101: Identify whether there is face information in the scene, and if so, proceed to the next step;

[0089] Step S1103: Determine whether there is anyone entering or leaving; if yes, play a voice prompt; if no, proceed to the next step

[0090] Step S1105: determining the number of faces in the collected facial image information;

[0091] If the number of faces in the facial image information is greater than 1, a voice prompt is played; specifically, the voice prompt requires the customer behind or on either side to maintain a distance of one meter and exit the shooting range of the camera device;

[0092] If the number of faces in the image is equal to 1, proceed to the next step;

[0093] If the number of faces in the image is equal to 0, proceed to step S1101;

[0094] Step S1107: crop the collected facial image information, and send the cropped facial image information to the controller.

[0095] In order to solve the problem of inaccurate identity information acquisition caused by the inconsistency between the face recognition area and the identifiable identity area detected by the camera of the calling device in the prior art, in some optional embodiments, a camera with a face recognition module (the camera may also be other camera devices) and a calling machine (the calling machine may also be other calling devices) are installed on the same device;

[0096] Specifically, if Figure 6-8 As shown, the camera installed on the calling machine determines the facial information collection area and collects facial information; the collection area is located directly in front of the calling machine; facial image information is collected by the vertically installed camera; the picture of the facial image information is displayed in a vertical screen, with less left and right pictures, which has the beneficial effect of reducing the impact of human body shaking on recognition; the embodiment of the present invention installs the camera device vertically, so that the ratio of the picture collected by the camera device is 9:16, and the redundant pictures in the left and right picture areas can be cropped, and only the display area directly in front of the camera device is retained; when the customer enters the face recognition area, the customer's facial information is identified; the face collection module interacts with the face recognition module 23; the customer's identity is determined by the verification unit 27 and the background management unit 30;

[0097] The controller 20 is used to analyze the facial image information and the environmental image captured by the acquisition unit 10 of the camera device through the identity detection unit 40 and the processing module 42;

[0098] The camera is installed on the calling machine, and the controller records the customer identity information of the first transaction. The calling machine and the controller work together; through the camera installed on the calling machine, the customer identity information can be called through the background management unit to crop and identify the facial image information collected by the camera; the calling machine and the camera work together, and the camera will only collect the customer's facial image information when the customer appears in the set collection area, avoiding the camera from collecting too much useless information, thereby having the beneficial effect of speeding up the system operation rate and saving loading resources.

[0099] like Figure 3 As shown, Figure 3 The controller of one embodiment of the present invention receives the cropped facial image information for recognition and matches the customer identity information, and further includes a flowchart of the steps, the steps comprising:

[0100] Step S1201: Send the facial image information captured by the camera to the face recognition module for recognition. Specifically, the facial image information captured by the camera is sent to a controller, for example, to a mask recognition module. The controller can then send the information to a background management unit, for example, to the information interaction module 35, which sends the facial recognition information to an application page for specific business processing in the bank's internal system that is visible to bank staff.

[0101] Step S1203: The call machine and the face recognition camera interact with each other to determine whether the collected face information meets the requirements. If yes, proceed to the next step; if not, replace the face image information and proceed to step S1201.

[0102] Step S1205: Mapping the stored facial features with the collected customer facial image to match the customer with their identity, allowing the customer to determine a unique identifier;

[0103] For example, a one-to-one mapping relationship is formed between the customer's face and the customer ID; it can be 1:1 recognition to determine whether it is the same person;

[0104] The embodiment of the present invention uses a camera installed vertically on the calling machine to display the picture in a vertical screen with less left and right pictures, which reduces the impact of human body shaking on face recognition, greatly reduces the width of the picture that needs to be cropped, and has the beneficial effect of improving the operating efficiency of the system.

[0105] like Figure 4 As shown, Figure 4 In one embodiment of the present invention, the customer inputs the type of business to be handled through the call machine. The call machine matches the customer identity information with the type of business to be handled based on the risk category of the business type to form a business handling mode, which also includes a flowchart of specific steps, the steps comprising:

[0106] Step S1301: If the type of business to be handled entered by the customer is a non-high-risk business type, automatic verification of the facial image information is performed after the initial facial image information verification;

[0107] Specifically, the customer's identity information is obtained and automatically verified for non-high-risk businesses, without the need to verify the customer's facial image information again;

[0108] Step S1303: If the type of business required by the customer is a high-risk business, the ticket machine initiates a request for manual verification of the facial image information;

[0109] Specifically, if Figure 7 、 Figure 4As shown, the automatic verification module 26 automatically verifies non-high-risk businesses, and does not require customers who have not left the surveillance area of ​​the camera device to confirm their identity information again through face recognition;

[0110] Step S1305: If the facial image information is manually verified, the ticket calling machine sends a command to the camera to track the customer's movement trajectory in the business hall. The camera tracks the customer according to the command and saves the customer's movement trajectory data in real time.

[0111] Step S1307: If the customer applies for high-risk services again, the ticket calling machine determines whether the customer has left the camera monitoring area by calling the real-time stored customer movement trajectory data;

[0112] If yes, proceed to step S1303;

[0113] If no, proceed to the next step;

[0114] Step S1309: No more manual verification of facial image information is required, and the high-risk business that is re-applied for can be directly processed.

[0115] Specifically, if Figure 7 、 Figure 4 As shown, the tracking module 50 is used to determine whether the customer has left the business hall based on the movement trajectory tracking data described by the customer; the camera device is also used to track the customer who has passed the first face recognition according to the instructions of the tracking module 50.

[0116] In some optional embodiments, before forming a mapping relationship between the stored facial features and the collected customer facial image and matching the customer with the identity to enable the customer to determine the unique identification, the present invention further includes the following specific steps:

[0117] Determine whether the customer in the transmitted facial image information is wearing a mask; if so, restrict the types of business that the customer wearing a mask can handle;

[0118] In some optional embodiments, if the type of business to be handled entered by the customer is a high-risk business type, the calling machine may initiate a request for manual verification of the facial image information before further steps are included:

[0119] If the type of business that the customer inputs is a high-risk business type, the calling machine prompts the customer to take off the mask and perform face recognition again in step S110; the prompt may be in the form of voice and / or text.

[0120] Specifically, if Figure 6 、 7As shown in FIG8 , the mask recognition module 54 determines whether the transmitted customer face image is wearing a mask, so as to identify the person for epidemic prevention;

[0121] The controller 20 sorts the input and output facial image information and / or various data through the information sorting module 52;

[0122] The processing module 42 can send data to the background management unit 30, the collection unit 10, and other designated servers. The data includes facial image information, customer identity information, and the business processing mode.

[0123] In some optional embodiments, the mask recognition method steps include: when a customer's facial image is recognized, the facial recognition module will copy the customer's facial image information to the mask recognition module for judgment, and after recognizing that the customer is wearing a mask, it will continue to send it in a loop until the customer leaves; this can solve the problem that the customer initially wears a mask and then takes off the mask while waiting in the lobby, causing the facial image information to change. The mask recognition module can return whether the customer is wearing a mask to the facial recognition module and mark it. The facial recognition module will re-identify, match and use the facial image information based on this mark; this step has the beneficial effect of updating the matching status in real time and improving the bank's work efficiency and accuracy.

[0124] like Figure 5 As shown, Figure 5 This is a flowchart of the specific steps of the bank staff handling business according to the business handling mode matching customer identity information in an embodiment of the present invention, and the steps include:

[0125] Step S1401: Automatically match the customer's identity information and the customer's facial recognition image information with the type of service the customer needs to handle input via the call machine to form the service handling mode;

[0126] Specifically, the customer information module 31 is used to automatically match the customer's identity information and the customer's facial recognition image information with the type of business that the customer needs to handle input through the call machine to form the business handling model; it is used to integrate customer information into the entire process of customer business handling, such as: the number ticket page when the customer takes the number, the lobby manager's prompt page after the number is taken, and the teller's call for business when the teller calls the customer to handle the business. It is also used to automatically record the data of the customer's business handling and save it in the customer information module for query by the query module 33; the recorded data of the customer's business handling includes the business type, amount, currency, time, entrustment relationship, etc.

[0127] Step S1403: The bank staff performs a query when the customer inputs the type of business to be handled through the call machine;

[0128] Specifically, if Figure 8 As shown, the query module 33 is used to query. When the bank staff processes the type of business that the customer needs to handle through the call machine, the query is performed; this has the beneficial effect of making the query more convenient and efficient; for example, query by date, query by customer gender, query by customer age group, query by identity information segment, etc.; this has the beneficial effect of making the bank's work more efficient and saving customers' time;

[0129] Step S1405: sending and receiving data with the bank's customer identity detection unit via the customer information monitoring interface, and also feeding back the normal customer information service processing status to the customer in real time via the normal customer information service processing status interface;

[0130] Specifically, the feedback is provided through mobile terminals and / or counter display devices; Figure 7 、 Figure 8 As shown, the background management unit 30 sends and receives data with the controller 20, its identity detection unit 40 and verification unit 27 through the information interaction module 35, through the customer information monitoring interface 32, and also feeds back the normal customer information business processing status to the customer in real time through the normal customer information business processing status interface 34; the background management unit 30 includes multiple interfaces, for example, the customer information monitoring interface 32, the normal customer information business processing status interface 34, etc., providing internal and / or external interfaces for multi-directional information transmission and reception.

[0131] See also Figure 6-Figure 8 , Figure 6 This is a schematic diagram of a collection unit of a bank customer identity detection system according to an embodiment of the present invention; the system includes: a camera (not shown in the figure), a number calling machine (not shown in the figure), a controller 20, and a background management unit 30;

[0132] The camera includes a collection unit 10; the camera corresponds to the calling machine;

[0133] The camera is used to determine the identifiable area, collect facial image information, crop the collected facial image information, and send the cropped facial image information to the controller;

[0134] The acquisition unit 10 includes:

[0135] A face acquisition module 11 is used to acquire face image information;

[0136] A cropping module 12, used to crop the collected facial image information;

[0137] Interaction module 13, used to send the cropped facial image information to the controller;

[0138] The controller 20 is used to receive the cropped facial image information for recognition and match the customer identity information;

[0139] The calling machine is used for customers to input the type of business they need to handle, and matches the customer's identity information with the business handling mode according to the risk category of the business type;

[0140] The backend management unit 30 is used for bank staff to handle business according to the business handling mode matching the customer identity information.

[0141] Specifically, the patent application embodiment of the present invention relates to a bank customer identity detection system, which is a customer detection system based on one or two customer identity detections, including a call machine for intelligent customer queuing for business; a camera device, such as a camera, which corresponds one-to-one with the call machine, and is set on the call machine, and the camera is used to collect facial information of people in the same area as the call machine area; a controller 20, which is used to match the collected customer facial information with the customer identity information, guide the customer to handle business in the bank, and help bank staff to quickly handle bank business based on the matching of customer identity information; a backend management module 30, which is used to analyze customer identity data, generate reports based on identity information, and connect with bank departments to use, file and transmit customer identity information. This embodiment detects customer identity information in the bank service hall in real time, and prompts customers on the business they need to handle based on the customer identity information, which has the beneficial effect of being able to report and trace bank business.

[0142] like Figure 7 As shown, Figure 7 Schematic diagram of a controller of a bank customer identity detection system according to an embodiment of the present invention; the controller of the bank customer identity detection system according to an embodiment of the present invention includes a verification unit; the verification unit 27 includes:

[0143] The facial recognition module 23 is used to identify and match facial image information collected by the camera device; the facial image information collected by the camera device is matched by forming a mapping relationship between the stored facial features and the collected customer facial image to match the customer with the identity, so that the customer can determine the unique identification;

[0144] The face feature library module 21 is used to store face image information and receive call instructions;

[0145] A face comparison module 25 is used to identify whether there is any face information in the scene, determine whether there are people entering or leaving, and determine the number of faces in the collected face image information;

[0146] A face calling module 24 is used to encode and call the stored face image information;

[0147] Automatic verification module 26, used to automatically verify non-high-risk businesses based on the customer's identity information, without requiring the customer to confirm again;

[0148] like Figure 7 As shown, the controller 21 further includes: an identity detection unit 40; the identity detection unit includes:

[0149] Identity information detection module 41, used to match customer identity information with business processing mode;

[0150] The identity information calling module 43 is used to call the customer identity information from the customer management unit;

[0151] The controller 20 further includes:

[0152] Tracking module 50, used to obtain and save customer movement trajectory data in real time;

[0153] The risk classification module 51 is used to classify business types or set risk categories;

[0154] Specifically, it is used to set and store various types of business information, and to set and store the various types of business information separately according to different risk levels;

[0155] For example, the risk classification level can be divided into high-risk business and non-high-risk business. The risk classification method is as follows:

[0156] Non-high-risk businesses include:

[0157] Personal loans: loan enquiry and printing;

[0158] Comprehensive query and printing: deposit query and printing, and reprinting of personal receipts;

[0159] Credit card: statement inquiry and printing;

[0160] Financial management: various financial products inquiry and recommendation;

[0161] Others: Print product details under the customer's name;

[0162] High-risk businesses, including:

[0163] Account opening and account services: personal account opening, card replacement, bank card activation, account upgrade and downgrade, account overview inquiry, and account cancellation;

[0164] Online financial services: opening e-banking, changing mobile phone numbers, and resetting login passwords;

[0165] Transfer and remittance: current transfer, transfer to enterprises, transfer to other banks;

[0166] Deposits and investment management: purchase of financial products;

[0167] Personal foreign exchange: RMB purchase of foreign exchange, foreign currency settlement;

[0168] Credit card: card application, activation and password setting, information modification, online face-to-face interview, personal loan;

[0169] Quick Loan: basic information maintenance, loan application;

[0170] An information sorting module 52 is used to sort the input and output data information;

[0171] A mask recognition module 54 is used to determine whether the customer in the transmitted facial image information is wearing a mask;

[0172] Specifically, if yes, the types of business handled by the customer wearing a mask are restricted; if the customer chooses to handle high-risk business, the customer is prompted to take off the mask and re-perform the step S110 for face recognition; the prompt is in the form of voice and / or text; it has the beneficial effect of being able to quickly identify customers for epidemic prevention, and take different response measures according to the risk level of the customer's business, thereby improving the bank's work efficiency, reducing customer waiting time, and improving the level of epidemic prevention safety.

[0173] The processing module 42 is also used to enable bank staff to handle business according to the business handling mode that matches the customer identity information.

[0174] like Figure 6-8 As shown, Figure 8 This is a schematic diagram of a backend management unit of the bank customer identity detection system according to one embodiment of the present invention. The system according to one embodiment of the present invention further includes a backend management unit. The backend management unit includes:

[0175] Query module 33, used by the bank staff to query when the customer inputs the type of business to be handled through the calling machine;

[0176] The customer information module 31 is used to send the customer's identity information to the business processing module and automatically match the type of business that the customer needs to handle input through the calling machine;

[0177] The information interaction module 35 is used to send and receive data in the bank's customer identity detection system through the customer information monitoring interface 32, and also to feed back the normal customer information service processing status to the customer in real time through the normal customer information service processing status interface 34.

[0178] An embodiment of the present invention further provides an electronic device, which is used to implement the bank customer identity detection method described in any embodiment of the present invention.

[0179] An embodiment of the present invention further provides a storage medium storing a computer program, wherein the computer program, when executed by a controller, implements the bank customer identity detection method described in any embodiment of the present invention.

[0180] An embodiment of the present invention further provides a bank customer identity detection device, which is used to implement the bank customer identity detection method described in any embodiment of the present invention.

[0181] The invention application fully meets the actual usage of the bank customer identity detection method, effectively reduces costs, reasonably configures processes, improves the efficiency of electronic equipment, can work continuously and stably, and has very good results.

[0182] If the components / modules / units integrated in the system / computer device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a controller, it can implement the steps of the above-mentioned various method implementations. The above-mentioned hardware includes a controller. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0183] Matters not covered in this invention are known technologies. The methods or steps in this invention correspond to functional modules / units / components in the system or device. In the several specific embodiments provided in this invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system implementation described above is merely illustrative. For example, the division of the functional modules / units / components is merely a logical functional division, and other division methods may be used in actual implementation.

[0184] In addition, the functional modules / components in various embodiments of the present invention may be integrated into the same processing module / component, each functional module / unit / component may exist physically separately, or two or more modules / components may be integrated into the same module / component. The aforementioned integrated modules / components may be implemented in the form of hardware or hardware plus software functional modules / components.

[0185] It is obvious to those skilled in the art that the embodiments of the present invention are not limited to the details of the above-mentioned exemplary embodiments, and that the embodiments of the present invention can be implemented in other specific forms without departing from the spirit or essential features of the embodiments of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the embodiments of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the embodiments of the present invention. Any figure marks in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units, modules or devices stated in the system, device or terminal claims may also be implemented by the same unit, module or device through software or hardware. Words such as first and second are used to indicate names and do not indicate any particular order.

[0186] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be determined by the appended claims.

Claims

1. A bank customer identity detection method, characterized in that: The method comprises: Determine the identifiable identity area through the camera corresponding to the calling machine, collect facial image information, crop the collected facial image information, and send the cropped facial image information to the controller; The controller receives the cropped facial image information for recognition and matches the customer identity information; The customer inputs the type of business they need to handle through the call machine. The call machine matches the customer's identity information with the type of business they need to handle based on the risk category of the business type, forming a business handling mode. If the business type entered by the customer is not a high-risk business type, the facial image information is automatically verified after the first facial image information verification. If the business type entered by the customer is a high-risk business type, the call machine initiates a request for manual verification of the facial image information. If the facial image information is manually verified, the call machine sends an instruction to the camera to track the customer's movement trajectory in the business hall. The camera tracks the customer according to the instruction and saves the customer's movement trajectory data in real time. If the customer applies for a high-risk business again, the call machine determines whether the customer has left the camera monitoring area by calling the real-time saved customer movement trajectory data. If so, the call machine initiates a request for manual verification of the facial image information. If not, the call machine proceeds to the next step. No manual verification of the facial image information is required, and the high-risk business applied for again is directly processed. Bank staff handles business in accordance with the business handling model that matches the customer's identity information.

2. The bank customer identity detection method according to claim 1, characterized in that: The method further includes the steps of determining an identifiable identity area by using a camera corresponding to the number calling machine, collecting facial image information, cropping the collected facial image information, and sending the cropped facial image information to the controller: Identify whether there is face information in the scene, if so, proceed to the next step; Determine whether there is anyone entering or exiting; if yes, play a voice prompt; if not, proceed to the next step Determining the number of faces in the collected facial image information; If the number of faces in the face image information is greater than 1, a voice prompt will be played; If the number of faces in the image is equal to 1, proceed to the next step; If the number of faces in the image is equal to 0, then proceed to the step of identifying whether there is face information in the scene, and if so, proceed to the next step; The collected facial image information is cropped and the cropped facial image information is sent to the controller.

3. The bank customer identity detection method according to claim 1, characterized in that: The controller receives the cropped facial image information for identification and matches the customer identity information, further comprising the steps of: Send the facial image information collected by the camera to the face recognition module for identification; The calling machine and the face recognition camera interact with each other to determine whether the collected face image information meets the requirements. If so, proceed to the next step. If not, replace the face image information and send the face image information collected by the camera to the face recognition module for recognition; A mapping relationship is formed between the stored facial features and the collected customer facial images to match customers with identities, allowing customers to determine their unique identification.

4. The bank customer identity detection method according to claim 3, characterized in that: The process of forming a mapping relationship between the stored facial features and the collected customer facial images, matching the customer with the identity, and enabling the customer to determine a unique identification, also includes the following steps: Determine whether the customer in the transmitted facial image information is wearing a mask; if so, restrict the types of business that the customer wearing a mask can handle; If the type of business to be handled input by the customer is a high-risk business type, before the ticket calling machine initiates a request for manual verification of the facial image information, the following steps are also included: If the type of business that the customer inputs is a high-risk business type, the calling machine prompts the customer to take off the mask and proceed again. The camera corresponding to the calling machine determines the recognizable identity area, collects facial image information, crops the collected facial image information, and sends the cropped facial image information to the controller; the prompt is in the form of voice and / or text.

5. The bank customer identity detection method according to claim 1, characterized in that: Also includes: The bank staff handles the business according to the business handling mode matching the customer identity information, further comprising the steps of: Automatically matching the customer's identity information and the customer's facial recognition image information with the type of business that the customer needs to handle through the calling machine to form the business handling mode; The bank staff makes inquiries when the customer inputs the type of business to be handled through the calling machine; Data is sent and received in the bank's customer identity detection system through the customer information monitoring interface, and the normal customer information business processing status is fed back to the customer in real time through the normal customer information business processing status interface.

6. A bank customer identity detection system, characterized in that: The system includes: a camera, a calling machine, a controller, and a background management unit; The camera includes a collection unit; the camera corresponds to the calling machine; The camera is used to determine the identifiable area, collect facial image information, crop the collected facial image information, and send the cropped facial image information to the controller; The acquisition unit includes: A face acquisition module, used to acquire face image information; A cropping module, used to crop the collected facial image information; An interaction module, used to send the cropped facial image information to a controller; The controller is configured to receive the cropped facial image information for recognition and match the cropped facial image information with the customer's identity information; The calling machine is used for customers to input the type of business they need to handle, and matches the customer's identity information with the business handling mode according to the risk category of the business type; The backend management unit is used for bank staff to handle business according to the business handling model that matches the customer identity information.

7. The bank customer identity detection system according to claim 6, characterized in that: The controller includes a verification unit; the verification unit includes: A facial recognition module is used to identify and match facial image information captured by a camera device; the facial image information captured by the camera device is matched by mapping the stored facial features with the captured customer facial image to match the customer with the customer's identity, thereby allowing the customer to determine a unique identification; Face feature library module, used to store face image information; A face comparison module is used to identify whether there is any face information in the scene, determine whether there are people entering or leaving, and determine the number of faces in the collected face image information; A face calling module is used to encode and call the stored face image information; The automatic verification module is used to automatically verify non-high-risk businesses based on the customer's identity information, without the need for the customer to confirm again.

8. The bank customer identity detection system according to claim 7, characterized in that: The controller further includes an identity detection unit; the identity detection unit includes: Identity information detection module, used to match customer identity information with business processing mode; The identity information calling module is used to call customer identity information.

9. The bank customer identity detection system according to claim 8, characterized in that: The controller further includes: Tracking module, used to obtain and save customer movement trajectory data in real time; Risk classification module, used to classify business types or set risk categories; Information sorting module, used to sort input and output data information; A mask recognition module is used to determine whether the customer in the transmitted facial image information is wearing a mask; The processing module is used to enable bank staff to handle business according to the business handling model that matches the customer identity information.

10. The bank customer identity detection system according to claim 9, characterized in that: The system also includes a background management unit; The background management unit includes: A query module, used by the bank staff to query when the customer inputs the type of business to be handled through the call machine; The customer information module is used to automatically match the customer's identity information and the customer's facial recognition image information with the type of business that the customer needs to handle input through the calling machine to form the business handling mode; The information interaction module is used to send and receive data in the bank's customer identity detection system through the customer information monitoring interface, and also to provide real-time feedback of the normal customer information business processing status to the customer through the normal customer information business processing status interface.

11. An electronic device, characterized in that: The electronic device is used to implement the bank customer identity detection method according to any one of claims 1 to 5.

12. A storage medium, characterized in that: A computer program is stored thereon, wherein the computer program implements the bank customer identity detection method according to any one of claims 1 to 5 when executed by the controller.

Images