WO2020238915A1 - 用户身份识别方法及装置、电子设备、存储介质 - Google Patents

用户身份识别方法及装置、电子设备、存储介质 Download PDF

Info

Publication number
WO2020238915A1
WO2020238915A1 PCT/CN2020/092395 CN2020092395W WO2020238915A1 WO 2020238915 A1 WO2020238915 A1 WO 2020238915A1 CN 2020092395 W CN2020092395 W CN 2020092395W WO 2020238915 A1 WO2020238915 A1 WO 2020238915A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
face image
image
behavior data
operation behavior
Prior art date
Application number
PCT/CN2020/092395
Other languages
English (en)
French (fr)
Inventor
朱艳华
Original Assignee
京东方科技集团股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 京东方科技集团股份有限公司 filed Critical 京东方科技集团股份有限公司
Priority to US17/281,861 priority Critical patent/US20210398133A1/en
Publication of WO2020238915A1 publication Critical patent/WO2020238915A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G06F21/316—User authentication by observing the pattern of computer usage, e.g. typical user behaviour
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401—Transaction verification
    • G06Q20/4014—Identity check for transactions
    • G06Q20/40145—Biometric identity checks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/405—Establishing or using transaction specific rules
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/02—Banking, e.g. interest calculation or account maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2221/00—Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F2221/21—Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F2221/2139—Recurrent verification

Definitions

  • the present disclosure relates to a data processing method, in particular to a user identification method and device, electronic equipment, and storage medium.
  • the first aspect of the embodiments of the present disclosure provides a user identification method, including:
  • the user's operation behavior data on the collection terminal is received, and the The operating behavior data is associated with the user identification of the specific user; wherein, the collection terminal is an operating device in a bank branch.
  • the collection terminal may be a card swiping device, a wealth management product display device or a heavy metal product display device in a bank branch.
  • performing face recognition processing on the user image includes:
  • the face image of the user matches the face image of the specific user, it is determined that the user identification of the specific user is the user identification of the user.
  • the user identity recognition method further includes:
  • the user image is cropped according to the position of the face in the user image, and the face image of the user is retained.
  • the user identity identification method further includes:
  • the user information of the user with the special identity and the face image of the user are sent to a designated terminal, where the designated terminal is set in advance to receive the special identity
  • the terminal device of the user information of the user and the face image of the user is set in advance to receive the special identity
  • the user information of the user with a special identity is user information after desensitization processing.
  • the user identity identification method further includes:
  • the operation behavior data includes data generated when the user performs an operation behavior on the collection terminal and/or designated terminal; the operation behavior includes swiping a card to obtain an account number, viewing wealth management products, paying attention to wealth management products, and purchasing One or more of wealth management products, viewing precious metal products, paying attention to precious metal products, and purchasing precious metal products.
  • the user identity identification method further includes:
  • the user identity identification method further includes:
  • the face image of the user is not detected in the user image, and/or if the face image of the user does not match the face image of any specific user, continue to acquire the user image.
  • the user identity identification method further includes:
  • the user’s face image is not detected in the user image after a preset duration threshold, and/or if the user’s face image is identical to that of any particular user after the preset duration threshold has passed If the face images do not match, stop acquiring user images.
  • the user identity identification method further includes:
  • the face image of the user is detected in the user image but the face image of the user does not match the face image of any specific user, the face image of the user is temporarily stored and the face image is received.
  • the user's operation behavior data on the terminal is collected, and the operation behavior data is associated with the user's face image.
  • the user identity identification method further includes:
  • the operation behavior data associated with the face image of the user is associated with the user identification of the new user .
  • a second aspect of the embodiments of the present disclosure provides a user identification device, including:
  • a receiving module configured to obtain user images and receive operation behavior data of the user on the collection terminal
  • the face recognition module is used to perform face recognition processing on the user image
  • the identity determination module if the face image of the user is detected in the user image and the face image of the user matches the face image of a specific user, is used to compare the operation behavior data with the specific user
  • the user identification of the user is associated; wherein, the collection terminal is an operating device in a bank branch.
  • the third aspect of the embodiments of the present disclosure provides an electronic device, including:
  • At least one processor and,
  • a memory communicatively connected with the at least one processor; wherein,
  • the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the user identification method.
  • a fourth aspect of the embodiments of the present disclosure provides a computer-readable storage medium storing a computer program, wherein the computer program implements the steps of the user identification method when executed by a processor.
  • FIG. 1a is a schematic flowchart of an embodiment of a user identification method according to an embodiment of the disclosure
  • FIG. 1b is a schematic flowchart of an embodiment of a user identification method according to an embodiment of the disclosure
  • FIG. 2 is a schematic flowchart of an embodiment of pushing user information and facial images for a user with a special identity in the present disclosure
  • FIG. 3 is a schematic flowchart of an embodiment of product recommendation for users in this disclosure
  • FIG. 4 is a schematic structural diagram of an embodiment of a user identification device according to an embodiment of the disclosure.
  • FIG. 5 is a schematic structural diagram of an embodiment of an apparatus for implementing a user identity recognition method according to an embodiment of the disclosure.
  • the first aspect of the embodiments of the present disclosure provides a user identification method, which can solve the problem of difficult analysis of user behavior in bank branches to a certain extent.
  • the user identification method can optionally be applied to a server or a terminal.
  • the user identification method is applied to a collection terminal, the collection terminal is required to have certain data processing capabilities.
  • the user identification method includes the following steps:
  • Step 10 Obtain user images.
  • the collection terminal acquires a user image;
  • the execution subject of the method is a server, the server receives the user image sent by the collection terminal.
  • Step 20 Perform face recognition processing on the user image.
  • Step 30 If the face image of the user is detected in the user image and the face image of the user matches the face image of a specific user, receive the user's operation behavior data on the collection terminal , And associate the operating behavior data with the user identification of the specific user; wherein, the collection terminal is an operating device in a bank branch.
  • the user’s information in the collection is received
  • the operation behavior data on the terminal, and the operation behavior data is associated with the user ID of the specific user; in this way, the operation behavior data is associated with the user identity through face recognition, so that the operation that cannot identify the user identity is changed. It is necessary to be able to identify the user's identity, and then be able to use these operational behavior data to collect and analyze user behavior, so as to solve the problem of user behavior difficult to analyze in bank branches to a certain extent.
  • the user identification process of the user identification device is insensitive to the user, and the user experience is better.
  • the user identification method includes the following steps:
  • Step 11 Receive the user image sent by the collection terminal.
  • the collection terminal may be various operating equipment in a bank branch, such as card swiping equipment, wealth management product display equipment, heavy metal product display equipment, etc.; these collection terminals are all equipped with collection devices (such as cameras) for The image of the user currently operating the collection terminal (that is, the user image) is collected to determine the identity of the user accordingly.
  • these collection terminals are all equipped with collection devices (such as cameras) for The image of the user currently operating the collection terminal (that is, the user image) is collected to determine the identity of the user accordingly.
  • the user may be any person who visits a bank branch to use various operating devices in the bank branch.
  • the user may be a user who has opened an account at the bank branch or the bank, or may not be at the bank branch or the bank. The user who opened the account.
  • the collection operation of the collection terminal may be triggered by a user's operation behavior on the collection terminal.
  • the collection terminal detects the user's operation behavior, it sends the operation behavior to the server, and after the server receives the user's operation behavior, the server sends a collection instruction to the collection terminal to trigger the collection terminal Perform a collection operation, take the user image and send it to the server; or, for example, after detecting the user's operation behavior, the collection terminal directly starts the collection operation, takes the user image and sends it to the server.
  • the operation behavior of the user on the collection terminal may be, for example, the user swiping the card on the card swiping device, clicking on service items, etc., or the user viewing the product content and selecting the product type on the wealth management product display device or the heavy metal product display device And other operations, or users can view other products, services, and other operations on other operating devices at bank branches.
  • the server uses a web service
  • the collection terminal uses a windows system
  • the collection terminals communicate with each other through an http API interface
  • the server and the collection terminal share data through a database.
  • the server and the collection terminal communicate through a wired network.
  • Step 12 Perform face recognition processing on the user image.
  • the function of the face recognition processing can be implemented using the python language web framework bottle (a lightweight python web framework that can be adapted to various web servers), and the face recognition algorithm is encapsulated in the business logic SeetaFace (a face recognition framework), the algorithm can include three parts: face detection module, facial feature positioning module, face feature extraction and comparison module.
  • the step 12-performing face recognition processing on the user image may further include the following steps:
  • Step 121 Determine whether there is a face image of the user in the user image, to determine whether a qualified user image is captured, that is, a user image sufficient for face comparison.
  • the user image is an image collected by the collecting terminal for the user
  • the user's face image is the user's face image obtained through face recognition from the user image.
  • Step 122 If the face image of the user is detected in the user image, compare the face image of the user with the face image of the user stored in advance; optionally, the face image of the user stored in advance
  • the face image of is usually the face image entered into the banking system when the user first registered as a bank customer.
  • the face image can be the face image collected by the bank during registration, or the user’s identity The face image on the user’s ID card, etc.
  • the similarity between the face image of the user and the face image of each user can be judged whether it is the same person by calculating the similarity between the face image of the user and the face image of each user stored in advance.
  • the face image of the user is different from the face image of a specific user
  • the similarity is higher than the similarity threshold, it is determined that the user and the specific user are the same person, that is, the facial image of the user matches the facial image of the specific user.
  • the similarities between the facial images of multiple specific users and the facial images of the users all reach the similarity threshold, it is determined that the specific user with the highest similarity is the user that matches the user.
  • step 14 that is, send an instruction to continue collecting images to the collection terminal, in order to collect images that can be used for image comparison.
  • the right face image of the user is not detected in the user image.
  • Step 123 If the face image of the user matches the face image of the specific user, determine that the user ID of the specific user is the user ID of the user; optionally, the user ID stored in the system may be The user identifier of the specific user is bound to the user, so as to associate the user's operating behavior data with the specific user's operating behavior data.
  • the user identification includes the user's identity information, such as an ID number, etc., and the user identification may also include the user's nickname. (Explain the user ID)
  • the user image can be cropped according to the position of the face in the user image, and the user's face image is retained for archiving and subsequent operations.
  • the user image collected by the aforementioned trigger collection terminal and the cropping of the face image can be obtained through opencv (a cross-platform computer vision library based on the BSD (Berkeley Software Distribution, Berkeley Software Distribution) license (open source)) )to realise.
  • opencv a cross-platform computer vision library based on the BSD (Berkeley Software Distribution, Berkeley Software Distribution) license (open source)
  • step 14 that is, send an instruction to continue collecting images to the collection terminal, in order to collect the The face image of a specific user that matches the face image of the user.
  • the above step 12 of performing face recognition processing on the user image can be implemented in a collection terminal in addition to being implemented on the server side.
  • the collection terminal and the server can be implemented through HTTP API (application programming interface). ) To communicate.
  • Step 13 If the face image of the user is detected in the user image and the face image of the user matches the face image of a specific user, receive the user's operation on the collection terminal Behavior data, and associate the operation behavior data with the user identification of the specific user.
  • the operation behavior data includes data generated when the user performs an operation behavior on the collection terminal and/or designated terminal; the operation behavior includes swiping a card to obtain an account number, viewing wealth management products, paying attention to wealth management products, and purchasing One or more of wealth management products, viewing precious metal products, paying attention to precious metal products, and purchasing precious metal products.
  • the collection terminal displays the product through a built-in windows desktop application, all key points in the windows desktop application have embedded points, various types of wealth management product list buttons, and details of each product Button, "Like” button, "Viewed” button, “Purchased” button and so on.
  • the application sends a request to the server.
  • the server receives the request, it sends a request for image capture to the collection terminal. This request triggers the built-in camera of the collection terminal to take a photo.
  • the photos stored in the storage system are compared with the captured photos, the user's ID (such as identity information) is found and sent to the collection terminal through the server, and the terminal's management function is collected to generate the user's operation behavior log, and the user's operation behavior
  • the log is synchronized to the server.
  • the user identity recognition method further includes step 14: if the user's face image is not detected in the user image, and/or if the user's face image is consistent with any specific user If none of the face images match, then an instruction to continue collecting images is sent to the collection terminal. In this way, when the face image is not detected and/or the face image cannot be matched, the user's image is continuously collected to complete face recognition and user information matching.
  • the user identity recognition method further includes step 15: if the user's face image is not detected in the user image after a preset time threshold has passed, and/or if the After the time threshold is set, the face image of the user does not match the face image of any specific user, and the sending of the instruction to continue collecting images is stopped.
  • the user identification method may further include the following steps:
  • the server can temporarily store the user’s face image and receive the user’s operation behavior data on the collection terminal, and compare the operation behavior data with the user’s face The images are associated. In this way, the face images of unregistered users are associated with their operation behavior data to prepare for emergencies.
  • the prerequisite to be met in the foregoing steps is that the face image of the user is detected in the user image, but the face image of the user does not match the face image of any specific user.
  • the conditions and the preconditions of step 14 overlap, but this does not mean that the steps of this embodiment and step 14 are in an exclusive relationship.
  • the server may temporarily store the user's face image and receive the user's operation behavior data on the collection terminal for association processing , It is also possible to send an instruction to continue collecting images to the collection terminal, and these two processing steps can be carried out at the same time, or can be carried out sequentially, and both can achieve the desired effect of the embodiment of the present disclosure. There is no contradiction between these two processing steps, which can be achieved by the processing capabilities of the server itself.
  • the user identification method may further include the following steps:
  • the face image of the new user may be the face image on the ID card of the new user, or the face image of the new user
  • the face image may be the face image of the new user collected by the camera of the bank counter when the new user registers
  • the operation behavior data associated with the face image of the user is associated with the user identification of the new user .
  • the new user can be immediately associated with the new user before registration.
  • the operation behavior data generated in the bank branch can better serve the new user.
  • the user identity recognition method collects user images and performs face recognition.
  • the operation behavior data of the user on the collection terminal is received, and the operation behavior data is associated with the user identification of the specific user; in this way, the operation behavior data is combined with the user through face recognition.
  • the association of identities makes it possible to identify the user’s identity for operations that could not originally identify the user’s identity, and then use these operational behavior data to collect and analyze user behavior, thereby solving the difficulty of analyzing user behavior in bank branches to a certain extent.
  • the user identity recognition method accurately binds user information and user behavior through the face recognition method when the customer has no perception. The entire user identity recognition process is insensitive to the user, and the user experience is better.
  • the user identification method further includes the following steps:
  • Step 21 Determine whether the specific user is a user with a special identity according to the user identification of the specific user.
  • the user with a special identity may refer to a user with a special identity for the bank or bank branch, for example, a VIP customer of a bank, a user with a deposit exceeding a certain amount, etc.; or the user with a special identity may also be Users with special identities who need additional help, such as the elderly, the disabled, soldiers, etc.
  • Step 22 If the specific user is a user with a special identity, send the user information of the user with the special identity and the face image of the user to a designated terminal.
  • the person holding the designated terminal can respond in a timely manner to provide services for the user with the special identity as soon as possible; wherein, the user information can enable the holding
  • the personnel of the designated terminal quickly understands the situation of the user with the special identity, and the face image can facilitate the personnel to find the user with the special identity.
  • the designated terminal may be a terminal device that is set in advance to receive the user information of the user with the special identity and the face image of the user, such as a handheld PAD of a lobby manager (which may be an Android system or an IOS system). ), optionally, the handheld PAD communicates with the server via wireless WIFI.
  • the user information of the user with a special identity may also be a nickname of the user, and the face image of the user may also be a user avatar obtained from a storage system.
  • the user information of the user with a special identity in step 22 is user information that has undergone desensitization processing.
  • the user information is desensitized to prevent leakage of user information.
  • data desensitization refers to data deformation of some sensitive information through desensitization rules to achieve reliable protection of sensitive privacy data.
  • the real data should be modified and used for testing without violating system rules, such as personal information such as ID card number, mobile phone number, card number, customer number, etc.
  • the user information may be retrieved from the bank's internal customer relationship management system (Customer Relationship Management System, CRM) system.
  • CRM Customer Relationship Management System
  • the bank only opens part of the user information in the bank’s internal CRM system to the server, and the user information retrieved by the server from the bank is user information that has been desensitized by the bank, thereby preventing the bank
  • the internally stored user information is not leaked; therefore, the user information that the server can retrieve from the bank's internal CRM system may be desensitized, for example.
  • this embodiment only mentions that user information of users with special identities has undergone desensitization processing, in some implementations, user information of ordinary users has also undergone desensitization processing to prevent bank user information from being leaked.
  • the server cannot directly obtain the specific user identification from the collection terminal, and the server needs to perform face recognition on the user image. It assists in determining the user ID of the current user so that the corresponding operation behavior data can be associated with the user ID of the user.
  • the user information may include user data, property data, historical purchase data, and wealth management product information of the user with a special identity.
  • an example of user information after desensitization is as follows:
  • ⁇ ID 0010003, nickname: Mr. Zhang, property: a little money, VIP: yes, purchase product: [gold bar, regular financial management, dividend insurance] ⁇ .
  • Step 23 If the specific user is a common identity user, no processing is performed.
  • the foregoing embodiment determines whether it is a user with a special identity according to the user ID of a specific user. If so, the user information of the user with the special identity and the face image of the user are sent to the designated terminal, so that the person holding the designated terminal can timely Serving the special-identity user, thereby improving the user experience of the special-identity user.
  • the user identification method further includes:
  • Step 31 Obtain historical operation behavior data and product data related to the user identification of the specific user.
  • the historical operation behavior data is a historical record of the operation behavior data of the specific user, and the historical record may be a record of the operation behavior data of the specific user at each branch of the bank.
  • the product data may be related information and data of various products provided by the bank, such as the seven-day annualized return rate of wealth management products, product term, product attributes, product risk levels, transaction rules, product highlights, Common product problems, product safety and security, etc.
  • Step 32 According to the operation behavior data and the historical operation behavior data, combined with the product data to generate product recommendation content.
  • the big data analysis platform is built using CDH (Cloudera Hadoop distribution), and its components include Hadoop, Hive, and Spark.
  • CDH Cloudera Hadoop distribution
  • Hadoop is a distributed file system used to store behavior log data
  • Hive is used to store intermediate results of calculations and interactive queries
  • Spark is used for memory calculations and data analysis.
  • the step of generating product recommendation content can be based on the user's portrait data (which can be generated based on the user's basic identity information), asset information, operating behavior data, historical operating behavior data, on-sale wealth management/financial product data, etc., Generate wealth management products suitable for users through the big data analysis platform.
  • Step 33 Send the product recommendation content to the collection terminal and/or designated terminal.
  • the product recommendation content for the user is sent to the collection terminal , So that the user can immediately see the product content specifically recommended for him; when the user is using the designated terminal (the user image collected by the designated terminal can be used to determine whether the user is using the designated terminal).
  • the user's recommended product content is sent to the designated terminal, so that the user can immediately see the product content specifically recommended for him, and at the same time, the person holding the designated terminal can also introduce the product to the user accordingly.
  • the product recommendation content is sent to the terminal the user is browsing, and the product recommendation content pops up on the screen, and the user can make a feasible purchase, thereby reducing the user's blindness in browsing wealth management products, improving the accuracy of product marketing, and achieving precision Targeting users and precise marketing have improved the operating efficiency of bank branches.
  • the user identification method further includes:
  • Step 34 Receive operation behavior data of the user on the collection terminal and/or the designated terminal for the recommended content of the product.
  • the user's operation behavior data for the recommended content of the product may be, for example, viewing the recommended product in the recommended content of the product (indicating that the user is interested in the recommended content), or closing the product recommended content interface (indicating that the user Not interested in recommended content), etc.
  • Step 35 According to the user's operation behavior data for the product recommendation content, combining the historical operation behavior data and the product data to generate new product recommendation content. For example, if it is determined that the user is interested or not interested in a certain product according to the user's operational behavior data for the recommended content of the product, the weight of this type of product is increased or decreased during product recommendation, and then the recommended content is regenerated.
  • Step 36 Send the new product recommendation content to the collection terminal and/or designated terminal.
  • the product recommendation content is regenerated, so that the product recommendation can be more accurate and the user experience is improved.
  • the user identification method is applied to the server as an example for exemplification. It should be noted that any embodiment of the above method or permutation and combination of the embodiments, except when applied to the server In addition, it can also be applied to other devices, as long as the device itself has the corresponding hardware conditions, so the protection scope of the present disclosure should not be limited to the server.
  • the second aspect of the embodiments of the present disclosure provides a user identification device, which can solve the problem of difficult analysis of user behavior in bank branches to a certain extent.
  • the user identity recognition device includes:
  • the receiving module 41 is configured to obtain user images and receive operation behavior data of the user on the collection terminal;
  • the face recognition module 42 is configured to perform face recognition processing on the user image
  • the identity determination module 43 if the face image of the user is detected in the user image and the face image of the user matches the face image of a specific user, is used to send the user to the collection terminal
  • the operation behavior data on the above is associated with the user identification of the specific user; wherein, the collection terminal is an operating device in a bank branch.
  • the user identity recognition device acquires a user image and performs face recognition.
  • the operation behavior data of the user on the collection terminal is received, and the operation behavior data is associated with the user identification of the specific user; in this way, the operation behavior data is combined with the user through face recognition.
  • the association of identities makes it possible to identify the user’s identity for operations that could not originally identify the user’s identity, and then use these operational behavior data to collect and analyze user behavior, thereby solving the difficulty of analyzing user behavior in bank branches to a certain extent.
  • the user identification process of the user identification device is insensitive to the user, and the user experience is better.
  • the face recognition module 42 may also be specifically used for:
  • the face image of the user matches the face image of the specific user, it is determined that the user identification of the specific user is the user identification of the user.
  • the face recognition module 42 may also be specifically used for:
  • the user image is cropped according to the position of the face in the user image, and the face image of the user is retained.
  • the user identity recognition device further includes a sending module 44;
  • the identity determining module 43 is further configured to determine whether the specific user is a user with a special identity according to the user identity of the specific user;
  • the sending module 44 is configured to send the user information of the user with the special identity and the face image of the user to a designated terminal, wherein the designated terminal is set in advance A good terminal device that receives the user information of the user with the special identity and the face image of the user.
  • the user information of the user with a special identity is user information after desensitization processing.
  • the user identity recognition device further includes a recommendation module 45;
  • the recommendation module 45 is configured to obtain historical operation behavior data and product data related to the user identification of the specific user; and, according to the operation behavior data and the historical operation behavior data, combine the product data to generate Product recommendations.
  • the receiving module 41 is further configured to receive user operation behavior data for the recommended content of the product.
  • the recommendation module 45 is further configured to generate new product recommendation content based on the user's operating behavior data for the product recommended content, combining the historical operating behavior data and the product data.
  • the receiving module 41 if the face image of the user is not detected in the user image, and/or if the face image of the user does not match the face image of any specific user, the receiving module 41. It is also used to continue acquiring user images.
  • the receiving module 41 is also used to stop acquiring the user image.
  • the face recognition module is also used for The face image of the user is temporarily stored, the receiving module is also used to receive the user's operation behavior data on the collection terminal, and the identity determination module is also used to compare the operation behavior data with the user To associate the face images of.
  • the receiving module is also used to receive new user registration information
  • the face recognition module is configured to extract the face image of the new user from the new user registration information
  • the identity determination module is further configured to associate the operation behavior data associated with the face image of the user with all The user ID of the new user is associated.
  • the third aspect of the embodiments of the present disclosure proposes an embodiment of an apparatus for performing the user identity identification method.
  • FIG. 5 it is a schematic diagram of the hardware structure of an embodiment of the apparatus for performing the user identification method provided by the present disclosure.
  • the device includes:
  • One or more processors 51 and memory 52 are taken as an example.
  • the device for executing the user identification method may further include: an input device 53 and an output device 54.
  • the processor 51, the memory 52, the input device 53, and the output device 54 may be connected by a bus or in other ways.
  • the connection by a bus is taken as an example.
  • the memory 52 as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, as described in the user identification method in the embodiments of this application.
  • Program instructions/modules for example, the receiving module 41, the face recognition module 42, and the identity determination module 43 shown in FIG. 4.
  • the processor 51 executes various functional applications and data processing of the server by running non-volatile software programs, instructions, and modules stored in the memory 52, that is, realizing the user identification method of the foregoing method embodiment.
  • the memory 52 may include a program storage area and a data storage area.
  • the program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created according to the use of the user identification device.
  • the memory 52 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices.
  • the memory 52 may optionally include a memory remotely provided with respect to the processor 51, and these remote memories may be connected to a member user behavior monitoring device through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
  • the input device 53 can receive the input number or character information, and generate key signal input related to the user setting and function control of the user identification device.
  • the output device 54 may include a display device such as a display screen.
  • the one or more modules are stored in the memory 52, and when executed by the one or more processors 51, the user identification method in any of the foregoing method embodiments is executed.
  • the technical effect of the embodiment of the apparatus for executing the user identification method is the same as or similar to any of the foregoing method embodiments.
  • An embodiment of the present application provides a non-transitory computer storage medium that stores computer-executable instructions, and the computer-executable instructions can execute the processing method of the list item operation in any of the foregoing method embodiments.
  • the technical effect of the embodiment of the non-transitory computer storage medium is the same as or similar to any of the foregoing method embodiments.
  • the programs can be stored in a computer readable storage.
  • the medium when the program is executed, it may include the procedures of the above-mentioned method embodiments.
  • the storage medium may be a magnetic disk, an optical disc, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.
  • the embodiment of the computer program has the same or similar technical effect as any of the foregoing method embodiments.
  • the devices, devices, etc. described in the present disclosure may be various electronic terminal devices, such as mobile phones, personal digital assistants (PDA), tablet computers (PAD), smart TVs, etc., or large-scale terminal devices, such as Servers, etc., therefore, the protection scope of the present disclosure should not be limited to a specific type of device or equipment.
  • the client described in the present disclosure may be applied to any of the above electronic terminal devices in the form of electronic hardware, computer software or a combination of both.
  • the method according to the present disclosure may also be implemented as a computer program executed by a CPU, and the computer program may be stored in a computer-readable storage medium.
  • the computer program executes the above-mentioned functions defined in the method of the present disclosure.
  • the above method steps and system units can also be implemented using a controller and a computer-readable storage medium for storing a computer program that enables the controller to implement the above steps or unit functions.
  • non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory Memory.
  • Volatile memory can include random access memory (RAM), which can act as external cache memory.
  • RAM can be obtained in various forms, such as synchronous RAM (DRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchronous link DRAM (SLDRAM) and direct RambusRAM (DRRAM).
  • DRAM synchronous RAM
  • DRAM dynamic RAM
  • SDRAM synchronous DRAM
  • DDR SDRAM double data rate SDRAM
  • ESDRAM enhanced SDRAM
  • SLDRAM Synchronous link DRAM
  • DRRAM direct Rambus RAM
  • the storage devices of the disclosed aspects are intended to include, but are not limited to, these and other suitable types of memory.
  • DSP digital signal processors
  • ASIC dedicated Integrated circuit
  • FPGA field programmable gate array
  • a general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine.
  • the processor may also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors combined with a DSP core, or any other such configuration.
  • the steps of the method or algorithm described in combination with the disclosure herein may be directly included in hardware, a software module executed by a processor, or a combination of the two.
  • the software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.
  • An exemplary storage medium is coupled to the processor such that the processor can read information from or write information to the storage medium.
  • the storage medium may be integrated with the processor.
  • the processor and the storage medium may reside in the ASIC.
  • the ASIC can reside in the user terminal.
  • the processor and the storage medium may reside as discrete components in the user terminal.
  • the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions can be stored as one or more instructions or codes on a computer-readable medium or transmitted through the computer-readable medium.
  • Computer-readable media include computer storage media and communication media, including any media that facilitates the transfer of a computer program from one location to another.
  • a storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.
  • the computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage devices, magnetic disk storage devices or other magnetic storage devices, or may be used for carrying or storing instructions in the form of Or any other medium that can be accessed by a general-purpose or special-purpose computer or a general-purpose or special-purpose processor. Also, any connection is properly termed a computer-readable medium.
  • coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave to send software from a website, server, or other remote source
  • coaxial cable Cable, fiber optic cable, twisted pair, DSL or wireless technologies such as infrared, radio and microwave are all included in the definition of media.
  • magnetic disks and optical disks include compact disks (CDs), laser disks, optical disks, digital versatile disks (DVD), floppy disks, and Blu-ray disks. Disks generally reproduce data magnetically, while optical disks use lasers to optically reproduce data .
  • the combination of the above content should also be included in the scope of computer-readable media.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Physics & Mathematics (AREA)
  • Finance (AREA)
  • Computer Security & Cryptography (AREA)
  • Databases & Information Systems (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Computer Hardware Design (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Technology Law (AREA)
  • Social Psychology (AREA)
  • Collating Specific Patterns (AREA)

Abstract

一种用户身份识别方法及装置、电子设备和存储介质，该方法包括：获取用户图像；对所述用户图像进行人脸识别处理；若在所述用户图像中检测到所述用户的人脸图像且所述用户的人脸图像与特定用户的人脸图像相匹配，则接收所述用户在所述采集终端上的操作行为数据，并将所述操作行为数据与所述特定用户的用户标识进行关联；其中，所述采集终端是银行网点内的操作设备。

Description

用户身份识别方法及装置、电子设备、存储介质
相关申请的交叉引用
本申请主张在2019年5月31日在中国提交的中国专利申请号No.201910470241.5的优先权，其全部内容通过引用包含于此。
技术领域
本公开涉及数据处理方法，特别是指一种用户身份识别方法及装置、电子设备、存储介质。
背景技术
随着数字化信息化的推进，移动互联网技术的发展，金融渠道多样化，互联网金融的繁荣发展，线下银行网点营销任务加重，对客户进行精准营销越发重要。
发明内容
本公开实施例的第一个方面，提供了一种用户身份识别方法，包括：
获取用户图像；
对所述用户图像进行人脸识别处理；
若在所述用户图像中检测到所述用户的人脸图像且所述用户的人脸图像与特定用户的人脸图像相匹配，则接收所述用户在采集终端上的操作行为数据，并将所述操作行为数据与所述特定用户的用户标识进行关联；其中，所述采集终端是银行网点内的操作设备。
可选地，所述采集终端可以银行网点内的刷卡设备、理财产品展示设备或重金属产品展示设备。
可选地，对所述用户图像进行人脸识别处理，包括：
确定所述用户图像中是否存在所述用户的人脸图像；
若在所述用户图像中检测到所述用户的人脸图像，则比对所述用户的人脸图像与预存的用户的人脸图像；
若所述用户的人脸图像与特定用户的人脸图像相匹配，则确定所述特定用户的用户标识为所述用户的用户标识。
可选地，所述在用户图像中检测到所述用户的人脸图像时，所述用户身份识别方法还包括：
根据所述用户图像中的人脸位置裁剪所述用户图像，保留所述用户的人脸图像。
可选地，所述用户身份识别方法还包括：
根据所述特定用户的用户标识，确定所述特定用户是否为特殊身份用户；
若所述特定用户为特殊身份用户，则将所述特殊身份用户的用户信息和所述用户的人脸图像发送到指定终端，其中，所述指定终端是提前设定好的接收所述特殊身份用户的用户信息和所述用户的人脸图像的终端设备。
可选地，
所述特殊身份用户的用户信息为经过脱敏处理后的用户信息。
可选地，所述用户身份识别方法还包括：
获取与所述特定用户的用户标识相关的历史操作行为数据以及产品数据；
根据所述操作行为数据与所述历史操作行为数据，结合所述产品数据，生成产品推荐内容。
可选地，所述操作行为数据包括所述用户在所述采集终端和/或指定终端上实施操作行为时产生的数据；所述操作行为包括刷卡取号、查看理财产品、关注理财产品、购买理财产品、查看贵金属产品、关注贵金属产品、购买贵金属产品中的一种或多种。
可选地，所述用户身份识别方法还包括：
接收所述用户在所述采集终端和/或所述指定终端上针对所述产品推荐内容的操作行为数据；
根据所述用户针对所述产品推荐内容的操作行为数据，结合所述历史操作行为数据和所述产品数据，生成新的产品推荐内容。
可选地，所述用户身份识别方法还包括：
若未在所述用户图像中检测到所述用户的人脸图像，和/或，若所述用户的人脸图像与任何特定用户的人脸图像均不匹配，则继续获取用户图像。
可选地，所述用户身份识别方法还包括：
若在经过预设时长阈值后仍未在所述用户图像中检测到所述用户的人脸图像，和/或，若在经过预设时长阈值后所述用户的人脸图像与任何特定用户的人脸图像均不匹配，则停止获取用户图像。
可选地，所述用户身份识别方法还包括：
若在所述用户图像中检测到所述用户的人脸图像但所述用户的人脸图像与任何特定用户的人脸图像均不匹配，则暂存所述用户的人脸图像并接收所述用户在所述采集终端上的操作行为数据，并将所述操作行为数据与所述用户的人脸图像进行关联。
可选地，所述用户身份识别方法还包括：
接收新用户注册信息；
从所述新用户注册信息中提取所述新用户的人脸图像；
若所述新用户的人脸图像与暂存的所述用户的人脸图像相匹配，则将与所述用户的人脸图像关联的所述操作行为数据与所述新用户的用户标识相关联。
本公开实施例的第二个方面，提供了一种用户身份识别装置，包括：
接收模块，用于获取用户图像以及接收所述用户在所述采集终端上的操作行为数据；
人脸识别模块，用于对所述用户图像进行人脸识别处理；
身份确定模块，若在所述用户图像中检测到所述用户的人脸图像且所述用户的人脸图像与特定用户的人脸图像相匹配，用于将所述操作行为数据与所述特定用户的用户标识进行关联；其中，所述采集终端是银行网点内的操作设备。
本公开实施例的第三个方面，提供了一种电子设备，包括：
至少一个处理器；以及，
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行所述用户身份识别方法。
本公开实施例的第四个方面，提供了一种存储有计算机程序的计算机可读存储介质，其中，所述计算机程序在由处理器执行时实现所述用户身份识别方法的步骤。
附图说明
为了更清楚地说明本公开实施例的技术方案，下面将对实施例的附图作简单地介绍，显而易见地，下面描述中的附图仅仅涉及本公开的一些实施例，而非对本公开的限制。
图1a为本公开实施例的用户身份识别方法的一个实施例的流程示意图；
图1b为本公开实施例的用户身份识别方法的一个实施例的流程示意图；
图2为本公开中针对特殊身份用户进行用户信息和人脸图像推送的实施例的流程示意图；
图3为本公开中针对用户进行产品推荐的实施例的流程示意图；
图4为本公开实施例的用户身份识别装置的一个实施例的结构示意图；
图5为本公开实施例的实现用户身份识别方法的装置的一个实施例的结构示意图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚，下面将结合本公开实施例的附图，对本公开实施例的技术方案进行清楚、完整地描述。显然，所描述的实施例是本公开的一部分实施例，而不是全部的实施例。基于所描述的本公开的实施例，本领域普通技术人员在无需创造性劳动的前提下所获得的所有其他实施例，都属于本公开保护的范围。
本公开实施例的第一个方面，提供了一种用户身份识别方法，能够在一定程度上解决银行网点中用户行为难以分析的问题。
如图1a所示，所述用户身份识别方法，可选地，可以应用于服务器或终端。当所述用户身份识别方法应用于采集终端时，则要求该采集终端具备一定的数据处理能力。所述用户身份识别方法包括以下步骤：
步骤10：获取用户图像。
当所述方法的执行主体为采集终端时，则采集终端获取用户图像；当所述方法的执行主体为服务器时，则所述服务器接收采集终端发送的用户图像。
步骤20：对所述用户图像进行人脸识别处理。
步骤30：若在所述用户图像中检测到所述用户的人脸图像且所述用户的人脸图像与特定用户的人脸图像相匹配，则接收所述用户在采集终端上的操作行为数据，并将所述操作行为数据与所述特定用户的用户标识进行关联；其中，所述采集终端是银行网点内的操作设备。
上述方案中，通过获取用户图像并进行人脸识别，当检测到所述用户的人脸图像且所述用户的人脸图像与特定用户的人脸图像相匹配，接收所述用户在所述采集终端上的操作行为数据，并将所述操作行为数据与所述特定用户的用户标识进行关联；这样，通过人脸识别将操作行为数据与用户身份关联起来，使得本来不能识别用户身份的操作变得能够识别用户身份，进而能够将这些操作行为数据用于对用户行为进行采集和分析，从而能够在一定程度上解决银行网点中用户行为难以分析的问题。此外，该用户身份识别装置的用户身份识别过程对用户无感，用户体验更好。
下述描述以所述用户身份识别方法应用于服务器为例进行说明，如图1b所示，所述用户身份识别方法包括以下步骤：
步骤11：接收采集终端发送的用户图像。
可选地，所述采集终端可以是银行网点内的各操作设备，例如刷卡设备、理财产品展示设备、重金属产品展示设备等等；这些采集终端上均设置有采集装置(如摄像头)，用于采集当前操作该采集终端的用户的图像(即所述用户图像)，用以据此判断该用户的身份。
例如，所述用户可以是任何到银行网点使用银行网点内的各操作设备的人，该用户可以是已经在该银行网点或该银行开具账户的用户，也可以是未在该银行网点或该银行开具账户的用户。
可选地，所述采集终端的采集操作可以通过用户在该采集终端上的操作行为而触发。例如，当所述采集终端在检测到用户的操作行为后，将所述操作行为发送到所述服务器，所述服务器接收到用户的操作行为后，服务器向 采集终端发送采集指令触发所述采集终端进行采集操作，拍摄所述用户图像并发送到服务器；或者，例如，所述采集终端在检测到用户的操作行为后，直接启动采集操作，拍摄所述用户图像并发送到服务器。所述用户在该采集终端上的操作行为例如可以是，用户在刷卡设备上刷卡、点选服务项目等操作，或者，用户在理财产品展示设备或重金属产品展示设备上查看产品内容、选择产品类型等操作，或者，用户在银行网点的其他操作设备上查看其他产品、服务等操作。
可选地，所述服务器采用的是web服务，所述采集终端采用的是windows系统，所述采集终端之间以http API接口进行通信，服务器与采集终端之间通过数据库进行数据共享。可选地，所述服务器与采集终端通过有线网络通信。
步骤12：对所述用户图像进行人脸识别处理。
可选地，所述人脸识别处理的功能可以用python语言的web框架bottle(一种轻量级的python web框架，可以适配各种web服务器)实现，业务逻辑中封装了人脸识别算法SeetaFace(一种人脸识别框架)，算法可包括人脸检测模块、面部特征定位模块、人脸特征提取与比对模块三部分。
可选地，所述步骤12——对所述用户图像进行人脸识别处理，还可进一步包括以下步骤：
步骤121：确定所述用户图像中是否存在所述用户的人脸图像，以判断是否拍到了合格的用户图像，即足以进行人脸比对的用户图像。例如，所述用户图像是采集终端针对该用户采集得到的图像，而所述用户的人脸图像是从所述用户图像中通过人脸识别得到的该用户的人脸图像。
步骤122：若在所述用户图像中检测到所述用户的人脸图像，则比对所述用户的人脸图像与预先存储的用户的人脸图像；可选地，所述预先存储的用户的人脸图像通常可以是该用户在第一次注册为该银行客户时录入到银行系统中的人脸图像，该人脸图像可以是注册时银行采集的人脸图像，也可以是采集用户身份证信息时用户身份证上的人脸图像，等等。
这里，可通过计算所述用户的人脸图像与预先存储的各用户的人脸图像的相似度来判断是否为同一个人，当所述用户的人脸图像与某一特定用户的 人脸图像的相似度高于相似度阈值，则判定所述用户与该特定用户为同一个人，即所述用户的人脸图像与特定用户的人脸图像相匹配。当然，若有多个特定用户的人脸图像与所述用户的人脸图像的相似度都达到了相似度阈值，则判定相似度最高的特定用户为与该用户相匹配的用户。
可选地，若在所述用户图像中未检测到所述用户的人脸图像，则可跳转到步骤14，即向所述采集终端发送继续采集图像指令，以期采集到能够用以图像比对的所述用户的人脸图像。
步骤123：若所述用户的人脸图像与特定用户的人脸图像相匹配，则确定所述特定用户的用户标识为所述用户的用户标识；可选地，可将系统中存储的所述特定用户的用户标识与所述用户绑定，以将所述用户的操作行为数据关联到所述特定用户的操作行为数据中。
其中，所述用户标识包括用户的身份信息，如身份证号等，所述用户标识还可以包括用户昵称等。(对用户标识进行解释)
进一步地，还可根据所述用户图像中的人脸位置裁剪所述用户图像，保留所述用户的人脸图像，以供存档以及后续操作使用。
这里，可选地，前述触发采集终端采集用户图像与此处的人脸图像的裁剪均可通过opencv(一个基于BSD(Berkeley Software Distribution，伯克利软件套件)许可(开源)发行的跨平台计算机视觉库)来实现。
可选地，若所述用户的人脸图像与特定用户的人脸图像不匹配，则可跳转到步骤14，即向所述采集终端发送继续采集图像指令，以期采集到能够采集到与某一特定用户的人脸图像相匹配的所述用户的人脸图像。
可选地，上述对所述用户图像进行人脸识别处理的步骤12，除了可以在服务器端实现外，还可以在采集终端中实现，此时采集终端与服务器可以通过HTTP API(应用程序编程接口)进行通信。
步骤13：若在所述用户图像中检测到所述用户的人脸图像且所述用户的人脸图像与特定用户的人脸图像相匹配，则接收所述用户在所述采集终端上的操作行为数据，并将所述操作行为数据与所述特定用户的用户标识进行关联。
可选地，所述操作行为数据包括所述用户在所述采集终端和/或指定终端 上实施操作行为时产生的数据；所述操作行为包括刷卡取号、查看理财产品、关注理财产品、购买理财产品、查看贵金属产品、关注贵金属产品、购买贵金属产品中的一种或多种。
这样，通过将操作行为数据与特定用户的用户标识相关联，从而能够对特定用户进行相应的行为分析，进而更好地为该用户服务。
可选地，所述采集终端对于产品的展示是通过内置的windows桌面应用来完成的，windows桌面应用内所有的关键点位均有埋点，各种类型的理财产品列表按钮、每个产品详情按钮、“喜欢”按钮、“查看过”按钮、“已购买”按钮等均有打点。例如，当用户点击“查看理财产品”按钮时，应用向服务器发送请求，服务器收到请求后，向采集终端发送采集图像请求，此请求触发采集终端的内置的摄像头进行拍照，通过人脸识别将存储系统内存储的照片与拍摄的照片进行特征比对，找到用户的ID(如身份信息)并通过服务器发送给采集终端，采集终端的打点功能生成用户的操作行为日志，并将用户的操作行为日志同步到服务器。
可选地，所述用户身份识别方法，还包括步骤14：若未在所述用户图像中检测到所述用户的人脸图像，和/或，若所述用户的人脸图像与任何特定用户的人脸图像均不匹配，则向所述采集终端发送继续采集图像指令。这样，当没有检测到人脸图像和/或人脸图像不能匹配时，继续采集用户的图像以完成人脸识别和用户信息匹配。
可选地，所述用户身份识别方法，还包括步骤15：若在经过预设时长阈值后仍未在所述用户图像中检测到所述用户的人脸图像，和/或，若在经过预设时长阈值后所述用户的人脸图像与任何特定用户的人脸图像均不匹配，则停止发送所述继续采集图像指令。
可选地，所述用户身份识别方法，还可包括以下步骤：
若在所述用户图像中检测到所述用户的人脸图像但所述用户的人脸图像与任何特定用户的人脸图像均不匹配，则说明采集终端当前采集的用户图像所对应的用户并不属于该银行的用户，因此，服务器可以暂存所述用户的人脸图像并接收所述用户在所述采集终端上的操作行为数据，并将所述操作行为数据与所述用户的人脸图像进行关联。这样，通过将未注册用户的人脸图 像与其操作行为数据进行关联，以备不时之需。
需要说明的是，前述步骤所要满足的前提条件是在所述用户图像中检测到所述用户的人脸图像但所述用户的人脸图像与任何特定用户的人脸图像均不匹配，该前提条件与步骤14的前提条件存在交叉，但这并不表示本实施例的步骤与步骤14之间是排斥关系。本领域技术人员可以理解，当满足本实施例的前提条件时，所述服务器可以既暂存所述用户的人脸图像并接收所述用户在所述采集终端上的操作行为数据以进行关联处理，也可以向所述采集终端发送继续采集图像指令，这两个处理步骤可以同时进行，也可以前后顺序进行，均能达到本公开实施例想要达到的效果。这两个处理步骤之间不会互相矛盾，这是服务器本身的处理能力能够达到的。
可选地，所述用户身份识别方法，还可包括以下步骤：
接收新用户注册信息；
从所述新用户注册信息中提取所述新用户的人脸图像；例如，所述新用户的人脸图像可以是所述新用户的身份证上的人脸图像，或者，所述新用户的人脸图像可以是所述新用户在注册时银行柜台的摄像头采集的该新用户的人脸图像；
若所述新用户的人脸图像与暂存的所述用户的人脸图像相匹配，则将与所述用户的人脸图像关联的所述操作行为数据与所述新用户的用户标识相关联。
这样，通过在先的暂存人脸图像并关联操作行为数据的步骤，结合后续的新用户注册信息的人脸比对，使得新用户在注册后能够马上关联到新用户在注册前即已在银行网点中产生的操作行为数据，从而能够更好地为该新用户进行服务。
从上述实施例可以看出，本公开提供的用户身份识别方法，通过采集用户图像并进行人脸识别，当检测到所述用户的人脸图像且所述用户的人脸图像与特定用户的人脸图像相匹配，接收所述用户在所述采集终端上的操作行为数据，并将所述操作行为数据与所述特定用户的用户标识进行关联；这样，通过人脸识别将操作行为数据与用户身份关联起来，使得本来不能识别用户身份的操作变得能够识别用户身份，进而能够将这些操作行为数据用于对用 户行为进行采集和分析，从而能够在一定程度上解决银行网点中用户行为难以分析的问题。此外，该用户身份识别方法，在客户无感知情况下，通过人脸识别的方法，精确绑定用户信息和用户行为，整个用户身份识别过程对用户无感，用户体验更好。
可选地，如图2所示，所述用户身份识别方法，还包括以下步骤：
步骤21：根据所述特定用户的用户标识，确定所述特定用户是否为特殊身份用户。这里，所述特殊身份用户可以是指对于银行或银行网点来说身份比较特殊的用户，例如，银行的VIP客户，存款超过某一数额的用户等等；或者，所述特殊身份用户也可以是本身身份比较特殊且需要额外帮助的用户，例如老人、残疾人、军人，等等。
步骤22：若所述特定用户为特殊身份用户，则将所述特殊身份用户的用户信息和所述用户的人脸图像发送到指定终端。
通过将特殊身份用户的用户信息和对应的人脸图像发送到指定终端，使持有该指定终端的人员能够及时反应以尽快为该特殊身份用户提供服务；其中，所述用户信息能够让持有该指定终端的人员快速了解该特殊身份用户的情况，所述人脸图像能够方便该人员查找该特殊身份用户。可选地，所述指定终端可以是提前设定好的接收所述特殊身份用户的用户信息和所述用户的人脸图像的终端设备，例如大堂经理的手持PAD(可以是Andriod系统或IOS系统)，可选地，手持PAD与服务器通过无线WIFI通信。
可选地，所述特殊身份用户的用户信息还可以是该用户的昵称，所述用户的人脸图像还可以是从存储系统中取得的用户头像。
可选地，所述步骤22中所述特殊身份用户的用户信息为经过脱敏处理后的用户信息，这样，对用户信息进行脱敏处理，防止用户信息泄露。其中，数据脱敏是指对某些敏感信息通过脱敏规则进行数据的变形，实现敏感隐私数据的可靠保护。在涉及客户安全数据或者一些商业性敏感数据的情况下，在不违反系统规则条件下，对真实数据进行改造并提供测试使用，如身份证号、手机号、卡号、客户号等个人信息都需要进行数据脱敏处理。可选地，所述用户信息可以是从银行内部客户关系管理系统(Customer relationship management system，CRM)系统中调取的。例如，银行为了对用户信息进行 保密，仅对所述服务器开放银行内部CRM系统中的一部分用户信息，且服务器从银行调取的用户信息为经过银行进行脱敏处理后的用户信息，从而防止银行内部存储的用户信息不被泄露；因此，服务器能够从银行内部CRM系统中调取的用户信息例如可以是经过了脱敏处理的。换言之，本实施例中虽然仅提到特殊身份用户的用户信息经过了脱敏处理，但在一些实施方式中，普通用户的用户信息也经过了脱敏处理，以防银行的用户信息被泄露。
同时，由于银行只向服务器提供部分用户信息的数据接口且这些用户信息经过了脱敏处理，因此服务器无法从采集终端处直接获得具体的用户标识，而服务器则需要对用户图像进行人脸识别来辅助确定当前用户的用户标识，进而才能将相应的操作行为数据与用户的用户标识进行关联。
可选地，所述用户信息其中可包括所述特殊身份用户的用户数据、财产数据、历史购买数据、理财产品信息。
可选地，脱敏后的用户信息示例参考如下：
{ID：0010003，昵称：张先生，财产：有点小钱，是否VIP：是，购买产品：[金条，定期理财，分红保险]}。
步骤23：若所述特定用户为普通身份用户，则不作处理。
上述实施例根据特定用户的用户标识确定是否为特殊身份用户，若是，则将该特殊身份用户的用户信息和所述用户的人脸图像发送到指定终端，使持有该指定终端的人员能够及时为所述特殊身份用户进行服务，从而提升特殊身份用户的用户体验。
可选地，如图3所示，所述用户身份识别方法，还包括：
步骤31：获取与所述特定用户的用户标识相关的历史操作行为数据以及产品数据。
可选地，所述历史操作行为数据为该特定用户的操作行为数据的历史记录，该历史记录可以是该特定用户在该银行旗下的各网点的操作行为数据的记录。可选地，所述产品数据可以是银行提供的各种产品的相关信息和数据，例如理财产品的七日年化收益率、产品期限、产品属性、产品的风险等级、交易规则、产品亮点、产品的常见问题、产品的财产安全保障情况等等。
步骤32：根据所述操作行为数据与所述历史操作行为数据，结合所述产 品数据，生成产品推荐内容。
可选地，大数据分析平台使用CDH(Cloudera Hadoop发行版)搭建，组件包括Hadoop、Hive、Spark。Hadoop是分布式文件系统，用于存储行为日志数据，Hive用于存储计算的中间结果和交互式查询，Spark用于进行内存计算、数据分析。
可选地，所述生成产品推荐内容的步骤可根据用户的画像数据(可根据用户的基本身份信息生成)、资产信息、操作行为数据、历史操作行为数据、在售理财/金融产品数据等，通过所述大数据分析平台生成适合用户的理财产品。
步骤33：将所述产品推荐内容发送到所述采集终端和/或指定终端。
可选地，当所述用户当前正在使用采集终端时(可通过该采集终端采集到的用户图像来确定用户在使用哪个采集终端)，针对该用户的所述产品推荐内容则发送到该采集终端，使得该用户马上就能看到针对其特别推荐的产品内容；当所述用户正在使用指定终端时(可通过该指定终端采集到的用户图像来确定用户是否正在使用该指定终端)，针对该用户的所述产品推荐内容则发送到该指定终端，使得该用户马上就能看到针对其特别推荐的产品内容，同时，持有该指定终端的人员也可以据此向该用户介绍该产品。
通过上述实施例，向用户正在浏览的终端发送产品推荐内容，该产品推荐内容弹出到屏幕上，用户便可以可行购买，从而减少用户浏览理财产品的盲目性、提升产品营销的准确性，实现精准定位用户和精准营销，提升了银行网点的运行效率。
可选地，如图3所示，所述用户身份识别方法，还包括：
步骤34：接收所述用户在所述采集终端和/或所述指定终端上针对所述产品推荐内容的操作行为数据。
可选地，用户针对所述产品推荐内容的操作行为数据例如可以是，查看了该产品推荐内容中推荐的产品(说明用户对推荐内容感兴趣)，或者，将产品推荐内容界面关闭(说明用户对推荐内容不感兴趣)，等等。
步骤35：根据所述用户针对所述产品推荐内容的操作行为数据，结合所述历史操作行为数据和所述产品数据，生成新的产品推荐内容。例如，假设 根据用户针对所述产品推荐内容的操作行为数据确定用户对某一产品感兴趣或不感兴趣，则在产品推荐时提高或降低该类产品的权重，然后重新生成产品推荐内容。
步骤36：将所述新的产品推荐内容发送到所述采集终端和/或指定终端。
通过结合用户对产品推荐内容的操作行为数据所反映的信息，重新生成产品推荐内容，使得产品推荐能够更加精准，同时提升了用户体验。
需要说明的是，上述实施例中以该用户身份识别方法应用于服务器为例进行了示例性说明，需要知道的是，上述方法的任一实施例或实施例的排列、组合，除了应用于服务器外，也可以应用于其他设备中，只要设备本身具备相应的硬件条件即可，因此不应将本公开的保护范围限定在应用于服务器。
本公开实施例的第二个方面，提供了一种用户身份识别装置，能够在一定程度上解决银行网点中用户行为难以分析的问题。
如图4所示，所述用户身份识别装置，包括：
接收模块41，用于获取用户图像以及接收所述用户在采集终端上的操作行为数据；
人脸识别模块42，用于对所述用户图像进行人脸识别处理；
身份确定模块43，若在所述用户图像中检测到所述用户的人脸图像且所述用户的人脸图像与特定用户的人脸图像相匹配，用于将所述用户在所述采集终端上的操作行为数据与所述特定用户的用户标识进行关联；其中，所述采集终端是银行网点内的操作设备。
从上述实施例可以看出，本公开提供的用户身份识别装置，通过获取用户图像并进行人脸识别，当检测到所述用户的人脸图像且所述用户的人脸图像与特定用户的人脸图像相匹配，接收所述用户在所述采集终端上的操作行为数据，并将所述操作行为数据与所述特定用户的用户标识进行关联；这样，通过人脸识别将操作行为数据与用户身份关联起来，使得本来不能识别用户身份的操作变得能够识别用户身份，进而能够将这些操作行为数据用于对用户行为进行采集和分析，从而能够在一定程度上解决银行网点中用户行为难以分析的问题。此外，该用户身份识别装置的用户身份识别过程对用户无感， 用户体验更好。
可选地，所述人脸识别模块42，还可具体用于：
确定所述用户图像中是否存在所述用户的人脸图像；
若在所述用户图像中检测到所述用户的人脸图像，则比对所述用户的人脸图像与预存的用户的人脸图像；
若所述用户的人脸图像与特定用户的人脸图像相匹配，则确定所述特定用户的用户标识为所述用户的用户标识。
可选地，所述人脸识别模块42，还可具体用于：
根据所述用户图像中的人脸位置裁剪所述用户图像，保留所述用户的人脸图像。
可选地，所述用户身份识别装置，还包括发送模块44；
所述身份确定模块43，还用于根据所述特定用户的用户标识，确定所述特定用户是否为特殊身份用户；
若所述特定用户为特殊身份用户，所述发送模块44，用于将所述特殊身份用户的用户信息和所述用户的人脸图像发送到指定终端，其中，所述指定终端是提前设定好的接收所述特殊身份用户的用户信息和所述用户的人脸图像的终端设备。
可选地，所述特殊身份用户的用户信息为经过脱敏处理后的用户信息。
可选地，所述用户身份识别装置，还包括推荐模块45；
所述推荐模块45，用于获取与所述特定用户的用户标识相关的历史操作行为数据以及产品数据；以及，根据所述操作行为数据与所述历史操作行为数据，结合所述产品数据，生成产品推荐内容。
可选地，所述接收模块41，还用于接收用户针对所述产品推荐内容的操作行为数据；
所述推荐模块45，还用于根据所述用户针对所述产品推荐内容的操作行为数据，结合所述历史操作行为数据和所述产品数据，生成新的产品推荐内容。
可选地，若未在所述用户图像中检测到所述用户的人脸图像，和/或，若所述用户的人脸图像与任何特定用户的人脸图像均不匹配，所述接收模块41， 还用于继续获取用户图像。
可选地，若在经过预设时长阈值后仍未在所述用户图像中检测到所述用户的人脸图像，和/或，若在经过预设时长阈值后所述用户的人脸图像与任何特定用户的人脸图像均不匹配，所述接收模块41，还用于停止获取用户图像。
可选地，若在所述用户图像中检测到所述用户的人脸图像但所述用户的人脸图像与任何特定用户的人脸图像均不匹配，则所述人脸识别模块还用于暂存所述用户的人脸图像，所述接收模块还用于接收所述用户在所述采集终端上的操作行为数据，所述身份确定模块还用于将所述操作行为数据与所述用户的人脸图像进行关联。
可选地，所述接收模块还用于接收新用户注册信息；
所述人脸识别模块，用于从所述新用户注册信息中提取所述新用户的人脸图像；
若所述新用户的人脸图像与暂存的所述用户的人脸图像相匹配，则所述身份确定模块还用于将与所述用户的人脸图像关联的所述操作行为数据与所述新用户的用户标识相关联。
上述用户身份识别装置的各实施例与前述的用户身份识别方法的各实施例呈对应关系，在这里不再赘述用户身份识别装置各实施例的技术效果。
基于上述目的，本公开实施例的第三个方面，提出了一种执行所述用户身份识别方法的装置的一个实施例。如图5所示，为本公开提供的执行所述用户身份识别方法的装置的一个实施例的硬件结构示意图。
如图5所示，所述装置包括：
一个或多个处理器51以及存储器52，图5中以一个处理器51为例。
所述执行所述用户身份识别方法的装置还可以包括：输入装置53和输出装置54。
处理器51、存储器52、输入装置53和输出装置54可以通过总线或者其他方式连接，图5中以通过总线连接为例。
存储器52作为一种非易失性计算机可读存储介质，可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块，如本申请实施例中的所述 用户身份识别方法对应的程序指令/模块(例如，附图4所示的接收模块41、人脸识别模块42和身份确定模块43)。处理器51通过运行存储在存储器52中的非易失性软件程序、指令以及模块，从而执行服务器的各种功能应用以及数据处理，即实现上述方法实施例的用户身份识别方法。
存储器52可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储根据用户身份识别装置的使用所创建的数据等。此外，存储器52可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实施例中，存储器52可选包括相对于处理器51远程设置的存储器，这些远程存储器可以通过网络连接至会员用户行为监控装置。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
输入装置53可接收输入的数字或字符信息，以及产生与用户身份识别装置的用户设置以及功能控制有关的键信号输入。输出装置54可包括显示屏等显示设备。
所述一个或者多个模块存储在所述存储器52中，当被所述一个或者多个处理器51执行时，执行上述任意方法实施例中的用户身份识别方法。所述执行所述用户身份识别方法的装置的实施例，其技术效果与前述任意方法实施例相同或者类似。
本申请实施例提供了一种非暂态计算机存储介质，所述计算机存储介质存储有计算机可执行指令，该计算机可执行指令可执行上述任意方法实施例中的列表项操作的处理方法。所述非暂态计算机存储介质的实施例，其技术效果与前述任意方法实施例相同或者类似。
最后需要说明的是，本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory，ROM)或随机存储记忆体(Random Access  Memory，RAM)等。所述计算机程序的实施例，其技术效果与前述任意方法实施例相同或者类似。
此外，典型地，本公开所述的装置、设备等可为各种电子终端设备，例如手机、个人数字助理(PDA)、平板电脑(PAD)、智能电视等，也可以是大型终端设备，如服务器等，因此本公开的保护范围不应限定为某种特定类型的装置、设备。本公开所述的客户端可以是以电子硬件、计算机软件或两者的组合形式应用于上述任意一种电子终端设备中。
此外，根据本公开的方法还可以被实现为由CPU执行的计算机程序，该计算机程序可以存储在计算机可读存储介质中。在该计算机程序被CPU执行时，执行本公开的方法中限定的上述功能。
此外，上述方法步骤以及系统单元也可以利用控制器以及用于存储使得控制器实现上述步骤或单元功能的计算机程序的计算机可读存储介质实现。
此外，应该明白的是，本文所述的计算机可读存储介质(例如，存储器)可以是易失性存储器或非易失性存储器，或者可以包括易失性存储器和非易失性存储器两者。作为例子而非限制性的，非易失性存储器可以包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦写可编程ROM(EEPROM)或快闪存储器。易失性存储器可以包括随机存取存储器(RAM)，该RAM可以充当外部高速缓存存储器。作为例子而非限制性的，RAM可以以多种形式获得，比如同步RAM(DRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据速率SDRAM(DDR SDRAM)、增强SDRAM(ESDRAM)、同步链路DRAM(SLDRAM)以及直接RambusRAM(DRRAM)。所公开的方面的存储设备意在包括但不限于这些和其它合适类型的存储器。
本领域技术人员还将明白的是，结合这里的公开所描述的各种示例性逻辑块、模块、电路和算法步骤可以被实现为电子硬件、计算机软件或两者的组合。为了清楚地说明硬件和软件的这种可互换性，已经就各种示意性组件、方块、模块、电路和步骤的功能对其进行了一般性的描述。这种功能是被实现为软件还是被实现为硬件取决于具体应用以及施加给整个系统的设计约束。本领域技术人员可以针对每种具体应用以各种方式来实现所述的功能，但是 这种实现决定不应被解释为导致脱离本公开的范围。
结合这里的公开所描述的各种示例性逻辑块、模块和电路可以利用被设计成用于执行这里所述功能的下列部件来实现或执行：通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或其它可编程逻辑器件、分立门或晶体管逻辑、分立的硬件组件或者这些部件的任何组合。通用处理器可以是微处理器，但是可替换地，处理器可以是任何传统处理器、控制器、微控制器或状态机。处理器也可以被实现为计算设备的组合，例如，DSP和微处理器的组合、多个微处理器、一个或多个微处理器结合DSP核、或任何其它这种配置。
结合这里的公开所描述的方法或算法的步骤可以直接包含在硬件中、由处理器执行的软件模块中或这两者的组合中。软件模块可以驻留在RAM存储器、快闪存储器、ROM存储器、EPROM存储器、EEPROM存储器、寄存器、硬盘、可移动盘、CD-ROM、或本领域已知的任何其它形式的存储介质中。示例性的存储介质被耦合到处理器，使得处理器能够从该存储介质中读取信息或向该存储介质写入信息。在一个替换方案中，所述存储介质可以与处理器集成在一起。处理器和存储介质可以驻留在ASIC中。ASIC可以驻留在用户终端中。在一个替换方案中，处理器和存储介质可以作为分立组件驻留在用户终端中。
在一个或多个示例性设计中，所述功能可以在硬件、软件、固件或其任意组合中实现。如果在软件中实现，则可以将所述功能作为一个或多个指令或代码存储在计算机可读介质上或通过计算机可读介质来传送。计算机可读介质包括计算机存储介质和通信介质，该通信介质包括有助于将计算机程序从一个位置传送到另一个位置的任何介质。存储介质可以是能够被通用或专用计算机访问的任何可用介质。作为例子而非限制性的，该计算机可读介质可以包括RAM、ROM、EEPROM、CD-ROM或其它光盘存储设备、磁盘存储设备或其它磁性存储设备，或者是可以用于携带或存储形式为指令或数据结构的所需程序代码并且能够被通用或专用计算机或者通用或专用处理器访问的任何其它介质。此外，任何连接都可以适当地称为计算机可读介质。例如，如果使用同轴线缆、光纤线缆、双绞线、数字用户线路(DSL)或诸如红 外线、无线电和微波的无线技术来从网站、服务器或其它远程源发送软件，则上述同轴线缆、光纤线缆、双绞线、DSL或诸如红外先、无线电和微波的无线技术均包括在介质的定义。如这里所使用的，磁盘和光盘包括压缩盘(CD)、激光盘、光盘、数字多功能盘(DVD)、软盘、蓝光盘，其中磁盘通常磁性地再现数据，而光盘利用激光光学地再现数据。上述内容的组合也应当包括在计算机可读介质的范围内。
公开的示例性实施例，但是应当注公开的示例性实施例，但是应当注意，在不背离权利要求限定的本公开的范围的前提下，可以进行多种改变和修改。根据这里描述的公开实施例的方法权利要求的功能、步骤和/或动作不需以任何特定顺序执行。此外，尽管本公开的元素可以以个体形式描述或要求，但是也可以设想多个，除非明确限制为单数。
应当理解的是，在本文中使用的，除非上下文清楚地支持例外情况，单数形式“一个”(“a”、“an”、“the”)旨在也包括复数形式。还应当理解的是，在本文中使用的“和/或”是指包括一个或者一个以上相关联地列出的项目的任意和所有可能组合。
上述本公开实施例序号仅仅为了描述，不代表实施例的优劣。
本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成，也可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，上述提到的存储介质可以是只读存储器，磁盘或光盘等。
所属领域的普通技术人员应当理解：以上任何实施例的讨论仅为示例性的，并非旨在暗示本公开的范围(包括权利要求)被限于这些例子；在本公开实施例的思路下，以上实施例或者不同实施例中的技术特征之间也可以进行组合，并存在如上所述的本公开实施例的不同方面的许多其它变化，为了简明它们没有在细节中提供。因此，凡在本公开实施例的精神和原则之内，所做的任何省略、修改、等同替换、改进等，均应包含在本公开实施例的保护范围之内。

Claims (16)

  1. 一种用户身份识别方法，包括：
    获取用户图像；
    对所述用户图像进行人脸识别处理；
    若在所述用户图像中检测到所述用户的人脸图像且所述用户的人脸图像与特定用户的人脸图像相匹配，则接收所述用户在采集终端上的操作行为数据，并将所述操作行为数据与所述特定用户的用户标识进行关联；其中，所述采集终端是银行网点内的操作设备。
  2. 根据权利要求1所述的方法，其中，所述采集终端可以银行网点内的刷卡设备、理财产品展示设备或重金属产品展示设备。
  3. 根据权利要求1所述的方法，其中，对所述用户图像进行人脸识别处理，包括：
    确定所述用户图像中是否存在所述用户的人脸图像；
    若在所述用户图像中检测到所述用户的人脸图像，则比对所述用户的人脸图像与预存的用户的人脸图像；
    若所述用户的人脸图像与特定用户的人脸图像相匹配，则确定所述特定用户的用户标识为所述用户的用户标识。
  4. 根据权利要求3所述的方法，其中，所述在用户图像中检测到所述用户的人脸图像时，所述用户身份识别方法还包括：
    根据所述用户图像中的人脸位置裁剪所述用户图像，保留所述用户的人脸图像。
  5. 根据权利要求4所述的方法，还包括：
    根据所述特定用户的用户标识，确定所述特定用户是否为特殊身份用户；
    若所述特定用户为特殊身份用户，则将所述特殊身份用户的用户信息和所述用户的人脸图像发送到指定终端，其中，所述指定终端是提前设定好的接收所述特殊身份用户的用户信息和所述用户的人脸图像的终端设备。
  6. 根据权利要求5所述的方法，其中，
    所述用户信息为经过脱敏处理后的用户信息。
  7. 根据权利要求1所述的方法，还包括：
    获取与所述特定用户的用户标识相关的历史操作行为数据以及产品数据；
    根据所述操作行为数据与所述历史操作行为数据，结合所述产品数据，生成产品推荐内容。
  8. 根据权利要求7所述的方法，其中，所述操作行为数据包括所述用户在所述采集终端和/或指定终端上实施操作行为时产生的数据；所述操作行为包括刷卡取号、查看理财产品、关注理财产品、购买理财产品、查看贵金属产品、关注贵金属产品、购买贵金属产品中的一种或多种。
  9. 根据权利要求7所述的方法，还包括：
    接收所述用户在所述采集终端和/或所述指定终端上针对所述产品推荐内容的操作行为数据；
    根据所述用户针对所述产品推荐内容的操作行为数据，结合所述历史操作行为数据和所述产品数据，生成新的产品推荐内容。
  10. 根据权利要求1所述的方法，还包括：
    若未在所述用户图像中检测到所述用户的人脸图像，和/或，若所述用户的人脸图像与任何特定用户的人脸图像均不匹配，则继续获取用户图像。
  11. 根据权利要求10所述的方法，还包括：
    若在经过预设时长阈值后仍未在所述用户图像中检测到所述用户的人脸图像，和/或，若在经过预设时长阈值后所述用户的人脸图像与任何特定用户的人脸图像均不匹配，则停止获取用户图像。
  12. 根据权利要求10所述的方法，还包括：
    若在所述用户图像中检测到所述用户的人脸图像但所述用户的人脸图像与任何特定用户的人脸图像均不匹配，则暂存所述用户的人脸图像并接收所述用户在所述采集终端上的操作行为数据，并将所述操作行为数据与所述用户的人脸图像进行关联。
  13. 根据权利要求12所述的方法，还包括：
    接收新用户注册信息；
    从所述新用户注册信息中提取所述新用户的人脸图像；
    若所述新用户的人脸图像与暂存的所述用户的人脸图像相匹配，则将与 所述用户的人脸图像关联的所述操作行为数据与所述新用户的用户标识相关联。
  14. 一种用户身份识别装置，包括：
    接收模块，用于获取用户图像以及接收所述用户在所述采集终端上的操作行为数据；
    人脸识别模块，用于对所述用户图像进行人脸识别处理；
    身份确定模块，若在所述用户图像中检测到所述用户的人脸图像且所述用户的人脸图像与特定用户的人脸图像相匹配，用于将所述操作行为数据与所述特定用户的用户标识进行关联；其中，所述采集终端是银行网点内的操作设备。
  15. 一种电子设备，包括：
    至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如权利要求1-13任一项所述的方法。
  16. 一种存储有计算机程序的计算机可读存储介质，所述计算机程序在由处理器执行时实现权利要求1-13中任一项所述的方法的步骤。
PCT/CN2020/092395 2019-05-31 2020-05-26 用户身份识别方法及装置、电子设备、存储介质 WO2020238915A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/281,861 US20210398133A1 (en) 2019-05-31 2020-05-26 User identity recognition method and device, electronic device and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910470241.5A CN112016985B (zh) 2019-05-31 2019-05-31 用户身份识别方法及装置、电子设备、存储介质
CN201910470241.5 2019-05-31

Publications (1)

Publication Number Publication Date
WO2020238915A1 true WO2020238915A1 (zh) 2020-12-03

Family

ID=73502088

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/092395 WO2020238915A1 (zh) 2019-05-31 2020-05-26 用户身份识别方法及装置、电子设备、存储介质

Country Status (3)

Country Link
US (1) US20210398133A1 (zh)
CN (1) CN112016985B (zh)
WO (1) WO2020238915A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111726788B (zh) * 2020-06-05 2021-06-15 南京甄视智能科技有限公司 基于iot提高局域网设备间数据通讯可靠性的方法及系统
CN112634483A (zh) * 2020-12-24 2021-04-09 深兰盛视科技（苏州）有限公司 签到方法、装置、电子设备及存储介质
CN112733635A (zh) * 2020-12-28 2021-04-30 北京迈格威科技有限公司 对象识别方法、装置及电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104852908A (zh) * 2015-04-22 2015-08-19 中国建设银行股份有限公司 一种业务资讯的推荐方法及装置
CN107169861A (zh) * 2017-04-07 2017-09-15 平安科技（深圳）有限公司 网点销售服务系统及方法
CN109345680A (zh) * 2018-08-29 2019-02-15 中国建设银行股份有限公司 一种全场景互动方法、控制设备及计算机可读介质
CN109410027A (zh) * 2018-08-29 2019-03-01 中国建设银行股份有限公司 一种基于特征识别的金融信息处理方法、智能终端及介质
CN109685610A (zh) * 2018-12-14 2019-04-26 深圳壹账通智能科技有限公司 产品推送方法、装置、计算机设备和存储介质

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105095431A (zh) * 2015-07-22 2015-11-25 百度在线网络技术（北京）有限公司 根据用户的行为信息推送视频的方法和装置
CN105100269A (zh) * 2015-08-27 2015-11-25 努比亚技术有限公司 一种移动终端及基于不同用户的内容推荐方法
CN106709776A (zh) * 2015-11-17 2017-05-24 腾讯科技（深圳）有限公司 商品推送方法及装置
CN106779292A (zh) * 2016-11-18 2017-05-31 浪潮（苏州）金融技术服务有限公司 一种基于人脸识别为客户提供服务的方法及装置
CN107423355B (zh) * 2017-05-26 2019-03-15 北京三快在线科技有限公司 信息推荐方法及装置、电子设备
CN107437198A (zh) * 2017-05-26 2017-12-05 阿里巴巴集团控股有限公司 确定用户风险偏好的方法、信息推荐方法及装置
CN107590676A (zh) * 2017-07-28 2018-01-16 百度在线网络技术（北京）有限公司 提供个性化服务的方法、装置、设备和计算机存储介质
US10795979B2 (en) * 2017-09-27 2020-10-06 International Business Machines Corporation Establishing personal identity and user behavior based on identity patterns
US11055674B1 (en) * 2018-01-18 2021-07-06 Wells Fargo Bank, N.A. Systems and methods for check masking and interdiction
CN110458644A (zh) * 2019-07-05 2019-11-15 深圳壹账通智能科技有限公司 一种信息处理方法及相关设备
CN110415113A (zh) * 2019-08-05 2019-11-05 深圳怡化电脑股份有限公司 金融数据处理方法、装置、服务器及可读存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104852908A (zh) * 2015-04-22 2015-08-19 中国建设银行股份有限公司 一种业务资讯的推荐方法及装置
CN107169861A (zh) * 2017-04-07 2017-09-15 平安科技（深圳）有限公司 网点销售服务系统及方法
CN109345680A (zh) * 2018-08-29 2019-02-15 中国建设银行股份有限公司 一种全场景互动方法、控制设备及计算机可读介质
CN109410027A (zh) * 2018-08-29 2019-03-01 中国建设银行股份有限公司 一种基于特征识别的金融信息处理方法、智能终端及介质
CN109685610A (zh) * 2018-12-14 2019-04-26 深圳壹账通智能科技有限公司 产品推送方法、装置、计算机设备和存储介质

Also Published As

Publication number Publication date
CN112016985B (zh) 2023-10-27
CN112016985A (zh) 2020-12-01
US20210398133A1 (en) 2021-12-23

Similar Documents

Publication Publication Date Title
WO2020238915A1 (zh) 用户身份识别方法及装置、电子设备、存储介质
WO2020024398A1 (zh) 生物特征辅助支付方法、装置、计算机设备及存储介质
CN109165940B (zh) 一种防盗方法、装置及电子设备
US9077678B1 (en) Facilitating photo sharing
US10069891B2 (en) Channel accessible single function micro service data collection process for light analytics
US10897461B2 (en) Pharmacy database access methods and systems
US10796136B2 (en) Secondary source authentication of facial biometric
US20210117652A1 (en) Method and System for Customizing User Experience
US20230044612A1 (en) Transaction Terminal Fraud Processing
US10755344B2 (en) System framework processor for channel contacts
WO2019024497A1 (zh) 客户回访事件的生成方法、装置、终端设备及介质
US10693897B2 (en) Behavioral and account fingerprinting
JP2023538832A (ja) 失敗したユーザ・インターフェイスの解決
US20170091050A1 (en) System for aggregation and transformation of real-time data
US10049306B2 (en) System and method for learning from the images of raw data
US11880852B2 (en) Merchant advertisement informed item level
JPWO2015145727A1 (ja) 本人情報取得システムおよび本人情報取得方法
US20170091859A1 (en) System for real-time data structuring and storage
US11854008B2 (en) Systems and methods for conducting remote user authentication
US11816668B2 (en) Dynamic contactless payment based on facial recognition
US11704524B2 (en) System and method for generating a dynamic machine readable code
US10891355B2 (en) Pharmacy authentication methods and systems
EA038077B1 (ru) Способ и система маркировки действий пользователя для последующего анализа и накопления
US20230403268A1 (en) Reducing false positives in entity matching based on image-linking graphs
RU2693646C1 (ru) Способ и система подбора предложений для пользователя на основании анализа его действий

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20812761

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20812761

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20812761

Country of ref document: EP

Kind code of ref document: A1