A face recognition method, apparatus and device

Abstract

The embodiment of the specification discloses a face recognition method, device and equipment, and the method comprises the following steps: in the case that a face recognition request is acquired, acquiring face recognition willingness information of a current user, the face recognition willingness information comprising one or more of lip language information, face position information and face posture information of the current user; based on the face recognition willingness information of the current user, determining a target user in the current user who needs to perform face recognition; performing face recognition processing corresponding to the face recognition request on the target user.

Description

Technical Field

[0001] This specification relates to the field of computer technology, and in particular to a facial recognition method, apparatus, and device. Background Technology

[0002] With the continuous development of biometric technology, facial recognition has become one of the important technologies in the current development of biometric technology due to its simple and fast recognition process. However, facial recognition also faces many challenges in practical applications. If multiple different users are within the shooting range of the facial recognition device's camera, the device will have difficulty determining which user truly needs facial recognition, resulting in low efficiency or even failure to perform facial recognition. Therefore, a more efficient facial recognition mechanism is needed when multiple users are within the shooting range of the camera. Summary of the Invention

[0003] The purpose of the embodiments in this specification is to provide a facial recognition mechanism with higher facial recognition efficiency when multiple users are within the shooting range of the camera component.

[0004] To achieve the above technical solution, the embodiments in this specification are implemented as follows:

[0005] This specification provides an embodiment of a facial recognition method, the method comprising: upon receiving a facial recognition request, acquiring facial recognition intention information of the current user, the facial recognition intention information including one or more of the current user's lip reading information, facial position information, and facial pose information; based on the current user's facial recognition intention information, determining a target user among the current users who needs to undergo facial recognition; and performing facial recognition processing corresponding to the facial recognition request on the target user.

[0006] This specification provides an embodiment of a facial recognition method, the method comprising: upon receiving a facial recognition request, acquiring facial recognition intention information of the current user, the facial recognition intention information including one or more of the current user's lip reading information, facial position information, and facial pose information; providing the current user's facial recognition intention information to a preset blockchain system, so that the blockchain system processes the current user's facial recognition intention information through a pre-deployed smart contract to obtain target users among the current users who need to undergo facial recognition; receiving the target user's information sent by the blockchain system, and performing facial recognition processing corresponding to the facial recognition request on the target user.

[0007] This specification provides a facial recognition method applied to a blockchain system. The method includes: receiving facial recognition intention information of a current user sent by a facial recognition device. The facial recognition intention information is information obtained by the facial recognition device upon receiving a facial recognition request, and includes one or more of the current user's lip reading information, facial position information, and facial pose information. Based on a pre-deployed first smart contract, the facial recognition intention information of the current user is processed to identify target users among the current users who require facial recognition. The first smart contract is used to trigger the facial recognition intention information processing of the current users. The information of the target users is sent to the facial recognition device, so that the facial recognition device performs the facial recognition processing corresponding to the facial recognition request for the target users.

[0008] This specification provides an embodiment of a facial recognition device, comprising: a willingness information acquisition module, which, upon receiving a facial recognition request, acquires facial recognition willingness information of the current user, the facial recognition willingness information including one or more of the current user's lip reading information, facial position information, and facial pose information; a user determination module, which, based on the current user's facial recognition willingness information, determines a target user among the current users who needs to undergo facial recognition; and a facial recognition module, which performs facial recognition processing corresponding to the facial recognition request on the target user.

[0009] This specification provides an embodiment of a facial recognition device, comprising: an information acquisition module, which, upon receiving a facial recognition request, acquires facial recognition intention information of the current user, the facial recognition intention information including one or more of the current user's lip reading information, facial position information, and facial pose information; an information provision module, which provides the current user's facial recognition intention information to a preset blockchain system, enabling the blockchain system to process the current user's facial recognition intention information through a pre-deployed smart contract to obtain target users among the current users who require facial recognition; and an information receiving module, which receives the target user's information sent by the blockchain system and performs facial recognition processing corresponding to the facial recognition request on the target user.

[0010] This specification provides an embodiment of a facial recognition device, comprising: an information receiving module, which receives facial recognition intention information of a current user sent by a facial recognition device. The facial recognition intention information of the current user is information acquired by the facial recognition device upon receiving a facial recognition request, and includes one or more of the current user's lip reading information, facial position information, and facial pose information; and an intention recognition module, which performs recognition processing on the current user's facial recognition intention information based on a pre-deployed first smart contract to obtain target users among the current users who require facial recognition. The first smart contract is used to trigger the recognition processing of the current user's facial recognition intention information. An information sending module sends the information of the target user to the facial recognition device, so that the facial recognition device performs facial recognition processing corresponding to the facial recognition request on the target user.

[0011] This specification provides an embodiment of a facial recognition device, comprising: a processor; and a memory arranged to store computer-executable instructions, wherein the executable instructions, when executed, cause the processor to: upon receiving a facial recognition request, acquire facial recognition intention information of the current user, the facial recognition intention information including one or more of the current user's lip reading information, facial position information, and facial pose information; based on the current user's facial recognition intention information, determine a target user among the current users who requires facial recognition; and perform facial recognition processing corresponding to the facial recognition request on the target user.

[0012] This specification provides an embodiment of a facial recognition device, comprising: a processor; and a memory arranged to store computer-executable instructions, wherein the executable instructions, when executed, cause the processor to: upon receiving a facial recognition request, acquire facial recognition intention information of the current user, the facial recognition intention information including one or more of the current user's lip reading information, facial position information, and facial pose information; provide the current user's facial recognition intention information to a preset blockchain system, so that the blockchain system performs recognition processing on the current user's facial recognition intention information through a pre-deployed smart contract to obtain target users among the current users who need to undergo facial recognition; receive information of the target users sent by the blockchain system, and perform facial recognition processing corresponding to the facial recognition request on the target users.

[0013] This specification provides an embodiment of a facial recognition device, comprising: a processor; and a memory arranged to store computer-executable instructions, wherein the executable instructions, when executed, cause the processor to: receive facial recognition intention information of a current user sent by the facial recognition device, the facial recognition intention information of the current user being information acquired by the facial recognition device upon receiving a facial recognition request, the facial recognition intention information including one or more of the current user's lip reading information, facial position information, and facial pose information; perform recognition processing on the current user's facial recognition intention information based on a pre-deployed first smart contract to obtain target users among the current users who require facial recognition, the first smart contract being used to trigger the recognition processing on the current user's facial recognition intention information; and send the information of the target user to the facial recognition device, so that the facial recognition device performs facial recognition processing corresponding to the facial recognition request for the target user.

[0014] This specification also provides a storage medium for storing computer-executable instructions. When executed, these instructions implement the following process: Upon receiving a facial recognition request, obtain the current user's facial recognition intention information, which includes one or more of the current user's lip reading information, facial position information, and facial pose information. Based on the current user's facial recognition intention information, determine the target user among the current users who requires facial recognition. Perform facial recognition processing corresponding to the facial recognition request on the target user.

[0015] This specification also provides a storage medium for storing computer-executable instructions. When executed, these instructions implement the following process: Upon receiving a facial recognition request, the system obtains the current user's facial recognition intention information, which includes one or more of the current user's lip-reading information, facial position information, and facial pose information. The system provides this information to a pre-defined blockchain system, which then processes it using a pre-deployed smart contract to identify target users requiring facial recognition. Finally, the system receives information about the target users from the blockchain system and performs facial recognition processing corresponding to the facial recognition request on those target users.

[0016] This specification also provides a storage medium for storing computer-executable instructions. When executed, these instructions implement the following process: receiving facial recognition intention information of a current user sent by a facial recognition device. This facial recognition intention information is information obtained by the facial recognition device upon receiving a facial recognition request, and includes one or more of the current user's lip reading information, facial position information, and facial pose information. Based on a pre-deployed first smart contract, the facial recognition intention information of the current user is processed to identify target users among the current users who require facial recognition. The first smart contract is used to trigger the facial recognition intention information processing of the current user. The information of the target user is sent to the facial recognition device, causing the facial recognition device to perform facial recognition processing corresponding to the facial recognition request for the target user. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is an embodiment of a facial recognition method described in this specification;

[0019] Figure 2 This is another embodiment of the facial recognition method described in this specification;

[0020] Figure 3 This is yet another embodiment of the facial recognition method described in this specification;

[0021] Figure 4 This is yet another embodiment of the facial recognition method described in this specification;

[0022] Figure 5 This is yet another embodiment of the facial recognition method described in this specification;

[0023] Figure 6 This is one embodiment of a facial recognition device described in this specification;

[0024] Figure 7 This is another embodiment of a facial recognition device described in this specification;

[0025] Figure 8 This is yet another embodiment of a facial recognition device described in this specification;

[0026] Figure 9This is an embodiment of a facial recognition device described in this specification. Detailed Implementation

[0027] This specification provides an embodiment of a facial recognition method, apparatus, and device.

[0028] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0029] Example 1

[0030] like Figure 1 As shown in the embodiments of this specification, a facial recognition method is provided. The subject executing this method can be a facial recognition device, which can be a terminal device or a machine capable of facial recognition, such as a mobile terminal device like a mobile phone or tablet computer. The machine can be a vending machine for a product or a access verification machine for a certain area. The method specifically includes the following steps:

[0031] In step S102, when a facial recognition request is received, the facial recognition intention information of the current user is obtained. The facial recognition intention information includes one or more of the current user's lip reading information, facial position information, and facial pose information.

[0032] The facial recognition request can be a notification message requesting facial recognition. This request can be triggered in various ways, such as by a user clicking a facial recognition button on the device, or by the user directly inputting specified voice data into the device via voice activation. The specific method can be customized based on actual circumstances, and this specification does not limit this. The current user can be any user whose facial information can be captured by the camera component of the facial recognition device. There can be one or more current users. The camera component can be the component in the facial recognition device used for image acquisition, such as a camera or webcam in a vending machine. Facial recognition intention information can be used to determine whether a user intends to undergo facial recognition. Lip reading information can be information obtained by distinguishing the user's lip movements during speech. Lip reading information can determine the content of the words or sentences spoken by the user, or whether the words or sentences spoken by the user are specified. Facial location information can be the coordinates or area of ​​a user's face in the image preview interface of the camera component. Facial pose information can be information about the posture of the user's face. Facial pose information may include, for example, the angle between the user's face and a specified reference plane. The specific settings can be made according to the actual situation, and this specification does not limit this.

[0033] In practice, with the continuous development of biometric technology, facial recognition, with its advantages of simple and fast recognition process, has become one of the important technologies in the current development of biometric technology. However, facial recognition also faces many challenges in practical applications. If multiple different users are within the shooting range of the facial recognition device's camera component, the device will have difficulty determining which user truly needs facial recognition, resulting in low efficiency or even failure to perform facial recognition. Therefore, a facial recognition mechanism with higher efficiency is needed when multiple users are within the shooting range of the camera component. This specification provides an achievable technical solution, which may include the following:

[0034] When multiple different users' faces are within the capture range of a facial recognition device's camera, if the facial recognition mechanism is triggered, the device may struggle to accurately determine which user requires facial recognition. Therefore, it's necessary to determine whether the current user intends to undergo facial recognition. Specifically, the facial recognition device can include a camera component, which may be located at the top, middle, or bottom of the device. Additionally, the device can also include a sound acquisition component (such as a microphone), which can be positioned at a designated location on the facial recognition device (e.g., top, middle, or bottom). The facial recognition device may also include a trigger button for facial recognition. This trigger button can be a physical button or a virtual button located in the display component of the facial recognition device. In practical applications, to improve the user experience, the trigger button may not be necessary, and a facial recognition request can be generated via voice triggering. The specific process can be as follows: When a user needs to perform facial recognition, they can speak a command to start facial recognition to the facial recognition device. For example, the user can say "Start facial recognition," "Facial recognition," or "Facial payment," etc. The specific settings can be configured according to the actual situation, and this specification does not limit this. The voice acquisition component in a facial recognition device can capture and recognize the user's voice to determine if the user is uttering a specified command word. If so, the facial recognition device can generate a facial recognition request, which it can then acquire. Furthermore, during the detection of the user's facial recognition command, the device can also activate the camera component to capture images of the user's lip movements within its field of view. These images can be analyzed to determine the lip-reading information. Simultaneously, the device can capture facial images of each user within its field of view, determining their facial position and posture. Each user's face can be numbered and tracked in real-time, providing a foundation for accurately determining the user's facial recognition intent.

[0035] After receiving a facial recognition request, the facial recognition device can obtain facial recognition intention information for each user within the shooting range of the camera component. This facial recognition intention information can be one or more of the following: lip reading information, facial position information, and facial posture information for each user within the shooting range of the camera component.

[0036] It should be noted that the above is only one feasible processing method. In practical applications, the user's facial recognition intention information can also include multiple types, which can be set according to the actual situation. This specification does not limit this.

[0037] In step S104, based on the current user's facial recognition intention information, the target users among the current users who need to undergo facial recognition are determined.

[0038] The current user can be a user within the shooting range of the camera component, or a user in a designated area within the shooting range of the camera component, etc. The specific settings can be made according to the actual situation, and this specification does not limit this.

[0039] In implementation, if the camera module's shooting range includes multiple different users, and not all of these users require facial recognition, to accurately determine which user needs facial recognition, the determination can be based on the user's willingness to undergo facial recognition. Specifically, lip-reading information of each user within the camera module's shooting range can be acquired and analyzed to determine the user's speech content. If a user's speech content matches a specified keyword, it can be determined that the user has the willingness to undergo facial recognition and needs to be identified; in this case, the user can be marked. If a user's speech content does not match the specified keyword, it can be determined that the user does not have the willingness to undergo facial recognition. And / or, facial position information of each user within the camera module's shooting range can be acquired and analyzed to determine the user's location. The user's location can be combined with the aforementioned lip-reading information to more accurately determine which user has the willingness to undergo facial recognition. And / or, facial pose information of each user within the camera module's shooting range can be acquired and analyzed to determine the user's facial pose, which can then be used to track the user. By combining the user's location, facial posture, and the aforementioned lip-reading information, it is possible to more accurately determine which user intends to undergo facial recognition. Analyzing the facial recognition intention information of each user allows us to identify the target users among the current users who require facial recognition.

[0040] For example, if the trigger command for a facial recognition request is the user's voice input "facial recognition," the facial recognition device can collect the user's voice information through the sound acquisition component. At the same time, it can activate the camera component to collect relevant images during the user's voice input process. By analyzing the voice information and the collected images, the device can obtain each user's lip reading information, facial position information, and facial posture information. Based on each user's lip reading information, facial position information, and facial posture information, the device can identify the user who input the voice input "facial recognition" and use the identified user as the target user for facial recognition.

[0041] In step S106, the facial recognition process corresponding to the facial recognition request is performed on the target user.

[0042] In practice, after the facial recognition device determines that the target user is the user who needs to undergo facial recognition, it can activate the facial recognition mechanism corresponding to the aforementioned facial recognition request for the target user. Through this facial recognition mechanism, the camera component can capture the target user's facial image, and the captured facial image can be compared with a pre-stored reference image. If the two match, it can be determined that the target user has passed the facial recognition process; otherwise, the target user can be notified that the facial recognition has failed.

[0043] This specification provides a facial recognition method. When a facial recognition request is received, the method acquires the current user's facial recognition intention information, which includes one or more of the current user's lip reading information, facial position information, and facial pose information. Then, based on the current user's facial recognition intention information, the method identifies the target user among the current users who needs facial recognition, and performs facial recognition processing corresponding to the facial recognition request on the target user. In this way, a facial recognition intention recognition method based on the fusion of the user's lip reading, facial position, and facial pose information is provided. This method can not only accurately identify the user who truly needs facial recognition among multiple different users within the shooting range of the facial recognition device's camera component, thus improving facial recognition efficiency, but also enrich the user's facial recognition interactive experience and avoid the risks associated with user intention.

[0044] Example 2

[0045] like Figure 2 As shown in the embodiments of this specification, a facial recognition method is provided. The subject executing this method can be a facial recognition device, which can be a terminal device or a machine capable of facial recognition, such as a mobile terminal device like a mobile phone or tablet computer. The machine can be a vending machine for a product or a access verification machine for a certain area. The method specifically includes the following steps:

[0046] In practical applications, in order to improve data processing efficiency and the accuracy of user intention recognition, a model for recognizing user intentions can be pre-trained, namely the intention recognition model. For details, please refer to the processing steps S202 and S204 below.

[0047] In step S202, historical facial recognition intention information of multiple different users is obtained. This historical facial recognition intention information includes one or more of the following: historical lip reading information, historical facial position information, and historical facial pose information of multiple different users.

[0048] Among them, historical facial recognition intention information can be information about a user's intention to undergo facial recognition at a certain point in time or within a certain period of history.

[0049] In implementation, historical facial recognition intention information of multiple different users can be obtained in various ways. For example, lip reading information, facial position information, and facial pose information of users at a certain point in time or within a certain time period can be purchased from different users. Alternatively, users can be invited to experience a developed application first through an exchange. The lip reading information, facial position information, and facial pose information generated by users during the use of the application can be used by the developers for model training, etc. In addition to the above methods, various other methods can also be included. The specific methods can be set according to the actual situation, and the embodiments in this specification do not limit them.

[0050] In step S204, the intention recognition model is trained using historical facial recognition intention information to obtain the trained intention recognition model.

[0051] In implementation, a corresponding algorithm can be pre-set according to the actual situation. This algorithm can be a machine learning algorithm or other algorithms, such as a pre-set expert decision-making algorithm or a pre-set evaluation algorithm. The algorithm can be used to construct the model architecture of the intention recognition model, which can include one or more different parameters to be determined. Then, the intention recognition model can be trained using the historical facial recognition intention information of multiple different users obtained above. Specifically, the historical facial recognition intention information of multiple different users can be input into the intention recognition model to obtain a system of equations about the parameters to be determined. Solving these equations yields the initial values ​​of each parameter. Then, the historical facial recognition intention information of the remaining users is input into the intention recognition model with the initial values ​​of the above parameters, and finally, updated parameter values ​​can be obtained. In this way, optimal parameter values ​​can be obtained, ultimately leading to the trained intention recognition model.

[0052] In step S206, the camera component collects the current user's lip reading information and voice information.

[0053] The voice information can be the voice information input by the user when waking up the facial recognition device through a specified wake-up command. The voice information can be the voice form of the wake-up command, for example, the wake-up command can be "face payment". The voice information can be the voice information collected by the facial recognition device during the process of the user reading "face payment".

[0054] In practice, facial recognition devices can activate the camera module and continuously capture multiple images of the user's mouth movements, or continuously capture videos of the user's mouth movements. Then, the multiple images of the user can be analyzed separately to determine the user's lip reading information. In addition, voice information input by the user can be collected through a sound acquisition device.

[0055] In step S208, the lip reading information is input into a pre-trained lip reading model, and the current user's voice information is input into a pre-trained speech recognition model to obtain the recognition result corresponding to the lip reading information and the recognition result corresponding to the voice information, respectively.

[0056] The lip-reading model can be constructed in various ways, such as through a convolutional neural network model. The specific method can be determined based on the actual situation, and this specification does not limit this approach. Similarly, the speech recognition model can be an n-gram language model, and the specific method can be determined based on the actual situation, and this specification does not limit this approach.

[0057] In implementation, corresponding algorithms for constructing lip-reading and speech recognition models can be set according to actual conditions. The model architecture for both lip-reading and speech recognition can be constructed based on pre-defined algorithms. Lip-reading information from multiple different users can be acquired and used to train the lip-reading model, resulting in a trained lip-reading model. Similarly, speech information from multiple different users can be acquired and used to train the speech recognition model, resulting in a trained speech recognition model. After obtaining the current user's lip-reading information through the above methods, this information can be input into the trained lip-reading model to obtain the corresponding recognition result. Likewise, after obtaining the current user's speech information through the above methods, this speech information can be input into the trained speech recognition model to obtain the corresponding recognition result.

[0058] In step S210, based on the recognition results corresponding to the lip reading information and the recognition results corresponding to the voice information, it is determined whether the current user needs to undergo facial recognition.

[0059] In practice, the recognition results corresponding to the lip reading information and the recognition results corresponding to the voice information can be combined through expert decision-making and other methods to ultimately determine whether the current user needs to undergo facial recognition.

[0060] In step S212, if so, a face recognition request is generated.

[0061] In practice, if the recognition result corresponding to the above lip reading information is that the user has spoken the specified instruction word, and the recognition result corresponding to the above voice information is the instruction word, it can be determined that the current user needs to perform facial recognition. At this time, the facial recognition device will be activated, and the facial recognition device can generate a facial recognition request.

[0062] In practical applications, the process of generating facial recognition requests in steps S206 to S212 can be varied. Two more implementation methods are provided below, which can be found in Method 1 and Method 2.

[0063] Method 1 involves triggering a facial recognition request by recognizing lip reading information. For details, please refer to steps A2 to A6 below.

[0064] In step A2, the lip reading information of the current user is collected through the camera component.

[0065] In step A4, the above lip reading information is input into a pre-trained lip reading model to determine whether the current user needs facial recognition.

[0066] In practice, the lip reading information can be analyzed using a pre-trained lip reading model to determine whether the recognition result corresponding to the lip reading information indicates that the user has spoken the specified instruction word (such as "facial recognition" or "face payment"). If the lip reading information indicates that the user has spoken the specified instruction word, it is determined that the current user needs to undergo facial recognition. If the lip reading information indicates that the user has not spoken the specified instruction word, it is determined that the current user does not need to undergo facial recognition.

[0067] In step A6, if yes, a facial recognition request is generated.

[0068] Method 2: A facial recognition request is generated by recognizing lip reading and speech information. For details, please refer to steps B2 to B10 below.

[0069] In step B2, the camera component is used to collect the current user's lip reading information and voice information.

[0070] In step B4, the above lip reading information is input into a pre-trained lip reading model to obtain the first recognition result corresponding to the lip reading information.

[0071] In implementation, the first recognition result can be a probability value or information about the user whose lip-reading information might contain a specified instruction word. If the lip-reading information is input into a pre-trained lip-reading model, and a probability value is obtained indicating that the content of the lip-reading information might contain a specified instruction word (i.e., the first recognition result corresponding to the lip-reading information), this probability value can be compared with a preset probability threshold. Information about users whose probability value is greater than the probability threshold can be obtained. If the lip-reading information is input into a pre-trained lip-reading model, and information about users whose lip-reading information might contain a specified instruction word is obtained, then the user's information can be directly obtained.

[0072] In step B6, the user's voice information corresponding to the first recognition result is input into a pre-trained speech recognition model to obtain the second recognition result.

[0073] Among them, the user's voice information corresponding to the first recognition result may be the content of the lip reading information or the user's voice information of the specified instruction word.

[0074] In step B8, based on the second recognition result, it is determined whether the current user needs to undergo facial recognition.

[0075] In practical applications, the processing of step B8 above can be varied. Here is another possible method, which can include: inputting the user's voice information corresponding to the second recognition result into a pre-trained semantic recognition model to obtain the corresponding third recognition result, and determining whether the current user needs to undergo facial recognition based on the third recognition result.

[0076] Among them, the user's voice information corresponding to the second recognition result may be the user's voice information whose content may be the specified instruction word.

[0077] In implementation, to improve the accuracy of user identification, a semantic recognition model can be pre-set. This model can be constructed using various algorithms or models, such as a Hidden Markov Model. The specific model can be set according to the actual situation, and this specification does not limit this. The semantic recognition model can determine whether the current user needs facial recognition.

[0078] In step B10, if so, a face recognition request is generated.

[0079] In step S214, if a facial recognition request is received, the facial recognition intention information of the current user is obtained. The facial recognition intention information includes one or more of the current user's lip reading information, facial position information, and facial pose information.

[0080] In step S216, the facial recognition intention information of the current user is input into the pre-trained intention recognition model to obtain the information of the target users who need to undergo facial recognition among the current users.

[0081] In step S218, the facial recognition process corresponding to the facial recognition request is performed on the target user.

[0082] This specification provides a facial recognition method. Upon receiving a facial recognition request, it acquires the current user's facial recognition intention information, which includes one or more of the current user's lip-reading information, facial position information, and facial pose information. Then, based on the current user's facial recognition intention information, it identifies the target user among the current users who needs facial recognition and performs facial recognition processing corresponding to the request on the target user. This provides a facial recognition intention recognition method based on the fusion of the user's lip-reading, facial position, and facial pose information. This method not only accurately identifies the user who truly needs facial recognition among multiple different users within the camera's field of view, improving facial recognition efficiency, but also enriches the user's facial recognition interactive experience and avoids the risks associated with user intention. Furthermore, it also provides a facial recognition mechanism that supports lip-reading wake-up and intention recognition.

[0083] Example 3

[0084] like Figure 3 As shown in the embodiments of this specification, a facial recognition method is provided. The subject executing this method can be a facial recognition device, which can be a terminal device or a machine capable of facial recognition, such as a mobile terminal device like a mobile phone or tablet computer. The machine can be a vending machine for a product or a access verification machine for a certain area. The method specifically includes the following steps:

[0085] In step S302, when a facial recognition request is received, the facial recognition intention information of the current user is obtained. The facial recognition intention information includes one or more of the current user's lip reading information, facial position information, and facial pose information.

[0086] In step S304, the facial recognition intention information of the current user is provided to a preset blockchain system, so that the blockchain system can identify and process the facial recognition intention information of the current user through a pre-deployed smart contract to obtain the target users among the current users who need to undergo facial recognition.

[0087] The smart contract can contain rules for recognizing a user's facial recognition intent. By using the rules set in the smart contract, the target users who need to undergo facial recognition can be identified. Due to the tamper-proof nature of the blockchain system, the accuracy of recognizing a user's facial recognition intent can be guaranteed.

[0088] In step S306, the information of the target user sent by the blockchain system is received, and the facial recognition processing corresponding to the facial recognition request is performed on the target user.

[0089] This specification provides a facial recognition method. Upon receiving a facial recognition request, it acquires the current user's facial recognition intention information, which includes one or more of the current user's lip-reading information, facial position information, and facial pose information. This information is then provided to a pre-defined blockchain system. The blockchain system processes this information through a pre-deployed smart contract to identify the target user requiring facial recognition. The system receives the target user's information from the blockchain system and performs facial recognition processing corresponding to the request. This provides a facial recognition intention recognition method based on the fusion of lip-reading, facial position, and facial pose information. This method not only accurately identifies the user truly requiring facial recognition among multiple different users within the camera's field of view, improving facial recognition efficiency, but also enriches the user's interactive experience and mitigates risks associated with user intention. Furthermore, using a blockchain system for user intention recognition improves the accuracy of the process.

[0090] Example 4

[0091] like Figure 4 As shown in the embodiments of this specification, a facial recognition method is provided. The executing entity of this method can be a blockchain system, which can be composed of terminal devices or servers. The terminal devices can be mobile terminal devices such as mobile phones and tablets, or devices such as personal computers. The server can be a single server or a server cluster composed of multiple servers. Specifically, the method may include the following steps:

[0092] In step S402, the facial recognition intention information of the current user sent by the facial recognition device is received. The facial recognition intention information of the current user is the information obtained by the facial recognition device when it receives a facial recognition request. The facial recognition intention information includes one or more of the current user's lip reading information, facial position information and facial pose information.

[0093] In step S404, the facial recognition intention information of the current user is identified and processed based on the pre-deployed first smart contract to obtain the target users among the current users who need to undergo facial recognition. The first smart contract is used to trigger the facial recognition intention information of the current user to be identified and processed.

[0094] The first smart contract can be configured with rules for recognizing a user's facial recognition intent, such as lip-reading analysis rules and facial pose analysis rules. These rules can be tailored to specific needs and are not limited in this embodiment. By using the rules set in the first smart contract, the target users requiring facial recognition can be identified. Due to the tamper-proof nature of the blockchain system, the accuracy of recognizing a user's facial recognition intent can be guaranteed.

[0095] In step S406, the target user's information is sent to the facial recognition device so that the facial recognition device performs the facial recognition processing corresponding to the facial recognition request for the target user.

[0096] This specification provides a facial recognition method. Upon receiving a facial recognition request, it acquires the current user's facial recognition intention information, which includes one or more of the current user's lip-reading information, facial position information, and facial pose information. This information is then provided to a pre-defined blockchain system. The blockchain system processes this information through a pre-deployed smart contract to identify the target user requiring facial recognition. The system receives the target user's information from the blockchain system and performs facial recognition processing corresponding to the request. This provides a facial recognition intention recognition method based on the fusion of lip-reading, facial position, and facial pose information. This method not only accurately identifies the user truly requiring facial recognition among multiple different users within the camera's field of view, improving facial recognition efficiency, but also enriches the user's interactive experience and mitigates risks associated with user intention. Furthermore, using a blockchain system for user intention recognition improves the accuracy of the process.

[0097] Example 5

[0098] like Figure 5As shown in the embodiments of this specification, a facial recognition method is provided. The executing entity of this method can be a blockchain system, which can be composed of terminal devices or servers. The terminal devices can be mobile terminal devices such as mobile phones and tablets, or devices such as personal computers. The server can be a single server or a server cluster composed of multiple servers. Specifically, the method may include the following steps:

[0099] In practical applications, a pre-trained model can be used to analyze a user's facial recognition intent. Furthermore, considering that pre-trained models often require continuous updates, they can be stored on a designated storage device, and their storage address can be uploaded to the blockchain system. The model training process is detailed above and will not be repeated here. Then, a corresponding smart contract can be constructed based on the rules for analyzing the user's facial recognition intent, and this smart contract can be deployed on the blockchain system. See the following for details:

[0100] In step S502, the lip reading information and voice information of the current user collected by the facial recognition device through the camera component are received.

[0101] In step S504, based on the pre-deployed second smart contract, the index information of the pre-trained lip reading model and the index information of the pre-trained speech recognition model are obtained from the blockchain system, and the lip reading model and speech recognition model are obtained based on the obtained index information. The second smart contract is used to trigger the recognition processing of the current user's lip reading information and speech information.

[0102] In step S506, based on the second smart contract, the lip reading information is input into the lip reading model, and the current user's voice information is input into the voice recognition model, so as to obtain the recognition result corresponding to the lip reading information and the recognition result corresponding to the voice information respectively.

[0103] Furthermore, in practical applications, the processing of step S506 above can be varied. One optional processing method is provided below, which may include the following: Based on the second smart contract, the lip-reading information is input into a pre-trained lip-reading model to obtain a first recognition result corresponding to the lip-reading information. Based on the second smart contract, the user's voice information corresponding to the first recognition result is input into a pre-trained speech recognition model to obtain a second recognition result. The second recognition result is then sent to the facial recognition device so that the facial recognition device can determine whether the current user needs to undergo facial recognition based on the second recognition result.

[0104] In step S508, the recognition results corresponding to the lip reading information and the recognition results corresponding to the voice information are sent to the facial recognition device so that the facial recognition device can determine whether the current user needs to perform facial recognition based on the recognition results corresponding to the lip reading information and the recognition results corresponding to the voice information. If it is determined that the current user needs to perform facial recognition, a facial recognition request is generated.

[0105] In practical applications, the process of generating a face recognition request in steps S502 to S508 can be varied. Here is another possible method, which can be found in steps A2 to A8 below.

[0106] In step A2, the lip reading information of the current user is received by the facial recognition device through the camera component.

[0107] In step A4, the index information of the pre-trained lip reading model is obtained from the blockchain system based on the pre-deployed fourth smart contract, and the lip reading model is obtained based on the obtained index information. The fourth smart contract is used to trigger the recognition and processing of the current user's lip reading information.

[0108] In step A6, based on the fourth smart contract, the above lip reading information is input into the pre-trained lip reading model to determine whether the current user needs to undergo facial recognition.

[0109] In step A8, the recognition result corresponding to the lip reading information is sent to the facial recognition device so that the facial recognition device can determine whether the current user needs to undergo facial recognition based on the recognition result corresponding to the lip reading information. If it is determined that the current user needs to undergo facial recognition, a facial recognition request is generated.

[0110] In step S510, the facial recognition intention information of the current user sent by the facial recognition device is received. The facial recognition intention information of the current user is the information obtained by the facial recognition device when it receives a facial recognition request. The facial recognition intention information includes one or more of the current user's lip reading information, facial position information and facial pose information.

[0111] In step S512, the index information of the pre-trained intention recognition model is obtained from the blockchain system based on the first smart contract, and the intention recognition model is obtained based on the index information.

[0112] In step S514, based on the first smart contract, the facial recognition intention information of the current user is input into the pre-trained intention recognition model to obtain the information of the target users who need to undergo facial recognition among the current users.

[0113] In step S516, the target user's information is sent to the facial recognition device so that the facial recognition device can perform facial recognition processing corresponding to the facial recognition request for the target user.

[0114] In step S518, a facial recognition request from the target user is received from the facial recognition device. The facial recognition request includes a facial image of the target user captured by the facial recognition device.

[0115] In step S520, the target user is authenticated based on the pre-deployed third smart contract and the facial image, and the corresponding authentication result is obtained. The third smart contract is used to trigger the authentication of the user who initiated the facial recognition.

[0116] In step S522, the authentication result is sent to the facial recognition device.

[0117] Furthermore, the processing in steps S518 to S522 above can also be as follows: receiving a service request from a target user sent by a facial recognition device, the service request including a facial image of the target user collected by the facial recognition device; performing identity authentication on the target user based on a pre-deployed fifth smart contract and the facial image, obtaining the corresponding authentication result, and processing the service corresponding to the service request based on the authentication result, the fifth smart contract being used to trigger identity authentication on the user initiating facial recognition, and processing the service corresponding to the service request based on the authentication result; and sending the authentication result and the service processing result to the facial recognition device.

[0118] This specification provides a facial recognition method. Upon receiving a facial recognition request, it acquires the current user's facial recognition intention information, which includes one or more of the current user's lip-reading information, facial position information, and facial pose information. This information is then provided to a pre-defined blockchain system. The blockchain system processes this information through a pre-deployed smart contract to identify the target user requiring facial recognition. The system receives the target user's information from the blockchain system and performs facial recognition processing corresponding to the request. This provides a facial recognition intention recognition method based on the fusion of lip-reading, facial position, and facial pose information. This method not only accurately identifies the user truly requiring facial recognition among multiple different users within the camera's field of view, improving facial recognition efficiency, but also enriches the user's interactive experience and mitigates risks associated with user intention. Furthermore, using a blockchain system for user intention recognition improves the accuracy of the process.

[0119] Example 6

[0120] The above are the facial recognition methods provided in the embodiments of this specification. Based on the same idea, the embodiments of this specification also provide a facial recognition device, such as... Figure 6 As shown.

[0121] The facial recognition device includes: an information acquisition module 601, an information providing module 602, and an information receiving module 603, wherein:

[0122] The information acquisition module 601, upon receiving a facial recognition request, acquires the facial recognition intention information of the current user, wherein the facial recognition intention information includes one or more of the current user's lip reading information, facial position information, and facial posture information;

[0123] The information providing module 602 provides the facial recognition intention information of the current user to a preset blockchain system, so that the blockchain system can identify and process the facial recognition intention information of the current user through a pre-deployed smart contract to obtain the target users among the current users who need to undergo facial recognition.

[0124] The information receiving module 603 receives the information of the target user sent by the blockchain system and performs facial recognition processing corresponding to the facial recognition request on the target user.

[0125] This specification provides a facial recognition method. Upon receiving a facial recognition request, it acquires the current user's facial recognition intention information, which includes one or more of the current user's lip-reading information, facial position information, and facial pose information. This information is then provided to a pre-defined blockchain system. The blockchain system processes this information through a pre-deployed smart contract to identify the target user requiring facial recognition. The system receives the target user's information from the blockchain system and performs facial recognition processing corresponding to the request. This provides a facial recognition intention recognition method based on the fusion of lip-reading, facial position, and facial pose information. This method not only accurately identifies the user truly requiring facial recognition among multiple different users within the camera's field of view, improving facial recognition efficiency, but also enriches the user's interactive experience and mitigates risks associated with user intention. Furthermore, using a blockchain system for user intention recognition improves the accuracy of the process.

[0126] Example 7

[0127] Following the same line of thought, this specification also provides a facial recognition device, such as... Figure 7 As shown.

[0128] The facial recognition device includes: an information receiving module 701, a willingness recognition module 702, and an information sending module 703, wherein:

[0129] The information receiving module 701 receives the facial recognition intention information of the current user sent by the facial recognition device. The facial recognition intention information of the current user is the information obtained by the facial recognition device when it receives a facial recognition request. The facial recognition intention information includes one or more of the current user's lip reading information, facial position information and facial posture information.

[0130] The intention recognition module 702 recognizes and processes the facial recognition intention information of the current user based on a pre-deployed first smart contract to obtain the target users among the current users who need to undergo facial recognition. The first smart contract is used to trigger the recognition and processing of the facial recognition intention information of the current user.

[0131] The information sending module 703 sends the target user's information to the facial recognition device, so that the facial recognition device performs facial recognition processing corresponding to the facial recognition request on the target user.

[0132] In this embodiment of the specification, the intention recognition module 702 includes:

[0133] The model acquisition unit obtains the index information of the pre-trained intention recognition model from the blockchain system based on the first smart contract, and obtains the intention recognition model based on the index information.

[0134] The intention recognition unit, based on the first smart contract, inputs the facial recognition intention information of the current user into a pre-trained intention recognition model to obtain information on the target users among the current users who need to undergo facial recognition.

[0135] In the embodiments described in this specification, the device further includes:

[0136] The lip-reading and voice receiving module receives the lip-reading information and voice information of the current user collected by the facial recognition device through the camera component.

[0137] The model acquisition module obtains the index information of the pre-trained lip reading model and the index information of the pre-trained speech recognition model from the blockchain system based on a pre-deployed second smart contract, and obtains the lip reading model and the speech recognition model based on the obtained index information. The second smart contract is used to trigger the recognition processing of the current user's lip reading information and speech information.

[0138] The recognition module, based on the second smart contract, inputs the lip reading information into the lip reading model and inputs the current user's voice information into the voice recognition model, respectively obtaining the recognition result corresponding to the lip reading information and the recognition result corresponding to the voice information;

[0139] The result sending module sends the recognition results corresponding to the lip reading information and the recognition results corresponding to the voice information to the facial recognition device, so that the facial recognition device can determine whether the current user needs to perform facial recognition based on the recognition results corresponding to the lip reading information and the recognition results corresponding to the voice information. If it is determined that the current user needs to perform facial recognition, the facial recognition request is generated.

[0140] In the embodiments described in this specification, the device further includes:

[0141] The request receiving module receives a facial recognition request from the target user sent by the facial recognition device, wherein the facial recognition request includes a facial image of the target user captured by the facial recognition device.

[0142] The authentication module, based on a pre-deployed third smart contract and the facial image, performs identity authentication on the target user and obtains the corresponding authentication result. The third smart contract is used to trigger identity authentication for the user who initiates facial recognition.

[0143] The authentication result sending module sends the authentication result to the facial recognition device.

[0144] This specification provides a facial recognition device that, upon receiving a facial recognition request, acquires the current user's facial recognition intention information. This intention information includes one or more of the current user's lip-reading information, facial position information, and facial pose information. The device provides this information to a pre-defined blockchain system, which then processes the information via a pre-deployed smart contract to identify the target user requiring facial recognition. The device receives the target user's information from the blockchain system and performs facial recognition processing corresponding to the request. This provides a facial recognition intention recognition method based on the fusion of lip-reading, facial position, and facial pose information. This method not only accurately identifies the user truly requiring facial recognition among multiple different users within the camera's field of view, improving facial recognition efficiency, but also enriches the user's interactive experience and mitigates risks associated with user intention. Furthermore, using a blockchain system for user intention recognition improves the accuracy of the process.

[0145] Example 8

[0146] The above are the facial recognition methods provided in the embodiments of this specification. Based on the same idea, the embodiments of this specification also provide a facial recognition device, such as... Figure 8 As shown.

[0147] The facial recognition device includes: a willingness information acquisition module 801, a user determination module 802, and a facial recognition module 803, wherein:

[0148] The willingness information acquisition module 801, upon receiving a facial recognition request, acquires the facial recognition willingness information of the current user, wherein the facial recognition willingness information includes one or more of the current user's lip reading information, facial position information, and facial posture information;

[0149] The user identification module 802 identifies target users among the current users who need to undergo facial recognition based on the facial recognition intention information of the current users.

[0150] The facial recognition module 803 performs facial recognition processing corresponding to the facial recognition request on the target user.

[0151] In the embodiments described in this specification, the device further includes:

[0152] The first information collection module collects the current user's lip reading information through a camera component;

[0153] The first recognition and determination module inputs the lip reading information into a pre-trained lip reading model to determine whether the current user needs to undergo facial recognition.

[0154] If so, the first request generation module generates the facial recognition request.

[0155] In the embodiments described in this specification, the device further includes:

[0156] The second information acquisition module acquires the current user's lip reading information and voice information through a camera component;

[0157] The first recognition module inputs the lip reading information into a pre-trained lip reading model and inputs the current user's voice information into a pre-trained voice recognition model to obtain the recognition result corresponding to the lip reading information and the recognition result corresponding to the voice information, respectively.

[0158] The second recognition and determination module determines whether the current user needs to undergo facial recognition based on the recognition results corresponding to the lip reading information and the recognition results corresponding to the voice information.

[0159] If so, the second request generation module generates the facial recognition request.

[0160] In the embodiments described in this specification, the device further includes:

[0161] The third information acquisition module acquires the current user's lip reading information and voice information through a camera component;

[0162] The second recognition module inputs the lip reading information into a pre-trained lip reading model to obtain the first recognition result corresponding to the lip reading information;

[0163] The third recognition module inputs the user's voice information corresponding to the first recognition result into a pre-trained voice recognition model to obtain the second recognition result;

[0164] The third identification and determination module determines, based on the second identification result, whether the current user needs to undergo facial recognition;

[0165] If so, the third request generation module generates the facial recognition request.

[0166] In this embodiment of the specification, the third recognition determination module inputs the voice information of the user corresponding to the second recognition result into a pre-trained semantic recognition model to obtain the corresponding third recognition result, and determines whether the current user needs to undergo facial recognition based on the third recognition result.

[0167] In this embodiment of the specification, the user determination module 802 inputs the facial recognition intention information of the current user into a pre-trained intention recognition model to obtain information on the target users among the current users who need to undergo facial recognition.

[0168] In the embodiments described in this specification, the device further includes:

[0169] The historical information acquisition module acquires historical facial recognition intention information from multiple different users. The historical facial recognition intention information includes one or more of the following: historical lip reading information, historical facial location information, and historical facial pose information from multiple different users.

[0170] The model training module trains the intention recognition model using the historical facial recognition intention information to obtain the trained intention recognition model.

[0171] This specification provides a facial recognition device that, upon receiving a facial recognition request, acquires the current user's facial recognition intention information. This intention information includes one or more of the current user's lip reading information, facial position information, and facial pose information. Then, based on this intention information, it identifies the target user among the current users who needs facial recognition and performs facial recognition processing corresponding to the request on that target user. This provides a facial recognition intention recognition method based on the fusion of the user's lip reading, facial position, and facial pose information. This not only accurately identifies the user who truly needs facial recognition among multiple different users within the camera's field of view, improving facial recognition efficiency, but also enriches the user's interactive experience and mitigates the risks associated with user intention. Furthermore, a facial recognition mechanism supporting lip reading wake-up and intention recognition is also provided.

[0172] Example 9

[0173] The above are examples of facial recognition devices provided in the embodiments of this specification. Based on the same concept, embodiments of this specification also provide a facial recognition device, such as... Figure 9 As shown.

[0174] The facial recognition device can be the terminal device provided in the above embodiments or a blockchain node in a blockchain system, etc.

[0175] Facial recognition devices can vary significantly in configuration and performance, and may include one or more processors 901 and memory 902. Memory 902 may store one or more application programs or data. Memory 902 may be temporary or persistent storage. The application programs stored in memory 902 may include one or more modules (not shown), each module including a series of computer-executable instructions for the facial recognition device. Furthermore, processor 901 may be configured to communicate with memory 902 and execute the series of computer-executable instructions stored in memory 902 on the facial recognition device. The facial recognition device may also include one or more power supplies 903, one or more wired or wireless network interfaces 904, one or more input / output interfaces 905, and one or more keyboards 906.

[0176] Specifically, in this embodiment, the facial recognition device includes a memory and one or more programs, wherein one or more programs are stored in the memory, and one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the facial recognition device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following:

[0177] Upon receiving a facial recognition request, the system obtains the current user's facial recognition intention information, which includes one or more of the current user's lip reading information, facial position information, and facial pose information.

[0178] Based on the current user's facial recognition intention information, the target users among the current users who need to undergo facial recognition are identified;

[0179] Perform facial recognition processing corresponding to the facial recognition request on the target user.

[0180] The embodiments in this specification also include:

[0181] The camera component captures the current user's lip-reading information.

[0182] The lip reading information is input into a pre-trained lip reading model to determine whether the current user needs facial recognition.

[0183] If so, then generate the facial recognition request.

[0184] The embodiments in this specification also include:

[0185] The camera component captures the lip-reading information of the current user and also captures the voice information of the current user.

[0186] The lip reading information is input into a pre-trained lip reading model, and the current user's voice information is input into a pre-trained speech recognition model to obtain the recognition results corresponding to the lip reading information and the recognition results corresponding to the voice information, respectively.

[0187] Based on the recognition results corresponding to the lip reading information and the recognition results corresponding to the voice information, determine whether the current user needs to undergo facial recognition.

[0188] If so, then generate the facial recognition request.

[0189] The embodiments in this specification also include:

[0190] The camera component captures the lip-reading information of the current user and also captures the voice information of the current user.

[0191] The lip reading information is input into a pre-trained lip reading model to obtain the first recognition result corresponding to the lip reading information;

[0192] The user's voice information corresponding to the first recognition result is input into a pre-trained voice recognition model to obtain the second recognition result;

[0193] Based on the second recognition result, determine whether the current user needs to undergo facial recognition;

[0194] If so, then generate the facial recognition request.

[0195] In the embodiments of this specification, determining whether the current user needs to undergo facial recognition based on the second recognition result includes:

[0196] The user's voice information corresponding to the second recognition result is input into a pre-trained semantic recognition model to obtain the corresponding third recognition result, and based on the third recognition result, it is determined whether the current user needs to undergo facial recognition.

[0197] In the embodiments of this specification, determining the target users among the current users who need to undergo facial recognition based on the current user's facial recognition intention information includes:

[0198] The facial recognition intention information of the current user is input into a pre-trained intention recognition model to obtain information about the target users among the current users who need to undergo facial recognition.

[0199] The embodiments in this specification also include:

[0200] Acquire historical facial recognition intention information from multiple different users, wherein the historical facial recognition intention information includes one or more of the following: historical lip reading information, historical facial location information, and historical facial pose information from multiple different users;

[0201] The intention recognition model is trained using the historical facial recognition intention information to obtain the trained intention recognition model.

[0202] Furthermore, specifically in this embodiment, the facial recognition device includes a memory and one or more programs, wherein one or more programs are stored in the memory, and one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the facial recognition device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following:

[0203] Upon receiving a facial recognition request, the system obtains the current user's facial recognition intention information, which includes one or more of the current user's lip reading information, facial position information, and facial pose information.

[0204] The facial recognition intention information of the current user is provided to a preset blockchain system, so that the blockchain system can identify and process the facial recognition intention information of the current user through a pre-deployed smart contract to obtain the target users among the current users who need to undergo facial recognition.

[0205] The system receives information about the target user sent by the blockchain system and performs facial recognition processing corresponding to the facial recognition request on the target user.

[0206] In addition, specifically in this embodiment, the facial recognition device includes a memory and one or more programs, wherein one or more programs are stored in the memory, and one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the facial recognition device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following:

[0207] The system receives facial recognition intention information of the current user sent by the facial recognition device. The facial recognition intention information of the current user is information obtained by the facial recognition device when it receives a facial recognition request. The facial recognition intention information includes one or more of the current user's lip reading information, facial position information, and facial pose information.

[0208] The facial recognition intention information of the current user is identified and processed based on a pre-deployed first smart contract to obtain the target users among the current users who need to undergo facial recognition. The first smart contract is used to trigger the facial recognition intention information of the current user.

[0209] The information of the target user is sent to the facial recognition device so that the facial recognition device performs facial recognition processing corresponding to the facial recognition request for the target user.

[0210] In this embodiment of the specification, the step of identifying and processing the facial recognition intention information of the current user based on a pre-deployed first smart contract to obtain the target users among the current users who need to undergo facial recognition includes:

[0211] Based on the first smart contract, the index information of the pre-trained intention recognition model is obtained from the blockchain system, and the intention recognition model is obtained based on the index information;

[0212] Based on the first smart contract, the facial recognition intention information of the current user is input into a pre-trained intention recognition model to obtain the information of the target users among the current users who need to undergo facial recognition.

[0213] The embodiments in this specification also include:

[0214] Receive the lip reading information and voice information of the current user collected by the facial recognition device through the camera component;

[0215] Based on a pre-deployed second smart contract, the index information of a pre-trained lip reading model and the index information of a pre-trained speech recognition model are obtained from the blockchain system, and the lip reading model and speech recognition model are obtained based on the obtained index information. The second smart contract is used to trigger the recognition processing of the current user's lip reading information and speech information.

[0216] Based on the second smart contract, the lip reading information is input into the lip reading model, and the current user's voice information is input into the voice recognition model to obtain the recognition result corresponding to the lip reading information and the recognition result corresponding to the voice information, respectively.

[0217] The recognition results corresponding to the lip reading information and the recognition results corresponding to the voice information are sent to the facial recognition device so that the facial recognition device can determine whether the current user needs to perform facial recognition based on the recognition results corresponding to the lip reading information and the recognition results corresponding to the voice information. If it is determined that the current user needs to perform facial recognition, the facial recognition request is generated.

[0218] The embodiments in this specification also include:

[0219] The system receives a facial recognition request from the target user sent by the facial recognition device, the facial recognition request including a facial image of the target user captured by the facial recognition device.

[0220] Based on a pre-deployed third smart contract and the facial image, the target user is authenticated to obtain the corresponding authentication result. The third smart contract is used to trigger the authentication of the user who initiates facial recognition.

[0221] The authentication result is sent to the facial recognition device.

[0222] This specification provides a facial recognition device that, upon receiving a facial recognition request, acquires the current user's facial recognition intention information. This intention information includes one or more of the current user's lip reading information, facial position information, and facial pose information. Then, based on this intention information, it can determine the target user among the current users who needs facial recognition, and perform facial recognition processing corresponding to the request on the target user. This provides a facial recognition intention recognition method based on the fusion of the user's lip reading, facial position, and facial pose information. This not only accurately identifies the user who truly needs facial recognition among multiple different users within the camera's field of view, improving facial recognition efficiency, but also enriches the user's facial recognition interactive experience and avoids risks associated with user intention. Furthermore, a facial recognition mechanism supporting lip reading wake-up and intention recognition is also provided.

[0223] Example 10

[0224] Furthermore, based on the above Figure 1 and Figure 5 The method shown in this specification, along with one or more embodiments, also provides a storage medium for storing computer-executable instruction information. In one specific embodiment, the storage medium can be a USB flash drive, optical disc, hard disk, etc. When the computer-executable instruction information stored in the storage medium is executed by a processor, it can achieve the following process:

[0225] Upon receiving a facial recognition request, the system obtains the current user's facial recognition intention information, which includes one or more of the current user's lip reading information, facial position information, and facial pose information.

[0226] Based on the current user's facial recognition intention information, the target users among the current users who need to undergo facial recognition are identified;

[0227] Perform facial recognition processing corresponding to the facial recognition request on the target user.

[0228] The embodiments in this specification also include:

[0229] The camera component captures the current user's lip-reading information.

[0230] The lip reading information is input into a pre-trained lip reading model to determine whether the current user needs facial recognition.

[0231] If so, then generate the facial recognition request.

[0232] The embodiments in this specification also include:

[0233] The camera component captures the lip-reading information of the current user and also captures the voice information of the current user.

[0234] The lip reading information is input into a pre-trained lip reading model, and the current user's voice information is input into a pre-trained speech recognition model to obtain the recognition results corresponding to the lip reading information and the recognition results corresponding to the voice information, respectively.

[0235] Based on the recognition results corresponding to the lip reading information and the recognition results corresponding to the voice information, determine whether the current user needs to undergo facial recognition.

[0236] If so, then generate the facial recognition request.

[0237] The embodiments in this specification also include:

[0238] The camera component captures the lip-reading information of the current user and also captures the voice information of the current user.

[0239] The lip reading information is input into a pre-trained lip reading model to obtain the first recognition result corresponding to the lip reading information;

[0240] The user's voice information corresponding to the first recognition result is input into a pre-trained voice recognition model to obtain the second recognition result;

[0241] Based on the second recognition result, determine whether the current user needs to undergo facial recognition;

[0242] If so, then generate the facial recognition request.

[0243] In the embodiments of this specification, determining whether the current user needs to undergo facial recognition based on the second recognition result includes:

[0244] The user's voice information corresponding to the second recognition result is input into a pre-trained semantic recognition model to obtain the corresponding third recognition result, and based on the third recognition result, it is determined whether the current user needs to undergo facial recognition.

[0245] In the embodiments of this specification, determining the target users among the current users who need to undergo facial recognition based on the current user's facial recognition intention information includes:

[0246] The facial recognition intention information of the current user is input into a pre-trained intention recognition model to obtain information about the target users among the current users who need to undergo facial recognition.

[0247] The embodiments in this specification also include:

[0248] Acquire historical facial recognition intention information from multiple different users, wherein the historical facial recognition intention information includes one or more of the following: historical lip reading information, historical facial location information, and historical facial pose information from multiple different users;

[0249] The intention recognition model is trained using the historical facial recognition intention information to obtain the trained intention recognition model.

[0250] In another specific embodiment, the storage medium can be a USB flash drive, optical disc, hard disk, etc. When the computer-executable instruction information stored in the storage medium is executed by the processor, it can realize the following process:

[0251] Upon receiving a facial recognition request, the system obtains the current user's facial recognition intention information, which includes one or more of the current user's lip reading information, facial position information, and facial pose information.

[0252] The facial recognition intention information of the current user is provided to a preset blockchain system, so that the blockchain system can identify and process the facial recognition intention information of the current user through a pre-deployed smart contract to obtain the target users among the current users who need to undergo facial recognition.

[0253] The system receives information about the target user sent by the blockchain system and performs facial recognition processing corresponding to the facial recognition request on the target user.

[0254] In another specific embodiment, the storage medium can be a USB flash drive, optical disc, hard disk, etc., and the computer-executable instruction information stored in the storage medium can achieve the following process when executed by the processor:

[0255] The system receives facial recognition intention information of the current user sent by the facial recognition device. The facial recognition intention information of the current user is information obtained by the facial recognition device when it receives a facial recognition request. The facial recognition intention information includes one or more of the current user's lip reading information, facial position information, and facial pose information.

[0256] The facial recognition intention information of the current user is identified and processed based on a pre-deployed first smart contract to obtain the target users among the current users who need to undergo facial recognition. The first smart contract is used to trigger the facial recognition intention information of the current user.

[0257] The information of the target user is sent to the facial recognition device so that the facial recognition device performs facial recognition processing corresponding to the facial recognition request for the target user.

[0258] In this embodiment of the specification, the step of identifying and processing the facial recognition intention information of the current user based on a pre-deployed first smart contract to obtain the target users among the current users who need to undergo facial recognition includes:

[0259] Based on the first smart contract, the index information of the pre-trained intention recognition model is obtained from the blockchain system, and the intention recognition model is obtained based on the index information;

[0260] Based on the first smart contract, the facial recognition intention information of the current user is input into a pre-trained intention recognition model to obtain the information of the target users among the current users who need to undergo facial recognition.

[0261] The embodiments in this specification also include:

[0262] Receive the lip reading information and voice information of the current user collected by the facial recognition device through the camera component;

[0263] Based on a pre-deployed second smart contract, the index information of a pre-trained lip reading model and the index information of a pre-trained speech recognition model are obtained from the blockchain system, and the lip reading model and speech recognition model are obtained based on the obtained index information. The second smart contract is used to trigger the recognition processing of the current user's lip reading information and speech information.

[0264] Based on the second smart contract, the lip reading information is input into the lip reading model, and the current user's voice information is input into the voice recognition model to obtain the recognition result corresponding to the lip reading information and the recognition result corresponding to the voice information, respectively.

[0265] The recognition results corresponding to the lip reading information and the recognition results corresponding to the voice information are sent to the facial recognition device so that the facial recognition device can determine whether the current user needs to perform facial recognition based on the recognition results corresponding to the lip reading information and the recognition results corresponding to the voice information. If it is determined that the current user needs to perform facial recognition, the facial recognition request is generated.

[0266] The embodiments in this specification also include:

[0267] The system receives a facial recognition request from the target user sent by the facial recognition device, the facial recognition request including a facial image of the target user captured by the facial recognition device.

[0268] Based on a pre-deployed third smart contract and the facial image, the target user is authenticated to obtain the corresponding authentication result. The third smart contract is used to trigger the authentication of the user who initiates facial recognition.

[0269] The authentication result is sent to the facial recognition device.

[0270] This specification provides a storage medium that, upon receiving a facial recognition request, acquires the current user's facial recognition intention information. This intention information includes one or more of the current user's lip-reading information, facial position information, and facial pose information. Then, based on this intention information, it can determine the target user among the current users who needs facial recognition, and perform facial recognition processing corresponding to the request on the target user. This provides a facial recognition intention recognition method based on the fusion of the user's lip-reading, facial position, and facial pose information. This method not only accurately identifies the user who truly needs facial recognition among multiple different users within the camera's field of view, improving facial recognition efficiency, but also enriches the user's facial recognition interactive experience and mitigates the risks associated with user intention. Furthermore, a facial recognition mechanism supporting lip-reading wake-up and intention recognition is also provided.

[0271] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0272] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using a hardware physical module. For example, a Programmable Logic Device (PLD) (e.g., a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program a digital system themselves to "integrate" it onto a PLD, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0273] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, ASICs, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0274] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0275] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0276] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, one or more embodiments of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0277] Embodiments in this specification are described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable parallel device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable parallel device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0278] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable fraud device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0279] These computer program instructions can also be loaded onto a computer or other programmable device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable device for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0280] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0281] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0282] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0283] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0284] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, one or more embodiments of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0285] One or more embodiments of this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a particular task or implement a particular abstract data type. One or more embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0286] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0287] The above description is merely an embodiment of this specification and is not intended to limit this specification. Various modifications and variations can be made to this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of the claims of this specification.

Claims

1. A facial recognition method, the method comprising: The camera component captures the lip-reading information of the current user and also captures the voice information of the current user. The lip reading information is input into a pre-trained lip reading model to obtain the first recognition result corresponding to the lip reading information; The user's voice information corresponding to the first recognition result is input into a pre-trained voice recognition model to obtain the second recognition result; Based on whether the second recognition result is a specified instruction word, determine whether the current user needs to undergo facial recognition; If so, generate a facial recognition request; Upon receiving a facial recognition request, the system obtains the current user's facial recognition intention information, which includes the current user's lip reading information, or includes the current user's lip reading information, and also includes one or more of facial position information and facial pose information. Based on the lip-reading information of the current user in the facial recognition intention information, the speech content of the current user is determined. Based on the matching between the speech content of the current user and the specified keywords, the target user among the current users who needs to undergo facial recognition is determined. Alternatively, based on the facial recognition intention information of the current user, the target user among the current users who needs to undergo facial recognition is determined through a pre-trained intention recognition model. The intention recognition model is obtained by training the model with historical facial recognition intention information, which includes one or more of the following: historical lip-reading information, historical facial position information, and historical facial pose information of multiple different users. Perform facial recognition processing corresponding to the facial recognition request on the target user.

2. The method according to claim 1, wherein determining whether the current user needs to undergo facial recognition based on the second recognition result includes: The user's voice information corresponding to the second recognition result is input into a pre-trained semantic recognition model to obtain the corresponding third recognition result, and based on the third recognition result, it is determined whether the current user needs to undergo facial recognition.

3. The method according to claim 1, wherein determining the target users among the current users who need to undergo facial recognition based on the facial recognition intention information of the current user and through a pre-trained intention recognition model includes: The facial recognition intention information of the current user is input into a pre-trained intention recognition model to obtain information about the target users among the current users who need to undergo facial recognition.

4. The method according to claim 3, further comprising: Acquire historical facial recognition intention information from multiple different users, wherein the historical facial recognition intention information includes one or more of the following: historical lip reading information, historical facial location information, and historical facial pose information from multiple different users; The intention recognition model is trained using the historical facial recognition intention information to obtain the trained intention recognition model.

5. A facial recognition method, the method comprising: Upon receiving a facial recognition request, the system acquires the current user's facial recognition intention information. This intention information includes the current user's lip-reading information, or includes the current user's lip-reading information, and also includes one or more of facial position information and facial posture information. The facial recognition request is initiated when the blockchain system receives the current user's lip-reading information and voice information collected by the facial recognition device through its camera component. Based on a pre-deployed second smart contract, the system acquires the index information of a pre-trained lip-reading model and the index information of a pre-trained voice recognition model from the blockchain system, and acquires the lip-reading model and the voice recognition model based on the acquired index information. The second smart contract is used to trigger the recognition processing of the current user's lip-reading information and voice information. Based on the second smart contract, the above lip reading information is input into a pre-trained lip reading model to obtain the first recognition result corresponding to the lip reading information; Based on the second smart contract, the user's voice information corresponding to the first recognition result is input into a pre-trained voice recognition model to obtain the second recognition result. The second recognition result is then sent to the facial recognition device so that the facial recognition device can determine whether the current user needs to undergo facial recognition based on whether the second recognition result is a specified instruction word. The current user's facial recognition intention information is provided to a pre-defined blockchain system. The blockchain system, through a pre-deployed smart contract, determines the current user's speech content based on the user's lip-reading information within the facial recognition intention information. Based on the matching between the current user's speech content and specified keywords, it identifies target users among the current users who require facial recognition. Alternatively, based on the current user's facial recognition intention information, a pre-trained intention recognition model is used to identify target users among the current users who require facial recognition. This intention recognition model is trained using historical facial recognition intention information, which includes one or more of the following: historical lip-reading information, historical facial position information, and historical facial pose information from multiple different users. The system receives information about the target user sent by the blockchain system and performs facial recognition processing corresponding to the facial recognition request on the target user.

6. A facial recognition method applied to a blockchain system, the method comprising: Receive lip reading information and voice information of the current user collected by the facial recognition device through the camera component; Based on a pre-deployed second smart contract, the index information of the pre-trained lip reading model and the index information of the pre-trained speech recognition model are obtained from the blockchain system, and the lip reading model and speech recognition model are obtained based on the obtained index information. The second smart contract is used to trigger the recognition and processing of the current user's lip reading information and speech information. Based on the second smart contract, the above lip reading information is input into a pre-trained lip reading model to obtain the first recognition result corresponding to the lip reading information; Based on the second smart contract, the user's voice information corresponding to the first recognition result is input into a pre-trained voice recognition model to obtain the second recognition result. The second recognition result is then sent to the facial recognition device so that the facial recognition device can determine whether the current user needs to undergo facial recognition based on whether the second recognition result is a specified instruction word. The device receives facial recognition intention information of the current user sent by the facial recognition device. The facial recognition intention information of the current user is information obtained by the facial recognition device when it receives a facial recognition request. The facial recognition intention information includes the lip reading information of the current user, or includes the lip reading information of the current user, and also includes one or more of facial position information and facial posture information. Based on a pre-deployed first smart contract and the current user's lip reading information from the current user's facial recognition intention information, the current user's speech content is determined. Based on the matching between the current user's speech content and specified keywords, the target user among the current users who needs to undergo facial recognition is determined. Alternatively, based on the current user's facial recognition intention information, the target user among the current users who needs to undergo facial recognition is determined through a pre-trained intention recognition model. The intention recognition model is obtained by training the model using historical facial recognition intention information, which includes one or more of the following: historical lip reading information, historical facial position information, and historical facial pose information from multiple different users. The first smart contract is used to trigger the recognition processing of the current user's facial recognition intention information. The information of the target user is sent to the facial recognition device so that the facial recognition device performs facial recognition processing corresponding to the facial recognition request for the target user.

7. The method according to claim 6, wherein, based on a pre-deployed first smart contract and the facial recognition intention information of the current user, a pre-trained intention recognition model is used to determine the target user among the current users who needs to undergo facial recognition, comprising: Based on the first smart contract, the index information of the pre-trained intention recognition model is obtained from the blockchain system, and the intention recognition model is obtained based on the index information; Based on the first smart contract, the facial recognition intention information of the current user is input into a pre-trained intention recognition model to obtain the information of the target users among the current users who need to undergo facial recognition.

8. The method according to claim 6, further comprising: The system receives a facial recognition request from the target user sent by the facial recognition device, the facial recognition request including a facial image of the target user captured by the facial recognition device. Based on a pre-deployed third smart contract and the facial image, the target user is authenticated to obtain the corresponding authentication result. The third smart contract is used to trigger the authentication of the user who initiates facial recognition. The authentication result is sent to the facial recognition device.

9. A facial recognition device, the device comprising: The third information acquisition module acquires the current user's lip reading information and voice information through a camera component; The second recognition module inputs the lip reading information into a pre-trained lip reading model to obtain the first recognition result corresponding to the lip reading information; The third recognition module inputs the user's voice information corresponding to the first recognition result into a pre-trained voice recognition model to obtain the second recognition result; The third identification and determination module determines whether the current user needs to undergo facial recognition based on whether the second identification result is a specified instruction word. The third request generation module generates a facial recognition request if the request is yes. The willingness information acquisition module, upon receiving a facial recognition request, acquires the facial recognition willingness information of the current user. The facial recognition willingness information includes the lip reading information of the current user, or includes the lip reading information of the current user, and also includes one or more of facial position information and facial posture information. The user identification module determines the current user's speech content based on the current user's lip-reading information in the current user's facial recognition intention information. Based on the matching between the current user's speech content and specified keywords, it identifies the target users among the current users who need to undergo facial recognition. Alternatively, based on the current user's facial recognition intention information, it identifies the target users among the current users who need to undergo facial recognition through a pre-trained intention recognition model. The intention recognition model is trained using historical facial recognition intention information, which includes one or more of the following: historical lip-reading information, historical facial position information, and historical facial pose information from multiple different users. The facial recognition module performs facial recognition processing corresponding to the facial recognition request for the target user.

10. A facial recognition device, the device comprising: The information acquisition module, upon receiving a facial recognition request, acquires the current user's facial recognition intention information. This intention information includes the current user's lip-reading information, or includes the current user's lip-reading information, and also includes one or more of facial position information and facial posture information. The facial recognition request is initiated by the blockchain system receiving the current user's lip-reading information and voice information collected by the facial recognition device through its camera component. Based on a pre-deployed second smart contract, the module acquires the index information of a pre-trained lip-reading model and the index information of a pre-trained voice recognition model from the blockchain system, and acquires the lip-reading model and voice recognition model based on the acquired index information. The second smart contract is used to trigger the recognition processing of the current user's lip-reading information and voice information. Based on the second smart contract, the above lip reading information is input into a pre-trained lip reading model to obtain the first recognition result corresponding to the lip reading information; Based on the second smart contract, the user's voice information corresponding to the first recognition result is input into a pre-trained voice recognition model to obtain the second recognition result. The second recognition result is then sent to the facial recognition device so that the facial recognition device can determine whether the current user needs to undergo facial recognition based on whether the second recognition result is a specified instruction word. The information providing module provides the current user's facial recognition intention information to a preset blockchain system. The blockchain system, through a pre-deployed smart contract, determines the current user's speech content based on the user's lip-reading information within the facial recognition intention information. Based on the matching between the current user's speech content and specified keywords, it identifies target users among the current users who require facial recognition. Alternatively, based on the current user's facial recognition intention information, it identifies target users among the current users who require facial recognition through a pre-trained intention recognition model. This intention recognition model is trained using historical facial recognition intention information, which includes one or more of the following: historical lip-reading information, historical facial position information, and historical facial posture information from multiple different users. The information receiving module receives the information of the target user sent by the blockchain system and performs facial recognition processing corresponding to the facial recognition request on the target user.

11. A facial recognition device, the device comprising: The device receives lip reading information and voice information of the current user collected by the facial recognition device through the camera component; Based on a pre-deployed second smart contract, the index information of the pre-trained lip reading model and the index information of the pre-trained speech recognition model are obtained from the blockchain system, and the lip reading model and speech recognition model are obtained based on the obtained index information. The second smart contract is used to trigger the recognition and processing of the current user's lip reading information and speech information. Based on the second smart contract, the above lip reading information is input into a pre-trained lip reading model to obtain the first recognition result corresponding to the lip reading information; Based on the second smart contract, the user's voice information corresponding to the first recognition result is input into a pre-trained voice recognition model to obtain the second recognition result. The second recognition result is then sent to the facial recognition device so that the facial recognition device can determine whether the current user needs to undergo facial recognition based on whether the second recognition result is a specified instruction word. The information receiving module receives the facial recognition intention information of the current user sent by the facial recognition device. The facial recognition intention information of the current user is the information obtained by the facial recognition device when it receives a facial recognition request. The facial recognition intention information includes the lip reading information of the current user, or includes the lip reading information of the current user, and also includes one or more of facial position information and facial posture information. The intention recognition module determines the current user's speech content based on a pre-deployed first smart contract and the current user's lip-reading information in the current user's facial recognition intention information. Based on the matching between the current user's speech content and specified keywords, it determines the target user among the current users who needs to undergo facial recognition. Alternatively, based on the current user's facial recognition intention information, it determines the target user among the current users who needs to undergo facial recognition through a pre-trained intention recognition model. The intention recognition model is obtained by training the model using historical facial recognition intention information, which includes one or more of the following: historical lip-reading information, historical facial position information, and historical facial pose information from multiple different users. The first smart contract is used to trigger the recognition processing of the current user's facial recognition intention information. The information sending module sends the target user's information to the facial recognition device, so that the facial recognition device performs facial recognition processing corresponding to the facial recognition request on the target user.

12. A facial recognition device, the facial recognition device comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to: The camera component captures the lip-reading information of the current user and also captures the voice information of the current user. The lip reading information is input into a pre-trained lip reading model to obtain the first recognition result corresponding to the lip reading information; The user's voice information corresponding to the first recognition result is input into a pre-trained voice recognition model to obtain the second recognition result; Based on whether the second recognition result is a specified instruction word, determine whether the current user needs to undergo facial recognition; If so, generate a facial recognition request; Upon receiving a facial recognition request, the system obtains the current user's facial recognition intention information, which includes the current user's lip reading information, or includes the current user's lip reading information, and also includes one or more of facial position information and facial pose information. Based on the lip-reading information of the current user in the facial recognition intention information, the speech content of the current user is determined. Based on the matching between the speech content of the current user and the specified keywords, the target user among the current users who needs to undergo facial recognition is determined. Alternatively, based on the facial recognition intention information of the current user, the target user among the current users who needs to undergo facial recognition is determined through a pre-trained intention recognition model. The intention recognition model is obtained by training the model with historical facial recognition intention information, which includes one or more of the following: historical lip-reading information, historical facial position information, and historical facial pose information of multiple different users. Perform facial recognition processing corresponding to the facial recognition request on the target user.

13. A storage medium for storing computer-executable instructions, which, when executed, perform the following process: The camera component captures the lip-reading information of the current user and also captures the voice information of the current user. The lip reading information is input into a pre-trained lip reading model to obtain the first recognition result corresponding to the lip reading information; The user's voice information corresponding to the first recognition result is input into a pre-trained voice recognition model to obtain the second recognition result; Based on whether the second recognition result is a specified instruction word, determine whether the current user needs to undergo facial recognition; If so, generate a facial recognition request; Upon receiving a facial recognition request, the system obtains the current user's facial recognition intention information, which includes the current user's lip reading information, or includes the current user's lip reading information, and also includes one or more of facial position information and facial pose information. Based on the lip-reading information of the current user in the facial recognition intention information, the speech content of the current user is determined. Based on the matching between the speech content of the current user and the specified keywords, the target user among the current users who needs to undergo facial recognition is determined. Alternatively, based on the facial recognition intention information of the current user, the target user among the current users who needs to undergo facial recognition is determined through a pre-trained intention recognition model. The intention recognition model is obtained by training the model with historical facial recognition intention information, which includes one or more of the following: historical lip-reading information, historical facial position information, and historical facial pose information of multiple different users. Perform facial recognition processing corresponding to the facial recognition request on the target user.

14. A facial recognition device, the facial recognition device comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to: Upon receiving a facial recognition request, the system acquires the current user's facial recognition intention information. This intention information includes the current user's lip-reading information, or includes the current user's lip-reading information, and also includes one or more of facial position information and facial posture information. The facial recognition request is initiated when the blockchain system receives the current user's lip-reading information and voice information collected by the facial recognition device through its camera component. Based on a pre-deployed second smart contract, the system acquires the index information of a pre-trained lip-reading model and the index information of a pre-trained voice recognition model from the blockchain system, and acquires the lip-reading model and the voice recognition model based on the acquired index information. The second smart contract is used to trigger the recognition processing of the current user's lip-reading information and voice information. Based on the second smart contract, the above lip reading information is input into a pre-trained lip reading model to obtain the first recognition result corresponding to the lip reading information; Based on the second smart contract, the user's voice information corresponding to the first recognition result is input into a pre-trained voice recognition model to obtain the second recognition result. The second recognition result is then sent to the facial recognition device so that the facial recognition device can determine whether the current user needs to undergo facial recognition based on whether the second recognition result is a specified instruction word. The current user's facial recognition intention information is provided to a pre-defined blockchain system. The blockchain system, through a pre-deployed smart contract, determines the current user's speech content based on the user's lip-reading information within the facial recognition intention information. Based on the matching between the current user's speech content and specified keywords, it identifies target users among the current users who require facial recognition. Alternatively, based on the current user's facial recognition intention information, a pre-trained intention recognition model is used to identify target users among the current users who require facial recognition. This intention recognition model is trained using historical facial recognition intention information, which includes one or more of the following: historical lip-reading information, historical facial position information, and historical facial pose information from multiple different users. The system receives information about the target user sent by the blockchain system and performs facial recognition processing corresponding to the facial recognition request on the target user.

15. A storage medium for storing computer-executable instructions, which, when executed, perform the following process: Upon receiving a facial recognition request, the system acquires the current user's facial recognition intention information. This intention information includes the current user's lip-reading information, or includes the current user's lip-reading information, and also includes one or more of facial position information and facial posture information. The facial recognition request is initiated when the blockchain system receives the current user's lip-reading information and voice information collected by the facial recognition device through its camera component. Based on a pre-deployed second smart contract, the system acquires the index information of a pre-trained lip-reading model and the index information of a pre-trained voice recognition model from the blockchain system, and acquires the lip-reading model and the voice recognition model based on the acquired index information. The second smart contract is used to trigger the recognition processing of the current user's lip-reading information and voice information. Based on the second smart contract, the above lip reading information is input into a pre-trained lip reading model to obtain the first recognition result corresponding to the lip reading information; Based on the second smart contract, the user's voice information corresponding to the first recognition result is input into a pre-trained voice recognition model to obtain the second recognition result. The second recognition result is then sent to the facial recognition device so that the facial recognition device can determine whether the current user needs to undergo facial recognition based on whether the second recognition result is a specified instruction word. The current user's facial recognition intention information is provided to a pre-defined blockchain system. The blockchain system, through a pre-deployed smart contract, determines the current user's speech content based on the user's lip-reading information within the facial recognition intention information. Based on the matching between the current user's speech content and specified keywords, it identifies target users among the current users who require facial recognition. Alternatively, based on the current user's facial recognition intention information, a pre-trained intention recognition model is used to identify target users among the current users who require facial recognition. This intention recognition model is trained using historical facial recognition intention information, which includes one or more of the following: historical lip-reading information, historical facial position information, and historical facial pose information from multiple different users. The system receives information about the target user sent by the blockchain system and performs facial recognition processing corresponding to the facial recognition request on the target user.

16. A facial recognition device, the facial recognition device comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to: Receive lip reading information and voice information of the current user collected by the facial recognition device through the camera component; Based on a pre-deployed second smart contract, the index information of the pre-trained lip reading model and the index information of the pre-trained speech recognition model are obtained from the blockchain system, and the lip reading model and speech recognition model are obtained based on the obtained index information. The second smart contract is used to trigger the recognition and processing of the current user's lip reading information and speech information. Based on the second smart contract, the above lip reading information is input into a pre-trained lip reading model to obtain the first recognition result corresponding to the lip reading information; Based on the second smart contract, the user's voice information corresponding to the first recognition result is input into a pre-trained voice recognition model to obtain the second recognition result. The second recognition result is then sent to the facial recognition device so that the facial recognition device can determine whether the current user needs to undergo facial recognition based on whether the second recognition result is a specified instruction word. The device receives facial recognition intention information of the current user sent by the facial recognition device. The facial recognition intention information of the current user is information obtained by the facial recognition device when it receives a facial recognition request. The facial recognition intention information includes the lip reading information of the current user, or includes the lip reading information of the current user, and also includes one or more of facial position information and facial posture information. Based on a pre-deployed first smart contract and the current user's lip reading information from the current user's facial recognition intention information, the current user's speech content is determined. Based on the matching between the current user's speech content and specified keywords, the target user among the current users who needs to undergo facial recognition is determined. Alternatively, based on the current user's facial recognition intention information, the target user among the current users who needs to undergo facial recognition is determined through a pre-trained intention recognition model. The intention recognition model is obtained by training the model using historical facial recognition intention information, which includes one or more of the following: historical lip reading information, historical facial position information, and historical facial pose information from multiple different users. The first smart contract is used to trigger the recognition processing of the current user's facial recognition intention information. The information of the target user is sent to the facial recognition device so that the facial recognition device performs facial recognition processing corresponding to the facial recognition request for the target user.

17. A storage medium for storing computer-executable instructions, which, when executed, perform the following process: Receive lip reading information and voice information of the current user collected by the facial recognition device through the camera component; Based on a pre-deployed second smart contract, the index information of the pre-trained lip reading model and the index information of the pre-trained speech recognition model are obtained from the blockchain system, and the lip reading model and speech recognition model are obtained based on the obtained index information. The second smart contract is used to trigger the recognition and processing of the current user's lip reading information and speech information. Based on the second smart contract, the above lip reading information is input into a pre-trained lip reading model to obtain the first recognition result corresponding to the lip reading information; Based on the second smart contract, the user's voice information corresponding to the first recognition result is input into a pre-trained voice recognition model to obtain the second recognition result. The second recognition result is then sent to the facial recognition device so that the facial recognition device can determine whether the current user needs to undergo facial recognition based on whether the second recognition result is a specified instruction word. The device receives facial recognition intention information of the current user sent by the facial recognition device. The facial recognition intention information of the current user is information obtained by the facial recognition device when it receives a facial recognition request. The facial recognition intention information includes the lip reading information of the current user, or includes the lip reading information of the current user, and also includes one or more of facial position information and facial posture information. Based on a pre-deployed first smart contract and the current user's lip reading information from the current user's facial recognition intention information, the current user's speech content is determined. Based on the matching between the current user's speech content and specified keywords, the target user among the current users who needs to undergo facial recognition is determined. Alternatively, based on the current user's facial recognition intention information, the target user among the current users who needs to undergo facial recognition is determined through a pre-trained intention recognition model. The intention recognition model is obtained by training the model using historical facial recognition intention information, which includes one or more of the following: historical lip reading information, historical facial position information, and historical facial pose information from multiple different users. The first smart contract is used to trigger the recognition processing of the current user's facial recognition intention information. The information of the target user is sent to the facial recognition device so that the facial recognition device performs facial recognition processing corresponding to the facial recognition request for the target user.

Images