HK40053647B - Method and apparatus for recognizing human faces, computer readable medium and electronic device - Google Patents

Description

Facial recognition methods, devices, computer-readable media and electronic devices

Technical Field

This application relates to the field of blockchain technology, and more specifically, to a face recognition method, device, computer-readable medium, and electronic device.

Background Technology

Currently, facial recognition is mainly performed offline by storing the facial feature database locally on the terminal. However, facial feature database files are often very large. Therefore, storing the facial feature database locally on the terminal not only consumes a lot of network traffic, but also occupies a lot of local storage resources, resulting in a waste of storage resources.

Summary of the Invention

Embodiments of this application provide a face recognition method, apparatus, computer-readable medium, and electronic device, which can at least to some extent reduce the network traffic and storage resources consumed by storing the face feature database locally on the terminal.

Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

According to one aspect of the embodiments of this application, a face recognition method is provided. The method includes: using a terminal device connected to a local area network (LAN) for face recognition as a blockchain node, establishing a blockchain network for data communication within the LAN, the blockchain network including a target node for generating and storing target blocks and a query node for searching the target blocks; when the target node is connected to the Internet, downloading face-related data for offline storage from a server through the target node, and generating a target block containing the face-related data on the target node; storing the target block on the target node, and broadcasting on-chain information of the target block on the blockchain network through the target node, the on-chain information indicating the link relationship between the target block and other blocks on the blockchain; when the query node receives the on-chain information broadcast in the blockchain network, storing a block record generated based on the on-chain information on the query node, the block record including a query path for searching the target block; and in response to a face recognition request, traversing each block in the blockchain according to the block record stored on the query node to obtain a face recognition result.

According to one aspect of the embodiments of this application, a face recognition device is provided. The device includes: a building unit, configured to build a blockchain network for data communication within the local area network, using a terminal device for face recognition connected to a local area network as a blockchain node; the blockchain network includes target nodes for generating and storing target blocks and query nodes for searching the target blocks; a downloading and generating unit, configured to download face-related data for offline storage from a server through the target node when the target node is connected to the Internet, and generate a target block containing the face-related data on the target node; and a saving and broadcasting unit, configured to... The target block is stored on the target node, and the target node broadcasts the on-chain information of the target block on the blockchain network. The on-chain information is used to indicate the link relationship between the target block and other blocks on the blockchain. A receiving and storing unit is used to store a block record generated based on the on-chain information on the query node when the query node receives the on-chain information broadcast on the blockchain network. The block record includes a query path for finding the target block. A traversal unit is used to traverse each block in the blockchain to obtain the face recognition result in response to a face recognition request, based on the block record stored on the query node.

In some embodiments of this application, based on the foregoing scheme, the download and generation unit is configured to: obtain the identification information of the target node and the first hash value in the latest block added to the blockchain; determine the second hash value based on the identification information of the target node, the first hash value and the face-related data; and generate a block based on the identification information of the target node, the face-related data, the first hash value and the second hash value.

In some embodiments of this application, based on the foregoing scheme, the download and generation unit is configured to: encrypt the face-related data to obtain encrypted face-related data; and package the target node's identification information, the encrypted face-related data, the first hash value, and the second hash value into a block.

In some embodiments of this application, based on the foregoing scheme, the on-chain information includes a hash value and the identification information of the target node, and the receiving and saving unit is configured to: when the query node receives the on-chain information broadcast in the blockchain network, save the hash value and the identification information of the target node contained in the on-chain information as a block record to the query node.

In some embodiments of this application, based on the aforementioned scheme, the traversal unit is configured to: obtain the face data in the face recognition request; determine the query path of each block in the blockchain according to the hash value and node identification information in the block record; and send the face data to each node in the blockchain network in sequence according to the query path, so that each node can retrieve the face data in the stored blocks and obtain the face recognition result returned by each node.

In some embodiments of this application, based on the foregoing scheme, the download and generation unit is further configured to: monitor the working status of the target node through the query node; when the query node detects that the target node in the blockchain network is offline, download the face-related data in the target block generated by the target node from the server, and generate a target backup block containing the face-related data in the target block on the query node; save the target backup block on the query node, and broadcast the associated node information of the target backup block on the blockchain network through the query node, so that other nodes in the blockchain network save the content in the associated node information to the block record, wherein the associated node information includes the identification information of the query node and the identification information of the target node.

In some embodiments of this application, based on the foregoing scheme, the download and generation unit is configured to: receive work status information periodically sent by the target node in the blockchain network; and determine that the target node is offline if it has not periodically received work status information from the target node.

In some embodiments of this application, based on the foregoing scheme, after the associated node information of the target backup block is broadcast on the blockchain network through the query node, the download and generation unit is further configured to: determine that the target node has recovered to the online state based on the working status information received periodically from the target node, and clear the stored target backup block.

In some embodiments of this application, based on the aforementioned scheme, each node in the blockchain network is able to collect facial data.

In some embodiments of this application, based on the aforementioned scheme, each node in the blockchain network is used for facial recognition payment, and each node in the blockchain network corresponds to the same merchant identifier.

In some embodiments of this application, based on the aforementioned scheme, after responding to a face recognition request and traversing each block in the blockchain according to the block records stored on the query node to obtain the face recognition result, the traversal unit is further configured to: if face-related data matching the face data in the face recognition request is found, then a payment instruction is sent to the server through the query node, and the server performs a payment operation on the payment account corresponding to the face-related data; if no face-related data matching the face data in the face recognition request is found, then the face data is uploaded to the server through the query node, and the server performs a payment operation on the payment account after determining the payment account matching the face data.

In some embodiments of this application, based on the foregoing scheme, the traversal unit is configured to: if face-related data matching the face data in the face recognition request is retrieved, then when the query node is connected to the network, send a payment instruction to the server, and the server performs a payment operation on the payment account corresponding to the face-related data.

According to one aspect of the embodiments of this application, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the face recognition method as described in the above embodiments.

According to one aspect of the embodiments of this application, an electronic device is provided, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the face recognition method as described in the above embodiments.

In some embodiments of this application, a blockchain network is constructed using terminal devices as blockchain nodes. Each terminal device in the blockchain network generates a block based on the face-related data after acquiring it and uploads the block to the blockchain. Simultaneously, each block is stored on the terminal device that generated it, and offline face recognition is achieved by searching within the blockchain. Therefore, the face-related data is downloaded locally from the server, eliminating the need to upload the face data for face matching, thus improving the efficiency of face recognition. Furthermore, the face-related data is distributed across the blockchain network, with each node storing only a portion of the data. This not only reduces network traffic consumed by storing face-related data locally on the terminal but also significantly reduces storage resources. Moreover, since the face-related data is stored on the blockchain, data security is guaranteed, improving the security of user privacy data.

It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application.

Attached Figure Description

The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

Figure 1 illustrates a schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of this application can be applied;

Figure 2 shows a flowchart of a face recognition method according to an embodiment of this application;

Figure 3 illustrates a schematic diagram of the application architecture of a face recognition method according to an embodiment of this application;

Figure 4 shows a schematic diagram of the status monitoring interface of a node in a blockchain network downloading a face feature database from a server according to an embodiment of this application;

Figure 5 shows a flowchart of the block generation process according to an embodiment of this application;

Figure 6 shows a flowchart detailing step 530 in Figure 5 according to an embodiment of this application;

Figure 7 illustrates a flowchart of blockchain retrieval according to an embodiment of this application;

Figure 8 shows a flowchart of the processing procedure when the target node in the blockchain network is offline, according to an embodiment of this application.

Figure 9 shows a flowchart of the steps following step 250 in Figure 2 according to an embodiment of this application;

Figure 10 shows a block diagram of a face recognition device according to an embodiment of this application;

Figure 11 shows a schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application.

Detailed Implementation

Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and/or processor devices and/or microcontroller devices.

The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations/steps, nor do they necessarily have to be performed in the described order. For example, some operations/steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

Currently, many scenarios require offline facial recognition. As mentioned earlier, in related technologies, the main solution for implementing offline facial recognition is to store the offline facial feature database locally on the terminal. However, the file size of an offline facial feature database is often several hundred megabytes, which consumes a lot of network bandwidth and occupies a lot of local storage resources, resulting in a waste of storage resources.

Therefore, this application first provides a face recognition method. Face recognition is a biometric technology that identifies individuals based on their facial features. This technology involves using a camera or webcam to capture images or video streams containing faces, automatically detecting and tracking faces within the images, and then performing face recognition on the detected faces. It is also commonly referred to as portrait recognition or facial recognition. The face recognition method in this application reduces the network traffic and storage resources consumed in storing face-related data by distributing face-related data across various nodes in a blockchain network and performing face recognition based on this data.

Figure 1 illustrates a schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of this application can be applied. As shown in Figure 1, the system architecture may include a blockchain network 100, a network 110, and a cloud server 120. The blockchain network 100 includes at least a first node 101, a second node 102, a third node 103, a fourth node 104, and a fifth node 105. Each node in the blockchain network 100 is a facial recognition Internet of Things (IoT) device. The facial recognition IoT device can be installed in a merchant's store. The facial recognition IoT device has a camera that can collect facial data. The facial recognition IoT device is used to make facial recognition payments when consumers pay, and it can also make offline payments. Any two nodes in the blockchain network 100 can communicate with each other, and each node in the blockchain network 100 can also communicate with the cloud server 120 through the network 110. The process of implementing face recognition using the system architecture shown in Figure 1 is as follows: First, each node in the blockchain network 100 downloads data from the cloud server 120 through network 110 to obtain face-related data; then, each node generates a block based on the obtained face-related data and adds the block to the blockchain, thereby establishing the blockchain, which is then stored on multiple nodes in the blockchain network; finally, when a node in the blockchain network 100 receives a face retrieval request, that is, when a face-scanning IoT device needs to make face-scanning payments, it completes face recognition by retrieving face-related data from the blockchain in each node.

It should be noted that Figure 1 shows only one embodiment of this application. Although the face recognition in the embodiment of Figure 1 is used in a face-scanning payment scenario, the face recognition method provided by this application can also be applied to access control and other scenarios requiring face recognition. Although in the embodiment of Figure 1, the face-related data is downloaded by each node from a cloud server, in other embodiments of this application, the face-related data can be downloaded by the nodes from a server cluster or database cluster including multiple servers. Although the blockchain network in the embodiment of Figure 1 includes only five nodes, in other embodiments or specific applications, the blockchain network may include more or fewer nodes. This application does not limit the scope of protection of this application in any way.

Furthermore, it is easy to understand that the face recognition method provided in this application embodiment is executed by a face-scanning device, and correspondingly, the face recognition device is generally a face-scanning device. However, in other embodiments of this application, the server may also have similar functions to the face-scanning device, thereby executing the face recognition scheme provided in this application embodiment.

The face recognition method provided in this application is based on blockchain.

Blockchain is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and cryptographic algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying platform, a platform product service layer, and an application service layer.

The underlying blockchain platform can include processing modules such as user management, basic services, smart contracts, and operational monitoring. The user management module is responsible for managing the identity information of all blockchain participants, including maintaining public and private key generation (account management), key management, and maintaining the correspondence between user real identities and blockchain addresses (access management). Furthermore, under authorization, it monitors and audits transactions of certain real identities and provides risk control rule configuration (risk control audit). The basic services module is deployed on all blockchain node devices to verify the validity of business requests. After consensus is reached on valid requests, they are recorded in storage. For a new business request, the basic services first perform interface adaptation parsing and authentication (interface adaptation), and then encrypt the business information through a consensus algorithm (consensus management). After encryption, the data is transmitted completely and consistently to the shared ledger (network communication) and recorded and stored. The smart contract module is responsible for contract registration, issuance, triggering, and execution. Developers can define contract logic using a programming language and publish it to the blockchain (contract registration). According to the contract terms, the key or other events are invoked to trigger execution and complete the contract logic. It also provides functions for contract upgrades and cancellations. The operation monitoring module is mainly responsible for deployment, configuration modification, contract settings, cloud adaptation, and real-time status visualization output during product release, such as alarms, monitoring network conditions, and monitoring the health status of node devices.

The platform's product service layer provides the basic capabilities and implementation frameworks for typical applications. Developers can leverage these basic capabilities, along with the specific characteristics of their business needs, to implement blockchain-based business logic. The application service layer provides blockchain-based application services to business stakeholders.

The implementation details of the technical solutions in the embodiments of this application are described in detail below:

Figure 2 shows a flowchart of a face recognition method according to an embodiment of this application. This face recognition method can be executed by a terminal device with computing and communication functions. These terminal devices can also collect facial data through a camera, such as the face-scanning IoT device shown in Figure 1, specifically the smart payment hardware devices used by WeChat Pay, such as the Frog Generation 1 and Frog Generation 2. Specifically, in the embodiment of Figure 2, the executing entity can be a node in a blockchain network existing in the form of a terminal device. Any node in the blockchain network can execute the face recognition method of this application embodiment. Referring to Figure 2, the face recognition method includes at least the following steps:

In step 210, a blockchain network for data communication within the local area network is established by using a terminal device connected to the local area network for face recognition as a blockchain node.

A blockchain network includes target nodes that generate and store target blocks, and query nodes that are used to find target blocks.

The query node here refers to a node in the blockchain network other than the target node; a blockchain network can include multiple query nodes. Although this step distinguishes between target nodes and query nodes in the blockchain network, this is merely to make the scheme of this application easier to understand. In reality, any node in the blockchain network can generate and store blocks, and any node in the blockchain network can also search for blocks.

In a blockchain network, any two nodes can communicate with each other. Each node can have a client installed, and nodes can communicate with each other using the client. A local area network covers a relatively small area, such as a school, a shopping mall, or even a shop.

In step 220, if the target node is connected to the Internet, the target node downloads face-related data for offline storage from the server and generates a target block containing the face-related data on the target node.

Face-related data refers to any data that can be used to identify the identity information corresponding to a face. For example, face-related data can be a facial photograph, a single image frame from a facial video stream, or even a set of image frames from a facial video stream—data that can completely record facial information. Furthermore, face-related data can also be facial feature data extracted from the aforementioned facial photographs, single image frames, or sets of image frames that can completely record facial information. Here, facial feature data refers to feature data that can describe the shape of facial features and the distance characteristics between them, and is helpful for face classification.

When the target node connects to the internet, it downloads face-related data from the server. A block is a data structure that includes face-related data and may also include other information. Any node in the blockchain network can download face-related data from the server for offline storage.

The server can be any terminal or device that can be used to store data, such as a server or a cluster of servers. In cloud technology scenarios, the server can also be a cloud server located in the cloud.

The target node can download face-related data from the server at various times according to various methods and rules.

For example, face-related data can be downloaded from the server when the target node performs system initialization.

Figure 3 illustrates a schematic diagram of the application architecture of a face recognition method according to an embodiment of this application. When the solution of this embodiment is applied to Figure 3, it is actually applied to a scenario of using a face-scanning IoT device for face-scanning payment. Referring to Figure 3, the three boxes arranged from top to bottom represent the three parts of the application architecture. The middle box and the bottom box represent two parts of the private blockchain terminal network, which in this embodiment represents a private blockchain network established using terminal devices. The content in the middle box describes how face-related data is stored on the blockchain within the blockchain network, while the content in the bottom box describes the specific process of face-scanning payment based on the private blockchain terminal network. As shown in the content of the bottom box in Figure 3, after face scanning begins, feature retrieval is performed at each node in the blockchain network to achieve face recognition.

Referring to Figure 3, the backend in the upper box is the server. It stores face-related data in the form of a face feature database, which is face feature data. The face feature database is a file storing batches of face feature data. Each face feature database is 5MB in size, and each database stores different face feature data, allowing for batch and organized storage of face feature data. Nodes in the blockchain network download face-related data in units of face feature databases. Specifically, as shown in the middle box of Figure 3, the blockchain network includes three nodes: Node 1, Node 2, and Node 3. Each node stores several blocks, and each block contains three feature databases. Each feature database is downloaded from the backend (server) by the node that stores the block containing that feature database.

In this embodiment of the application, the face-related data is face feature data, and the file size of the face feature library storing the face feature data is 5M. This face feature library can store hundreds of thousands of face feature data. It can be seen that for two files of the same size, the number of face feature data that the file can store is far greater than the number of face photos. Therefore, the use of a face feature library to store face feature data in this embodiment of the application can greatly reduce the storage resources consumed by face recognition.

Figure 4 illustrates a schematic diagram of the status monitoring interface of a node in a blockchain network downloading a facial feature database from a server, according to an embodiment of this application. Referring to Figure 4, this status monitoring interface can be displayed on the node in the blockchain network or on the server. In Figure 4, the large cylinder at the top represents the download status of all facial feature databases on the server. The relative size of the dark portion within this large cylinder represents the ratio of the number of downloaded facial feature databases to the total number of facial feature databases. The interface also displays specific numbers: the total number of facial feature databases is 200, and 120 have been downloaded. The smaller cylinder below the large cylinder represents the storage capacity status of each node in the blockchain network. The relative size of the dark portion within this smaller cylinder represents the ratio of the occupied capacity of a node to the total capacity. The interface also displays specific capacity values for each node; for example, the total capacity of each node is 1GB, with node 1 having 590MB of available capacity, node 2 having 390MB, and node 3 having 230MB. Furthermore, the connection line between node 1 and the server is a dashed line, while the connections between nodes 2 and 3 and the server are solid lines. This indicates that, currently, node 1 is not downloading data from the server, while nodes 2 and 3 are both downloading data from the server. Therefore, the status monitoring interface shown in Figure 4 provides a clear understanding of the overall system status in the blockchain network as nodes download the facial feature database from the server.

The face-related data stored on the server can be restricted from being downloaded by each node in the blockchain network, preventing nodes from downloading face-related data arbitrarily.

In one embodiment of this application, downloading face-related data for offline storage from the server via the target node includes: downloading face-related data corresponding to the geographic identification information of the target node from the server via the target node.

Specifically, for example, the administrator of the target node can send a download request to the server by operating the target node as a terminal device. This download request carries the geographic identification information of the target node. The server stores the geographic identification information and the corresponding facial data. After receiving the download request from the target node, the server obtains the geographic identification information of the target node from the download request. Based on the geographic identification information of the target node, the server returns a download page to the target node. This target node contains a download entry for the facial data corresponding to the geographic identification information of the target node. The administrator of the target node can download the facial data corresponding to the geographic identification information of the target node through this download entry.

For example, in a payment scenario, corresponding regional identification information can be set for each area within a region. When a merchant purchases a facial recognition IoT device, the corresponding facial recognition IoT device can be provided based on the address provided by the merchant. These facial recognition IoT devices are configured with the regional identification information corresponding to the area where the merchant's address belongs. Therefore, the download requests sent by these facial recognition IoT devices to the server can carry the regional identification information of each node.

For example, taking the payment scenario as an example again, the facial recognition method provided in this application embodiment can be applied to a payment system. The payment system includes a server. When registering a payment account with the payment system's server, each user submits information such as address, registered address, telephone number, and raw facial data. When using the payment system, users can also provide location information. In this way, the server can use the raw facial data to generate facial-related data. At the same time, the server will also determine the corresponding geographic identification information based on the address, registered address, telephone number, and location information provided by the user. Then, the server can associate the facial-related data with the geographic identification information.

Therefore, in the above embodiments, the facial recognition IoT device only needs to download the face-related data corresponding to the regional identification information. Thus, less face-related data needs to be downloaded, thereby saving network and storage resources. At the same time, the address, registered address, telephone number, location information, and other information of a payment account may correspond to different regional identification information. Therefore, in this embodiment, it is also possible to associate one face-related data with multiple regional identification information. This improves the storage redundancy of face-related data, enabling the same user to make offline facial recognition payments on facial recognition IoT devices in different regions, thereby improving the user experience.

In one embodiment of this application, downloading face-related data corresponding to the geographic identification information of the target node from the server by the target node includes: receiving broadcast information sent by the server to nodes in the blockchain network by the target node, determining that the server has added face-related data corresponding to the geographic identification information of the target node, and downloading face-related data corresponding to the geographic identification information of the target node from the server, wherein the broadcast information includes the geographic identification information of the target node.

In this embodiment, once the server updates the face-related data, the corresponding terminal device can receive the broadcast information sent by the server, and then these terminal devices can download the latest updated face-related data from the server in a timely manner, ensuring the reliability of face recognition.

In one embodiment of this application, downloading face-related data from the server for offline storage is performed periodically.

In one embodiment of this application, before downloading face-related data for offline storage from the server via the target node, the method further includes: determining the frequency of face recognition requests received by the target node every hour of every day within a predetermined number of days prior to the current day; for each day within the predetermined number of days, determining the hour with the lowest frequency of face recognition requests received that day as the low-frequency period for that day; determining the target low-frequency period for the current day based on the low-frequency periods for each day; and downloading face-related data for offline storage from the server via the target node, including: downloading face-related data for offline storage from the server via the target node during the target low-frequency period of the current day.

In one embodiment of this application, determining the target low-frequency period of a day based on the low-frequency periods of each day includes: determining the number of days corresponding to each low-frequency period; and taking the low-frequency period with the largest number of days as the target low-frequency period of the day.

For example, if the reservation period is 7 days, then if the number of days with low frequency period from 21:00 to 22:00 is 1, the number of days with low frequency period from 22:00 to 23:00 is 2, and the number of days with low frequency period from 23:00 to 24:00 is 4, then the determined target low frequency period is 23:00 to 24:00. In other words, the face-related data will be downloaded from the server within 23:00 to 24:00 on the same day.

When a terminal device receives a high frequency of face recognition requests within an hour, it indicates a high load on the device. Downloading face-related data from the server at this time would further increase the load and potentially impact the device's performance. In this embodiment, by predicting the low-frequency periods of the day and downloading face-related data during these periods, data is downloaded from the server when the terminal device's load is low, thus avoiding impacting its performance. Furthermore, the low-frequency periods are determined based on the frequency of face recognition requests received in each hour within a predetermined number of days prior to the current day, improving the accuracy of the predicted low-frequency periods.

In one embodiment of this application, after each node in the blockchain network sends a download request to the server, it sends the download requests to the request message queue in the order of the request time. Each node downloads face-related data from the server in the order in which the downloaded requests are sorted in the request message queue.

In this embodiment, download requests from each node are stored in a request message queue in the order they are sent, and the server processes each download request sequentially. The message queue is used to smooth out the peaks of download requests, preventing the server from crashing due to a large number of download requests received in a short period of time, thus improving the availability of the system.

In one embodiment of this application, the target node is the terminal device in the blockchain network that has been in an idle state for the longest period of time. The idle state is the state in which the terminal device has not downloaded face-related data and has not generated a block.

In other words, the target node is the terminal device with the longest idle time among all terminal devices. Idle time is the time between the last time a block was generated and the current time. The idle time lengths of each terminal device can be sorted from largest to smallest, and each terminal device downloads face-related data sequentially according to this sorting, and generates and packages blocks based on the face-related data.

In this embodiment, each terminal device downloads face-related data and generates blocks sequentially according to the length of its idle time. This not only greatly reduces the pressure on the server but also makes full use of idle terminal devices in the blockchain network, thereby improving resource utilization.

In one embodiment of this application, the specific steps of the block generation process are shown in Figure 5. Figure 5 illustrates a flowchart of the block generation process according to an embodiment of this application. Referring to Figure 5, the process specifically includes the following steps:

In step 510, the identification information of the target node and the first hash value in the latest block added to the blockchain are obtained.

The identification information of a target node is information that can uniquely identify a target node. The data type of the identification information of a target node can be a string, which can include letters, numbers, underscores, etc.

The blocks added to the blockchain are linked together sequentially to form the blockchain. Therefore, the blocks are added to the blockchain in a specific order. The most recently added block is the last block added before the current time, and each block contains a hash value.

In step 520, the second hash value is determined based on the target node's identification information, the first hash value, and face-related data.

Specifically, a hash operation is performed on the combination of the first hash value, face-related data, and the identification information of the target node to obtain the second hash value.

In step 530, a block is generated based on the target node's identification information, face-related data, first hash value, and second hash value.

The role and position of the second hash value in the generated block are similar to the role and position of the first hash value in the most recently added block of the blockchain.

In one embodiment of this application, the specific steps of step 530 can be as shown in FIG6. FIG6 shows a flowchart detailing step 530 in FIG5 according to an embodiment of this application. As shown in FIG6, step 530 specifically includes the following steps:

In step 531, the face-related data is encrypted to obtain encrypted face-related data.

In one embodiment of this application, encrypting face-related data to obtain encrypted face-related data includes: encrypting face-related data using a key stored locally on the target node to obtain encrypted face-related data, wherein the key cannot be obtained by the user of the target node.

For example, in payment scenarios, symmetric keys can be used to encrypt facial recognition data. These symmetric keys are programmed into the ROM (Read-Only Memory) of the facial recognition IoT device. By programming the symmetric key into the ROM, it becomes impossible to forcibly obtain it through technical means, thus improving data storage security.

In one embodiment of this application, before encrypting the face-related data to obtain the encrypted face-related data, the method further includes: obtaining an encrypted symmetric key periodically sent by the server, wherein the encrypted symmetric key is generated by the server using the public key of the target node to encrypt the symmetric key; decrypting the encrypted symmetric key based on the private key of the target node to obtain the symmetric key; and encrypting the face-related data to obtain the encrypted face-related data, which includes: encrypting the face-related data using the symmetric key to obtain the encrypted face-related data.

The target node's private key, like its symmetric key, is burned into the target node's ROM to enhance security.

In this embodiment, the automatic updating of the symmetric key in the terminal device is realized, which effectively ensures the encryption security of face-related data. Since the symmetric key is generated by the server using the public key of the terminal device, and the private key of the terminal device is only stored on the terminal device, only the terminal device can obtain the plaintext of the symmetric key, thereby improving the transmission security of the symmetric key.

In step 532, the target node's identification information, encrypted face-related data, first hash value, and second hash value are packaged into a block.

Specifically, the target node's identification information, encrypted face-related data, first hash value, and second hash value are encapsulated according to the block's data structure to obtain a block. The order of these information in the block can be arbitrary.

Because face-related data in the blockchain is encrypted, it is necessary to decrypt the encrypted face-related data when face retrieval is required.

According to the embodiment shown in Figure 6, by first encrypting the face-related data and then packaging it into blocks, the security of the face-related data is further improved, and the leakage of user privacy is avoided.

In one embodiment of this application, face-related data is stored in a face feature database located on the server. The method further includes: if, based on the size of the target face feature database being downloaded, it is determined that the size of the block file packaged from the downloaded but unpackaged face feature database will exceed a predetermined file size after the target face feature database is downloaded, then the currently downloaded but unpackaged face feature database will be packaged into a block.

The target facial feature library is currently being downloaded; therefore, the facial feature library that has been downloaded but not yet packaged does not include the target facial feature library.

Please refer to Figure 3. As shown in the middle box, each block includes the hash value of the previous block and the hash value of the current block. Blocks are sequentially linked based on their hash values to form a blockchain. Each block includes three facial feature databases. For example, the genesis block includes feature databases 1, 2, and 3; block 1 includes feature databases 4, 5, and 6, and so on. The genesis block is the first block generated in the blockchain, and its hash value is empty when it is packaged. In this embodiment, when the facial feature database downloaded by each facial recognition IoT device is about to exceed 20MB, the device is responsible for packaging these databases into a single block file. Since each facial feature database file is 5MB, after downloading three databases, the device needs to package them into a block. This is because the block also includes hash values, node identification information, and other information. Downloading four databases before packaging would result in an excessively large block.

Please refer to Figure 2. In step 230, the target block is stored on the target node, and the on-chain information of the target block is broadcast on the blockchain network through the target node.

On-chain information is used to represent the link relationship between the target block and other blocks on the blockchain.

In a blockchain network, facial recognition data downloaded by terminal devices from the server is ultimately stored in the form of blocks. All nodes on the blockchain network, except the target node, can receive the information uploaded to the chain.

Specifically, the on-chain information may include the identifier information, first hash value, and second hash value of the target block. Since the first hash value belongs to the most recently added block, the link relationship between the target block and other blocks can be determined based on the first hash value of the most recently added block and the second hash value of the target block. Of course, the on-chain information may only include the identifier information, second hash value, and timestamp of the target block. The timestamp reflects the time when the on-chain information was sent. Therefore, the link relationship between the target block and other blocks can be determined based on the order of the timestamps.

In step 240, when the query node receives the on-chain information broadcast in the blockchain network, it saves the block record generated based on the on-chain information on the query node.

Block records include query paths used to locate the target block.

The data in a block record can take many forms. A block record includes links between blocks in the blockchain, and these links form part of the query path for each block.

Specifically, in one embodiment of this application, the on-chain information includes a hash value and the identification information of the target node. When the query node receives the on-chain information broadcast in the blockchain network, it saves the block record generated based on the on-chain information on the query node, including: when the query node receives the on-chain information broadcast in the blockchain network, it saves the hash value and the identification information of the target node contained in the on-chain information as a block record on the query node.

In fact, the information uploaded to the blockchain can be a part of the block record, and the information uploaded to the blockchain corresponds to this part of the target block in the block record.

The hash value in the on-chain information saved as a block record on the query node can be either a second hash value or a combination of both. When the hash value is the second hash value, the on-chain information can also include a timestamp, which can also be saved as a block record on the query node. The order of these timestamps represents the linking relationship between the blocks.

This application embodiment establishes a blockchain by broadcasting on-chain information to other nodes in the blockchain network, so that each block added to the blockchain can receive information about the newly added blocks.

In step 250, in response to the face recognition request, the blockchain is traversed according to the block records stored on the query node to obtain the face recognition result.

The content of a face recognition request includes facial data. Face recognition requests are typically triggered by calls to functional modules that rely on face recognition. For example, in a payment scenario, the functional module is the payment module; when a user performs a face-scanning payment operation on a face-scanning IoT device, a face recognition request is generated. It should be noted that this face recognition request does not necessarily have to be a network request; it can be an API call request or a parameter passing between methods.

Facial data is any data that can be used to identify the identity information corresponding to a face. For example, facial data can be a facial photograph, a single image frame from a facial video stream, or even a set of image frames from a facial video stream—data that can completely record facial information. In addition, facial data can also be facial feature data extracted from the aforementioned facial photographs, single image frames, or sets of image frames—data that can completely record facial information.

The node receiving the face recognition request can be any query node in the blockchain network. Since the block record includes the query path for each block, it is possible to traverse each block in the blockchain based on the block record.

Traversing blocks in a blockchain is essentially a process of searching the blockchain. Facial recognition results are provided by nodes in the blockchain network; when searching each node, each node can return the facial recognition result. In this embodiment, the blocks in the blockchain are generated based on facial-related data. Therefore, by searching the blockchain, facial-related data corresponding to facial data can be identified. Since the identity information bound to the facial-related data is known, the identity information corresponding to the facial data can be recognized.

If a search on the target node reveals that the face-related data in the target block matches the face data included in the face recognition request, then the target node will return the face recognition result to the node that received the face recognition request. The form of the face recognition result returned by the node in the blockchain network can be varied.

For example, nodes can store identity information corresponding to face-related data. When a node retrieves face-related data that matches the face data, it can return the corresponding identity information as the face recognition result. If no face-related data matching the face data is found on the node, the node can return a face recognition result such as "No relevant data found," indicating a failed query. This identity information can be any information that uniquely identifies the identity corresponding to the face. For example, identity information can be a user's ID card number, bank card number, mobile phone number, or other user-specific information, or it can be identification information that corresponds one-to-one with user-specific information such as ID card number, bank card number, and mobile phone number.

For example, when a node retrieves face-related data that matches the face data, the node can return "query successful" or similar information indicating a successful query as the face recognition result. When no face-related data matching the face data is retrieved at the node, the face recognition result returned by the node can be "query failed" or similar information indicating a failed query.

Figure 7 shows a flowchart of a blockchain retrieval process according to an embodiment of this application.

Please refer to Figure 7, which includes the following steps:

In step 710, the face data in the face recognition request is obtained.

The facial recognition request carries facial data.

The face-related data here can be either face photos or other data that can completely record face information, or the aforementioned face feature data that can describe the shape of face organs and the distance characteristics between them, and help with face classification.

In step 720, the query path for each block in the blockchain is determined based on the hash value in the block record and the node's identification information.

When each block is packaged and uploaded to the blockchain, other terminal devices will receive the on-chain information broadcast by the terminal device that packaged the block. The hash value and the terminal device's identification information in the on-chain information will be stored in the block record.

Based on the hash values (such as the first hash value and the second hash value) in the block record, the linking relationship of each block can be determined. Therefore, each terminal device in the blockchain network knows the connection order of each block in the blockchain. Then, based on the node identification information corresponding to each hash value in the block record, the query path used to indicate which block on which node in the blockchain network to query in sequence can be determined.

In step 730, according to the query path, face data is sent to each node in the blockchain network in sequence, and each node retrieves the face recognition results returned by each node in the stored blocks.

After the face-related data stored on various terminal devices is encrypted, it needs to be decrypted first, and then it needs to be determined whether the stored face-related data matches the face data. Each terminal device can use various algorithms such as deep learning models to determine whether the face-related data matches the face data.

Figure 3 also shows that different blocks are distributed and stored across multiple nodes. In addition to the stored blocks, each node also displays the storage order of the blocks in the blockchain. This storage order is the block query path, which corresponds to the connection relationship between blocks in the blockchain. For example, the genesis block is located on node 1, while block 1 is located on node 3. Therefore, the storage order of the genesis block and block 1 is node 1 -> node 3, meaning that facial data needs to be sent to node 1 first, and then to node 3.

According to the embodiment shown in Figure 7, face data can be retrieved based on the storage order of blocks on each terminal device, thereby avoiding repeated retrieval and ensuring retrieval efficiency.

In one embodiment of this application, if no face-related data matching the face data is found on a node in the blockchain network, the node will directly send the face data to the next node according to the query path.

In this embodiment, when no matching face-related data is found on a terminal device, the current terminal device does not need to send face data to other terminal devices after receiving the face recognition result returned by that terminal device, thus improving face recognition efficiency. This embodiment also implements a backup mechanism.

Figure 8 illustrates a flowchart of the processing procedure when a target node in a blockchain network is offline, according to an embodiment of this application. Referring to Figure 8, the backup mechanism can be implemented through the following process:

In step 810, the working status of the target node is monitored by querying the node.

In one embodiment of this application, the monitoring of the target node's working status by querying the node includes: receiving working status information periodically sent by the target node in the blockchain network; and determining that the target node is offline if working status information is not periodically received from the target node.

For example, every 5 minutes, all terminal devices in the entire blockchain network will broadcast a message to other terminal devices to inform them of their current status. Therefore, each terminal device knows the liveness status of each other on the chain in near real time. If the time elapsed between the current terminal device receiving the broadcast message from the target terminal device and the current time exceeds a predetermined time, it can be determined that the target terminal device is offline.

In this embodiment, by determining that other terminal devices are offline based on the fact that they have not periodically received working status information from other terminal devices in the blockchain network, other terminal devices in the blockchain network can also know the status information of a terminal device when it crashes or malfunctions, thereby improving the operational reliability of the blockchain network.

In step 820, when the query node detects that the target node in the blockchain network is offline, it downloads the face-related data from the target block generated by the target node from the server and generates a target backup block containing the face-related data from the target block on the query node.

The face-related data is downloaded by the node from the server. Therefore, the server can know which face-related data was downloaded and packaged by the target node, and thus know which face-related data is contained in the target block generated by the target node. In this way, the server can provide the face-related data in the target block to the query node.

In step 830, the target backup block is stored on the query node, and the associated node information of the target backup block is broadcast on the blockchain network through the query node, so that other nodes in the blockchain network can save the content of the associated node information into the block record.

The associated node information includes the identifier information of the query node and the identifier information of the target node.

Since the target node is offline, in order to use the face-related data in the target block for face recognition, a query node needs to replace the target node in the blockchain network to store the face-related data in the target block.

When other nodes in the blockchain network receive the associated node information, they will save the content of the associated node information for use in the facial recognition retrieval process.

The associated node information corresponds to the target backup block, reflecting both which node generated the target backup block and which node the target backup block is used to replace.

Other nodes can at least save the identifier information of the query node from the associated node information to the block record. Specifically, other nodes can replace the identifier information of the target node stored in their local block record with the identifier information of the query node based on the identifier information of the target node in the associated node information; other nodes can also store the identifier information of the query node and the identifier information of the target node correspondingly based on the identifier information of the target node in the associated node information. The face-related data in the target block has already been stored on the target backup block in the query node. Afterwards, other nodes replace the identifier information of the target node in the block record with the identifier information of the query node. In this way, when a node in the blockchain network needs to retrieve the face-related data in the target block, it knows that it needs to send the face data to the query node that stores the target backup block.

Based on the embodiment shown in Figure 8, the face-related data in the target block is backed up in the blockchain network. Even if a node in the blockchain network goes offline or crashes, other nodes can still perform face recognition smoothly.

It should be noted that the selection of a query node as the backup storage node for the target block can be determined based on various rules and mechanisms. For example, when various terminal devices in the blockchain detect that a terminal device has crashed, they can compete to request the server to retrieve the face-related data stored by that terminal device. The server will provide the corresponding face-related data to the first node to make the request. Since the current query node is the first node to make the request, it can obtain the face-related data stored by the crashed terminal device from the server. Alternatively, the query node capable of downloading the face-related data in the target block can be a node in the blockchain designated to retrieve the face-related data stored by the crashed terminal device.

In one embodiment of this application, after broadcasting the associated node information of the target backup block on the blockchain network through the query node, the method further includes: determining that the target node has recovered to the online state based on the working status information received periodically from the target node, and clearing the stored target backup block.

In one embodiment of this application, other nodes replace the target node's identifier information stored in their local block records with the query node's identifier information based on the target node's identifier information in the associated node information. After receiving the working status information periodically sent by the target node, other nodes reset the query node's identifier information in the block records, which was replaced by the target node's identifier information, back to the target node's identifier information based on the working status information periodically sent by the target node.

Since the target node can receive the working status information periodically sent by the target node again, it can be determined that the target node has been restored to the online state. At this time, the face-related data stored on the target node can be used for face recognition. By clearing the stored target backup block, the storage space occupied can be reduced. Furthermore, other nodes can reset the identification information of the query node to the identification information of the target node, so that when they need to use the face-related data in the target block for matching, they can use the target node.

In one embodiment of this application, each node in the blockchain network is able to collect facial data.

Specifically, when the embodiments of this application are used in a facial recognition payment scenario, each node in the blockchain network can be a facial recognition IoT device. In this case, the node can both store face-related data and directly collect face data.

In one embodiment of this application, each node in the blockchain network is used for facial recognition payment, and each node in the blockchain network corresponds to the same merchant identifier.

A merchant identifier is used to uniquely identify a merchant. Therefore, the scale of nodes corresponding to the same merchant identifier is very small. For example, each end node in the blockchain network corresponding to the same merchant identifier can be a facial recognition IoT device in a store. These facial recognition IoT devices can be deployed in a local area network. The local area network can be used to transmit data between nodes at high speed, thereby greatly reducing the latency of retrieval in the blockchain network. This makes the efficiency of facial recognition comparable to that of facial recognition when all facial-related data is stored locally.

Figure 9 shows a flowchart of the steps following step 250 in Figure 2 according to an embodiment of this application. As shown in Figure 9, after step 250, the following steps may also be included:

In step 910, if face-related data matching the face data in the face recognition request is retrieved, a payment instruction is sent to the server through the query node, and the server performs payment operation on the payment account corresponding to the face-related data.

For example, a node can store payment accounts corresponding to face-related data. When a face-related data on that node matches a face, the node can return the payment account corresponding to that face-related data to the current node. The current node can then send a payment instruction to the server, which includes the payment receipt corresponding to that payment account, thereby performing the payment operation.

Making a payment to a payment account involves transferring the amount of money spent from the payment account to the merchant's account.

In one embodiment of this application, if face-related data matching the face data in the face recognition request is retrieved, a payment instruction is sent to the server through the query node, and the server performs a payment operation on the payment account corresponding to the face-related data. This includes: if face-related data matching the face data in the face recognition request is retrieved, a payment instruction is sent to the server when the query node is connected to the network, and the server performs a payment operation on the payment account corresponding to the face-related data.

Specifically, once the search in the blockchain network is complete, the payment account corresponding to the face-related data that matches the face data can be obtained. At this point, since the current query node is not yet connected to the network, the payment receipt containing the payment account can be temporarily stored locally. Once the current query node is connected to the network, a payment instruction containing the payment receipt will be sent to the server.

In this embodiment, delayed payment is implemented. Through the solution of this application embodiment, even if the terminal device is temporarily not connected to the network, as long as the terminal device can restore the connection with the network, the payment operation can be completed smoothly.

In step 920, if no face-related data matching the face data in the face recognition request is found, the face data is uploaded to the server through the query node. After the server determines the payment account that matches the face data, it performs the payment operation on the payment account.

In this embodiment, face recognition is only performed by the server when the local area network cannot complete the face recognition and the corresponding payment operation is completed; in most cases, face recognition is performed on the local area network, thereby effectively reducing the risk of network congestion.

It is worth noting that, although in this embodiment, sending payment instructions and facial data to the server is executed by the query node that receives the facial recognition request, in other embodiments of this application, sending payment instructions and facial data to the server can be executed by nodes other than the current query node. Specifically, sending payment instructions to the server can be executed by a node that stores facial-related data matching the facial data, and sending facial data can be executed by a node that stores the last block in the blockchain network.

Please refer to Figure 3. According to the content in the box at the bottom of Figure 3, after feature retrieval, if the retrieval fails in the blockchain network, that is, there is no face-related data matching the face data in the blockchain, then face recognition is performed in the cloud, and the payment is deducted directly after the recognition is completed. If the retrieval is successful in the blockchain network, but the current node is not yet connected to the network, the payment receipt containing the payment account can be temporarily stored locally. When the current node is connected to the network, the payment instruction containing the payment receipt is sent to the server, thus realizing delayed payment.

It should be noted that, although in the embodiments of this application, the server performing the payment operation and the server from which the face-related data downloaded by the node originate are the same server, in other embodiments of this application, the server performing the payment operation and the server from which the face-related data originate may be different terminal devices.

In summary, the face recognition method provided in this application downloads face-related data from the server to the local machine, eliminating the need to upload face data for face matching, thus improving the efficiency of face recognition. While achieving face recognition, especially offline face recognition, it reduces network traffic consumed by storing face-related data locally on the terminal, as well as storage resources. Furthermore, storing face-related data in a blockchain ensures data security and effectively protects user privacy data.

The following describes an embodiment of the apparatus described in this application, which can be used to execute the face recognition method described above. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the face recognition method described above.

Figure 10 shows a block diagram of a face recognition device according to an embodiment of the present application. Referring to Figure 10, a face recognition device 1000 according to an embodiment of the present application includes: a component assembly unit 1010, a download and generation unit 1020, a storage and broadcast unit 1030, a receiving and storage unit 1040, and a traversal unit 1050.

The blockchain network is configured to establish a blockchain network for data communication within the local area network, using a terminal device connected to the local area network (LAN) for face recognition as a blockchain node. The blockchain network includes target nodes for generating and storing target blocks and query nodes for searching the target blocks. The download and generation unit 1020, when the target node is connected to the internet, downloads face-related data for offline storage from the server through the target node and generates a target block containing the face-related data on the target node. The storage and broadcast unit 1030 stores the target block on the target node. On the node, the target node broadcasts the on-chain information of the target block on the blockchain network. The on-chain information is used to indicate the link relationship between the target block and other blocks on the blockchain. The receiving and saving unit 1040 is used to save the block record generated according to the on-chain information on the query node when the query node receives the on-chain information broadcast in the blockchain network. The block record includes a query path for finding the target block. The traversal unit 1050 is used to traverse each block in the blockchain to obtain the face recognition result in response to the face recognition request, according to the block record saved on the query node.

In some embodiments of this application, based on the foregoing scheme, the download and generation unit 1020 is configured to: obtain the identification information of the target node and the first hash value in the latest block added to the blockchain; determine the second hash value based on the identification information of the target node, the first hash value and the face-related data; and generate a block based on the identification information of the target node, the face-related data, the first hash value and the second hash value.

In some embodiments of this application, based on the foregoing scheme, the download and generation unit 1020 is configured to: encrypt the face-related data to obtain encrypted face-related data; and package the identification information of the target node, the encrypted face-related data, the first hash value, and the second hash value into a block.

In some embodiments of this application, based on the foregoing scheme, the on-chain information includes a hash value and the identification information of the target node. The receiving and saving unit 1040 is configured to: when the query node receives the on-chain information broadcast in the blockchain network, save the hash value and the identification information of the target node contained in the on-chain information as a block record to the query node.

In some embodiments of this application, based on the aforementioned scheme, the traversal unit 1050 is configured to: obtain the face data in the face recognition request; determine the query path of each block in the blockchain according to the hash value and node identification information in the block record; and send the face data to each node in the blockchain network in sequence according to the query path, so that each node can retrieve the face data in the stored blocks and obtain the face recognition result returned by each node.

In some embodiments of this application, based on the foregoing scheme, the download and generation unit 1020 is further configured to: monitor the working status of the target node through the query node; when the query node detects that the target node in the blockchain network is offline, download the face-related data in the target block generated by the target node from the server, and generate a target backup block containing the face-related data in the target block on the query node; save the target backup block on the query node, and broadcast the associated node information of the target backup block on the blockchain network through the query node, so that other nodes in the blockchain network save the content in the associated node information to the block record, wherein the associated node information includes the identification information of the query node and the identification information of the target node.

In some embodiments of this application, based on the foregoing scheme, the download and generation unit 1020 is configured to: receive work status information periodically sent by the target node in the blockchain network; and determine that the target node is offline if it has not periodically received work status information from the target node.

In some embodiments of this application, based on the foregoing scheme, after the associated node information of the target backup block is broadcast on the blockchain network through the query node, the download and generation unit 1020 is further configured to: determine that the target node has recovered to the online state based on the working status information received periodically from the target node, and clear the stored target backup block.

In some embodiments of this application, based on the aforementioned scheme, each node in the blockchain network is able to collect facial data.

In some embodiments of this application, based on the aforementioned scheme, each node in the blockchain network is used for facial recognition payment, and each node in the blockchain network corresponds to the same merchant identifier.

In some embodiments of this application, based on the aforementioned scheme, after responding to a face recognition request and traversing each block in the blockchain according to the block records stored on the query node to obtain the face recognition result, the traversal unit 1050 is further configured to: if face-related data matching the face data in the face recognition request is found, then a payment instruction is sent to the server through the query node, and the server performs a payment operation on the payment account corresponding to the face-related data; if no face-related data matching the face data in the face recognition request is found, then the face data is uploaded to the server through the query node, and the server performs a payment operation on the payment account after determining the payment account matching the face data.

In some embodiments of this application, based on the aforementioned scheme, the traversal unit 1050 is configured to: if face-related data matching the face data in the face recognition request is retrieved, then when the query node is connected to the network, send a payment instruction to the server, and the server performs a payment operation on the payment account corresponding to the face-related data.

Figure 11 shows a schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application.

It should be noted that the computer system 1100 of the electronic device shown in Figure 11 is only an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

As shown in Figure 11, the computer system 1100 includes a Central Processing Unit (CPU) 1101, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 1102 or programs loaded from storage portion 1108 into Random Access Memory (RAM) 1103, such as performing the methods described in the above embodiments. Various programs and data required for system operation are also stored in RAM 1103. The CPU 1101, ROM 1102, and RAM 1103 are interconnected via bus 1104. An Input/Output (I/O) interface 1105 is also connected to bus 1104.

The following components are connected to I/O interface 1105: an input section 1106 including a keyboard, mouse, etc.; an output section 1107 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to I/O interface 1105 as needed. Removable media 1111, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1110 as needed so that computer programs read from them can be installed into storage section 1108 as needed.

Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1109, and/or installed from removable medium 1111. When the computer program is executed by central processing unit (CPU) 1101, it performs various functions defined in the system of this application.

It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such transmitted data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

In one aspect, this application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods described in the above embodiments.

It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of this application.

Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

The facial information used in this invention is legal.

Claims (15)

1. A face recognition method, characterized in that the method comprises: Using a terminal device connected to a local area network (LAN) for facial recognition as a blockchain node, a blockchain network for data communication is established within the LAN. The blockchain network includes target nodes that generate and store target blocks and query nodes for searching the target blocks. When the target node is connected to the Internet, face-related data for offline storage is downloaded from the server through the target node, and a target block containing the face-related data is generated on the target node; The target block is stored on the target node, and the on-chain information of the target block is broadcast on the blockchain network through the target node. The on-chain information is used to indicate the link relationship between the target block and other blocks on the blockchain. When the query node receives the on-chain information broadcast in the blockchain network, it saves a block record generated based on the on-chain information on the query node. The block record includes a query path for finding the target block. In response to a face recognition request, the system iterates through the blocks in the blockchain based on the block records stored on the query node to obtain the face recognition result. 2. The face recognition method according to claim 1, characterized in that, generating a target block containing the face-related data on the target node includes: Obtain the identification information of the target node and the first hash value in the latest block added to the blockchain; The second hash value is determined based on the identification information of the target node, the first hash value, and the face-related data; A block is generated based on the target node's identification information, the face-related data, the first hash value, and the second hash value. 3. The face recognition method according to claim 2, characterized in that, the step of generating a block based on the identifier information of the target node, the face-related data, the first hash value, and the second hash value includes: The face-related data is encrypted to obtain encrypted face-related data; The identification information of the target node, the encrypted face-related data, the first hash value, and the second hash value are packaged into a block. 4. The face recognition method according to claim 3, characterized in that the on-chain information includes a hash value and the identification information of the target node, wherein the hash value is the second hash value, or the hash value includes the first hash value and the second hash value; and when the query node receives the on-chain information broadcast in the blockchain network, storing a block record generated based on the on-chain information on the query node includes: When the query node receives the on-chain information broadcast in the blockchain network, it saves the hash value and the target node's identification information contained in the on-chain information as part of the block record to the query node. 5. The face recognition method according to claim 4, characterized in that, in response to a face recognition request, traversing each block in the blockchain to obtain a face recognition result based on the block records stored on the query node includes: Obtain the facial data from the facial recognition request; Based on the hash value and node identification information in the block record, the query path of each block in the blockchain is determined; According to the query path, the face data is sent to each node in the blockchain network in sequence, and each node retrieves the face recognition results returned by each node in the stored blocks. 6. The face recognition method according to claim 5, characterized in that the method further includes: The query node monitors the working status of the target node. When the query node detects that the target node in the blockchain network is offline, it downloads the face-related data from the target block generated by the target node from the server, and generates a target backup block containing the face-related data from the target block on the query node. The target backup block is stored on the query node, and the associated node information of the target backup block is broadcast on the blockchain network through the query node, so that other nodes in the blockchain network save the content of the associated node information to the block record. The associated node information includes the identification information of the query node and the identification information of the target node. 7. The face recognition method according to claim 6, characterized in that, the step of monitoring the working status of the target node through the query node includes: Receives periodic work status information from the target node in the blockchain network; Based on the fact that the target node has not periodically received working status information from the target node, it is determined that the target node is in an offline state. 8. The face recognition method according to claim 7, characterized in that, after broadcasting the associated node information of the target backup block on the blockchain network through the query node, the method further includes: Based on the working status information received periodically from the target node, it is determined that the target node has been restored to an online state, and the stored target backup block is cleared. 9. The face recognition method according to claim 1, wherein each node in the blockchain network is capable of collecting face data. 10. The face recognition method according to claim 9, wherein each node in the blockchain network is used for face payment, and each node in the blockchain network corresponds to the same merchant identifier. 11. The face recognition method according to claim 10, characterized in that, after responding to a face recognition request and traversing each block in the blockchain according to the block records stored on the query node to obtain the face recognition result, the method further includes: If face-related data matching the face data in the face recognition request is retrieved, a payment instruction is sent to the server through the query node, and the server performs a payment operation on the payment account corresponding to the face-related data. If no face-related data matching the face data in the face recognition request is found, the face data is uploaded to the server through the query node. After the server determines the payment account that matches the face data, it performs a payment operation on the payment account. 12. The face recognition method according to claim 11, characterized in that, if face-related data matching the face data in the face recognition request is retrieved, a payment instruction is sent to the server through the query node, and the server performs a payment operation on the payment account corresponding to the face-related data, comprising: If face-related data matching the face data in the face recognition request is retrieved, a payment instruction is sent to the server when the query node is connected to the network, and the server performs a payment operation on the payment account corresponding to the face-related data. 13. A face recognition device, characterized in that the device comprises: A building unit is used to build a blockchain network for data communication within the local area network by using a terminal device for face recognition connected to the local area network as a blockchain node. The blockchain network includes target nodes for generating and storing target blocks and query nodes for searching the target blocks. The download and generation unit is used to download face-related data for offline storage from the server through the target node when the target node is connected to the Internet, and to generate a target block containing the face-related data on the target node; A storage and broadcasting unit is used to store the target block on the target node and broadcast the on-chain information of the target block on the blockchain network through the target node. The on-chain information is used to indicate the link relationship between the target block and other blocks on the blockchain. A receiving and storing unit is configured to, when the query node receives the on-chain information broadcast in the blockchain network, store a block record generated based on the on-chain information on the query node, the block record including a query path for finding the target block; The traversal unit is used to respond to a face recognition request by traversing each block in the blockchain according to the block records stored on the query node to obtain the face recognition result. 14. A computer-readable medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the face recognition method as described in any one of claims 1 to 12. 15. An electronic device, characterized in that it comprises: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the face recognition method as described in any one of claims 1 to 12.