Identity verification method and device

Abstract

The present application provides an identity verification method and device, the method comprises the following steps: collecting the face information of a person to be verified; extracting the face feature data of the person to be verified from the face information of the person to be verified; searching for the real-name authentication identity information of the person to be verified in a real-name face database based on the face feature data of the person to be verified; the real-name face database is obtained through an associated application program; if the real-name authentication identity information of the person to be verified is not obtained, searching for the virtual identity information of the person to be verified in a plurality of anonymous face databases based on the face feature data of the person to be verified; the anonymous face databases are obtained through an associated application program; and determining the real-name authentication identity information of the person to be verified based on the virtual identity information of the person to be verified. Without pre-recording a large number of face features and without inputting the identity information of each face, the workload is reduced and the use cost is lowered.

Description

Technical Field

[0001] This invention relates to the field of identity recognition technology, and in particular to an identity verification method and apparatus. Background Technology

[0002] Due to its advantages such as high security, resistance to loss, and difficulty in counterfeiting, most existing identity verification methods rely on biometrics, such as facial recognition. However, this method requires users to pre-register their facial features and input their identity information; otherwise, identity verification cannot be performed, resulting in high upfront costs. For example, entering an industrial park requires identity verification before entry. This necessitates pre-registering the facial features of all personnel in the park and the corresponding real-name identity data for each face. This is not only time-consuming but also involves a large workload and high labor costs. Summary of the Invention

[0003] The purpose of this invention is to provide an identity verification method, apparatus, computer equipment, computer-readable storage medium, and computer program product that reduce usage costs.

[0004] In a first aspect, the present invention provides an identity verification method, comprising:

[0005] Collect facial information of the person to be verified;

[0006] Extract facial feature data of the person to be verified from their facial information;

[0007] Based on the facial feature data of the person to be verified, the real-name authentication identity information of the person to be verified is retrieved from the real-name face database; the real-name face database is obtained through associated applications;

[0008] If the real-name authentication information of the person to be verified is not obtained, the virtual identity information of the person to be verified is retrieved from multiple anonymous face databases based on the facial feature data of the person to be verified; the anonymous face databases are obtained through associated applications;

[0009] Based on the virtual identity information of the person to be verified, determine the real-name authentication identity information of the person to be verified.

[0010] In a second aspect, the present invention provides an identity verification device, comprising:

[0011] The face capture module is used to collect the facial information of the person to be verified.

[0012] The facial feature extraction module is used to extract facial feature data of the person to be verified from the facial information of the person to be verified.

[0013] The first identity information determination module is used to retrieve the real-name authentication identity information of the person to be verified from the real-name face database based on the facial feature data of the person to be verified; the real-name face database is obtained through an associated application.

[0014] The anonymous face database retrieval module is used to retrieve the virtual identity information of the person to be verified from multiple anonymous face databases based on the person's facial feature data if the real-name authentication identity information of the person to be verified is not obtained; the anonymous face databases are obtained through associated applications;

[0015] The second identity information determination module is used to determine the real-name authentication identity information of the person to be verified based on the virtual identity information of the person to be verified.

[0016] Thirdly, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the identity verification method as described above.

[0017] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that performs the above-described identity verification method in response to the computer program being executed by a processor.

[0018] Fifthly, the present invention provides a computer program product, the computer program product comprising a computer program, which, when executed by a processor, implements the identity verification method as described above.

[0019] The identity verification method provided in this invention involves: collecting the facial information of the person to be verified; extracting facial feature data from the facial information; retrieving the real-name authentication information of the person to be verified from a real-name face database based on the facial feature data; obtaining the real-name face database through an associated application; if the real-name authentication information of the person to be verified is not obtained, retrieving the virtual identity information of the person to be verified from multiple anonymous face databases based on the facial feature data; obtaining the anonymous face databases through an associated application; and determining the real-name authentication information of the person to be verified based on the virtual identity information. The method obtains the real-name face database through an associated application, performs facial recognition based on the real-name face database to determine the identity of the person to be verified; if the identity of the person to be verified cannot be determined based on the real-name face database, multiple anonymous face databases are obtained through an associated application for facial recognition to determine the identity of the person to be verified. This method eliminates the need to pre-enter a large number of facial features or input the identity information of each face, reducing workload and lowering usage costs. Attached Figure Description

[0020] The following figures are intended only to illustrate and explain the present invention and do not limit the scope of the invention. Wherein:

[0021] Figure 1 This is a schematic diagram of the identity verification method according to an embodiment of the present invention;

[0022] Figure 2 This is a schematic diagram illustrating the implementation process of step 103 in a specific embodiment of the present invention;

[0023] Figure 3 This is a schematic diagram illustrating the implementation process of step 104 in a specific embodiment of the present invention;

[0024] Figure 4 This is a schematic diagram illustrating the implementation process of step 301 in a specific embodiment of the present invention;

[0025] Figure 5 This is a schematic diagram of the identity verification device in an embodiment of the present invention;

[0026] Figure 6 This is a schematic diagram of the anonymous face database retrieval module 504 in a specific embodiment of the present invention;

[0027] Figure 7 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0028] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. Through these descriptions, the features and advantages of the present application will become clearer and more apparent.

[0029] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments. Although various aspects of embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated otherwise.

[0030] Furthermore, the technical features involved in the different embodiments of this application described below can be combined with each other as long as they do not conflict with each other.

[0031] This invention provides an identity verification method to reduce usage costs, such as... Figure 1 As shown, it includes:

[0032] Step 101: Collect the facial information of the person to be verified;

[0033] In practice, facial images are captured using hardware devices such as cameras to obtain the facial information of the person to be verified. For example, when identifying a person's identity at an access control system, the system uses cameras to capture facial images of the person to be verified to generate facial information.

[0034] Step 102: Extract facial feature data of the person to be verified from their facial information;

[0035] In the specific implementation of step 102, mature face recognition algorithms are used to extract key facial points, such as geometric feature-based methods, eigenface methods, local feature methods, specific face subspace methods, hidden Markov model methods, etc., which will not be elaborated here. First, the acquired face image is preprocessed, and feature extraction is performed based on the preprocessed image data to obtain the facial feature data of the person to be verified.

[0036] Step 103: Based on the facial feature data of the person to be verified, retrieve the real-name authentication identity information of the person to be verified from the real-name face database; wherein, the real-name face database is obtained through the associated application;

[0037] In the specific implementation of step 103, the real-name face database stores the facial feature data of multiple users and the real-name authentication information of each user. Specifically, the real-name face database is obtained through associated applications. Generally, it is formed when a registered user of an associated application uses the application and performs real-name authentication in scenarios requiring such authentication, such as making payments or logging into games. After the user completes real-name authentication, the associated application obtains and retains the relevant data, and the use of this data is authorized by the user. Specifically, the associated application collects the facial image of each user, extracts features to obtain the user's facial feature data, and stores the user's uploaded and successfully authenticated real-name authentication information into the real-name face database. For ease of subsequent use, a "key-value" storage method can be used.

[0038] Accordingly, the specific implementation process of step 103 is as follows: Figure 2 As shown, it includes:

[0039] Step 201: Using a face recognition algorithm, compare the facial feature data of the person to be verified with the facial feature data of multiple users in the real-name face database to determine the users whose face similarity exceeds the threshold;

[0040] Step 202: Determine the user's real-name authentication information as the real-name authentication information of the person to be verified.

[0041] Specifically, this threshold is preset, for example, it can be 70%, 75%, or 85%, and the specific value is not limited. In actual implementation, in order to ensure the accuracy of recognition, multiple face recognition tests are generally conducted in advance using the above-mentioned face recognition algorithm to ensure that the false recognition rate is below a very small value, such as one in ten million, so as to determine the approximate distribution range of face comparison similarity at this time, and thus determine the threshold.

[0042] Based on the facial feature data of the person to be verified, the system retrieves the person's real-name authentication information from a real-name face database. If the information is found, it is fed back to the user, thus completing the identity verification process. This eliminates the need to collect and record the person's facial data and real-name authentication information in advance. It leverages a real-name face database built with associated applications to quickly determine the person's identity, significantly reducing the upfront manpower and time costs associated with identity verification.

[0043] However, if the real-name authentication information of the person to be verified cannot be found in the real-name face database, that is, the person to be verified has not used the associated application for real-name authentication, then step 104 is executed.

[0044] Step 104: If the real-name authentication identity information of the person to be verified is not obtained, the virtual identity information of the person to be verified is retrieved from multiple anonymous face databases based on the facial feature data of the person to be verified; wherein, the anonymous face database is obtained through associated applications;

[0045] In a specific embodiment, the anonymous face database stores multiple facial feature data and virtual identity information for each face; the virtual identity information includes at least a virtual identity ID. In daily life, besides scenarios requiring real-name authentication, there are numerous scenarios where only faces are collected without requiring real identities, such as community access control systems, which only need to collect the faces of residents. Each face only needs to provide a simple identifier, such as a phone number, room number, or name. Each application scenario that collects faces and associates them with simple information can form an anonymous face database. Each anonymous face database contains multiple face images collected by the associated application in that application scenario and a virtual ID corresponding to each face image. This virtual ID can be one or any combination of a phone number, employee number, name, nickname, medical insurance number, or social security number. Those skilled in the art will understand that the above explanation of virtual IDs is merely illustrative and not intended to limit the scope of protection of this invention.

[0046] Furthermore, the application associated with obtaining the anonymous face database can be the same as or different from the application associated with obtaining the real-name face database; for example, it can be various mini-programs.

[0047] In specific embodiments, virtual identity information may also include AOI (Area of ​​Interest, geographical location), behavioral attributes, and other information. AOI refers to the location information of the face capture, i.e., the location of the virtual ID. By combining AOI and the capture time, the spatiotemporal behavioral attributes of the person corresponding to the face can be obtained. These attributes can be used to characterize a person; for example, a person's daily movement path can characterize them, typically from home to work, and eating lunch at a few fixed locations. These fixed locations can be used to assist in identity verification. Behavioral attributes refer to descriptions or attribute definitions of a user's behavior in each application scenario corresponding to facial feature data. For example, in access control applications, the frequency of a face verification is important. A high verification frequency indicates that the person passes through the access control frequently and often uses this application scenario, which can be used to assist in identity verification. For instance, when comparing facial feature data, due to unclear images during capture, there may be more than one matching facial feature data in the anonymous face database; behavioral attributes can be used for further judgment. For example, in the access control application scenario mentioned above, face A is used more frequently. If the face recognition scores of face A and face B are consistent, face A in the anonymous face database will be prioritized as the person to be verified.

[0048] To facilitate retrieval, in this specific embodiment, multiple anonymous face databases are numbered. Accordingly, step 104 specifically includes: searching each anonymous face database sequentially using a face recognition algorithm, according to the database number, until the virtual identity information of the person to be verified is obtained. When searching within an anonymous face database, a face recognition algorithm compares the facial feature data of the person to be verified with multiple facial feature data in that anonymous face database to identify faces whose similarity exceeds a threshold; the virtual identity information of this face is then identified as the virtual identity information of the person to be verified.

[0049] In practice, multiple anonymous face databases often contain overlapping facial feature data, and these overlapping facial feature data are used in different scenarios, so the corresponding virtual identity information in multiple anonymous face databases may also be different. Therefore, to ensure that the virtual identity information of the identified person to be verified is more comprehensive, the implementation process of step 104 is as follows: Figure 3 As shown, it includes:

[0050] Step 301: Integrate multiple anonymous face databases to obtain a virtual ID face database; wherein, the virtual ID face database stores multiple facial feature data and virtual identity information for each face;

[0051] Step 302: Using a face recognition algorithm, compare the face feature data of the person to be verified with multiple face feature data in the virtual ID face database to identify faces whose face similarity exceeds a threshold;

[0052] Step 303: Identify the virtual identity information of faces whose facial similarity exceeds the threshold as the virtual identity information of the person to be verified.

[0053] The process involves merging multiple anonymous face databases after deduplication to obtain a unified virtual ID face database, which is then used for retrieval. During this integration, the virtual identity information of the same face in each anonymous face database needs to be combined. Specifically, step 301 is implemented as follows: Figure 4 As shown, it includes:

[0054] Step 401: Using a face recognition algorithm, identify multiple sets of faces in multiple anonymous face databases whose face similarity exceeds a threshold;

[0055] Step 402: Integrate the virtual identity information of each group of faces to obtain the integrated virtual identity information;

[0056] Step 403: Based on the face retention quality algorithm, select one face feature data from each group of face feature data;

[0057] Step 404: Select one person's facial feature data and the integrated virtual identity information as the backup data corresponding to that group of faces;

[0058] Step 405: Store the data corresponding to multiple sets of faces into the virtual ID face database;

[0059] Step 406: Determine the remaining data after removing multiple sets of facial feature data and virtual identity information of multiple anonymous face databases, and store the remaining data into the virtual ID face database.

[0060] First, using facial recognition algorithms, multiple sets of faces with similarity exceeding a threshold from various anonymous face databases can be identified. Each set of faces represents the same person. For each set of faces, the virtual identity information stored in multiple anonymous face databases needs to be integrated. For example, anonymous face database 01 stores the phone number corresponding to this face, while anonymous face database 02 stores the employee ID corresponding to this face. Both pieces of information are used as the integrated virtual identity information. In particular, if the virtual identity information stored in different anonymous face databases is inconsistent, since it is impossible to verify which one is genuine, they can all be integrated for subsequent use.

[0061] Next, since the facial feature data stored in each anonymous face database is not entirely identical, and the data quality varies, it is necessary to select the facial feature data with the best quality for retention to ensure more accurate subsequent use. In other words, the quality of the facial images collected varies in different application scenarios, and it is necessary to select the image with the best quality, clearest image, and highest degree of facial exposure. A face retention quality algorithm can be used to evaluate each set of facial feature data (each set of facial images), selecting the facial feature data with the highest evaluation score, and combining it with the integrated virtual identity information as the retention data corresponding to that set of faces. The face retention quality algorithm can employ an image classification algorithm, with classification criteria such as lighting conditions, image clarity, and face integrity.

[0062] After storing the corresponding data from multiple sets of faces into the virtual ID face database, the remaining data without duplicates from multiple anonymous face databases are also stored in the virtual ID face database, thus completing the data integration from multiple anonymous face databases to the virtual ID face database. Then, based on the virtual ID face database, a search is performed to determine the virtual identity information of the person to be verified.

[0063] Step 105: Based on the virtual identity information of the person to be verified, determine the real-name authentication identity information of the person to be verified.

[0064] In a specific embodiment, although the virtual identity information of the person to be verified is obtained, identity verification still requires determining the real-name authentication identity information of the person to be verified. Based on the virtual identity information, a request to obtain the real-name authentication identity information can be sent to the person to be verified, thereby quickly obtaining the real-name authentication identity information of the person to be verified. Specifically, based on the virtual identity information of the person to be verified, a real-name authentication request is sent to the person to be verified; and the real-name authentication identity information sent by the person to be verified is received.

[0065] In a specific embodiment, for example, a text message prompt is sent to the person to be verified via the mobile phone number in the virtual ID, or a message prompt is sent to the account associated with the mobile phone number. The person to be verified fills in real-name authentication identity information on the relevant page, such as an ID card number, or uploads a photo of the document.

[0066] Depend on Figure 1As can be seen from the steps described, the identity verification method provided in this embodiment of the invention involves: collecting the facial information of the person to be verified; extracting facial feature data of the person to be verified from the facial information; retrieving the real-name authentication identity information of the person to be verified from a real-name face database based on the facial feature data; and obtaining the real-name face database through an associated application. If the real-name authentication identity information of the person to be verified is not obtained, the virtual identity information of the person to be verified is retrieved from multiple anonymous face databases based on the facial feature data; and obtaining the anonymous face databases through an associated application. Based on the virtual identity information of the person to be verified, the real-name authentication identity information of the person to be verified is determined. The method obtains the real-name face database through an associated application, performs facial recognition based on the real-name face database, and determines the identity of the person to be verified. If the identity of the person to be verified cannot be determined based on the real-name face database, multiple anonymous face databases are obtained through an associated application, and facial recognition is performed to determine the identity of the person to be verified. This eliminates the need to pre-enter a large number of facial features or input the identity information of each face, reducing workload and lowering usage costs.

[0067] In a specific embodiment, after receiving the real-name authentication information sent by the person to be verified, the method further includes: verifying the real-name authentication information sent by the person to be verified; if the verification is successful, using the real-name authentication information sent by the person to be verified as the real-name authentication information of the person to be verified. That is, the real-name authentication information sent by the person to be verified also needs to be sent to the real-name authentication system of the relevant department to obtain the real-name authentication result fed back by the real-name authentication system, to ensure that the identity verification is correct.

[0068] Furthermore, to avoid requiring the person to submit their real-name authentication information again during subsequent verifications, their real-name authentication information and facial feature data are stored in the aforementioned real-name facial database after obtaining their authorization. When verifying the person's identity again, the verification can be completed based on the real-name facial database.

[0069] In practice, if the virtual identity information of the person to be verified cannot be found in multiple anonymous face databases, it proves that the person to be verified has never had their face collected in the aforementioned application scenario. In this case, a virtual ID registration prompt and a real-name authentication prompt can be sent to the person to be verified through the current application scenario, using methods such as mini-programs. The person to be verified is reminded to enter their mobile phone number and other information to register a virtual ID for the current application scenario. The person's facial feature data and virtual identity information containing the virtual ID are then stored together in the anonymous face database of the current application scenario and in the virtual ID face database. The person to be verified is then reminded to enter their real-name authentication information for subsequent real-name authentication. After authentication, the person's facial feature data and real-name authentication information are then stored together in the real-name face database.

[0070] To better illustrate the identity verification method provided in the embodiments of the present invention, a specific example is provided for further explanation. The specific example is that the gate of an industrial park verifies the identity of people entering the park, and only those whose identity verification is successful can pass through.

[0071] Visitors scan a QR code provided at the park entrance to access a mini-program for identity verification. They then upload their facial image, captured using their phone's camera. After uploading, a facial recognition algorithm extracts facial feature data from the image and searches a real-name facial database. If a matching facial feature is found (or the one with the highest match if multiple matches exist), the system confirms the user's identity and authorizes access. This real-name facial database is typically used by applications that require user authentication, such as banking apps, third-party financial apps, or gaming apps. It is created by compiling user-authorized information.

[0072] If no match is found, the virtual ID face database is used for retrieval. If a match is found, a real-name authentication request is sent to the visitor based on the virtual identity information or through the park's identity verification mini-program. The visitor is asked to fill in their real-name authentication information. The system receives the real-name authentication information and sends it to the relevant real-name authentication website or system to obtain the authentication result. If authentication is successful, the access control system is notified to grant access and an authorization request is sent to the visitor. After authorization, the currently collected face image is compared with the face feature data stored in the virtual ID face database. The image with the better features is selected and stored together with the real-name authentication information filled in by the visitor in the real-name face database. If authentication fails, the visitor is notified of the real-name authentication failure and is asked to re-upload their real-name authentication information or re-collect their face.

[0073] The virtual ID face database is derived from multiple anonymous face databases through data integration and ID normalization. Each anonymous face database corresponds to a specific use case, mostly localized, unregistered access control mini-programs. After obtaining user authorization, virtual identity information such as virtual IDs and corresponding facial feature data are organized to form individual anonymous face databases. The data from the identity verification mini-program in this park can also form an anonymous face database A. Due to the high repetition rate of visitors, searches can be prioritized in anonymous face database A. Combining this with behavioral attributes from the virtual identity information in anonymous face database A helps determine the visitor's identity, thus improving the verification success rate.

[0074] If the virtual ID face database still fails to find a matching facial feature data for the visitor, the visitor will be prompted to register a virtual ID (e.g., using a mobile phone number) through the park's identity verification mini-program. The visitor will then be prompted to fill in their real-name authentication information for identity verification. After successful verification and with the visitor's authorization, the relevant data will be added to the anonymous face database A, the virtual ID face database, and the real-name face database.

[0075] Because the real-name facial recognition database can cover a large population, it largely allows visitors to pass identity verification without registration, facial data entry, or filling in other information. For those not covered by the real-name facial recognition database, a virtual ID facial recognition database can be used to determine the anonymous identity of visitors using existing data. During real-name authentication, facial feature data stored in the virtual ID facial recognition database (which may have better clarity and shooting angle than the currently collected facial image) can be used. This increases the success rate of real-name authentication when the currently collected facial image is not good, avoiding the need for re-collection or re-uploading of real-name authentication data, reducing the workload of visitors, and improving verification efficiency.

[0076] Based on the same inventive concept, embodiments of the present invention also provide an identity verification device, the principle of which is similar to the identity verification method, and the repeated parts will not be described again. The specific structure is as follows: Figure 5 As shown, it includes:

[0077] The face acquisition module 501 is used to collect the face information of the person to be verified;

[0078] The face feature extraction module 502 is used to extract the face feature data of the person to be verified from the face information of the person to be verified;

[0079] The first identity information determination module 503 is used to retrieve the real-name authentication identity information of the person to be verified from the real-name face database based on the facial feature data of the person to be verified; the real-name face database is obtained through the associated application.

[0080] The anonymous face database retrieval module 504 is used to retrieve the virtual identity information of the person to be verified from multiple anonymous face databases based on the person's facial feature data if the real-name authentication identity information of the person to be verified is not obtained; the anonymous face databases are obtained through associated applications;

[0081] The second identity information determination module 505 is used to determine the real-name authentication identity information of the person to be verified based on the virtual identity information of the person to be verified.

[0082] In specific implementation, the real-name face database stores facial feature data of multiple users and real-name authentication identity information of each user; correspondingly, the first identity information determination module 503 is used for:

[0083] By using facial recognition algorithms, the facial feature data of the person to be verified is compared with the facial feature data of multiple users in the real-name facial database to identify users whose facial similarity exceeds a threshold.

[0084] The user's real-name authentication information is identified as the real-name authentication information of the person to be verified.

[0085] In a specific embodiment, the anonymous face database stores multiple facial feature data and virtual identity information for each face; the virtual identity information includes at least: a virtual identity ID.

[0086] Accordingly, the anonymous face database retrieval module 504 is used for:

[0087] Based on the anonymous face database number, the facial recognition algorithm searches through multiple anonymous face databases one by one until the virtual identity information of the person to be verified is obtained.

[0088] In one specific embodiment, the anonymous face database retrieval module 504, such as... Figure 6 As shown, it includes:

[0089] Anonymous face database integration unit 601 is used to integrate data from multiple anonymous face databases to obtain a virtual ID face database; the virtual ID face database stores multiple facial feature data and virtual identity information for each face;

[0090] The face recognition unit 602 is used to compare the face feature data of the person to be verified with multiple face feature data in the virtual ID face database through a face recognition algorithm to determine the face whose face comparison similarity exceeds a threshold.

[0091] The virtual identity information determination unit 603 is used to determine the virtual identity information of a face whose face comparison similarity exceeds a threshold as the virtual identity information of the person to be verified.

[0092] In specific implementation, the anonymous face database integration unit 601 is specifically used for:

[0093] Using facial recognition algorithms, multiple sets of faces with similarity exceeding a threshold were identified from multiple anonymous face databases.

[0094] The virtual identity information of each group of faces is integrated to obtain the integrated virtual identity information;

[0095] Based on the face retention quality algorithm, one face feature data is selected from each group of face feature data;

[0096] The selected facial feature data and the integrated virtual identity information are used as the backup data corresponding to this group of faces;

[0097] Store the data corresponding to multiple sets of faces into the virtual ID face database;

[0098] The remaining data after removing the aforementioned sets of facial feature data and virtual identity information from multiple anonymous face databases is determined, and the remaining data is stored in the virtual ID face database.

[0099] In a specific embodiment, the second identity information determination module 505 is specifically used for:

[0100] Based on the virtual identity information of the person to be verified, a real-name authentication request is sent to the person to be verified.

[0101] Receive the real-name authentication information sent by the person to be verified.

[0102] Furthermore, to ensure the accuracy of the verification, the second identity information determination module 505 is also used for:

[0103] The system verifies the real-name authentication information sent by the person to be verified. Once the verification is successful, the real-name authentication information sent by the person to be verified will be used as the real-name authentication information of the person to be verified.

[0104] To facilitate subsequent verification and continuously improve verification efficiency, in a specific embodiment, the second identity information determination module 505 is further used for:

[0105] The real-name authentication information and facial feature data of the person to be verified are stored in the real-name facial database.

[0106] This invention also provides a computer device. Figure 7 This is a schematic diagram of a computer device in an embodiment of the present invention. The computer device is capable of implementing all steps in the identity verification method described above. Specifically, the computer device includes the following components:

[0107] Processor 701, memory 702, communications interface 703, and communication bus 704;

[0108] The processor 701, memory 702, and communication interface 703 communicate with each other through the communication bus 704; the communication interface 703 is used to realize information transmission between related devices.

[0109] The processor 701 is used to call the computer program in the memory 702, and when the processor executes the computer program, it implements the identity verification method in the above embodiment.

[0110] This invention also provides a computer-readable storage medium storing a computer program that, in response to the computer program being executed by a processor, performs the operation of the above-described identity verification method.

[0111] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described identity verification method.

[0112] While this invention provides the method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual device or client product execution, the methods shown in the embodiments or drawings can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0113] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, apparatus (systems), or computer program products. Therefore, the embodiments of this specification can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0114] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0115] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0116] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0117] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments. In this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0118] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention is not limited to any single aspect, nor to any single embodiment, nor to any combination and / or substitution of these aspects and / or embodiments. Furthermore, each aspect and / or embodiment of the present invention can be used alone or in combination with one or more other aspects and / or embodiments thereof.

[0119] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. An identity verification method, characterized in that, include: Collect facial information of the person to be verified; Extract facial feature data of the person to be verified from their facial information; Based on the facial feature data of the person to be verified, the real-name authentication identity information of the person to be verified is retrieved from the real-name face database; the real-name face database is obtained through associated applications; If the real-name authentication identity information of the person to be verified is not obtained, the virtual identity information of the person to be verified is retrieved from multiple anonymous face databases based on the facial feature data of the person to be verified; the anonymous face databases are obtained through associated applications; the anonymous face databases store multiple facial feature data and virtual identity information for each face; the virtual identity information includes at least a virtual identity ID; Based on the virtual identity information of the person to be verified, a real-name authentication request is sent to the person to be verified. Receive the real-name authentication information sent by the person to be verified.

2. The identity verification method according to claim 1, characterized in that, The real-name face database stores facial feature data of multiple users and real-name authentication identity information of each user; Based on the facial feature data of the person to be verified, the real-name authentication identity information of the person to be verified is retrieved from the real-name face database, including: By using facial recognition algorithms, the facial feature data of the person to be verified is compared with the facial feature data of multiple users in the real-name facial database to identify users whose facial similarity exceeds a threshold. The user's real-name authentication information is determined as the real-name authentication information of the person to be verified.

3. The identity verification method according to claim 1, characterized in that, Based on the facial feature data of the person to be verified, the virtual identity information of the person to be verified is retrieved from multiple anonymous face databases, including: Based on the anonymous face database number, the facial recognition algorithm searches through multiple anonymous face databases one by one until the virtual identity information of the person to be verified is obtained.

4. The identity verification method according to claim 1, characterized in that, Based on the facial feature data of the person to be verified, the virtual identity information of the person to be verified is retrieved from multiple anonymous face databases, including: Multiple anonymous face databases are integrated to obtain a virtual ID face database; the virtual ID face database stores multiple facial feature data and virtual identity information for each face; By using a facial recognition algorithm, the facial feature data of the person to be verified is compared with multiple facial feature data in the virtual ID face database to identify faces whose facial similarity exceeds a threshold. The virtual identity information of faces whose facial similarity exceeds a threshold is identified as the virtual identity information of the person to be verified.

5. The identity verification method according to claim 4, characterized in that, By integrating data from multiple anonymous face databases, a virtual ID face database is obtained, including: Using facial recognition algorithms, multiple sets of faces with similarity exceeding a threshold were identified from multiple anonymous face databases. The virtual identity information of each group of faces is integrated to obtain the integrated virtual identity information; Based on the face retention quality algorithm, one face feature data is selected from each group of face feature data; The selected facial feature data and the integrated virtual identity information are used as the backup data corresponding to this group of faces; Store the data corresponding to multiple sets of faces into the virtual ID face database; The remaining data after removing the multiple sets of facial feature data and the virtual identity information of the multiple sets of faces from multiple anonymous face databases is determined, and the remaining data is stored in the virtual ID face database.

6. The identity verification method according to claim 1, characterized in that, Also includes: The system verifies the real-name authentication information sent by the person to be verified. Once the verification is successful, the real-name authentication information sent by the person to be verified will be used as the real-name authentication information of the person to be verified.

7. The identity verification method according to claim 6, characterized in that, Also includes: The real-name authentication information and facial feature data of the person to be verified are stored in the real-name facial database.

8. An identity verification device, characterized in that, include: The face capture module is used to collect the facial information of the person to be verified. The facial feature extraction module is used to extract facial feature data of the person to be verified from the facial information of the person to be verified. The first identity information determination module is used to retrieve the real-name authentication identity information of the person to be verified from the real-name face database based on the facial feature data of the person to be verified; the real-name face database is obtained through an associated application. An anonymous face database retrieval module is used to retrieve the virtual identity information of the person to be verified from multiple anonymous face databases based on the person's facial feature data if the real-name authentication identity information of the person to be verified is not obtained. The anonymous face databases are obtained through associated applications. The anonymous face databases store multiple facial feature data and virtual identity information for each face. The virtual identity information includes at least a virtual identity ID. The second identity information determination module is used to send a real-name authentication request to the person to be verified based on the virtual identity information of the person to be verified, and to receive the real-name authentication identity information sent by the person to be verified.

9. The identity verification device according to claim 8, characterized in that, The real-name face database stores facial feature data of multiple users and real-name authentication identity information of each user; The first identity information determination module is used for: By using facial recognition algorithms, the facial feature data of the person to be verified is compared with the facial feature data of multiple users in the real-name facial database to identify users whose facial similarity exceeds a threshold. The user's real-name authentication information is determined as the real-name authentication information of the person to be verified.

10. The identity verification device according to claim 8, characterized in that, The anonymous face database retrieval module is used for: Based on the anonymous face database number, the facial recognition algorithm searches through multiple anonymous face databases one by one until the virtual identity information of the person to be verified is obtained.

11. The identity verification device according to claim 8, characterized in that, The anonymous face database retrieval module includes: An anonymous face database integration unit is used to integrate data from multiple anonymous face databases to obtain a virtual ID face database; the virtual ID face database stores multiple facial feature data and virtual identity information for each face; The face recognition unit is used to compare the face feature data of the person to be verified with multiple face feature data in the virtual ID face database through a face recognition algorithm to determine the face whose face comparison similarity exceeds a threshold. The virtual identity information determination unit is used to determine the virtual identity information of a face whose facial similarity exceeds a threshold as the virtual identity information of the person to be verified.

12. The identity verification device according to claim 11, characterized in that, The anonymous face database integration unit is used for: Using facial recognition algorithms, multiple sets of faces with similarity exceeding a threshold were identified from multiple anonymous face databases. The virtual identity information of each group of faces is integrated to obtain the integrated virtual identity information; Based on the face retention quality algorithm, one face feature data is selected from each group of face feature data; The selected facial feature data and the integrated virtual identity information are used as the backup data corresponding to this group of faces; Store the data corresponding to multiple sets of faces into the virtual ID face database; The remaining data after removing the multiple sets of facial feature data and the virtual identity information of the multiple sets of faces from multiple anonymous face databases is determined, and the remaining data is stored in the virtual ID face database.

13. The identity verification device according to claim 8, characterized in that, The second identity information determination module is further configured to: The system verifies the real-name authentication information sent by the person to be verified. Once the verification is successful, the real-name authentication information sent by the person to be verified will be used as the real-name authentication information of the person to be verified.

14. The identity verification device according to claim 13, characterized in that, The second identity information determination module is further configured to: The real-name authentication information and facial feature data of the person to be verified are stored in the real-name facial database.

15. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 7.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, in response to execution by a processor, performs the operation of the identity verification method according to any one of claims 1 to 7.

17. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the identity verification method as described in any one of claims 1 to 7.

Images