Method for identifying users on public equipment and electronic equipment

Abstract

A method and electronic device for identifying users on a public device relate to the field of smart devices. The method can avoid users from frequently logging into their accounts or pre-entering biometrics when using a public device. The public device can automatically identify the identity of the user, thereby improving the interaction efficiency between multiple users and the public device. The method specifically includes: the public device obtains biometric data of multiple users, and sends at least part of the biometric data of the multiple users to a private device associated with the public device, the private device having a first biometric model of a first user, and the private device identifies the biometric data corresponding to the first user. Then, the public device learns a second biometric model corresponding to the first user based on the biometric data identified as corresponding to the first user, for use in identifying the first user.

Description

Technical Field

[0001] The present application relates to the field of smart devices, and in particular to a method for identifying a user on a public device and an electronic device. Background Art

[0002] With the development of smart devices, more and more smart devices are becoming part of users' daily lives. Some smart devices are privately owned by users, such as mobile phones, PCs, and smart wearable devices. Other smart devices are shared by multiple users, known as public devices, such as TVs, smart speakers, and in-car devices. As you can imagine, the user interaction and user experience on public devices are generally different from those on private devices.

[0003] Typically, public devices use a multi-account management method. That is, during the initialization of the public device (i.e., first use) or subsequent use (i.e., non-first use), new users are added by adding accounts. The public device will associate the added account with the user behavior under that account. Because public devices are multi-user, users need to frequently enter their account and password before using the public device, which is cumbersome.

[0004] To simplify the frequent entry of user IDs and passwords, in addition to multi-account management, users of each account can be required to register biometric features such as fingerprints, voiceprints, or facial features. Public devices can then automatically identify the user's account based on the biometric features they entered, and associate the identified account with the user's behavior. While this eliminates the need for users to enter their IDs and passwords when using public devices, they still need to pre-register their account and bind their biometric features, resulting in a poor user experience. Summary of the Invention

[0005] The present application provides a method for identifying users on a public device, which can avoid users from frequently logging into their accounts or pre-entering biometrics when using a public device, automatically identify the user's identity, and improve the interaction efficiency between multiple users and the public device.

[0006] In order to achieve the above objectives, the embodiments of the present application provide the following technical solutions:

[0007] In a first aspect, a system for identifying user identity on a public device is provided, the system comprising a first device and a second device associated with the first device, the second device storing a first biometric model corresponding to the first user; the first device is configured to obtain biometric data of a plurality of users; the first device is further configured to send at least part of the biometric data of the plurality of users to the second device; the second device is configured to identify the biometric data corresponding to the first user from at least part of the data based on the first biometric model; the second device is configured to send the identification result to the first device; and the first device is configured to learn a second biometric model corresponding to the first user based on the identification result.

[0008] For example, when multiple users alternately use a first device (i.e., a public device), the first device may record various types of user data (and biometric data) containing biometric features of the multiple users using the public device. The biometric data may be raw data received by the first device, such as a facial image captured by a camera, a fingerprint image captured by a fingerprint reader, or voice captured by an audio module. The biometric data may also be data processed by the first device based on the received raw data, such as facial features recognized from a facial image captured by a camera, or voiceprint features obtained from voice.

[0009] In summary, on electronic devices used by multiple users, multiple users do not need to register accounts or log in to the same account. Public devices can use private devices with user identification capabilities to identify biometric data on the public device, and then learn the biometric data of the identified user to obtain a biometric model of the user for subsequent identification of the user. It can be seen that the method provided in the embodiments of the present application can identify user identities without the user's perception, simplify the user's operation of using public devices, and improve the efficiency of interaction between multiple users and public devices.

[0010] In one possible implementation, the first device is further used to receive an operation after learning a second biometric model corresponding to the first user based on the recognition result; when it is determined that an operation corresponds to the first user based on the learned second biometric model, the first function is executed; when it is determined that an operation does not correspond to the first user based on the learned second biometric model, the second function is executed, wherein the first function is different from the second function.

[0011] It can be seen that public equipment can automatically identify user identities, provide personalized services to different users, and improve the efficiency of interaction between users and public equipment.

[0012] In one possible implementation, the association between the second device and the first device includes any one or more of the following: the first device and the second device have logged in to the same account, the first device and the second device are connected to the same wireless network, the account logged in by the first device and the account logged in by the second device belong to the same group, and the first device and the second device have established a communication connection.

[0013] In a possible implementation, the first biometric feature includes one or more of a voice feature, an image feature, and a behavior feature of the first user.

[0014] In one possible implementation, the voice features include voiceprint features and / or timbre features, the image features include one or more of facial features, iris features, fingerprint features, and palm print features, and the behavioral features include any one of the force features of pressing or clicking the screen and the trajectory features of the sliding operation.

[0015] In one possible implementation, sending at least part of the biometric data of multiple users to a second device includes: dividing the biometric data of the multiple users into multiple clusters, each of the multiple clusters corresponding to one user; and sending the biometric data corresponding to one or more of the multiple clusters to the second device.

[0016] In other words, clustering algorithms can be used to initially segment user data on public devices into user groups. It's important to note that when setting the clustering threshold, it's important to segment user groups as much as possible without compromising accuracy. This means striking a balance between distinguishing users and fragmenting the clusters. This ensures that each cluster corresponds to only one user, but the same user can be associated with multiple clusters.

[0017] In one specific implementation, the first device sends the biometric data of each cluster to the second device in sequence, and the second device identifies the biometric data in each cluster based on the stored first biometric model to identify whether the biometric data of each cluster corresponds to the first user. Then, the identification results of each cluster are returned to the first device in sequence. At this time, the identification result includes whether the biometric data in the corresponding cluster corresponds to the first user or not. In another example, the first device can send the biometric data of multiple clusters to the second device once or multiple times, and the second device identifies the biometric data in each cluster based on the stored first biometric model to identify whether the biometric data of each cluster corresponds to the first user. Then, the identifier of the cluster corresponding to the first user is returned to the first device. That is, at this time, the identification result includes the identifier of the cluster corresponding to the first user. This application does not limit the way in which the first device sends the biometric data of the cluster to the second device, nor the way in which the second device returns the identification result.

[0018] In one possible implementation, sending biometric data corresponding to one or more clusters from a plurality of clusters to a second device includes: selecting biometric data corresponding to one or more clusters of the same type as the first biometric model from the plurality of clusters, and sending the biometric data to the second device.

[0019] In other words, the public device can also perform an initial classification on the segmented clusters before selectively sending them to the corresponding private devices for feature comparison. For example, the public device can classify user groups based on information such as user gender and age group corresponding to the clusters, and then send each cluster to private devices with the same user group for feature comparison. For another example, the public device can also match different types of clusters to the capabilities of each private device based on their different abilities to identify user identities. In other words, the public device can also select the corresponding type of private device for feature comparison based on the type of each cluster (e.g., voice data type, image data type, behavior data type).

[0020] In one possible implementation, biometric data corresponding to one or more clusters of the same type as the first biometric model are selected from multiple clusters and sent to the second device, including: when the type of the first biometric model is a voice feature class, biometric data corresponding to one or more clusters containing voice data are selected and sent to the second device; when the type of the first biometric model is an image feature class, biometric data corresponding to one or more clusters containing image data are selected and sent to the second device; when the type of the first biometric model is a behavior feature class, biometric data corresponding to one or more clusters containing behavior data are selected and sent to the second device.

[0021] In a second aspect, a method for identifying user identity on a public device is applied to a first device and a second device associated with the first device, wherein the second device stores a first biometric model corresponding to the first user; the method comprises: the first device obtains biometrics of multiple users; the first device sends at least part of the biometric data of the multiple users to the second device; the first device receives an identification result returned by the second device, wherein the identification result is a result of the second device identifying the biometric data corresponding to the first user from at least part of the data according to the first biometric model; and the first device learns a second biometric model corresponding to the first user according to the identification result.

[0022] In one possible implementation, after learning a second biometric model corresponding to the first user based on the recognition result, the first device receives an operation; when it is determined based on the learned second biometric model that an operation corresponds to the first user, the first device executes a first function; when it is determined based on the learned second biometric model that an operation does not correspond to the first user, the first device executes a second function, where the first function is different from the second function.

[0023] In one possible implementation, the association between the second device and the first device includes any one or more of the following: the first device and the second device have logged in to the same account, the first device and the second device are connected to the same wireless network, the account logged in by the first device and the account logged in by the second device belong to the same group, and the first device and the second device have established a communication connection.

[0024] In a possible implementation, the first biometric feature includes one or more of a voice feature, an image feature, and a behavior feature of the first user.

[0025] In one possible implementation, the voice features include voiceprint features and / or timbre features, the image features include one or more of facial features, iris features, fingerprint features, and palm print features, and the behavioral features include any one of the force features of pressing or clicking the screen and the trajectory features of the sliding operation.

[0026] In one possible implementation, sending at least part of the biometric data of multiple users to a second device includes: dividing the biometric data of the multiple users into multiple clusters, each of the multiple clusters corresponding to one user; and sending the biometric data corresponding to one or more of the multiple clusters to the second device.

[0027] In one possible implementation, sending biometric data corresponding to one or more clusters from a plurality of clusters to a second device includes: selecting biometric data corresponding to one or more clusters of the same type as the first biometric model from the plurality of clusters, and sending the biometric data to the second device.

[0028] In one possible implementation, biometric data corresponding to one or more clusters of the same type as the first biometric model are selected from multiple clusters and sent to the second device, including: when the type of the first biometric model is a voice feature class, biometric data corresponding to one or more clusters containing voice data are selected and sent to the second device; when the type of the first biometric model is an image feature class, biometric data corresponding to one or more clusters containing image data are selected and sent to the second device; when the type of the first biometric model is a behavior feature class, biometric data corresponding to one or more clusters containing behavior data are selected and sent to the second device.

[0029] According to a third aspect, an electronic device is provided, comprising: a processor, a memory, and a touch screen, wherein the memory and the touch screen are coupled to the processor, and the memory is used to store computer program code, wherein the computer program code includes computer instructions. When the processor reads the computer instructions from the memory, the electronic device performs the following operations: obtaining biometric features of multiple users; sending at least part of the biometric data of the multiple users to another electronic device associated with the electronic device, wherein the other electronic device stores a first biometric module corresponding to the first user; receiving an identification result returned by the other electronic device, wherein the identification result is a result of the other electronic device identifying the biometric data corresponding to the first user from at least part of the data according to the first biometric model; and learning a second biometric model corresponding to the first user according to the identification result.

[0030] In one possible implementation, when the processor reads computer instructions from the memory, it also causes the electronic device to perform the following operations: after learning a second biometric model corresponding to the first user based on the recognition result, an operation is received; when it is determined that an operation corresponds to the first user based on the learned second biometric model, a first function is executed; when it is determined that an operation does not correspond to the first user based on the learned second biometric model, a second function is executed, where the first function is different from the second function.

[0031] In one possible implementation, the association between another electronic device and the electronic device includes any one or more of the following: the electronic device and the other electronic device have logged in to the same account, the electronic device and the other electronic device are connected to the same wireless network, the account logged in to the electronic device and the account logged in to the other electronic device belong to the same group, and the electronic device and the other electronic device have established a communication connection.

[0032] In a possible implementation, the first biometric feature includes one or more of a voice feature, an image feature, and a behavior feature of the first user.

[0033] In one possible implementation, the voice features include voiceprint features and / or timbre features, the image features include one or more of facial features, iris features, fingerprint features, and palm print features, and the behavioral features include any one of the force features of pressing or clicking the screen and the trajectory features of the sliding operation.

[0034] In one possible implementation, sending at least part of the biometric data of multiple users to another electronic device includes: dividing the biometric data of the multiple users into multiple clusters, each of the multiple clusters corresponding to one user; and sending the biometric data corresponding to one or more of the multiple clusters to the other electronic device.

[0035] In one possible implementation, sending biometric data corresponding to one or more clusters among multiple clusters to another electronic device includes: selecting biometric data corresponding to one or more clusters of the same type as the first biometric model from the multiple clusters, and sending the biometric data to the other electronic device.

[0036] In one possible implementation, biometric data corresponding to one or more clusters of the same type as the first biometric model are selected from multiple clusters and sent to another electronic device, including: when the type of the first biometric model is a voice feature class, biometric data corresponding to one or more clusters containing voice data are selected and sent to another electronic device; when the type of the first biometric model is an image feature class, biometric data corresponding to one or more clusters containing image data are selected and sent to another electronic device; when the type of the first biometric model is a behavior feature class, biometric data corresponding to one or more clusters containing behavior data are selected and sent to another electronic device.

[0037] In a fourth aspect, a device is provided, which is included in an electronic device and has the function of implementing the electronic device behavior described in any of the above aspects and possible implementations. This function can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes at least one module or unit corresponding to the above function. For example, a receiving module or unit, a display module or unit, and a processing module or unit.

[0038] In a fifth aspect, a computer-readable storage medium is provided, comprising computer instructions. When the computer instructions are executed on a terminal, the terminal executes the method as described in the above aspects and any possible implementation thereof.

[0039] In the sixth aspect, a graphical user interface on an electronic device is provided, wherein the electronic device has a display screen, a camera, a memory, and one or more processors, wherein the one or more processors are used to execute one or more computer programs stored in the memory, and the graphical user interface includes a graphical user interface displayed when the electronic device executes the method described in the above aspect and any possible implementation method thereof.

[0040] In a seventh aspect, a computer program product is provided. When the computer program product is run on a computer, the computer is caused to execute the method as described in the above aspects and any possible implementation thereof.

[0041] In an eighth aspect, a chip system is provided, comprising a processor. When the processor executes an instruction, the processor executes the method described in the above aspects and any possible implementation thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of the structure of a communication system provided in an embodiment of the present application;

[0043] Figure 2A A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0044] Figure 2B A schematic diagram of the structure of another communication system provided in an embodiment of the present application;

[0045] Figure 3 A flowchart of a method for automatically identifying a user using a public device provided in an embodiment of the present application;

[0046] Figure 4 A schematic diagram of a clustering and segmentation method for multi-user data on a public device provided in an embodiment of the present application;

[0047] Figure 5 A schematic diagram of a feature comparison method for multi-user data clustering on a public device provided in an embodiment of the present application;

[0048] Figure 6 A schematic diagram of a method for labeling users with multi-user data on a public device provided in an embodiment of the present application;

[0049] Figure 7 A schematic diagram of a method for learning multiple user features on a public device provided in an embodiment of the present application;

[0050] Figures 8A-8C A schematic diagram of a public device display interface and voice playback content provided in an embodiment of the present application;

[0051] Figure 9 A flowchart of another method for automatically identifying a user using a public device provided in an embodiment of the present application;

[0052] Figure 10 A schematic structural diagram of a chip system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0054] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0055] like Figure 1 As shown, a communication system provided by an embodiment of the present application includes one or more public devices 100 and one or more private devices 200, such as a private device of user A and a private device of user B.

[0056] The public device 100 is a public electronic device for shared use by multiple users. Examples of such electronic devices include tablet computers, personal computers (PCs), personal digital assistants (PDAs), augmented reality (AR) devices, virtual reality (VR) devices, in-vehicle devices, smart screens, smart cars, smart speakers, and televisions. This application does not impose any specific restrictions on the specific form of such electronic devices. The private device 200 is typically a device dedicated to a single user, such as a mobile phone, PC, smartwatch, or wearable device.

[0057] For example, the public device 100 may be a large-screen electronic device (such as a TV or smart screen). Family members or colleagues in the company can project videos played on their private devices (such as mobile phones, tablets, and computers) onto large-screen electronic devices to enhance the visual experience. For another example, the public device 100 may be a smart speaker. Family members can play audio from their private devices (such as mobile phones, tablets, and smart wearables) through the smart speaker, and interact with other smart devices in the home. For another example, the public device 100 may be a car-mounted terminal, and family members can play audio from their private devices (such as mobile phones) through the car-mounted terminal while driving or riding in a car, or make and receive calls on private devices (such as mobile phones).

[0058] In the embodiment of the present application, when multiple users use the public device 100, they do not need to register and log in to an account, or multiple users can log in to the same account to operate. However, the public device 100 can automatically identify the characteristics of different users (including biometrics, behavioral characteristics, etc.) and recommend personalized services to different users. Among them, biometrics include physical characteristics such as the user's fingerprint, face, and pupils. Behavioral characteristics include the user's voiceprint, screen sliding operation habits, etc.

[0059] Typically, when a user is using a public device 100, there may be a situation where the user needs to associate it with his or her own private device 200. For example, when a user uses an application on a public device 100, he or she uses his or her own private device 200 to authorize the public device 100 to log in to the account logged in on the private device 200. For example, a user logs in to accounts such as "WeChat" application, "Alipay" application, "Network Disk" application, etc. by scanning the QR code on the public device 100 through the private device 200. For another example, the account logged in on the public device 100 is the same as the account on a user's private device 200 or belongs to the same family account. For another example, the public device 200 has established a wireless connection (such as a Bluetooth connection or a WIFI connection, etc.) with the user's own private device 200. Therefore, an embodiment of the present application proposes a method for automatically identifying users by a public device, which can use the user features learned on the private device 200 associated with the public device 100 to identify the user corresponding to the user data on the public device 100. The public device 100 then performs self-learning on the user data of the identified user to learn the user characteristics corresponding to the user, which are used to identify the subsequent newly input user data. Furthermore, the public device 100 can provide personalized services for different users. The specific technical solution will be described in detail below.

[0060] like Figure 2A , which is a structural diagram of the public equipment 100 .

[0061] The public device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0062] It should be understood that the illustrated structure of the embodiment of the present invention does not constitute a specific limitation on the public device 100. In other embodiments of the present application, the public device 100 may include more or fewer components than shown, or may combine or separate certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0063] The processor 110 may include one or more processing units. For example, the processor 110 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU). The different processing units may be independent devices or integrated into one or more processors.

[0064] The controller can generate operation control signals according to the instruction operation code and timing signal to complete the control of instruction fetching and execution.

[0065] Processor 110 may also include a memory for storing instructions and data. In some embodiments, the memory in processor 110 is a cache memory. This memory can store instructions or data that have just been used or are being recycled by processor 110. If processor 110 needs to use the same instruction or data again, it can directly access the memory. This avoids duplicate accesses, reduces processor 110 latency, and thus improves system efficiency.

[0066] In some embodiments, the processor 110 may include one or more interfaces. The interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface.

[0067] It is understandable that Figure 2AThe illustrated interface connection relationship between the modules is merely an illustrative illustration and does not constitute a structural limitation on the public device 100. In other embodiments of the present application, the public device 100 may also adopt different interface connection methods from the above embodiments, or a combination of multiple interface connection methods.

[0068] The charging management module 140 is configured to receive charging input from a charger. The charger can be either a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 140 can receive charging input from the wired charger via the USB interface 130. In some wireless charging embodiments, the charging management module 140 can receive wireless charging input via the wireless charging coil of the utility device 100. While charging the battery 142, the charging management module 140 can also power the electronic device through the power management module 141.

[0069] The power management module 141 is used to connect the battery 142, the charging management module 140, and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140, and provides power to the processor 110, the internal memory 121, the display 194, the camera 193, and the wireless communication module 160. The power management module 141 can also be used to monitor parameters such as battery capacity, battery cycle count, and battery health status (leakage, impedance). In some other embodiments, the power management module 141 can also be set in the processor 110. In other embodiments, the power management module 141 and the charging management module 140 can also be set in the same device.

[0070] The wireless communication function of the public device 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor and the baseband processor.

[0071] Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in public device 100 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In other embodiments, the antennas can be used in conjunction with a tuning switch.

[0072] The mobile communication module 150 can provide solutions for wireless communications including 2G / 3G / 4G / 5G applied to the public equipment 100. The mobile communication module 150 may include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves from the antenna 1, and filter, amplify, and process the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modulation and demodulation processor, and convert it into electromagnetic waves for radiation through the antenna 1. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the processor 110. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the same device as at least some of the modules of the processor 110.

[0073] The modem processor may include a modulator and a demodulator. The modulator is used to modulate the low-frequency baseband signal to be transmitted into a medium-high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After being processed by the baseband processor, the low-frequency baseband signal is passed to the application processor. The application processor outputs a sound signal through an audio device (not limited to the speaker 170A, etc.) or displays an image or video through the display screen 194. In some embodiments, the modem processor may be an independent device. In other embodiments, the modem processor may be independent of the processor 110 and be set in the same device as the mobile communication module 150 or other functional modules.

[0074] The wireless communication module 160 can provide wireless communication solutions including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc., which are applied to the public equipment 100. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, frequency modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 110. The wireless communication module 160 can also receive the signal to be sent from the processor 110, frequency modulate it, amplify it, and convert it into electromagnetic waves for radiation through the antenna 2.

[0075] In some examples of the present application, the public device 100 can establish a wireless connection with the user's private device 200 through the wireless communication module 160. The public device 100 can send user data to the private device 100 through the wireless connection, and the private device 100 performs a user feature comparison on the user data on the public device. The public device 100 can also receive a feature comparison returned by the private device 100 through the wireless connection. Of course, the public device 100 can also establish a wired connection with the private device 200 through, for example, a USB interface, and send the above-mentioned user data and receive the comparison results through the wired connection, but the embodiments of the present application are not limited to this.

[0076] In some embodiments, antenna 1 of the public device 100 is coupled to the mobile communication module 150, and antenna 2 is coupled to the wireless communication module 160, so that the public device 100 can communicate with a network and other devices via wireless communication technologies. The wireless communication technologies may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technology. The GNSS may include a global positioning system (GPS), a global navigation satellite system (GLONASS), a Beidou navigation satellite system (BDS), a quasi-zenith satellite system (QZSS) and / or a satellite based augmentation system (SBAS).

[0077] The utility device 100 implements display functionality through a GPU, display screen 194, and an application processor. The GPU is a microprocessor for image processing that connects the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs that execute program instructions to generate or modify display information.

[0078] Display screen 194 is used to display images, videos, and the like. Display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a MiniLED, a MicroLED, a Micro-oLed, or a quantum dot light-emitting diode (QLED). In some embodiments, utility device 100 may include one or N display screens 194, where N is a positive integer greater than one.

[0079] The public device 100 can implement a shooting function through an ISP, a camera 193, a video codec, a GPU, a display screen 194, and an application processor.

[0080] The ISP processes data fed back by camera 193. For example, when taking a photo, the shutter is opened, and light is transmitted through the lens to the camera's photosensitive element. The light signal is converted into an electrical signal, which is then passed to the ISP for processing and converted into a visible image. The ISP can also perform algorithmic optimization on image noise, brightness, and skin tone. It can also optimize parameters such as exposure and color temperature of the captured scene. In some embodiments, the ISP can be located within camera 193.

[0081] The above-mentioned camera 193 is used to capture still images or videos. The object generates an optical image through the lens and projects it onto the photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then transmits the electrical signal to the ISP to be converted into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in a standard RGB, YUV or other format. In some embodiments, the public device 100 may include 1 or N cameras 193, where N is a positive integer greater than 1. In other embodiments, the camera 193 is a liftable camera.

[0082] The digital signal processor is used to process digital signals. In addition to processing digital image signals, it can also process other digital signals. For example, when the public device 100 is selecting a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy.

[0083] Video codecs are used to compress or decompress digital video. The public device 100 may support one or more video codecs. This allows the public device 100 to play or record videos in various encoding formats, such as Moving Picture Experts Group (MPEG) 1, MPEG2, MPEG3, and MPEG4.

[0084] The NPU is a neural network (NN) computing processor. Drawing on the structure of biological neural networks, such as the transmission patterns between neurons in the human brain, it rapidly processes input information and can continuously self-learn. The NPU can enable intelligent cognitive applications in the utility device 100, such as image recognition, face recognition, speech recognition, and text comprehension.

[0085] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the utility device 100. The external memory card communicates with the processor 110 via the external memory interface 120 to implement data storage functions. For example, files such as music and videos can be stored on the external memory card.

[0086] The internal memory 121 can be used to store computer executable program codes, which include instructions. The internal memory 121 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc. The data storage area may store data created during the use of the public device 100 (such as audio data, a phone book, etc.), etc. In addition, the internal memory 121 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc. The processor 110 executes various functional applications and data processing of the public device 100 by running instructions stored in the internal memory 121 and / or instructions stored in a memory provided in the processor.

[0087] The public device 100 can implement audio functions such as music playback and recording through the audio module 170, the speaker 170A, the microphone 170C, the headphone jack 170D, and the application processor.

[0088] The audio module 170 is used to convert digital audio information into analog audio signal output, and is also used to convert analog audio input into digital audio signals. The audio module 170 can also be used to encode and decode audio signals. In some embodiments, the audio module 170 can be set in the processor 110, or some functional modules of the audio module 170 can be set in the processor 110. The speaker 170A, also known as the "speaker", is used to convert audio electrical signals into sound signals. The public device 100 can listen to music through the speaker 170A. The microphone 170C, also known as the "microphone" or "microphone", is used to convert sound signals into electrical signals. When making a call or sending a voice message, the user can speak by putting their mouth close to the microphone 170C to input the sound signal into the microphone 170C. The public device 100 can be provided with at least one microphone 170C. The headphone jack 170D is used to connect wired headphones. The headphone interface 170D may be a USB interface 130 or a 3.5 mm open mobile terminal platform (OMTP) standard interface or a cellular telecommunications industry association of the USA (CTIA) standard interface.

[0089] The buttons 190 include a power button, a volume button, etc. The button 190 can be a mechanical button. It can also be a touch button. The public device 100 can receive button input and generate key signal input related to the user settings and function control of the public device 100. The motor 191 can generate a vibration prompt. The motor 191 can be used for incoming call vibration prompts, and can also be used for touch vibration feedback. For example, touch operations acting on different applications (such as taking pictures, audio playback, etc.) can correspond to different vibration feedback effects. The indicator 192 can be an indicator light, which can be used to indicate the charging status, power changes, and can also be used to indicate messages, missed calls, notifications, etc. The SIM card interface 195 is used to connect the SIM card. The SIM card can be inserted into the SIM card interface 195 or pulled out from the SIM card interface 195 to achieve contact and separation with the public device 100. The public device 100 can support 1 or N SIM card interfaces, where N is a positive integer greater than 1.

[0090] Figure 2B It is a schematic diagram of the interaction between the public device 100 and the private device 200 involved in the method of an embodiment of the present invention.

[0091] For example, the public device 100 may include a feature collection module, a feature clustering / labeling module, a feature learning module, and a feature storage module. The private device 200 may include a feature collection module, a feature learning module, a feature storage module, and a feature recognition module.

[0092] In some examples, after the public device 100 receives operations input by multiple users, the feature collection module can collect features of the operations of multiple users, such as collecting the user's biometric features (such as voice, fingerprint, face image, eye image, etc.), collecting the trajectory features of the user's sliding screen operation, the force features of the user's pressing the screen, etc. Then, the feature clustering / labeling module of the public device 100 can execute a clustering algorithm on the operations of multiple users and the features corresponding to the operations of multiple users, and divide the operations of multiple users into multiple clusters. Among them, one cluster corresponds to one user. In other words, one cluster contains multiple operations of the user and the features corresponding to each operation. The public device 100 inputs each divided cluster into each private device 200 connected to the public device 100, and the feature recognition module on the private device performs feature recognition to assist the public device 100 in determining the identity of the user corresponding to each cluster and marking the cluster with the identified identity. Based on the annotation results from the feature clustering / annotation module, the feature learning module of the public device 100 performs feature learning on all clusters annotated with the same user identity. For example, it learns the features of user A, user B, and user C and stores them in the feature storage module. Subsequently, when the public device 100 receives a new user operation, it can identify the new user operation based on the features of each user stored in the feature storage module, thereby recommending personalized services based on the identified user. The specific technical solution is described in detail below and is not elaborated on here.

[0093] It should be noted that private device 200 must pre-learn the characteristics of its own user (i.e., the user of private device 200, typically a single user). Specifically, the feature acquisition module of private device 200 identifies operational characteristics based on the user's operations. The feature learning module then learns the user's characteristics based on the identified operational characteristics and stores them in the feature storage module. Subsequently, when it is necessary to determine whether the user who performed a user operation is the user of private device 200, the feature recognition module can retrieve the data in the feature storage module for identification.

[0094] The technical solutions involved in the following embodiments can all be implemented in the public device 100 and the private device 200 having the above-mentioned hardware architecture and software architecture.

[0095] like Figure 3 FIG. 1 is a flowchart of a method for automatically identifying a user using a public device according to an embodiment of the present application, specifically including:

[0096] S301. A public device receives data of multiple users without logging into an account or logging into the same account or multiple accounts belonging to the same group.

[0097] For example, to facilitate users to alternately use a public device without the need for additional account registration and login, the public device may not require an account, or may require a single account or multiple accounts belonging to the same group (e.g., a family group) to be logged in, allowing multiple users to use the public device together. The public device may record various types of user data collected by multiple users using the public device. For example, user data includes, but is not limited to, voice data, image data, behavioral data, application records, and other information.

[0098] Among them, voice data includes user input captured by a public device through a microphone or external headphones. For example, a public device may have a voice assistant application installed on it, allowing the user to input voice commands into the public device using the voice assistant application. Voice data includes the user's voice and may also include the results of voice recognition performed by the public device on the user's voice. Image data includes images captured by a public device through a camera or an external camera. Image data includes facial images and may also include the results of facial recognition or iris recognition performed based on images. Behavioral data includes user actions when operating a public device, such as swiping, tapping, or pressing the screen. Behavioral data may also include information such as user operating habits analyzed based on user actions when operating a public device. For example, based on a swipe, the user's trajectory characteristics may be determined; based on a press, the user's pressure may be determined. Application records include, but are not limited to, application type, application name, application usage frequency, application start and close time (or application startup duration), application function, etc. Application records also include user preferences extracted based on the user's use of the application, such as the web content that the user likes to browse, the types of movies that the user likes to watch, the music that the user often listens to, and the items that the user often purchases.

[0099] Optionally, the public device can also further analyze the recorded user data to extract features related to the user's identity. For example, the timbre of the user's voice in the voice data can be analyzed to extract the user's gender. For another example, the content in the voice data (such as titles, language terms, etc.) can be analyzed to extract the user's identity or age group. For another example, face recognition or iris recognition can be performed on the image data obtained by the public device to identify the user's identity (including gender, age group, etc.). For another example, the public device can extract the user's gender based on the force with which the user presses the screen or clicks the screen. For another example, when different users perform the same sliding operation, the trajectory of the finger sliding is usually different. Therefore, the public device can also identify whether it is the same user based on the trajectory of the user's sliding operation.

[0100] Optionally, the public device can screen and classify all recorded user data, which may include features related to the user identity obtained by analyzing the original user data information, to determine the user data related to the user identity and the user data related to the user preferences. Among them, the user data related to the user identity includes, for example, voice data, image data, behavioral data, etc., which can be used to subsequently identify the user identity. The user data related to the user preferences includes, for example, behavioral data, application records, etc., which can be used to subsequently provide or recommend personalized services to the user based on the user identity. It should be noted that the user data related to the user identity and the user data related to the user preferences may overlap. For example, behavioral data may contain both information related to the user identity and information related to the user preferences.

[0101] It should be noted that in the stage when multiple users just start using the public device (for example, the first week when the public device is just being used), since the public device does not have the ability to identify users, the public device may not provide personalized services for different users, or may randomly recommend services to different users, or recommend the same services to different users. The embodiments of the present application do not limit this.

[0102] S302: The public device clusters and divides the user data, wherein each cluster corresponds to the same user, and the same user may correspond to multiple clusters.

[0103] For example, after multiple users use a public device for a period of time (for example, a week or a month), user data of multiple users are recorded on the public device. The public device can use a clustering algorithm to cluster and segment the recorded user data or user data that has been determined to be related to the user identity, and divide user data with the same characteristics into a cluster. That is, a cluster contains only the user data of one user. In other words, a clustering algorithm can be used to perform a preliminary division of user data on the public device into user groups. It should be noted that when setting the preset threshold for clustering, it is necessary to divide the user groups as much as possible without affecting the accuracy. That is, an appropriate trade-off should be made between distinguishing users and clustering being too fragmented, so that each cluster after segmentation corresponds to only one user, but the same user can correspond to multiple clusters.

[0104] Among them, the above-mentioned clustering algorithm can be, for example, any one or more of the K-means method (for example, k-means algorithm, k-center point algorithm), hierarchical clustering method, density-based method (for example, density-based spatial clustering of applications with noise (Density-Based Spatial Clustering of Applications with Noise, DBSCAN), HDBSCAN, etc.), graph neural network (Graph Neural Network, GNN), etc.

[0105] In some examples, the same clustering algorithm can be used to perform clustering and segmentation on recorded user data or user data that has been determined to be related to the user identity, or different clustering algorithms can be used to perform segmentation on different types of recorded user data or user data that has been determined to be related to the user identity (such as voice data, image data, behavior data, etc.). The embodiments of the present application do not limit this.

[0106] like Figure 4 As shown, various user data of multiple users (such as user A, user B and user C) are stored in the public device. Each graphic in the figure represents a piece of user data. Graphics of the same shape represent a type of user data, for example, a circle represents voice data, a triangle represents image data, a square represents behavioral data, etc. It should be noted that at this time, the public device does not know the user corresponding to each piece of user data. The clustering algorithm of this step can be used to divide these user data with similar features into a cluster, and each cluster corresponds to a user. For example, after the public device executes the clustering algorithm, clusters 1 to 5 are formed. If there is user data that has not been successfully clustered, for example, other user data that has not been divided into clusters 1 to 5 in the figure is user data that has not been successfully clustered, then wait for new user data to be input subsequently. At this time, the user data that has not been successfully clustered can be clustered again together with the new user data to determine the clustering of each user data.

[0107] S303: The public device sends the divided clusters to one or more associated private devices, which perform user feature comparison.

[0108] S304: The public device labels users for each cluster based on the user feature comparison results returned by each private device.

[0109] In steps S303 and S304, while using a public device, each user may associate the public device with their own private device. For example, when using an application on a public device, user A may use their private device A (e.g., a mobile phone, tablet, etc.) to scan a QR code on the public device and authorize the application on the public device to log in to one of their accounts, such as WeChat, Alipay, email, or a video app. In another example, if user A logs in to an application on a public device using their mobile phone number, the public device is associated with user A's phone. In another example, user B uses a public device to connect to a hotspot shared by their private device B. In another example, user C transfers files between the public device and their private device C via Bluetooth or WLAN. In another example, the account user A uses to log in to the public device is the same as the account on user A's private device A, or they belong to the same group, such as a family group. In another example, if the public device is a large-screen device, user B projects a video or document played on private device B onto the public device. The embodiment of the present application does not limit the manner in which public devices and private devices are associated.

[0110] In other words, if a public device is associated with a private device, the private device can be confirmed as a trusted public device. Furthermore, since a user's private device generally stores a large amount of the user's user data and has learned the user's user features, it can identify the user data belonging to the user. Therefore, the public device can use the user features learned in the private device to identify the user's identity based on the user data on its own device. In other words, using the user feature recognition model in the private device, a correspondence is established between each cluster in the public device and the private device associated with the public device. That is, a correspondence is established between each cluster in the public device and the user corresponding to the private device, completing the user identity recognition of each cluster in the public device. User features include, but are not limited to, biometric features such as voiceprint features, facial features, iris features, fingerprint features, palm print features, and behavioral features.

[0111] like Figure 5As shown, private devices have user feature recognition models. For example, private device A has a voiceprint recognition model and a face recognition model, private device B has a voiceprint recognition model, a face recognition model, and a behavior recognition model, and private device C has a fingerprint recognition model and a face recognition model. The voiceprint recognition model can be used to extract voiceprint features from voice data and compare them with preset voiceprint templates in the model. If the confidence level of the comparison result is greater than or equal to a preset threshold, the voice data and the preset voiceprint template are considered to belong to the same user; otherwise, they are considered to belong to different users. The face recognition model can be used to extract facial features from image data and compare them with preset face templates in the model. If the confidence level of the comparison result is greater than or equal to a preset threshold, the image data and the preset face template are considered to belong to the same user; otherwise, they are considered to belong to different users. The behavior recognition model can be used to extract behavioral features from behavioral data and compare them with preset behavioral templates in the model. If the confidence level of the comparison result is greater than or equal to the preset threshold, the behavior data and the preset behavior template are considered to belong to the same user, otherwise they are considered to belong to different users. The fingerprint recognition model can be used to extract behavioral features from the behavior data and compare the extracted fingerprint features with the preset fingerprint template in the model. If the confidence level of the comparison result is greater than or equal to the preset threshold, the behavior data and the preset behavior template are considered to belong to the same user, otherwise they are considered to belong to different users. It should be noted that the preset thresholds corresponding to different user feature recognition models on the same device may be the same or different, and the preset thresholds of the same user feature recognition models on different devices may be the same or different.

[0112] The public device can then send the user data in each cluster divided in step S302 to one or more associated private devices. The private devices that receive the clusters perform a comparison using their own feature models and return the comparison results to the public device. The public device then determines the users corresponding to each cluster based on the returned comparison results and labels them.

[0113] In some examples, the public device may first send the clusters obtained by the above segmentation to one of the private devices for feature comparison. Then, based on the comparison results, the clusters that are not related to the private device are sent to another private device for feature comparison. And so on, until all the private devices associated with the public device have completed the comparison. For example, Figure 5In the example shown, the public device may first send clusters 1 to 5 to private device A for feature comparison. Among them, cluster 1 and cluster 4 are determined to correspond to private device A and belong to user A's user data. Cluster 2, cluster 3 and cluster 5 are not successfully compared. Then, the public device sends cluster 2, cluster 3 and cluster 5 to private device B for feature comparison. Among them, cluster 2 is determined to correspond to private device B and belong to user B's user data. Cluster 3 and cluster 5 are not successfully compared. Cluster 3 and cluster 5 are then sent to private device C for feature comparison, and it is determined that cluster 3 corresponds to private device C and belongs to user C's user data. Cluster 5 does not correspond to any private device. In other examples, the public device may also send all clusters to multiple private devices at the same time, and multiple private devices perform feature comparison at the same time. If it is determined that a cluster corresponds to multiple private devices based on the comparison results, it can be further determined that the cluster corresponds to the private device with the highest confidence. For example, Figure 5 In the example shown, the public device can send cluster 1 and cluster 5 to private device A, private device B and private device C respectively for feature comparison. Among them, cluster 1, cluster 3 and cluster 4 correspond to private device A, cluster 2 is determined to correspond to private device B, and cluster 3 corresponds to private device C. It can be noted that cluster 3 corresponds to private device A and private device C. Assuming that the preset thresholds of the face recognition models in private device A and private device C are both 80, the confidence level of the comparison result of cluster 3 with the face recognition model in private device A is 85, and the confidence level of the comparison result with the face recognition model in private device C is 90, then it is finally determined that cluster 3 corresponds to private device C and belongs to the data of user C. In some other examples, the public device can first send different clusters to different private devices for comparison. Then, the clusters that have not been compared and do not correspond to private devices are sent to idle private devices for comparison. For example, Figure 5 In the example shown, the public device can first send cluster 1 to private device A, cluster 2 to private device B, and cluster 3 to private device C for feature comparison. The comparison results show that cluster 1 corresponds to private device A, cluster 2 is definitely associated with private device B, and cluster 3 corresponds to private device C. Next, cluster 4 is sent to private device A and cluster 5 to private device B for feature comparison. The comparison results show that cluster 4 corresponds to private device A, while cluster 5 does not correspond to private device B. Cluster 5 is then sent to private devices A and C for feature comparison, and the comparison results show that cluster 5 also does not correspond to private devices A and C, thus concluding the comparison.

[0114] In some other examples, the public device may first perform an initial classification on the segmented clusters, and then selectively send them to the corresponding private devices for feature comparison. For example, the public device may classify the user groups according to the user gender, age group and other information corresponding to the cluster, and then send each cluster to the private device with the same user group for feature comparison. For another example, the public device may also match different types of clusters to the capabilities of each private device based on the different capabilities of the private device in identifying the user identity. In other words, the public device may also select the corresponding type of private device for feature comparison based on the type of each cluster (such as voice data type, image data type, behavior data type). Specifically, the cluster of the voice data type is sent to a private device with voiceprint recognition capability for feature comparison. The cluster of the image data type is sent to a private device with face recognition capability or iris recognition capability for feature comparison. The cluster of the behavior data type is sent to a private device with behavior feature capability for feature comparison. It can be seen from this that clusters are first classified and selectively sent to private devices corresponding to the classification for feature comparison, which improves the comparison success rate, reduces the number of times user data is transmitted between multiple private devices, and speeds up the comparison efficiency.

[0115] In other examples, when a public device sends each cluster to a private device for comparison, the public device may send the entire cluster to the private device for comparison. Alternatively, a portion of the data in the cluster may be first sent to the private device for comparison. If the confidence level of the comparison result for this portion of data is close to a preset threshold, it is considered that the cluster is likely to correspond to the private device, and the remaining data may be sent to the private device for comparison. If the confidence level of the comparison result for this portion of data is far less than the preset threshold, it is considered that the cluster is likely not to correspond to the private device, and the remaining data may not be sent to the private device for comparison, and other private devices may be selected for comparison.

[0116] For example, Figure 6 The figure below shows an example of how clusters are labeled. Cluster 1 is labeled for user A, Cluster 2 is labeled for user B, Cluster 3 is labeled for user C, and Cluster 4 is labeled for user A. If any clusters are not successfully matched, such as Cluster 5, the system waits for new user data to be input. These unmatched clusters can be re-clustered with new user data and re-matched against private devices, or re-matched if new private devices are associated.

[0117] S305: Public devices are grouped and labeled as clusters of the same user, and a machine learning algorithm is used to learn the user characteristics of each user.

[0118] Exemplarily, the public device inputs clusters labeled as the same user into a preset machine learning model (e.g., a neural network model) for training, resulting in a user feature recognition model that is used to perform feature comparison on subsequently input user data and identify the user identity corresponding to the subsequently input user data. If the clusters labeled as the same user are different types of user data, they can also be learned by type. That is, user data of the same type labeled as the same user is input into a preset skill learning model for training to obtain the corresponding user feature recognition model. It should be noted that the same or different preset models can be used to train different types of input user data. For example, all clusters labeled as user A and of voice data type are input into preset model 1 for training to obtain a voiceprint recognition model for user A, which is used to identify the user identity corresponding to subsequently input voice data. All clusters labeled as user A and of image data type are input into preset model 2 for training to obtain a face recognition model or iris recognition model for user A, which is used to identify the user identity corresponding to subsequently input image data. The clusters labeled as user B and of behavioral data type are input into preset model 3 for training to obtain a behavior recognition model for user A, which is used to identify the user identity corresponding to the subsequent behavioral data input. All clusters labeled as user B and of image data type are input into preset model 2 for training to obtain a face recognition model or iris recognition model for user B, which is used to identify the user identity corresponding to the subsequent image data input.

[0119] For example, Figure 7 The figure shows an example of a user feature comparison model learned by a public device. The user feature recognition model 701 trained on the public device specifically includes a voiceprint recognition model for user A, a face recognition model for user A, a voiceprint recognition model for user B, and a face recognition model for user C.

[0120] It should be noted that if the data volume of a cluster is small and insufficient to learn user features, the cluster can wait until new user data is divided into users corresponding to the cluster, and then learn the user features together with the new user data.

[0121] It should also be noted that after obtaining the user characteristics of each user, the public device automatically learns the user's behavioral characteristics and preferences based on the user's behavioral data and application records. Figure 7As shown, it is an example of a user behavior characteristic and preference model learned by a public device. User behavior characteristic and preference model 702 is learned on the public device, specifically including the user behavior characteristics and preferences of user A, user B and user C. It should be noted that if the behavior data and application records and other information recorded in the public device at this time are not sufficient to learn the behavior characteristics or preferences of each user, it can also be learned after accumulating enough behavior data and application records and other information in the process of users using the public device in the future. That is, for new user data input by subsequent users, the public device identifies the user identity, binds the user identity with the new behavior data and application records and other information, and learns the behavior characteristics and preferences of the user. In other words, Figure 7 The user behavior characteristics and preference model 702 can be learned after the user feature recognition model 701. In some examples, if the network side stores information such as user behavior characteristics and preferences, the public device can also obtain information such as user behavior characteristics and preferences from the network side, which is not limited in this embodiment of the present application.

[0122] S306: The public device receives the newly input user data.

[0123] S307: The public device performs feature comparison on the newly input user data based on the learned user features to determine the user corresponding to the newly input user data.

[0124] In steps S306 and S307, after the public device has learned the user characteristics, if a user continues to use the public device and enters new user data (for example, by entering a voice command, capturing a user image, or performing a screen swipe operation), the public device compares the new user data with the learned user characteristic recognition model to determine the user identity of the new user data. For example, if the comparison result between the new user data and the voiceprint recognition model of user B meets the confidence level greater than a preset threshold, the new user data is considered to be user B's data.

[0125] It should be noted that if the new user data is unsuccessfully compared with the learned user feature recognition model on the public device, the public device has not identified the user identity of the new user data. The new user data can then be re-clustered and segmented along with the previously unlabeled user data, compared with the feature recognition model on the private device, and the user labeled. In other words, steps S302 through S305 are repeated.

[0126] S308: The public device provides corresponding personalized services to the user corresponding to the newly input user data.

[0127] After identifying the user corresponding to the new user data, personalized services can be recommended to the user based on the user's behavioral habits and preferences learned by the public device. For example, if the comparison result between the new user data and the voiceprint recognition model of user B meets the confidence level greater than a preset threshold, the new user data is considered to be user B's data. The public device then queries the user behavior characteristics and preference model for user B's behavioral characteristics and preferences and provides personalized services for user B. Personalized services can be pre-set applications or functions in the public device operating system, such as service recommendation applications, reminder applications, and notification filtering applications. Of course, these personalized services can also be third-party applications installed by the user, such as video applications, news applications, or music applications.

[0128] It should be noted that if a public device is connected to other devices, it can also provide personalized services based on the user's instructions to other devices. For example, if the public device is a smart speaker, the smart speaker can control other smart home devices to perform different operations when it recognizes different users, such as instructing the air conditioner to set a different temperature.

[0129] It can be seen from this that on public devices used by multiple users, multiple users can log in to the same account or not. The public devices can automatically identify the user's identity without the user's perception, and recommend personalized services to the user, simplifying the user's operation of using the public device and improving the interaction efficiency between multiple users and the public device.

[0130] The following describes the method provided in the embodiments of the present application in conjunction with specific application scenarios.

[0131] Scenario 1: Public devices are large-screen devices in the home, such as TVs and smart screens.

[0132] When a family purchases a new large-screen device, it is no longer necessary for all family members (elderly, father, mother, and children) to register accounts or enter their faces or fingerprints one by one. There is no need for each family member to log in to their accounts when using the large-screen device. Alternatively, the large-screen device can be logged in to a single account, meaning all family members can use the large-screen device directly through that account.

[0133] During the initial period (e.g., one week, one month), the large-screen device does not have the function of identifying the user and can provide the same service or randomly recommend services to family members.

[0134] While family members are using a large-screen device, Dad uses his phone to scan a QR code on the device, connecting it to the home network. A child casts an online course on his tablet onto the large-screen device. Mom uses Alipay on her phone to scan a QR code on the large-screen device to purchase a new movie. An elderly person casts a TV series on their phone onto the large-screen device. In other words, family members can establish connections between their personal devices and large-screen devices through various means.

[0135] Large-screen devices store data about each family member's use of the device. This includes, for example, voice data collected by the device when a family member uses the device's voice function. Another example is image data collected by the device during a video call. Another example is the user's habits when using the device. For example, when watching TV, a father likes to use his phone's remote control app to control the device and often plays science fiction and action films. An elderly person likes to use the device's included remote control to control the device and often plays family dramas. A child likes to use the touchscreen display to control the device and often plays cartoons.

[0136] Once the large-screen device has stored sufficient data for each family member and is associated with their private devices, such as mobile phones and tablets, it can automatically cluster and segment the user data using the methods described in the previous embodiments. This data is then sent to the private devices for comparison with user characteristics. Public devices then label each cluster based on the comparison results and aggregate data labeled as belonging to the same user for machine learning, learning the user's characteristics. These learned user characteristics can then be used to identify the user corresponding to subsequently input user data and recommend personalized services for that user.

[0137] For example, if it is recognized that the father is using a large-screen device, the large-screen device can recommend the latest science fiction movies, action movies, etc. Figure 8A The interface 801 shown in the figure shows recommended movies, etc. through text and image prompts. If the elderly are identified as using a large-screen device, the large-screen device can recommend the hottest family dramas, etc. The large-screen device displays Figure 8B The interface 802 shown in the figure displays recommended TV series through image prompts, and prompts the user to select TV series through voice playback. If the child is identified as using a large-screen device, the large-screen device can recommend highly rated cartoons. Figure 8C The interface 803 shown displays recommended animations through image prompts, and reminds the user to pay attention to the length of time to watch TV through voice playback.

[0138] For example, if it is recognized that the father is using a large-screen device, the large-screen device can push current affairs, military news, etc. If it is recognized that the mother is using a large-screen device, the large-screen device can push financial, entertainment news, etc.

[0139] For example, if it's identified that the father is using a large-screen device for a video call, the large-screen device can disable the beauty function. If it's identified that the mother is using a large-screen device for a video call, the large-screen device can enable the beauty function. If it's identified that the child is using a large-screen device, the large-screen device will automatically enter monitoring mode, for example, automatically shutting down the large-screen device when the playback time reaches a preset length (for example, half an hour).

[0140] It can be seen that when family members are not logged into their accounts, after a period of time, the large-screen device can learn the characteristics of each family member, automatically identify the identity of the family members, and recommend different services to different family members, thereby improving the user experience.

[0141] Scenario 2: The public device is a smart speaker in the home.

[0142] When a family purchases a new smart speaker, it is not necessary for all family members (elderly, father, mother, and children) to register accounts or record voiceprints one by one, nor do they need to log in to their accounts when using the smart speaker. Alternatively, the smart speaker can be logged in to a single account, meaning that all family members can use the smart speaker directly through that account.

[0143] During the initial period (such as one week or one month), the smart speaker does not have the function of identifying the user and can provide the same services to family members or randomly recommend services.

[0144] While family members are using a smart speaker, Dad uses his phone to scan the QR code displayed on the smart speaker, connecting it to the home network. A child connects his tablet to the smart speaker to listen to a story. Mom connects her phone to the smart speaker to play music. An elderly person connects their phone to the smart speaker to listen to a story. In other words, family members may establish connections between their personal devices and the smart speaker through various means. Furthermore, the smart speaker stores the voice data of each family member using the smart speaker.

[0145] Once the smart speaker has stored sufficient voice data from each family member and is associated with their personal devices, such as mobile phones and tablets, it can automatically cluster and segment the user's voice data using the methods described in the previous embodiments. This data is then sent to the personal devices for comparison with their voiceprint features. Public devices then label each cluster based on the comparison results and aggregate data associated with the same user for machine learning, learning the user's voiceprint features. The learned voiceprint features can then be used to identify the user corresponding to subsequent voice data input and recommend personalized services for that user.

[0146] For example, if the smart speaker recognizes that a dad is using the system, the smart speaker can add the name "Dad" when replying and recommend the dad's favorite music, news, etc. If the smart speaker recognizes that a child is using the system, the smart speaker can add the name "Baby" when replying and recommend the child's favorite nursery rhymes and stories.

[0147] If the smart speaker is associated with other smart devices in the home, the smart speaker can also instruct other smart devices to perform operations corresponding to the identified user identity based on the identified user identity.

[0148] For example, if it recognizes that Dad is using the smart speaker, it can turn on the ceiling light in the study or set the air conditioner to a lower temperature (for example, 18 degrees). If it recognizes that Mom is using the smart speaker, it can turn on the ceiling light in the living room or set the air conditioner to a higher temperature (for example, 25 degrees). If it recognizes that a child is using the smart speaker, it can turn on the ceiling light in the child's bedroom or set the air conditioner to a moderate temperature (for example, 20 degrees).

[0149] It can be seen that when family members are not logged into their accounts, after a period of time, the smart speaker can learn the characteristics of each family member, automatically identify the identities of family members, and recommend different services to different family members, thereby improving the user experience.

[0150] Scenario 3: The public equipment is vehicle-mounted equipment.

[0151] Similarly, multiple users driving or riding in a car can use the in-vehicle device without logging into their accounts. After a period of use, the in-vehicle device will store voice and video data from multiple users. After the user establishes a Bluetooth or wired connection between the in-vehicle device and their phone, the in-vehicle device and the user's phone are associated. Using the method described in the above embodiment, the in-vehicle device can automatically recognize the voiceprints or faces of different users and subsequently provide personalized services to each user.

[0152] like Figure 9FIG. 1 is a flow chart of another method for identifying a user on a public device provided in an embodiment of the present application, which is applied to a system including a first device and a second device. The second device is associated with the first device, and the second device stores a first biometric model corresponding to the first user, which can be used to identify the identity of the first user. The method includes:

[0153] S901. A first device obtains biometric data of multiple users.

[0154] For example, when multiple users alternately use a first device (i.e., a public device), the first device may record various types of user data (and biometric data) containing biometric features of the multiple users using the public device. The biometric data may be raw data received by the first device, such as a facial image captured by a camera, a fingerprint image captured by a fingerprint reader, or voice captured by an audio module. The biometric data may also be data processed by the first device based on the received raw data, such as facial features recognized from a facial image captured by a camera, or voiceprint features obtained from voice.

[0155] S902: The first device sends at least part of the biometric data of the multiple users to the second device.

[0156] S903. The second device identifies biometric data corresponding to the first user from the at least partial data according to the first biometric model.

[0157] S904: The second device returns the recognition result to the first device.

[0158] In steps S902-S904, a clustering algorithm can be used to illustratively perform preliminary segmentation of user groups on the user data of the public device. It should be noted that when setting the preset clustering threshold, it is necessary to segment user groups as much as possible without compromising accuracy. In other words, a proper balance should be struck between distinguishing users and overly fragmenting the clustering, so that each segmented cluster corresponds to only one user, but the same user can correspond to multiple clusters.

[0159] In one specific implementation, the first device sends the biometric data of each cluster to the second device in sequence, and the second device identifies the biometric data in each cluster based on the stored first biometric model to identify whether the biometric data of each cluster corresponds to the first user. Then, the identification results of each cluster are returned to the first device in sequence. At this time, the identification result includes whether the biometric data in the corresponding cluster corresponds to the first user or not. In another example, the first device can send the biometric data of multiple clusters to the second device once or multiple times, and the second device identifies the biometric data in each cluster based on the stored first biometric model to identify whether the biometric data of each cluster corresponds to the first user. Then, the identifier of the cluster corresponding to the first user is returned to the first device. That is, at this time, the identification result includes the identifier of the cluster corresponding to the first user. This application does not limit the way in which the first device sends the biometric data of the cluster to the second device, nor the way in which the second device returns the identification result.

[0160] S905. The first device learns a second biometric model corresponding to the first user according to the recognition result.

[0161] The second biometric model can be used to identify the first user. Since the second biometric model is learned by the first device based on the biometric data corresponding to the first user acquired by the first device, it is more suitable for identifying the user's operation on the first device and has a higher recognition rate.

[0162] S906: The first device receives a new user operation.

[0163] S907. The first device determines, based on the second biometric model, that the new user operation corresponds to the first user, and then executes the first function; and determines that the new user operation does not correspond to the first user, and then executes the second function.

[0164] The first function and the second function are different.

[0165] That is to say, the public device can identify the identity of the first user based on the learned second biometric model, provide personalized services to the first user, and improve the interaction efficiency between the user and the public device.

[0166] The present application also provides a chip system. Figure 10As shown, the chip system includes at least one processor 1301 and at least one interface circuit 1302. The processor 1301 and the interface circuit 1302 can be interconnected via lines. For example, the interface circuit 1302 can be used to receive signals from other devices (such as the memory of the public device 100). For another example, the interface circuit 1302 can be used to send signals to other devices (such as the processor 1301). Exemplarily, the interface circuit 1302 can read the instructions stored in the memory and send the instructions to the processor 1301. When the instructions are executed by the processor 1301, the electronic device can execute the various steps performed by the public device 100 (such as a mobile phone) in the above embodiment. Of course, the chip system can also include other discrete components, which is not specifically limited in the embodiments of the present application.

[0167] The present application also provides an apparatus, which is included in an electronic device and has the function of implementing the electronic device behavior in any of the methods in the above embodiments. This function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes at least one module or unit corresponding to the above function. For example, a detection module or unit, a display module or unit, a determination module or unit, and a calculation module or unit, etc.

[0168] An embodiment of the present application further provides a computer storage medium including computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes any one of the methods in the above embodiments.

[0169] An embodiment of the present application further provides a computer program product, which, when executed on a computer, enables the computer to execute any of the methods in the above embodiments.

[0170] An embodiment of the present application also provides a graphical user interface on an electronic device, wherein the electronic device has a display screen, a camera, a memory, and one or more processors, wherein the one or more processors are used to execute one or more computer programs stored in the memory, and the graphical user interface includes a graphical user interface displayed when the electronic device executes any of the methods in the above embodiments.

[0171] It is understandable that, in order to realize the above functions, the above-mentioned terminals etc. include hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the embodiments of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiments of the present invention.

[0172] The embodiment of the present application can divide the functional modules of the above-mentioned terminal etc. according to the above-mentioned method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present invention is schematic and is only a logical functional division. In actual implementation, there may be other division methods.

[0173] Through the description of the above embodiments, those skilled in the art will clearly understand that for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0174] The functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0175] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as flash memory, mobile hard disk, read-only memory, random access memory, magnetic disk or optical disk.

[0176] The above is only a specific embodiment of the present application, but the scope of protection of this application is not limited to this. Any changes or substitutions within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A system for identifying user identity on a public device, characterized in that: The system includes a first device and a second device associated with the first device, wherein the second device stores a first biometric model corresponding to a first user; the first device is a public device; The first device is used to obtain biometric data of multiple users; The first device is further configured to send at least part of the biometric data of the plurality of users to the second device; the second device is configured to identify biometric data corresponding to the first user from the at least partial data based on the first biometric model; The second device is configured to send the recognition result to the first device; The first device is configured to learn a second biometric model corresponding to the first user based on the recognition result; receive newly input user data; and perform feature comparison on the newly input user data based on the learned second biometric model to determine the user corresponding to the newly input user data; The sending at least part of the biometric data of the multiple users to the second device includes: dividing the biometric data of the multiple users into a plurality of clusters, each of the plurality of clusters corresponding to one user; Sending biometric data corresponding to one or more clusters of the plurality of clusters to the second device.

2. The system according to claim 1, wherein: The first device is further configured to receive an operation after learning a second biometric model corresponding to the first user based on the recognition result; When it is determined based on the learned second biometric model that the operation corresponds to the first user, a first function is executed; when it is determined based on the learned second biometric model that the operation does not correspond to the first user, a second function is executed, wherein the first function is different from the second function.

3. The system according to claim 1 or 2, characterized in that The association between the second device and the first device includes any one or more of the following: the first device and the second device have logged in to the same account, the first device and the second device are connected to the same wireless network, the account logged in by the first device and the account logged in by the second device belong to the same group, and the first device and the second device have established a communication connection.

4. The system according to claim 1 or 2, characterized in that The first biometric feature includes one or more of a voice feature, an image feature, and a behavior feature of the first user.

5. The system according to claim 4, characterized in that The voice features include voiceprint features and / or timbre features, the image features include one or more of facial features, iris features, fingerprint features, and palm print features, and the behavioral features are any one of the force features of pressing or clicking the screen and the trajectory features of the sliding operation.

6. The system according to claim 1, wherein: The sending, to the second device, the biometric data corresponding to one or more clusters among the plurality of clusters, includes: Biometric data corresponding to one or more clusters of the same type as the first biometric model are selected from the multiple clusters, and sent to the second device.

7. The system according to claim 6, characterized in that The selecting, from the plurality of clusters, biometric data corresponding to one or more clusters of the same type as the first biometric model, and sending the biometric data to the second device includes: When the type of the first biometric model is a voice feature class, selecting biometric data corresponding to one or more clusters containing voice data, and sending the biometric data to the second device; When the type of the first biometric model is an image characteristic class, selecting biometric data corresponding to one or more clusters containing image data, and sending the biometric data to the second device; When the type of the first biometric model is a behavioral feature type, biometric data corresponding to one or more clusters containing behavioral data are selected and sent to the second device.

8. A method for identifying a user's identity on a public device, characterized in that: The method is applied to a first device and a second device associated with the first device, wherein the second device stores a first biometric model corresponding to a first user; the first device is a public device; and the method comprises: The first device obtains biometric features of multiple users; The first device sends at least part of the biometric data of the plurality of users to the second device; The first device receives an identification result returned by the second device, where the identification result is a result of the second device identifying biometric data corresponding to the first user from the at least part of the data according to the first biometric model; The first device learns a second biometric model corresponding to the first user based on the recognition result; receives newly input user data; performs feature comparison on the newly input user data based on the learned second biometric model to determine the user corresponding to the newly input user data; The sending of at least part of the biometric data of the multiple users to the second device includes: dividing the biometric data of the multiple users into multiple clusters, each of the multiple clusters corresponding to one user; and sending the biometric data corresponding to one or more clusters of the multiple clusters to the second device.

9. The method according to claim 8, characterized in that After learning a second biometric model corresponding to the first user based on the recognition result, the first device receives an operation; When it is determined based on the learned second biometric model that the operation corresponds to the first user, the first device executes a first function; when it is determined based on the learned second biometric model that the operation does not correspond to the first user, the first device executes a second function, wherein the first function is different from the second function.

10. The method according to claim 8 or 9, characterized in that The association between the second device and the first device includes any one or more of the following: the first device and the second device have logged in to the same account, the first device and the second device are connected to the same wireless network, the account logged in by the first device and the account logged in by the second device belong to the same group, and the first device and the second device have established a communication connection.

11. The method according to claim 8 or 9, characterized in that The first biometric feature includes one or more of a voice feature, an image feature, and a behavior feature of the first user.

12. The method according to claim 11, characterized in that The voice features include voiceprint features and / or timbre features, the image features include one or more of facial features, iris features, fingerprint features, and palm print features, and the behavioral features are any one of the force features of pressing or clicking the screen and the trajectory features of the sliding operation.

13. The method according to claim 8, characterized in that The sending, to the second device, the biometric data corresponding to one or more clusters among the plurality of clusters, includes: Biometric data corresponding to one or more clusters of the same type as the first biometric model are selected from the multiple clusters, and sent to the second device.

14. The method according to claim 13, characterized in that The selecting, from the plurality of clusters, biometric data corresponding to one or more clusters of the same type as the first biometric model, and sending the biometric data to the second device includes: When the type of the first biometric model is a voice feature class, selecting biometric data corresponding to one or more clusters containing voice data, and sending the biometric data to the second device; When the type of the first biometric model is an image characteristic class, selecting biometric data corresponding to one or more clusters containing image data, and sending the biometric data to the second device; When the type of the first biometric model is a behavioral feature type, biometric data corresponding to one or more clusters containing behavioral data are selected and sent to the second device.

15. An electronic device, characterized in that: The electronic device is a public device, comprising: a processor, a memory, and a touch screen, wherein the memory and the touch screen are coupled to the processor, the memory is used to store computer program code, and the computer program code includes computer instructions. When the processor reads the computer instructions from the memory, the electronic device performs the following operations: Acquiring biometric data of a plurality of users; transmitting at least a portion of the biometric data of the plurality of users to another electronic device associated with the electronic device, the other electronic device storing a first biometric model corresponding to the first user; receiving an identification result returned by the other electronic device, the identification result being a result of the other electronic device identifying biometric data corresponding to the first user from the at least partial data according to the first biometric model; learning a second biometric model corresponding to the first user based on the recognition result; receiving newly input user data; performing feature comparison on the newly input user data based on the learned second biometric model to determine the user corresponding to the newly input user data; The sending of at least part of the biometric data of the multiple users to the other electronic device includes: dividing the biometric data of the multiple users into multiple clusters, each of the multiple clusters corresponding to one user; and sending the biometric data corresponding to one or more clusters of the multiple clusters to the other electronic device.

16. The electronic device according to claim 15, characterized in that When the processor reads the computer instructions from the memory, the electronic device is further caused to perform the following operations: After learning a second biometric model corresponding to the first user based on the recognition result, receiving an operation; When it is determined based on the learned second biometric model that the operation corresponds to the first user, a first function is executed; when it is determined based on the learned second biometric model that the operation does not correspond to the first user, a second function is executed, wherein the first function is different from the second function.

17. The electronic device according to claim 15 or 16, characterized in that: The association between the other electronic device and the electronic device includes any one or more of the following: the electronic device and the other electronic device have logged in to the same account, the electronic device and the other electronic device are connected to the same wireless network, the account logged in to the electronic device and the account logged in to the other electronic device belong to the same group, and the electronic device and the other electronic device have established a communication connection.

18. The electronic device according to claim 15 or 16, characterized in that: The first biometric feature includes one or more of a voice feature, an image feature, and a behavior feature of the first user.

19. The electronic device according to claim 18, wherein: The voice features include voiceprint features and / or timbre features, the image features include one or more of facial features, iris features, fingerprint features, and palm print features, and the behavioral features are any one of the force features of pressing or clicking the screen and the trajectory features of the sliding operation.

20. The electronic device according to claim 15, wherein The sending the biometric data corresponding to one or more clusters of the plurality of clusters to the other electronic device includes: Biometric data corresponding to one or more clusters of the same type as the first biometric model are selected from the multiple clusters, and sent to the other electronic device.

21. The electronic device according to claim 20, characterized in that The selecting, from the plurality of clusters, biometric data corresponding to one or more clusters of the same type as the first biometric model, and sending the biometric data to the other electronic device includes: When the type of the first biometric feature model is a voice feature class, selecting biometric feature data corresponding to one or more clusters containing voice data, and sending the biometric feature data to the other electronic device; When the type of the first biometric model is an image characteristic type, selecting biometric data corresponding to one or more clusters containing image data and sending the biometric data to the other electronic device; When the type of the first biometric feature model is a behavioral feature type, biometric feature data corresponding to one or more clusters containing behavioral data are selected and sent to the other electronic device.

22. A computer-readable storage medium, characterized in that The method comprises computer instructions, which, when executed on an electronic device, enable the electronic device to execute the method for identifying a user identity on a public device as claimed in any one of claims 8 to 14.

23. A chip system, characterized in that: The device comprises one or more processors. When the one or more processors execute instructions, the one or more processors perform the method for identifying user identity on a public device according to any one of claims 8 to 14.

Images