An identity recognition method and device

Abstract

The one or more embodiments of the specification provide an identity recognition method and device, wherein the method comprises: grouping Internet of Things devices in advance, dividing Internet of Things devices with a larger correlation degree into the same device group, and storing reference face images corresponding to the Internet of Things devices in the same shared face library, so as to subsequently compare a face image of a user collected in real time by the Internet of Things device with the shared face library of the device group to which the Internet of Things device belongs, and generate a corresponding user identity recognition result according to the comparison result.

Description

[0001] This application is a divisional application of Chinese patent application filed on September 30, 2019, with application number 201910945461.9 and title "An Identity Recognition Method and Device". Technical Field

[0002] This document relates to the field of Internet of Things (IoT) technology, and in particular to an identity recognition method and device. Background Technology

[0003] Currently, with the rapid development of IoT technology, IoT devices are being installed in designated locations to provide users with corresponding business services, thereby bringing convenience to people's daily lives. Simultaneously, with the rapid development of facial recognition technology, it is being applied to IoT devices. Users complete a facial recognition operation using these devices, allowing for facial identification based on the captured facial image, and then executing corresponding control operations based on the user's identity verification result. For example, with facial recognition-based self-service checkout machines or vending machines, payment is automatically executed after the user's facial recognition is successful. Similarly, with facial recognition-based smart access control devices, unlocking is automatically performed after the user's facial recognition is successful.

[0004] Currently, to reduce user steps and achieve user identity verification based solely on facial images, eliminating the need for users to input phone numbers and other information, thus improving user experience, facial images collected by IoT devices are typically compared with pre-stored facial images to determine user permissions. However, with the increasing number of IoT device users, the number of pre-stored facial images is growing exponentially. Using a full comparison of all facial images would inevitably impact facial recognition efficiency. Conversely, if a separate facial database is created for each IoT device to reduce the volume of comparisons, changes in the user's IoT device could result in the inability to find corresponding pre-stored facial images, thus reducing the success rate of facial search.

[0005] Therefore, there is a need to provide an identity recognition method that can improve the efficiency of identity recognition and ensure the success rate of searches. Summary of the Invention

[0006] The purpose of one or more embodiments of this specification is to provide an identity recognition method and apparatus that can improve identity recognition efficiency by reducing face image comparison data, and ensure face search success rate by targeted face image sharing, thereby achieving a balance between identity recognition efficiency and face search success rate.

[0007] To solve the above-mentioned technical problems, one or more embodiments of this specification are implemented as follows:

[0008] This specification provides one or more embodiments of an identity recognition method, including:

[0009] Use IoT devices to collect users' facial images;

[0010] Determine the device group to which the IoT device belongs;

[0011] The face image is compared with the shared face database of the device group to generate a comparison result;

[0012] The user's identity is identified based on the comparison results.

[0013] This specification provides one or more embodiments of an identity recognition device, including:

[0014] The face image acquisition module is used to collect users' face images using IoT devices;

[0015] The device group determination module is used to determine the device group to which the IoT device belongs;

[0016] The face image comparison module is used to compare the face image with the shared face database of the device group and generate a comparison result;

[0017] The user identity recognition module is used to identify the user's identity based on the comparison result.

[0018] This specification provides one or more embodiments of an identity recognition device, including:

[0019] A processor; and a memory arranged to store computer-executable instructions, which, when executed, cause the processor to:

[0020] Use IoT devices to collect users' facial images;

[0021] Determine the device group to which the IoT device belongs;

[0022] The face image is compared with the shared face database of the device group to generate a comparison result;

[0023] The user's identity is identified based on the comparison results.

[0024] This specification provides one or more embodiments of a storage medium for storing computer-executable instructions that, when executed by a processor, implement the following methods:

[0025] Use IoT devices to collect users' facial images;

[0026] Determine the device group to which the IoT device belongs;

[0027] The face image is compared with the shared face database of the device group to generate a comparison result;

[0028] The user's identity is identified based on the comparison results.

[0029] The identity recognition method and apparatus in one or more embodiments of this specification pre-group IoT devices, classifying IoT devices with high correlation into the same device group. Reference face images corresponding to each IoT device in the same device group are stored in a shared face database. This allows for subsequent comparison of the user's face image, collected in real-time by the IoT device, with the shared face database of the device group to which the IoT device belongs. Based on the comparison results, a corresponding user identity recognition result is generated. One or more embodiments of this specification enable a quick search for a matching face image from the shared face database corresponding to the same device group, regardless of which IoT device is used by the same user. This achieves both improved identity recognition efficiency by reducing face image comparison data and ensured a high face search success rate through targeted face image sharing, thus simultaneously balancing identity recognition efficiency and face search success rate. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in one or more embodiments of this specification or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in one or more of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 This is a schematic diagram illustrating an application scenario of the identity recognition system provided in one or more embodiments of this specification;

[0032] Figure 2 A schematic flowchart illustrating a first embodiment of an identity recognition method provided in this specification;

[0033] Figure 3A second flowchart illustrating an identity recognition method provided in one or more embodiments of this specification;

[0034] Figure 4 A schematic diagram illustrating the implementation of the grouping process of IoT devices in one or more embodiments of the identity recognition method provided in this specification;

[0035] Figure 5a A third flowchart illustrating an identity recognition method provided in one or more embodiments of this specification;

[0036] Figure 5b A schematic diagram of a fourth type of identity recognition method provided in one or more embodiments of this specification;

[0037] Figure 6 A fifth flowchart illustrating an identity recognition method provided in one or more embodiments of this specification;

[0038] Figure 7 A schematic diagram of a first type of module composition for an identity recognition device provided in one or more embodiments of this specification;

[0039] Figure 8 A schematic diagram illustrating a second type of module composition for an identity recognition device provided in one or more embodiments of this specification;

[0040] Figure 9 This is a schematic diagram of the structure of an identity recognition device provided in one or more embodiments of this specification. Detailed Implementation

[0041] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of one or more embodiments of this specification, and not all embodiments. Based on the embodiments in one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0042] This specification provides one or more embodiments of an identity recognition method and apparatus. For the same user, regardless of which IoT device in the same device group is used, a matching face image can be quickly searched from the shared face database corresponding to that device group. This achieves both improved identity recognition efficiency by reducing face image comparison data and ensured face search success rate through targeted face image sharing, thereby simultaneously balancing identity recognition efficiency and face search success rate.

[0043] Figure 1This is a schematic diagram illustrating an application scenario of the identity recognition system provided in one or more embodiments of this specification, such as... Figure 1 As shown, the system includes: IoT devices, servers, and users. The server can be a backend server for managing and controlling IoT devices and providing services to users, or it can be a backend server for a website (such as an online shopping website or a payment application). The server can be a standalone server or a server cluster consisting of multiple servers. The IoT device can be a smart terminal device connected to the Internet of Things and providing services to users, such as a facial recognition payment device, a self-service facial recognition shopping machine, a facial recognition parcel locker, a facial recognition ticket machine, or a facial recognition access control device. Taking a self-service facial recognition shopping machine as an example, the specific process of identity recognition is as follows:

[0044] (1) The server pre-groups IoT devices according to the device profile information of IoT devices to obtain multiple device groups, and builds a shared face database for each device group, as well as stores the correspondence between IoT devices, device groups and the shared face database.

[0045] In this process, N IoT devices are pre-grouped into M device groups, where 1 < M < N. Multiple IoT devices within each group correspond to the same shared face database. The similarity of device profile information among the IoT devices represents the probability of them being used by the same group of users. Specifically, the similarity of device profile information among IoT devices is positively correlated with the overlap of users using the IoT devices. The higher the similarity of device profile information among multiple IoT devices, the greater the overlap of users using those devices, and consequently, the higher the correlation between the multiple IoT devices. In other words, multiple IoT devices providing services to the same user group are grouped into the same device group. By predicting the probability of the same user group using different IoT devices, the IoT devices are grouped more accurately, so that the face search range can be precisely limited within a certain range during user identification.

[0046] (2) The Internet of Things (IoT) device collects the user's facial image and sends an identity recognition request to the server. The identity recognition request carries the collected facial image of the user and device identification information. The user refers to the user who uses the IoT device to enjoy a certain business service. The identity recognition request can be a facial recognition request.

[0047] (3) After receiving the identity recognition request, the server determines the device group to which the IoT device belongs based on the device identification information carried in the identity recognition request and the pre-stored correspondence between devices and device groups;

[0048] (4) The server compares the user's face image with the face images in the shared face database of the device group where the IoT device is located, and generates the corresponding comparison results;

[0049] (5) The server generates the user's identity recognition result based on the generated comparison result; wherein the identity recognition result includes: user identity recognition passed or user identity recognition failed;

[0050] In the user identification process, IoT devices are pre-grouped, with multiple highly correlated IoT devices assigned to the same group. All IoT devices within the same group share a common face database. This database contains reference face images of the user faced by all IoT devices in the group. Subsequently, after the server acquires a user's face image from a particular IoT device, it identifies the user based on the face images in the shared face database of that group. This ensures that for the same user, regardless of which IoT device within the same group is used, a matching face image can be quickly found in the corresponding shared face database. This achieves both improved identification efficiency by reducing the amount of face image comparison data and ensured a high success rate for face searches through targeted face image sharing, thus simultaneously balancing identification efficiency and face search success rate.

[0051] Figure 2 This is a schematic diagram of a first embodiment of the identity recognition method provided in this specification. Figure 2 The method in the middle can be derived from Figure 1 The process involves execution by a server, with the server as the execution subject used as an example. For IoT devices, the following points should be considered, and will not be elaborated upon here. Figure 2 As shown, the method includes at least the following steps:

[0052] S202, using an Internet of Things (IoT) device to collect a user's facial image; wherein, the user refers to a user who enjoys a certain business service using an IoT device, and the IoT device refers to a smart terminal device connected to the Internet of Things and providing business services to the user. For example, the IoT device may include any one of the following: facial recognition payment device, self-service facial recognition shopping machine, facial recognition parcel locker, facial recognition ticket machine, and facial recognition access control device.

[0053] Wherein, if the IoT device includes: facial recognition payment device or self-service facial recognition shopping machine, the corresponding business service can be a payment service provided based on facial recognition; if the IoT device includes: facial recognition parcel locker or facial recognition access control device, the corresponding business service can be a device unlocking service provided based on facial recognition; if the IoT device is a facial recognition ticket machine, the corresponding control operation is an automatic ticket printing operation.

[0054] Specifically, IoT devices capture users' facial images through camera devices. After capturing the facial images, they send an identity verification request to the server. This identity verification request carries the user's facial image and device identification information. Correspondingly, the server receives the identity verification request to obtain the user's facial image and the IoT device's identification information.

[0055] S204, determine the device group to which the above-mentioned IoT devices belong; in specific implementation, for the process of device grouping, the device group can be divided according to the device profile information of the IoT devices, wherein the comprehensive similarity of the device profile information of multiple IoT devices in each device group is greater than a preset threshold. Specifically, since the similarity of the device profile information between IoT devices is positively correlated with the overlap of users of IoT devices, the higher the similarity of the device profile information between multiple IoT devices, the greater the overlap of users of the multiple IoT devices, and correspondingly, the higher the degree of association of the multiple IoT devices.

[0056] Specifically, by pre-grouping IoT devices, multiple IoT devices with a high degree of correlation are divided into the same device group, and a shared face database is built for each device group. That is, multiple IoT devices in the same device group use the same shared face database, which contains the face images of all IoT devices in the device group facing the user. After the server obtains the face image of the user collected by a certain IoT device, it first determines the device group to which the IoT device belongs based on the pre-stored correspondence between devices and device groups.

[0057] S206, compare the collected face images with the shared face database of the identified device group, and generate comparison results;

[0058] Specifically, the comparison results include: the similarity between the user's face image and each face image in the shared face database, or the binary classification result of whether the user's face image is consistent with each face image in the shared face database, or whether there is a face image consistent with the user's face image among the face images in the shared face database.

[0059] S208, Based on the above comparison results, identify the user's identity; wherein, the user's identity identification result includes: identity identification passed or identity identification failed;

[0060] Specifically, if the comparison results determine that there is at least one reference face image in the shared face database that matches the user's face image, then the user's identity recognition is deemed successful; otherwise, the user's identity recognition is deemed unsuccessful. The reference face image that matches the user's face image includes: a reference face image whose similarity to the user's face image is greater than a first similarity threshold, or a reference face image that is identical to the user's face image.

[0061] Specifically, in the user identification process, the device group to which the IoT device requesting identification belongs is first determined, and then the user is identified based on the facial images in the shared facial database corresponding to that device group, resulting in the corresponding user identification result.

[0062] In one or more embodiments of this specification, IoT devices are pre-grouped, with highly correlated IoT devices belonging to the same group. Reference facial images corresponding to each IoT device in the same group are stored in a shared facial database. This allows for the subsequent comparison of a user's facial image, collected in real-time by the IoT device, with the shared facial database of that IoT device group. Based on the comparison results, a corresponding user identification result is generated. Thus, for the same user, regardless of which IoT device within the same group is used, a matching facial image can be quickly searched from the shared facial database corresponding to that group. This achieves both improved identification efficiency by reducing facial image comparison data and ensured a high success rate for facial search through targeted facial image sharing, thereby simultaneously balancing identification efficiency and facial search success rate.

[0063] To balance identity recognition efficiency and face search success rate, and to maximize success while minimizing the number of face comparisons, IoT devices are pre-grouped. Multiple IoT devices with high correlation are grouped into the same device group, and multiple IoT devices within the same group use the same shared face database. Based on this, such as... Figure 3 As shown, before collecting the user's facial image using an IoT device in S202, the following steps are also included:

[0064] S210, group multiple IoT devices according to a preset device grouping method to obtain multiple device groups; wherein, the overall similarity of the device profile information of multiple IoT devices in each device group is greater than a preset threshold.

[0065] The aforementioned preset device grouping methods include: manually calibrated device grouping methods or automatic intelligent device grouping methods. In specific implementation, the appropriate device grouping method is selected according to the actual application scenario. For example, when the number of IoT devices exceeds the preset threshold, it is preferable to use the automatic intelligent device grouping method to group multiple IoT devices.

[0066] Specifically, regardless of whether the device grouping method is manually labeled or automatically intelligent, it is based on device profile information. Multiple IoT devices with a high degree of similarity in device profile information are grouped into the same device group. Furthermore, the similarity of device profile information between IoT devices is positively correlated with the overlap of users of the IoT devices. That is, the higher the similarity of device profile information between multiple IoT devices, the greater the overlap of users of the multiple IoT devices, and correspondingly, the higher the degree of association between the multiple IoT devices.

[0067] S212, save the correspondence between each IoT device and device group; specifically, store the device-device group correspondence so that it can be used as a basis for determining the device group to which the IoT device belongs in the future;

[0068] S214, For each device group, construct a shared face database corresponding to that device group; specifically, store the correspondence between the device group and the shared face database;

[0069] Correspondingly, in S204 above, the device group to which the aforementioned IoT device belongs is determined, including:

[0070] S2041, Based on the pre-stored correspondence between devices and device groups, determine the device group to which the above-mentioned IoT device belongs.

[0071] Specifically, in S214 above, for each device group, a shared face database corresponding to that device group is constructed, including:

[0072] Step 1: For each device group, obtain the reference face image of the user that the device group is facing;

[0073] Step 2: Based on the acquired reference face images, construct a shared face database corresponding to the device group.

[0074] Specifically, the system records the identification information of each IoT device within each device group; and establishes a shared face database for each device group, storing reference face images of users faced by each IoT device in the group in this shared face database. Furthermore, it records the correspondence between the identification information of each device group and the identification information in the shared face database, so that the pre-stored reference face images in the shared face database can be used as the basis for comparing real-time user face images during subsequent user identification. The face images stored in the shared face database can be facial feature data used to uniquely identify users, and the face images in the shared face database are deduplicated.

[0075] Specifically, the reference face images in the shared face database of the device group can be determined based on user information from the historical usage records of each IoT device, and / or based on user information predicted by a device usage prediction model. The device usage prediction model can be obtained by training the model parameters of a preset machine learning model based on a training sample set. In other words, the reference face images in the shared face database include at least one of the following: face images of users who have used any IoT device group included in the device group corresponding to the shared face database, and face images of users who will use any IoT device group included in the device group corresponding to the shared face database within a preset time period in the future.

[0076] In a specific embodiment, such as Figure 4 As shown, if the preset device grouping method is followed, it can be seen that the device profile information of IoT devices with device identifiers 0001, 0025, 0048, and 0076 is highly similar. Therefore, IoT devices with device identifiers 0001, 0025, 0048, and 0076 are grouped into the same device group, and the group number can be set to IOT-group1. The device profile information of IoT devices with device identifiers 0002, 0012, 0056, 0120, and 0325 is also highly similar. Therefore, IoT devices with device identifiers 0002, 0012, 0056, 0120, and 0325 are grouped into the same device group, and the group number can be set to IOT-group2. Similarly, N IoT devices are divided into M device groups, that is, the group numbers are IOT-group1, IOT-group2, ..., IOT-groupM, where M is greater than 1 and M is less than N.

[0077] Specifically, after dividing multiple IoT devices into multiple device groups, it is also necessary to establish a shared face database for each device group, and each shared face database has a unique number. For example, the device group numbers are IOT-group1, IOT-group2, ..., IOT-groupM, and the corresponding shared face database numbers are share-data1, share-data2, ..., share-dataM.

[0078] Specifically, regarding the process of grouping IoT devices using manual calibration methods, such as... Figure 5a As shown, in step S210 above, multiple IoT devices are grouped according to a preset device grouping method to obtain multiple device groups, specifically including:

[0079] S2101, Receive a device grouping request for multiple IoT devices, wherein the device grouping request carries the correspondence between device identifiers and grouping numbers obtained based on the device profile information of IoT devices;

[0080] Specifically, relevant personnel group and label IoT devices on the display interface of the management terminal, manually input the correspondence between device identifiers and group numbers based on the device profile information of IoT devices, the management terminal generates a device grouping request carrying the correspondence, and sends the device grouping request to the server;

[0081] In specific implementation, it will still be based on Figure 4 Taking the device grouping results as an example, if the device profile information of IoT devices with device identifiers 0001, 0025, 0048, and 0076 is highly similar, then the device grouping request received by the server carries the correspondence between device identifiers 0001, 0025, 0048, and 0076 and group number IOT-group1. Similarly, the device grouping request also carries the correspondence between other device identifiers and group numbers.

[0082] S2102, Based on the correspondence between the received device identifier and the group number, multiple IoT devices are grouped to obtain multiple device groups;

[0083] Specifically, multiple IoT devices corresponding to the same group number are grouped into the same device group, resulting in M ​​device groups. The group numbers are IOT-group1, IOT-group2, ..., IOT-group M, where M is greater than 1 and less than N. Each of the M device groups contains N IoT devices.

[0084] Specifically, this refers to the process of grouping IoT devices using an automatic intelligent device grouping method, such as... Figure 5bAs shown, in step S210 above, multiple IoT devices are grouped according to a preset device grouping method to obtain multiple device groups, specifically including:

[0085] S2103, Obtain device profile information corresponding to the multiple IoT devices to be grouped, wherein the device profile information includes at least one of the following: device business type information, device geographical location information, device merchant information, and user attribute information;

[0086] The aforementioned user attribute information may include: the user's identity, occupation, age, gender, etc.

[0087] Specifically, when the equipment profile information includes multiple items, the similarity of each item can be weighted and averaged to obtain the overall similarity of the equipment profile information.

[0088] S2104, Based on the device profile information of each IoT device, multiple IoT devices are grouped to obtain multiple device groups;

[0089] Specifically, multiple IoT devices with a high degree of similarity in their device profile information are grouped into the same device group. For the initial device grouping, a preset clustering algorithm is used, based on the existing device profile information of each IoT device, to cluster multiple existing IoT devices, resulting in multiple device clusters. Each device cluster serves as an initial device group. These initial device groups are then used to determine the current multiple device groups. Any existing clustering algorithm can be used to obtain these multiple device clusters; for example, the K-means algorithm, the DBSCAN clustering algorithm, or the BIRCH clustering algorithm can be used.

[0090] Next, as IoT devices are continuously added, the initial device groups are continuously updated, and then the current multiple device groups are continuously updated. Specifically, when grouping devices for the first time, if there are newly added IoT devices, the newly added IoT devices are identified as IoT devices to be grouped, and the newly added IoT devices are grouped. The newly added IoT devices can be assigned to the established initial device groups or to the newly created initial device groups.

[0091] Specifically, regarding the process of automatically grouping IoT devices based on device profile information, if multiple initial device groups have already been established (i.e., this is not the first time device grouping has been performed), in step S2104 above, multiple IoT devices are grouped according to the device profile information of each IoT device to obtain multiple device groups, specifically including:

[0092] Step 1: For each IoT device to be grouped, determine the degree of matching between the IoT device and the multiple established initial device groups based on the device profile information of the IoT device; the higher the degree of matching between the IoT device and the initial device group, the higher the similarity between the device profile information of the IoT device and the IoT devices that have been assigned to the initial device group.

[0093] The aforementioned established initial device groups include: when performing device grouping for the first time, multiple device clusters are obtained by using a preset clustering algorithm based on the device profile information of existing IoT devices, and / or when the matching degree is less than a preset matching degree threshold, new initial device groups are created; subsequently, if a new IoT device is added, the new IoT device is identified as the IoT device to be grouped, so that the new IoT device can be grouped based on the established initial device groups to obtain the updated current multiple device groups;

[0094] Specifically, the device profile information of IoT devices is compared with the multi-dimensional attribute information of the initial device group to calculate the similarity of corresponding dimensions. The matching degree between the IoT device and the initial device group is determined based on the weighted average of the similarity of each dimension. The multi-dimensional attribute information of the device group involves the same information dimensions as the device profile information. For example, if the device profile information includes: device geographic location information, device merchant information, and user attribute information, the corresponding multi-dimensional attribute information of the initial device group includes: device geographic location range, device merchant category, and user attribute information category.

[0095] Step 2: Based on the determined matching degrees, identify the target device group that matches the IoT device to be grouped, and assign the IoT device to the target device group;

[0096] Specifically, it is determined whether at least one of the identified matching degrees is greater than a preset matching degree threshold; if so, the initial device group with the highest matching degree is determined as the target device group; if not, a new initial device group is created based on the device profile information of the IoT devices to be grouped, and the newly created initial device group is determined as the target device group; wherein, the multi-dimensional attribute information of the newly created initial device group is determined based on the category of each dimension information in the device profile information of the IoT devices to be grouped.

[0097] Step 3: Based on multiple initial device groups and target device groups, determine multiple device groups; and identify these multiple device groups as the established multiple initial device groups to be used in the next device grouping.

[0098] Specifically, if the target device group is any one of the multiple established initial device groups, the combination of the other initial device groups (excluding the initial device group with the highest matching degree) and the target device group is determined as multiple device groups; if the target device group is a newly created initial device group, the combination of the multiple established initial device groups and the newly created initial device group is determined as multiple device groups.

[0099] In particular, during the initial device grouping, the device profile information of multiple IoT devices in each device cluster is relatively similar, and the multi-dimensional attribute information of the device cluster is determined based on the device profile information of multiple IoT devices included in the device cluster. Furthermore, during non-initial device grouping, the IoT devices to be grouped are divided into target device groups with a matching degree greater than a preset matching degree threshold based on the device profile information. Therefore, the device profile information of multiple IoT devices in each device group is also relatively similar.

[0100] Specifically, regarding the process of determining the device group to which the IoT device belongs, S2041 above determines the device group to which the IoT device belongs based on the pre-stored device-device group correspondence, including:

[0101] Step 1: Obtain the device identification information of the aforementioned IoT device; specifically, this device identification information can be obtained from the identity verification request sent by the IoT device.

[0102] Step 2: Based on the pre-stored device-device group correspondence, determine the group identifier information corresponding to the obtained device identifier information;

[0103] Step 3: Identify the device group with the determined group identification information as the device group to which the above-mentioned IoT devices belong; specifically, after determining the device group to which the IoT devices belong, the shared face database corresponding to the device group to which the IoT devices belong can be determined.

[0104] Specifically, a first correspondence between the identification information of each IoT device and the identification information of the device group (i.e., group identification information) is pre-stored, as well as a second correspondence between the identification information of a device group and the identification information of the shared face database. Therefore, based on the first correspondence, the second correspondence, and the identification information of the IoT device requesting identity recognition, the device group to which the IoT device belongs and the shared face database corresponding to the device group can be determined.

[0105] For example, still using Figure 4Taking the device grouping results as an example, if the identification information of the IoT device requesting identity recognition is 0056, then the corresponding group number is determined to be IOT-group2, and the corresponding shared library identification information is determined to be share-data2. Therefore, the device group with group number IOT-group2 is determined to be the device group where the IoT device requesting identity recognition belongs, and the face image collected by the IoT device is compared with the reference face image in the shared face library numbered share-data2.

[0106] To further improve the success rate of face search, the relevance between device groups is determined in advance based on the multi-dimensional attribute information of the device groups. This not only identifies the shared face database directly corresponding to the IoT device requesting user identification, but also identifies the indirectly corresponding shared face database. The indirectly corresponding shared face database includes the shared face database directly corresponding to the device group to which the IoT device requesting user identification belongs has a relevance greater than a preset relevance threshold. Therefore, during the face image comparison process, if the face cannot be found in the directly corresponding shared face database, the search continues in the indirectly corresponding shared face database.

[0107] Based on this, the aforementioned determination of the shared face database corresponding to the device group where the IoT device is located specifically includes:

[0108] Based on the aforementioned second correspondence, the first shared face database (i.e., the directly corresponding shared face database) corresponding to the device group where the IoT device is located is determined; and,

[0109] Based on the pre-stored correlation between device groups, determine at least one associated device group whose correlation with the device group to which the IoT device belongs is greater than a preset correlation threshold;

[0110] Based on the above second correspondence, at least one associated device group is identified as the second shared face database (i.e., the indirectly corresponding shared face database);

[0111] The first and second shared face databases mentioned above are identified as the shared face databases corresponding to the device group where the IoT device is located.

[0112] Correspondingly, if the number of shared face databases corresponding to the identified IoT device group is multiple, that is, the shared face database includes: a first shared face database and at least one second shared face database, based on this, for the face image comparison process, in S206 above, the collected face image is compared with the identified shared face database of the device group to generate a comparison result, specifically:

[0113] The collected face images are compared with each reference face image in the first shared face database to generate the first comparison result;

[0114] If the first comparison result indicates that the face search is successful, then stop the face image comparison and continue to execute the above steps S208.

[0115] If the first comparison result indicates that the face search has failed, then in at least one second shared face database, one second shared face database is selected in descending order of relevance. The collected face image is compared with each reference face image in the selected second shared face database to generate a second comparison result.

[0116] If the second comparison result indicates that the face search is successful, then stop the face image comparison and continue to execute the above steps S208.

[0117] If the second comparison result indicates that the face search has failed, then the next second shared face database is selected from at least one second shared face database, until the currently selected second shared face database is the last second shared face database.

[0118] If a user's identity verification is successful, it indicates that the user possesses the corresponding privileges. Therefore, it is necessary to automatically trigger the execution of appropriate control operations to provide the user with the required business services. Based on this, such as... Figure 6 As shown, in step S208 above, after identifying the user's identity based on the comparison results, the following steps are also included:

[0119] S214, determine whether the user's identity recognition result is successful;

[0120] If the judgment result is yes, then in S216, the corresponding control operation is triggered, wherein the control operation includes any one of the following: payment operation, unlocking operation, and ticket printing operation;

[0121] Specifically, the type of control operation is determined according to the type of IoT device. For example, if the IoT device is a facial recognition payment device or a self-service facial recognition shopping machine, the corresponding control operation is automatic payment operation; if it is a facial recognition parcel locker or facial recognition access control device, the corresponding control operation is automatic unlocking operation; and if the IoT device is a facial recognition ticket machine, the corresponding control operation is automatic ticket printing operation.

[0122] If the judgment result is negative, then in step S218, a user identification failure message is sent.

[0123] Specifically, if no matching face image is found in the shared face database, the user's identity verification will be deemed to have failed, and the user will be shown the corresponding prompt information so that they can check the reason for the identity verification failure and apply for identity verification again.

[0124] The identity recognition method in one or more embodiments of this specification pre-groups IoT devices, classifying those with high correlation into the same device group. Reference face images corresponding to each IoT device in the same group are stored in a shared face database. This allows for the comparison of a user's face image, collected in real-time by the IoT device, with the shared face database of the device group to which the IoT device belongs. Based on the comparison results, a corresponding user identity recognition result is generated. One or more embodiments of this specification enable a quick search for a matching face image from the shared face database corresponding to the same device group, regardless of which IoT device is used by the same user. This achieves both improved identity recognition efficiency by reducing face image comparison data and ensured a high face search success rate through targeted face image sharing, thus simultaneously balancing identity recognition efficiency and face search success rate.

[0125] Corresponding to the above Figures 2 to 6 Based on the same technical concept, one or more embodiments of this specification also provide an identity recognition device for the described identity recognition method. Figure 7 This is a schematic diagram of a first module composition of an identity recognition device provided in one or more embodiments of this specification, the device being used to perform... Figures 2 to 6 The described identity recognition method, such as Figure 7 As shown, the device includes:

[0126] The face image acquisition module 701 is used to acquire the user's face image using an Internet of Things (IoT) device;

[0127] Device group determination module 702 is used to determine the device group to which the IoT device belongs;

[0128] The face image comparison module 703 is used to compare the face image with the shared face database of the device group and generate a comparison result;

[0129] User identity recognition module 704 is used to identify the user's identity based on the comparison result.

[0130] In one or more embodiments of this specification, IoT devices are pre-grouped, with highly correlated IoT devices belonging to the same group. Reference facial images corresponding to each IoT device in the same group are stored in a shared facial database. This allows for the subsequent comparison of a user's facial image, collected in real-time by the IoT device, with the shared facial database of that IoT device group. Based on the comparison results, a corresponding user identification result is generated. Thus, for the same user, regardless of which IoT device within the same group is used, a matching facial image can be quickly searched from the shared facial database corresponding to that group. This achieves both improved identification efficiency by reducing facial image comparison data and ensured a high success rate for facial search through targeted facial image sharing, thereby simultaneously balancing identification efficiency and facial search success rate.

[0131] Optionally, such as Figure 8 As shown, the device further includes: a device grouping module 705 and a shared library construction module 706;

[0132] The device grouping module 705 is used to group multiple IoT devices according to a preset device grouping method to obtain multiple device groups; and to save the correspondence between each IoT device and the device group; wherein the overall similarity of the device profile information of multiple IoT devices in each device group is greater than a preset threshold.

[0133] The shared library construction module 706 is used to construct a shared face library corresponding to each of the device groups.

[0134] Correspondingly, the device group determination module 702 is specifically used for:

[0135] Based on the correspondence, the device group to which the IoT device belongs is determined.

[0136] Optionally, the shared library construction module 706 is specifically used for:

[0137] For each of the device groups, obtain a reference face image of the user that the device group is facing;

[0138] Based on the obtained reference face images, a shared face database corresponding to the device group is constructed.

[0139] Optionally, the IoT device includes any one of the following: facial recognition payment device, self-service facial recognition shopping machine, facial recognition parcel locker, facial recognition ticket machine, and facial recognition access control device.

[0140] Optionally, the device grouping module 705 is specifically used for:

[0141] Receive device grouping requests for multiple IoT devices, wherein the device grouping request carries the correspondence between device identifiers and grouping numbers obtained based on the device profile information of IoT devices;

[0142] Based on the correspondence between the device identifier and the group number, the multiple IoT devices are grouped to obtain multiple device groups.

[0143] Optionally, the device grouping module 705 is further specifically used for:

[0144] Obtain device profile information corresponding to multiple IoT devices to be grouped, wherein the device profile information includes at least one of the following: device business type information, device geographical location information, device merchant information, and user attribute information;

[0145] Based on the device profile information of each IoT device, the multiple IoT devices are grouped to obtain multiple device groups.

[0146] Optionally, the device grouping module 705 is further specifically used for:

[0147] For each IoT device to be grouped, the matching degree between the IoT device and the multiple initial device groups already established is determined based on the device profile information of the IoT device.

[0148] Based on the determined matching degrees, target device groups that match the IoT devices are identified, and the IoT devices are assigned to the target device groups.

[0149] Multiple device groups are determined based on the initial device groups and the target device groups.

[0150] Optionally, the device group determination module 702 is further specifically used for:

[0151] Obtain the device identification information of the IoT device;

[0152] Based on the correspondence, determine the group identification information corresponding to the device identification information;

[0153] The device group with the group identification information is identified as the device group to which the IoT device belongs.

[0154] Optionally, the device further includes: a preset operation control module 707, used for:

[0155] If the user's identity verification result is successful, then the corresponding control operation is executed, wherein the control operation includes any one of the following: payment operation, unlocking operation, and ticket printing operation;

[0156] If the user's identity verification result is a failure, then the user will be prompted with an identity verification failure message.

[0157] The identity recognition device in one or more embodiments of this specification pre-groups IoT devices, classifying those with high correlation into the same device group. Reference face images corresponding to each IoT device in the same group are stored in a shared face database. This allows for subsequent comparison of the user's face image, collected in real-time by the IoT device, with the shared face database of the device group. Based on the comparison results, a corresponding user identity recognition result is generated. One or more embodiments of this specification enable the rapid search for a matching face image from the shared face database corresponding to the same device group, regardless of which IoT device is used by the same user. This achieves both improved identity recognition efficiency by reducing face image comparison data and ensured a high face search success rate through targeted face image sharing, thus simultaneously balancing identity recognition efficiency and face search success rate.

[0158] It should be noted that the embodiments of the identity recognition device in this specification and the embodiments of the identity recognition method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding identity recognition method mentioned above, and the repeated parts will not be described again.

[0159] Furthermore, corresponding to the above Figures 2 to 6 Based on the same technical concept, one or more embodiments of this specification also provide an identity recognition device for performing the above-described identity recognition method, such as... Figure 9 As shown.

[0160] Identity verification devices can vary significantly due to differences in configuration and performance. They may include one or more processors 901 and memory 902, with memory 902 storing one or more application programs or data. Memory 902 can be temporary or persistent storage. The application programs stored in memory 902 may include one or more modules (not shown in the figures), each module including a series of computer-executable instructions for the identity verification device. Furthermore, processor 901 may be configured to communicate with memory 902, executing the series of computer-executable instructions stored in memory 902 on the identity verification device. The identity verification device may also include one or more power supplies 903, one or more wired or wireless network interfaces 904, one or more input / output interfaces 905, one or more keyboards 906, etc.

[0161] In one specific embodiment, the identity verification device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the identity verification device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following:

[0162] Use IoT devices to collect users' facial images;

[0163] Determine the device group to which the IoT device belongs;

[0164] The face image is compared with the shared face database of the device group to generate a comparison result;

[0165] The user's identity is identified based on the comparison results.

[0166] In one or more embodiments of this specification, IoT devices are pre-grouped, with highly correlated IoT devices belonging to the same group. Reference facial images corresponding to each IoT device in the same group are stored in a shared facial database. This allows for the subsequent comparison of a user's facial image, collected in real-time by the IoT device, with the shared facial database of that IoT device group. Based on the comparison results, a corresponding user identification result is generated. Thus, for the same user, regardless of which IoT device within the same group is used, a matching facial image can be quickly searched from the shared facial database corresponding to that group. This achieves both improved identification efficiency by reducing facial image comparison data and ensured a high success rate for facial search through targeted facial image sharing, thereby simultaneously balancing identification efficiency and facial search success rate.

[0167] Optionally, the computer-executable instructions, when executed, further include, before acquiring the user's facial image using an IoT device:

[0168] Multiple IoT devices are grouped according to a preset device grouping method to obtain multiple device groups; wherein, the overall similarity of the device profile information of multiple IoT devices in each device group is greater than a preset threshold.

[0169] Store the correspondence between each IoT device and the device group;

[0170] For each of the device groups, a shared face database corresponding to the device group is constructed;

[0171] Correspondingly, determining the device group to which the IoT device belongs includes:

[0172] Based on the correspondence, the device group to which the IoT device belongs is determined.

[0173] Optionally, when the computer-executable instructions are executed, the step of constructing a shared face database corresponding to each of the device groups includes:

[0174] For each of the device groups, obtain a reference face image of the user that the device group is facing;

[0175] Based on the obtained reference face images, a shared face database corresponding to the device group is constructed.

[0176] Optionally, when the computer-executable instructions are executed, the IoT device includes any one of the following: facial recognition payment device, self-service facial recognition shopping machine, facial recognition parcel locker, facial recognition ticket machine, and facial recognition access control device.

[0177] Optionally, when the computer-executable instructions are executed, the step of grouping multiple IoT devices according to a preset device grouping method to obtain multiple device groups includes:

[0178] Receive device grouping requests for multiple IoT devices, wherein the device grouping request carries the correspondence between device identifiers and grouping numbers obtained based on the device profile information of IoT devices;

[0179] Based on the correspondence between the device identifier and the group number, the multiple IoT devices are grouped to obtain multiple device groups.

[0180] Optionally, when the computer-executable instructions are executed, the step of grouping multiple IoT devices according to a preset device grouping method to obtain multiple device groups includes:

[0181] Obtain device profile information corresponding to multiple IoT devices to be grouped, wherein the device profile information includes at least one of the following: device business type information, device geographical location information, device merchant information, and user attribute information;

[0182] Based on the device profile information of each IoT device, the multiple IoT devices are grouped to obtain multiple device groups.

[0183] Optionally, when the computer-executable instructions are executed, the step of grouping the plurality of IoT devices according to the device profile information of each IoT device to obtain a plurality of device groups includes:

[0184] For each IoT device to be grouped, the matching degree between the IoT device and the multiple initial device groups already established is determined based on the device profile information of the IoT device.

[0185] Based on the determined matching degrees, target device groups that match the IoT devices are identified, and the IoT devices are assigned to the target device groups.

[0186] Multiple device groups are determined based on the initial device groups and the target device groups.

[0187] Optionally, when the computer-executable instructions are executed, determining the device group to which the IoT device belongs based on the correspondence includes:

[0188] Obtain the device identification information of the IoT device;

[0189] Based on the correspondence, determine the group identification information corresponding to the device identification information;

[0190] The device group with the group identification information is identified as the device group to which the IoT device belongs.

[0191] Optionally, when the computer-executable instructions are executed, after generating a user identification result for the user based on the comparison result, the instructions further include:

[0192] If the user's identity verification result is successful, then the corresponding control operation is executed, wherein the control operation includes any one of the following: payment operation, unlocking operation, and ticket printing operation;

[0193] If the user's identity verification result is a failure, then the user will be prompted with an identity verification failure message.

[0194] The identity recognition device in one or more embodiments of this specification pre-groups IoT devices, classifying those with high correlation into the same device group. Reference face images corresponding to each IoT device in the same group are stored in a shared face database. This allows for subsequent comparison of user face images collected in real-time by IoT devices with the shared face database of the device group to which the IoT device belongs, and the generation of corresponding user identity recognition results based on the comparison results. One or more embodiments of this specification enable a quick search for a matching face image from the shared face database corresponding to the same device group, regardless of which IoT device is used by the same user. This achieves both improved identity recognition efficiency by reducing face image comparison data and ensured a high face search success rate through targeted face image sharing, thus simultaneously balancing identity recognition efficiency and face search success rate.

[0195] It should be noted that the embodiments of the identity recognition device in this specification and the embodiments of the identity recognition method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding identity recognition method mentioned above, and the repeated parts will not be described again.

[0196] Furthermore, corresponding to the above Figures 2 to 6 Based on the same technical concept, one or more embodiments of this specification also provide a storage medium for storing computer-executable instructions. In one specific embodiment, the storage medium can be a USB flash drive, optical disc, hard disk, etc. When the computer-executable instructions stored in the storage medium are executed by a processor, they can achieve the following process:

[0197] Use IoT devices to collect users' facial images;

[0198] Determine the device group to which the IoT device belongs;

[0199] The face image is compared with the shared face database of the device group to generate a comparison result;

[0200] The user's identity is identified based on the comparison results.

[0201] In one or more embodiments of this specification, IoT devices are pre-grouped, with highly correlated IoT devices belonging to the same group. Reference facial images corresponding to each IoT device in the same group are stored in a shared facial database. This allows for the subsequent comparison of a user's facial image, collected in real-time by the IoT device, with the shared facial database of that IoT device group. Based on the comparison results, a corresponding user identification result is generated. Thus, for the same user, regardless of which IoT device within the same group is used, a matching facial image can be quickly searched from the shared facial database corresponding to that group. This achieves both improved identification efficiency by reducing facial image comparison data and ensured a high success rate for facial search through targeted facial image sharing, thereby simultaneously balancing identification efficiency and facial search success rate.

[0202] Optionally, the computer-executable instructions stored in the storage medium, when executed by a processor before acquiring a user's facial image using an IoT device, further include:

[0203] Multiple IoT devices are grouped according to a preset device grouping method to obtain multiple device groups; wherein, the overall similarity of the device profile information of multiple IoT devices in each device group is greater than a preset threshold.

[0204] Store the correspondence between each IoT device and the device group;

[0205] For each of the device groups, a shared face database corresponding to the device group is constructed;

[0206] Correspondingly, determining the device group to which the IoT device belongs includes:

[0207] Based on the correspondence, the device group to which the IoT device belongs is determined.

[0208] Optionally, when the computer-executable instructions stored in the storage medium are executed by a processor, the step of constructing a shared face database corresponding to each of the device groups includes:

[0209] For each of the device groups, obtain a reference face image of the user that the device group is facing;

[0210] Based on the obtained reference face images, a shared face database corresponding to the device group is constructed.

[0211] Optionally, when the computer-executable instructions stored in the storage medium are executed by a processor, the Internet of Things device includes any one of the following: a facial recognition payment device, a self-service facial recognition shopping machine, a facial recognition parcel locker, a facial recognition ticket machine, and a facial recognition access control device.

[0212] Optionally, when the computer-executable instructions stored in the storage medium are executed by a processor, the grouping of multiple IoT devices according to a preset device grouping method to obtain multiple device groups includes:

[0213] Receive device grouping requests for multiple IoT devices, wherein the device grouping request carries the correspondence between device identifiers and grouping numbers obtained based on the device profile information of IoT devices;

[0214] Based on the correspondence between the device identifier and the group number, the multiple IoT devices are grouped to obtain multiple device groups.

[0215] Optionally, when the computer-executable instructions stored in the storage medium are executed by a processor, the grouping of multiple IoT devices according to a preset device grouping method to obtain multiple device groups includes:

[0216] Obtain device profile information corresponding to multiple IoT devices to be grouped, wherein the device profile information includes at least one of the following: device business type information, device geographical location information, device merchant information, and user attribute information;

[0217] Based on the device profile information of each IoT device, the multiple IoT devices are grouped to obtain multiple device groups.

[0218] Optionally, when the computer-executable instructions stored in the storage medium are executed by a processor, the grouping of the plurality of IoT devices according to the device profile information of each IoT device to obtain a plurality of device groups includes:

[0219] For each IoT device to be grouped, the matching degree between the IoT device and the multiple initial device groups already established is determined based on the device profile information of the IoT device.

[0220] Based on the determined matching degrees, target device groups that match the IoT devices are identified, and the IoT devices are assigned to the target device groups.

[0221] Multiple device groups are determined based on the initial device groups and the target device groups.

[0222] Optionally, when the computer-executable instructions stored in the storage medium are executed by a processor, determining the device group to which the IoT device belongs based on the correspondence includes:

[0223] Obtain the device identification information of the IoT device;

[0224] Based on the correspondence, determine the group identification information corresponding to the device identification information;

[0225] The device group with the group identification information is identified as the device group to which the IoT device belongs.

[0226] Optionally, when the computer-executable instructions stored in the storage medium are executed by a processor, after generating a user identification result for the user based on the comparison result, the method further includes:

[0227] If the user's identity verification result is successful, then the corresponding control operation is executed, wherein the control operation includes any one of the following: payment operation, unlocking operation, and ticket printing operation;

[0228] If the user's identity verification result is a failure, then the user will be prompted with an identity verification failure message.

[0229] When the computer-executable instructions stored in the storage medium in one or more embodiments of this specification are executed by the processor, the IoT devices are pre-grouped, with IoT devices of high correlation being grouped into the same device group. Reference face images corresponding to each IoT device in the same device group are stored in the same shared face database. This allows for subsequent comparison of the user's face image, which is collected in real-time using the IoT device, with the shared face database of the device group to which the IoT device belongs. Based on the comparison results, a corresponding user identification result is generated. One or more embodiments of this specification enable that, for the same user, regardless of which IoT device in the same device group is used, a matching face image can be quickly searched from the shared face database corresponding to that device group. This achieves both improved identification efficiency by reducing face image comparison data and ensured a high face search success rate through targeted face image sharing, thus simultaneously achieving both identification efficiency and face search success rate.

[0230] It should be noted that the embodiments concerning the storage medium in this specification and the embodiments concerning the identity recognition method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding identity recognition method described above, and the repeated parts will not be described again.

[0231] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0232] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using a hardware physical module. For example, a Programmable Logic Device (PLD) (e.g., a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program a digital system themselves to "integrate" it onto a PLD, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0233] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0234] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0235] For ease of description, the above devices are described in terms of function, divided into various units. Of course, when implementing one or more of these specifications, the functions of each unit can be implemented in one or more software and / or hardware.

[0236] Those skilled in the art will understand that one or more embodiments of this specification can be provided as a method, system, or computer program product. Therefore, one or more of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more of this specification may 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.

[0237] This specification, one or more, is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to one or more embodiments of this specification. 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, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0238] 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.

[0239] 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.

[0240] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0241] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0242] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0243] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0244] Those skilled in the art will understand that one or more embodiments of this specification can be provided as a method, system, or computer program product. Therefore, one or more of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more of this specification may 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.

[0245] This specification, one or more, can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification, one or more, can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0246] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. 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 in the method embodiments.

[0247] The above description is merely an embodiment of one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of the claims of this specification.

Claims

1. An identity recognition method, comprising: Multiple IoT devices are grouped according to a preset device grouping method to obtain multiple device groups; Store the correspondence between each IoT device and the device group; For each device group, a shared face database is constructed corresponding to the device group, wherein multiple IoT devices in the same device group use the same shared face database; the reference face images in the shared face database include at least one of the following: face images of users who have used any IoT device group included in the device group corresponding to the shared face database, and face images of users who will use any IoT device group included in the device group corresponding to the shared face database within a preset time period in the future; Use IoT devices to collect users' facial images; Based on the correspondence, the target device group to which the IoT device belongs is determined, and the similarity of device profile information among multiple IoT devices in the target device group is positively correlated with the overlap of users of the IoT devices. The face image is compared with the shared face database directly corresponding to the target device group. If the face image fails to match in the directly corresponding shared face database, the face image is compared with the shared face database indirectly corresponding to the target device group to generate a comparison result. The indirectly corresponding shared face database includes: the shared face database directly corresponding to the associated device group whose correlation with the target device group is greater than a preset correlation threshold. The user's identity is identified based on the comparison results.

2. The method according to claim 1, wherein, The overall similarity of the device profile information of multiple IoT devices in each device group is greater than a preset threshold.

3. The method according to claim 1, wherein, The step of constructing a shared face database corresponding to each of the device groups includes: For each of the device groups, obtain a reference face image of the user that the device group is facing; Based on the obtained reference face images, a shared face database corresponding to the device group is constructed.

4. The method according to claim 1, wherein, The IoT devices include any one of the following: facial recognition payment devices, self-service facial recognition shopping machines, facial recognition parcel lockers, facial recognition ticket machines, and facial recognition access control devices.

5. The method according to claim 1, wherein, The process of grouping multiple IoT devices according to a preset device grouping method to obtain multiple device groups includes: Receive device grouping requests for multiple IoT devices, wherein the device grouping request carries the correspondence between device identifiers and grouping numbers obtained based on the device profile information of IoT devices; Based on the correspondence between the device identifier and the group number, the multiple IoT devices are grouped to obtain multiple device groups.

6. The method according to claim 1, wherein, The process of grouping multiple IoT devices according to a preset device grouping method to obtain multiple device groups includes: Obtain device profile information corresponding to multiple IoT devices to be grouped, wherein the device profile information includes at least one of the following: device business type information, device geographical location information, device merchant information, and user attribute information; Based on the device profile information of each IoT device, the multiple IoT devices are grouped to obtain multiple device groups.

7. The method according to claim 6, wherein, The step involves grouping the multiple IoT devices according to their device profile information to obtain multiple device groups, including: For each IoT device to be grouped, the matching degree between the IoT device and the multiple initial device groups already established is determined based on the device profile information of the IoT device. Based on the determined matching degrees, target device groups that match the IoT devices are identified, and the IoT devices are assigned to the target device groups. Multiple device groups are determined based on the initial device groups and the target device groups.

8. The method according to claim 1, wherein, The step of determining the target device group to which the IoT device belongs based on the correspondence includes: Obtain the device identification information of the IoT device; Based on the correspondence, determine the group identification information corresponding to the device identification information; The device group with the group identification information is identified as the target device group to which the IoT device belongs.

9. The method according to any one of claims 1 to 8, wherein, After identifying the user's identity based on the comparison results, the process further includes: If the user's identity verification result is successful, then the corresponding control operation is executed, wherein the control operation includes any one of the following: payment operation, unlocking operation, and ticket printing operation; If the user's identity verification result is a failure, then the user will be prompted with an identity verification failure message.

10. An identity recognition device, comprising: A construction module is used to group multiple IoT devices according to a preset device grouping method to obtain multiple device groups, store the correspondence between each IoT device and the device group, and construct a shared face database for each device group. Multiple IoT devices in the same device group use the same shared face database. The reference face images in the shared face database include at least one of the following: face images of users who have already used any IoT device group included in the device group corresponding to the shared face database, and face images of users who will use any IoT device group included in the device group corresponding to the shared face database within a preset future time period. The face image acquisition module is used to collect users' face images using IoT devices; The device group determination module is used to determine the target device group to which the IoT device belongs based on the correspondence relationship. The similarity of device profile information among multiple IoT devices in the target device group is positively correlated with the overlap of users of the IoT devices. The face image comparison module is used to compare the face image with the shared face database directly corresponding to the target device group. If the face image fails to match in the directly corresponding shared face database, the face image is compared with the shared face database indirectly corresponding to the target device group to generate a comparison result. The indirectly corresponding shared face database includes: the shared face database directly corresponding to the associated device group whose correlation with the target device group is greater than a preset correlation threshold. The user identity recognition module is used to identify the user's identity based on the comparison result.

11. An identity recognition device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to: Multiple IoT devices are grouped according to a preset device grouping method to obtain multiple device groups; Store the correspondence between each IoT device and the device group; For each device group, a shared face database is constructed corresponding to the device group, wherein multiple IoT devices in the same device group use the same shared face database; the reference face images in the shared face database include at least one of the following: face images of users who have used any IoT device group included in the device group corresponding to the shared face database, and face images of users who will use any IoT device group included in the device group corresponding to the shared face database within a preset time period in the future; Use IoT devices to collect users' facial images; Based on the correspondence, the target device group to which the IoT device belongs is determined; The face image is compared with the shared face database directly corresponding to the target device group. If the face image fails to match in the directly corresponding shared face database, the face image is compared with the shared face database indirectly corresponding to the target device group to generate a comparison result. The indirectly corresponding shared face database includes: the shared face database directly corresponding to the associated device group whose correlation with the target device group is greater than a preset correlation threshold. The user's identity is identified based on the comparison results.

12. A storage medium for storing computer-executable instructions, which, when executed by a processor, implement the following methods: Multiple IoT devices are grouped according to a preset device grouping method to obtain multiple device groups; Store the correspondence between each IoT device and the device group; For each of the device groups, a shared face database corresponding to the device group is constructed, wherein, Multiple IoT devices in the same device group use the same shared face database; The reference face images in the shared face database include at least one of the following: face images of users who have already used any IoT device group included in the device group corresponding to the shared face database, and face images of users who will use any IoT device group included in the device group corresponding to the shared face database within a preset time period in the future. Use IoT devices to collect users' facial images; Based on the correspondence, the target device group to which the IoT device belongs is determined; The face image is compared with the shared face database directly corresponding to the target device group. If the face image fails to match in the directly corresponding shared face database, the face image is compared with the shared face database indirectly corresponding to the target device group to generate a comparison result. The indirectly corresponding shared face database includes: the shared face database directly corresponding to the associated device group whose correlation with the target device group is greater than a preset correlation threshold. The user's identity is identified based on the comparison results.

Images