Intelligent device control method, device, intelligent device and storage medium

By recording and analyzing the historical interaction data between users and smart devices, smart devices can make personalized bionic behaviors in different scenarios, solving the problem of low natural attributes of existing smart devices, improving user experience, and avoiding deep learning models Data generation is difficult.

CN117215403BActive Publication Date: 2024-12-03BEIJING XIAOMI ROBOT TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310927492.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-07-26
Publication Date
2024-12-03
Estimated Expiration
2043-07-26

AI Technical Summary

Technical Problem

Existing smart devices, such as robot dogs, are unable to perform personalized bionic behaviors in different interactive scenarios, resulting in lower natural attributes and stronger mechanical attributes, which reduces the user's user experience.

Method used

By recording the bionic behavior and its preference values ​​in the historical interaction scenario between the user and the smart device, determine the target interaction scenario consistent with the current interactive scenario, and select the target bionic behavior corresponding to the target preference value, and control the smart device to perform the target bionic behavior. .

Benefits of technology

Enhanced the natural properties of smart devices, lowered the mechanical properties, and made their behavior in different interactive scenarios closer to the interactive behavior of pets, improves the user experience, and avoids the difficulty of data generation and human labeling in deep learning model training. .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117215403B_ABST
    Figure CN117215403B_ABST
Patent Text Reader

Abstract

The present disclosure relates to a smart device control method, device, smart device and storage medium, and relates to the field of human-computer interaction technology. It includes: recording the bionic behavior of the smart device in multiple historical interaction scenarios of the interaction between the user and the smart device and the user's total preference value for the bionic behavior; determining a target interaction scene consistent with the current interaction scene from multiple historical interaction scenes; selecting a target bionic behavior corresponding to the target preference value from the total preference values ​​corresponding to multiple bionic behaviors in the target interaction scene; and controlling the smart device to execute the target bionic behavior. Using the smart device control method proposed in the present disclosure, the target bionic behavior that is triggered frequently by the user can be directly displayed without the user issuing an interaction behavior, thereby improving the natural attributes of the smart device.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of human-computer interaction technology, and in particular to a smart device control method, device, smart device and storage medium. Background Art

[0002] At present, more and more users choose to keep pets, but users need to spend a lot of time and energy to take care of their pets. In order to solve this problem, smart devices such as robot dogs have emerged. Robot dogs can provide users with pet-like companionship and emotional interaction, and users do not need to spend time and energy to take care of robot dogs.

[0003] In related technologies, robot dogs can recognize user gesture commands, voice commands and other instructions, and perform corresponding bionic behaviors based on these instructions. However, robot dogs can only perform bionic behaviors based on the user's explicit interactive commands, resulting in the robot dog's lower natural attributes and stronger mechanical attributes, thereby reducing the user experience. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present disclosure provides a smart device control method, apparatus, smart device and storage medium.

[0005] According to a first aspect of an embodiment of the present disclosure, there is provided a smart device control method, including:

[0006] Recording the bionic behaviors of the smart device and the user's total preference value for the bionic behaviors in multiple historical interaction scenarios between the user and the smart device, wherein the bionic behaviors are the behaviors fed back by the smart device after the user interacts with the smart device;

[0007] Determine a target interaction scene consistent with the current interaction scene from the plurality of historical interaction scenes;

[0008] Selecting a target bionic behavior corresponding to a target preference value from the total preference values ​​corresponding to a plurality of bionic behaviors in the target interaction scenario;

[0009] Control the smart device to execute the target bionic behavior.

[0010] Optionally, recording the bionic behaviors of the smart device and the user's total preference value for the bionic behaviors in multiple historical interaction scenarios of the interaction between the user and the smart device includes:

[0011] For each of the multiple historical interaction scenarios, according to the interaction behavior in which the user instructs the smart device to perform the bionic behavior, the preference value of the bionic behavior indicated by the interaction behavior is accumulated to obtain the user's total preference value for the bionic behavior.

[0012] Optionally, for each of the plurality of historical interaction scenarios, according to the interaction behavior in which the user instructs the smart device to perform the bionic behavior, accumulating the preference value of the bionic behavior indicated by the interaction behavior to obtain the user's total preference value for the bionic behavior includes:

[0013] For each of the multiple historical interaction scenarios, the preference values ​​of the bionic behaviors indicated by the interaction behaviors are accumulated according to the number of interaction behaviors of the user to obtain the total preference value; wherein the number of interaction behaviors is proportional to the total preference value.

[0014] Optionally, the bionic behavior includes at least one of interactive sound, bionic action and lighting effect; and recording the bionic behavior of the smart device and the user's total preference value for the bionic behavior includes at least one of the following:

[0015] Recording a plurality of different interactive sounds and corresponding total preference values;

[0016] Recording a plurality of different bionic actions and corresponding total preference values;

[0017] A plurality of different lighting effects and corresponding total preference values ​​are recorded.

[0018] Optionally, the bionic behavior includes at least one of interactive sound, bionic action and lighting effect; and the target bionic behavior corresponding to the target preference value is selected from the total preference values ​​corresponding to the plurality of bionic behaviors in the target interaction scene, including at least one of the following:

[0019] Selecting a target interactive sound corresponding to a target preference value from a plurality of total preference values ​​corresponding to the interactive sounds;

[0020] Selecting a target bionic action corresponding to a target preference value from the total preference values ​​corresponding to a plurality of different bionic actions;

[0021] A target lighting effect corresponding to a target preference value is selected from the total preference values ​​corresponding to a plurality of different lighting effects.

[0022] Optionally, selecting a target bionic behavior corresponding to a target preference value from the total preference values ​​corresponding to a plurality of bionic behaviors in the target interaction scenario includes:

[0023] Screening out a preset number of candidate preference values ​​from the plurality of total preference values, wherein a minimum preference value among the plurality of screened candidate preference values ​​is greater than a maximum preference value among the unscreened preference values;

[0024] Randomly selecting a candidate preference value from the plurality of candidate preference values ​​as the target preference value;

[0025] Determine the target bionic behavior corresponding to the target preference value.

[0026] Optionally, selecting a target bionic behavior corresponding to a target preference value from the total preference values ​​corresponding to a plurality of bionic behaviors in the target interaction scenario includes:

[0027] Selecting a maximum preference value from the plurality of total preference values ​​as the target preference value;

[0028] Determine the target bionic behavior corresponding to the target preference value.

[0029] Optionally, determining a target interaction scene consistent with the current interaction scene from the plurality of historical interaction scenes includes:

[0030] Determining target identity information from multiple historical identity information;

[0031] The target interaction scene is determined from the plurality of historical interaction scenes corresponding to the target identity information.

[0032] Optionally, the interactive behavior includes at least one of an action instruction, a voice instruction and an interactive instruction.

[0033] Optionally, the historical interaction scene or the current interaction scene includes at least one of the following information:

[0034] The time period when the user interacts with the smart device, the environment information when the user interacts with the smart device, and the status information of the user.

[0035] According to a second aspect of an embodiment of the present disclosure, there is provided a smart device control apparatus, comprising:

[0036] A total preference value determination module is configured to record the bionic behaviors of the smart device and the total preference value of the user for the bionic behaviors in multiple historical interaction scenarios between the user and the smart device, wherein the bionic behaviors are the behaviors fed back by the smart device after the user interacts with the smart device;

[0037] A scene screening module is configured to determine a target interaction scene that is consistent with the current interaction scene from the plurality of historical interaction scenes;

[0038] a preference value screening module configured to select a target bionic behavior corresponding to a target preference value from the total preference values ​​corresponding to a plurality of bionic behaviors in the target interaction scenario;

[0039] The control module is configured to control the smart device to execute the target bionic behavior.

[0040] According to a third aspect of an embodiment of the present disclosure, there is provided a smart device, including:

[0041] processor;

[0042] a memory for storing processor-executable instructions;

[0043] Wherein, the processor is configured to:

[0044] Execute the steps of the smart device control method provided in the first aspect of the embodiment of the present disclosure.

[0045] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the smart device control method provided in the first aspect of the present disclosure are implemented.

[0046] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0047] Through the above technical solution, the bionic behaviors that the user instructs the smart device to execute in historical interaction scenarios and the user's total preference value for the bionic behaviors can be recorded; and when the current interaction scenario is consistent with the historical interaction scenario, the target bionic behavior corresponding to the target preference value is selected from multiple bionic behaviors in historical interaction scenarios consistent with the current interaction scenario to be executed.

[0048] In this process, since the smart device has recorded the bionic behaviors triggered by the user through interactive behaviors in historical interaction scenarios, if the smart device determines that the current interaction scenario is a historical interaction scenario, it can directly select the user's favorite target bionic behavior from multiple bionic behaviors and control the smart device to execute the target bionic behavior without the user having to trigger the smart device's target bionic behavior through interactive behaviors. As a result, the natural properties of the smart device are enhanced and the mechanical properties are reduced. The target bionic behavior of the smart device is closer to the interactive behavior of a pet, thereby improving the user experience.

[0049] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0051] Figure 1 The figure is a flow chart of a method for controlling a smart device according to an exemplary embodiment.

[0052] Figure 2 The invention is a block diagram of a smart device control apparatus according to an exemplary embodiment.

[0053] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0054] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0055] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.

[0056] In the related technology, robot dogs can recognize the user's gesture commands, voice commands and other instructions, and perform corresponding bionic behaviors based on these instructions. However, robot dogs can only perform bionic behaviors based on the user's explicit interactive commands, resulting in the robot dog's lower natural attributes and stronger mechanical attributes. For example, the robot dog cannot perform personalized bionic behaviors for different interactive scenarios, which makes the robot dog lack the performance ability of a pet and unable to think and make decisions like a real pet.

[0057] To solve this problem, a deep learning model can be used. The deep learning model can enable the robot dog to perform personalized bionic behaviors in different interaction scenarios. However, using a deep learning model to train a robot dog has the following drawbacks:

[0058] First, training deep learning models requires a large amount of interaction data between users and robot dogs. The generation and collection of these interaction data are very difficult. For example, some of the collected interaction data may be useless or redundant, or some of the collected data may have data quality problems. These useless data, redundant data, or data with quality problems need to be pre-processed such as cleaning and filtering, which makes it very difficult to generate interaction data.

[0059] Secondly, some interaction data contain the user's personal identity and health status, which may lead to the leakage of user privacy. Therefore, corresponding protection measures need to be taken to protect user privacy, which also brings difficulties to the generation of interaction data.

[0060] Third, some interaction data are rather special and need to be manually labeled before they can be used to train deep learning models. The process of labeling interaction data requires a lot of manpower investment, which inevitably wastes a lot of human resources.

[0061] Based on this, Figure 1 is a flow chart of a method for controlling an intelligent device according to an exemplary embodiment. Figure 1 As shown, the smart device control method is used in a smart device and includes the following steps.

[0062] In step S11, the bionic behaviors of the smart device and the user's total preference value for the bionic behaviors in multiple historical interaction scenarios between the user and the smart device are recorded.

[0063] In fields such as robotics, artificial intelligence, and bioengineering, smart devices can imitate the behavior of living organisms to perceive the environment, avoid obstacles, or interact with people, thereby completing various tasks. Therefore, bionic behavior can be understood as imitating the behavior of living organisms.

[0064] In the disclosed embodiment, the bionic behavior is the behavior fed back to the user by the smart device after the user interacts with the smart device. The bionic behavior of the smart device is close to the interactive behavior of a pet. The bionic behavior includes at least one of interactive sound, bionic action and lighting effect. The interactive sound refers to the sound fed back by the smart device after the user interacts with the smart device. The sound can be a sound imitating a pet, such as barking, or an anthropomorphic sound, such as saying good morning or singing. The bionic action refers to the action fed back by the smart device after the user interacts with the smart device, such as shaking the butt, shaking the head, bowing, standing and squatting. The lighting effect is the lighting effect generated by the smart device, such as flashing, gradient and dimming.

[0065] Interactive behavior is the behavior of the user instructing the smart device to perform certain specific bionic behaviors. Interactive behavior includes at least one of action instructions, voice instructions and interactive instructions. Action instructions include human gestures, facial expressions and body movements. When the user issues an action instruction, he / she is not in direct contact with the smart device. The smart device can collect action instructions through the configured camera and other image acquisition devices; voice instructions are the voice issued by the user. The smart device can collect voice instructions through the configured microphone and other audio acquisition devices; interactive instructions refer to the human interactive actions perceived by the smart device when the user interacts with the smart device through touch. When the user issues an interactive instruction, he / she will be in direct contact with the smart device. The smart device can detect the user's interactive instructions such as touching and patting through sensors such as contact sensors and flight sensors (TOF).

[0066] In response to different user interaction behaviors, smart devices will provide feedback with different bionic behaviors.

[0067] For example, taking the smart device as a robot dog, the interactive behavior is the action instruction of "waving", and the corresponding bionic behavior is "shaking butt". If the robot dog has built-in logic of "responding to the user's action instruction of waving, controlling the robot dog to shake its butt", when the user waves at the robot dog, the robot dog will automatically shake its butt.

[0068] For example, taking the smart device as a robot dog, the interactive behavior is the voice command of "ABC, come here quickly", and the corresponding bionic behavior is "running and shaking the butt". If the robot dog has built-in logic of "responding to the user's voice command of "ABC, come here quickly", control the robot dog to shake its butt", when the user makes the sound of "ABC, come here quickly", the robot dog will run and shake its butt as it approaches the user.

[0069] For example, taking the smart device as a robot dog, the interactive behavior is the interactive instruction of "patting", and the corresponding bionic behavior is "squatting". If the robot dog has built-in logic of "responding to the user's action instruction of patting the robot dog's head, controlling the robot dog to squat", when the user pats the robot dog's head, the robot dog will automatically squat.

[0070] The historical interaction scene includes at least one of the time period when the user interacts with the smart device, the environment information when the user interacts with the smart device, and the user's state information. The user's state information at least includes information such as the user's emotions; the environment information at least includes the sound environment and light environment when the user interacts with the smart device, such as whether the sound environment is quiet or noisy, and whether the light environment is bright or dim.

[0071] The same user may have different interactive behaviors in different historical interaction scenarios. An account can be created for each user in the smart device, and the bionic behaviors triggered by the user corresponding to each account in different historical interaction scenarios and the total preference value corresponding to the bionic behaviors can be recorded.

[0072] Scene Number time User sentiment Ambient Sound Light S1 morning Pleasure Quiet Bright S2 night exhausted noisy Dark

[0073] Table 1

[0074] For example, please refer to Table 1. When the user is in the "morning" time period, the light is bright and the ambient sound is quiet, if the image acquisition device of the smart device captures that the emotion expressed by the user's face is happy, then morning, happy, quiet and bright will be established as historical interaction scene S1; when the user is in the "evening" time period, the light is dim and the environment is noisy, if the image acquisition device of the smart device captures that the emotion expressed by the user's face is tired, then evening, tired, noisy and dim will be established as historical interaction scene S2.

[0075] After establishing the historical interaction scene, it is also necessary to establish the bionic behaviors of the smart devices triggered by the users in the historical interaction scenes and the corresponding total preference values, that is, to establish a mapping table between the bionic behaviors in the historical interaction scenes and the total preference values ​​of the users for the bionic behaviors. The total preference value reflects the user's preference for the triggered bionic behaviors in the historical interaction scenes. For example, the higher the total preference value, the higher the user's preference for the triggered bionic behaviors in the historical interaction scenes.

[0076] Since bionic behavior includes interactive sounds, bionic actions and equivalents, recording the total preference value corresponding to the bionic actions also includes at least one of the following: recording multiple different interactive sounds and corresponding total preference values, recording multiple different bionic actions and corresponding total preference values, recording multiple different lighting effects and corresponding total preference values.

[0077]

[0078] Table 2

[0079] For example, please refer to the mapping table under the interactive scene S1 shown in Table 2. The interactive sounds corresponding to numbers V1 to V3 are woof, good morning and singing respectively; the interactive sounds corresponding to numbers M1 to M3 are shaking buttocks, shaking head and bowing respectively; the lighting effects corresponding to numbers L1 to L3 are flashing, gradient and dim respectively.

[0080] If in the historical interaction scenario S1 of morning, pleasure, quiet and bright, for interactive sound, the number of times the user triggers the smart device to sing > the number of times the user triggers the smart device to say good morning > the number of times the user triggers the smart device to say bark, so the total preference value corresponding to singing > the total preference value for saying good morning > the total preference value for bark; for bionic movements, the number of times the user triggers the smart device to bow > the number of times the user triggers the smart device to shake its head > the number of times the user triggers the smart device to shake its buttocks, so the total preference value corresponding to bowing > the total preference value corresponding to shaking its head > the total preference value corresponding to shaking its buttocks; for lighting effects, the number of times the user triggers flashing > the number of times the user triggers gradient > the number of times the user triggers dimming, so the total preference value corresponding to flashing > the total preference value corresponding to gradient > the total preference value corresponding to dimming.

[0081] As can be seen from Table 2, Table 2 records the total preference values ​​corresponding to different bionic behaviors triggered in the interactive scene S1 in a quiet environment in the morning when the user is in a pleasant mood. Similarly, the total preference values ​​corresponding to different bionic behaviors triggered in the interactive scene S2 in a noisy environment at night can also be recorded, and then the bionic behaviors triggered by the user in different interactive scenes such as S1 and S2 and the total preference values ​​corresponding to the bionic behaviors are obtained, that is, the bionic behaviors triggered by the user in different environments and different emotions and the user's preference for the bionic behaviors are recorded.

[0082] It is understandable that Table 2 is an example of the historical interaction scenario S1 and is not intended to limit the historical interaction scenario S1. The recording methods of the other historical interaction scenarios are similar to the mapping table of the historical interaction scenario S1 and are not described in detail here.

[0083] In step S12, a target interaction scene that is consistent with the current interaction scene is determined from the plurality of historical interaction scenes.

[0084] The current interaction scenario includes at least one of the time period when the user interacts with the smart device, the environment information when the user interacts with the smart device, and the user's state information.

[0085] The same user will trigger the smart device to perform bionic behaviors in different historical interaction scenarios such as different time periods, different environmental information, and different emotions. Therefore, the same user corresponds to multiple different historical interaction scenarios. After recording the multiple different historical interaction scenarios corresponding to the user in step S11, if the current interaction scenario of the user exists in multiple historical interaction scenarios, the target interaction scene consistent with the current interaction scenario is determined from the multiple scenarios.

[0086] For example, when a user triggers a smart device to perform a bionic behavior in the historical interaction scene S1 in the morning of X / X / X, when the user is in a good mood, the light is bright, and the ambient sound is quiet, if the time period of the user at the current moment is also the current interaction scene of morning, when the user is in a good mood, the light is bright, and the ambient sound is quiet, since the current interaction scene is the same as the historical interaction scene S1, the historical interaction scene S1 is used as the target interaction scene consistent with the current interaction scene.

[0087] It can be understood that the historical interaction scene that is consistent with the current interaction scene may be completely consistent with information such as time period, user emotion, ambient sound and light, or at least one of the information such as time period, user emotion, ambient sound and light may be consistent, and when they are relatively consistent, the priority of user emotion > the priority of ambient sound > the priority of time > the priority of light.

[0088] For example, if the emotion of the user in the historical interaction scene S1 is joyful, and if the emotion of the user in the current interaction scene is also joyful, it can also be determined that the historical interaction scene is consistent with the current interaction scene.

[0089] For another example, if the user's emotion in the historical interaction scene was pleasant and the ambient sound was quiet, if the user's emotion in the current interaction scene is also pleasant and the ambient sound is also quiet, it can be determined that the historical interaction scene is consistent with the current interaction scene.

[0090] When a historical interaction scene that is completely consistent with the time period, user emotion, ambient sound, light and other information of the current interaction scene is taken as the target interaction scene, since the compared information is more and richer, the obtained target interaction scene is the same as the current interaction scene, then the target bionic behavior performed based on the target interaction scene can accurately meet the user's preference in the target interaction scene; when a historical interaction scene that is consistent with at least one of the information such as the time period, user emotion, ambient sound and light of the current interaction scene is taken as the target interaction scene, a target interaction scene similar to the current interaction scene can be provided to the user when the number of historical interaction scenes corresponding to the user is small, and the target bionic behavior performed based on the similar target interaction scene is also close to the user's preference in the target interaction scene.

[0091] In step S13, a target bionic behavior corresponding to a target preference value is selected from the total preference values ​​corresponding to a plurality of bionic behaviors in the target interaction scenario.

[0092] The target bionic behavior corresponding to the target preference value selected from multiple total preference values ​​is the bionic behavior that the user prefers to trigger in the target interaction scenario, and can also be understood as the bionic behavior that the user triggers more frequently in the target interaction scenario.

[0093] The maximum preference value may be selected from multiple total preference values ​​as the target preference value, or a total preference value may be randomly selected from the top N total preference values ​​of the multiple total preference values ​​as the target preference value.

[0094] When selecting the target bionic behavior corresponding to the target preference value, bionic behaviors such as interactive sound, bionic action and lighting effect can be atomic behaviors, that is, the three are inseparable behaviors. In the target interaction scenario, the smart device will select "singing" from the interactive sound, "bowing" from the bionic action, and "flashing" from the lighting effect as the target bionic behavior. The smart device will simultaneously execute the target bionic behaviors of "singing", "bowing" and "flashing". These three target bionic behaviors are executed simultaneously by the smart device and are inseparable.

[0095] In step S14, the smart device is controlled to execute the target bionic behavior.

[0096] The target bionic behavior is a bionic behavior that the user prefers to trigger in the target interaction scenario, or it can be a bionic behavior that the user triggers a preset number of times in the target interaction scenario.

[0097] For example, please refer to the mapping table shown in Table 2. After establishing the mapping relationship between the interactive sound and the corresponding total preference value, the mapping relationship between the bionic action and the corresponding total preference value, and the mapping relationship between the lighting effect and the corresponding total preference value under the historical interaction scenes S1 of morning, pleasant mood, quiet and bright, if the smart device recognizes that the current interaction scene is the historical interaction scene S1, it will directly select "singing" from the interactive sound, "bowing" from the bionic action, and "flashing" from the lighting effect as the target bionic behavior, and then execute the target bionic behaviors of "singing", "bowing" and "flashing" without the user having to issue an interactive behavior as in the historical interaction scene, and can directly execute the user's favorite bionic behavior.

[0098] In the historical interaction scenario, the user needs to initiate an interaction behavior and then instruct the smart device to perform the bionic behavior; in the current interaction scenario, the user does not need to initiate an interaction behavior, and the smart device can also autonomously perform bionic behaviors based on multiple bionic behaviors that the user likes in the target interaction scenario consistent with the current interaction scenario.

[0099] For example, in the historical interaction scenario, the user needs to say "good morning" by voice before the smart device will respond with the voice of "good morning", perform the "shake butt" action, and flash the light; in the current interaction scenario, the user does not need to say "good morning". The smart device will autonomously send out the user's favorite "good morning" voice, perform the "shake butt" action, and flash the light based on the mapping table for different historical interaction scenarios recorded in Table 2, that is, according to the user's mood, current environment and time period.

[0100] Through the above technical solution, the bionic behaviors that the user instructs the smart device to execute in historical interaction scenarios and the total preference values ​​corresponding to the bionic behaviors can be recorded; and when the current interaction scenario is consistent with the historical interaction scenario, the target bionic behavior corresponding to the target preference value is selected from multiple bionic behaviors in historical interaction scenarios consistent with the current interaction scenario to be executed.

[0101] In this process, since the smart device has recorded the bionic behaviors triggered by the user through interactive behaviors in historical interaction scenarios, the smart device can directly select the user's favorite target bionic behavior from multiple bionic behaviors when determining that the current interaction scenario is a historical interaction scenario, and control the smart device to execute the target bionic behavior without the user triggering the target bionic behavior through interactive behaviors. As a result, the natural properties of the smart device are enhanced and the mechanical properties are reduced. The target bionic behavior of the smart device is closer to the behavior of a pet, thereby improving the user experience.

[0102] In addition, the present disclosure records the mapping relationship between bionic behaviors and corresponding total preference values ​​in multiple historical interaction scenarios, so the smart device can determine the target bionic behavior preferred by the user in different current interaction scenarios based on the mapping relationship. That is, the smart device can perform personalized target bionic behavior in different interaction scenarios without the help of deep learning models, thereby avoiding the difficulties in generating interaction data using deep learning models and the waste of manpower in manually annotating interaction data.

[0103] Some specific embodiments of the above steps S11 to S14 will be introduced below.

[0104] In a specific embodiment, for each of the multiple historical interaction scenarios, according to the interactive behavior in which the user instructs the smart device to perform the bionic behavior, the preference value of the bionic behavior indicated by the interactive behavior is accumulated to obtain the user's total preference value for the bionic behavior.

[0105] For each of the plurality of historical interaction scenarios, the preference values ​​of the bionic behaviors indicated by the interaction behaviors are accumulated according to the number of interaction behaviors of the user to obtain the total preference value.

[0106] The number of bionic behaviors indicated by the interactive behavior is proportional to the total preference value corresponding to the bionic behavior.

[0107] For example, please refer to Table 2. Taking the smart device as a robot dog as an example, in the first historical interaction scenario S1, if the user issues an interactive behavior of "good morning", the robot dog will respond with good morning and shake its butt and flash the light. At this time, the robot dog will add 1 to the preference value corresponding to "good morning", add 1 to the preference value corresponding to "shaking butt", and add 1 to the preference value for flashing lights.

[0108] In the second same historical interaction scenario S1, if the user initiates the interaction behavior of "stroking the robot dog's head", the robot dog will respond with a bark and shake its butt and the light will dim. At this time, the robot dog will add 1 to the preference value corresponding to "bark", add 1 to the preference value corresponding to "shake its butt", and add 1 to the preference value for flashing dim.

[0109] It can be understood that, in the initial state, the total preference value corresponding to each bionic behavior shown in Table 2 is 0. After the user has experienced the same historical interaction scenario many times, the robot dog will add a target value (for example, 1) to the preference value corresponding to the bionic behavior triggered by the user in each historical interaction scenario. In this way, the total preference value corresponding to multiple bionic behaviors in the historical interaction scenario is accumulated.

[0110] Similarly, for other historical interaction scenarios different from the historical interaction scenario S1, the total preference values ​​corresponding to multiple bionic behaviors in the other historical interaction scenarios are established only after the user has experienced the same historical interaction scenarios multiple times.

[0111] Through the above technical solution, the total preference value of bionic behaviors triggered by the user after experiencing the same historical interaction scene multiple times can be recorded in the mapping table corresponding to the historical interaction scene. In this way, the user's preference for different bionic behaviors in the historical interaction scene is obtained, and the smart device can display the target bionic behavior that the user likes in the current interaction scene according to the user's preference for different bionic behaviors in the historical interaction scene.

[0112] In a specific embodiment, when screening the target preference value, since the target bionic behavior corresponding to the target preference value is the bionic behavior that the user likes, the maximum preference value can be selected from multiple total preference values ​​as the target preference value; and then the target bionic behavior corresponding to the target preference value is determined according to the mapping relationship between the bionic behavior and the total preference value in the mapping table shown in Table 2.

[0113] A target interactive sound corresponding to the maximum preference value can be selected from the total preference values ​​corresponding to multiple different interactive sounds, a target bionic action corresponding to the maximum preference value can be selected from the total preference values ​​corresponding to multiple different bionic actions, and a target lighting effect corresponding to the maximum preference value can be selected from the total preference values ​​corresponding to multiple different lighting effects.

[0114] For example, please refer to Table 2, in the historical interaction scene S1 in the morning when the user is in a happy mood, quiet and bright light, the number of times singing, bowing and flashing lights are triggered is the largest. Therefore, the total preference value corresponding to singing is the largest among the total preference values ​​corresponding to multiple interactive sounds, the total preference value corresponding to bowing is the largest among the total preference values ​​corresponding to multiple bionic actions, and the total preference value corresponding to flashing is the largest among the total preference values ​​corresponding to multiple lighting effects.

[0115] If the smart device recognizes that the current interaction scene is the historical interaction scene S1, it will directly select "singing" with the largest total preference value from multiple interactive sounds, select "bowing" with the largest total preference value from multiple bionic actions, and select "flashing" with the largest total preference value from multiple lighting effects as the target bionic behaviors, and then execute the target bionic behaviors of "singing", "bowing" and "flashing" without the user having to make interactive behaviors as in the historical interaction scenes, and can directly execute bionic behaviors frequently triggered by the user.

[0116] Through the above technical solution, the target bionic behavior corresponding to the maximum preference value can be selected from multiple total preference values, that is, the target bionic behavior most frequently triggered by the user is selected to be executed, so that the target bionic behavior executed by the smart device is in line with the user's interests, thereby improving the user experience.

[0117] In a specific embodiment, if the current interaction scene of the user is the historical interaction scene S1, and the smart device is triggered to execute the same set of target bionic behaviors each time, this will undoubtedly reduce the user's sense of freshness and lead to a reduced user experience. Therefore, a preset number of multiple candidate preference values ​​can be screened out from the multiple total preference values, and the minimum preference value among the multiple screened candidate preference values ​​is greater than the maximum preference value among the unscreened preference values; a candidate preference value is randomly selected from the multiple candidate preference values ​​as the target preference value; and the target bionic behavior corresponding to the target preference value is determined.

[0118] A preset number of multiple candidate preference values ​​can be screened out from the total preference values ​​corresponding to multiple interactive sounds, the minimum preference value among the multiple screened candidate preference values ​​being greater than the maximum preference value among the unscreened preference values; a candidate preference value is randomly selected from the multiple candidate preference values ​​as the target preference value; and a target interactive sound corresponding to the target preference value is determined.

[0119] The bionic behaviors corresponding to the candidate preference values ​​are bionic behaviors that are frequently triggered by the user, and the non-candidate preference values ​​are bionic behaviors that are not frequently triggered by the user or are not triggered at all.

[0120] For example, please refer to Table 2. Taking the preset number of 2 as an example, the total preference values ​​1, 2, and 3 can be arranged in order from large to small, and then the first two total preference values, namely total preference value 3 and total preference value 2, are selected as candidate preference values; and then the total preference value 2 is randomly selected from the total preference value 2 and the total preference value 3 as the target preference value, and "Good morning" corresponding to the target preference value is used as the target interaction sound.

[0121] A preset number of multiple candidate preference values ​​can be screened out from the total preference values ​​corresponding to multiple bionic actions, the minimum preference value among the multiple screened candidate preference values ​​being greater than the maximum preference value among the unscreened preference values; a candidate preference value is randomly selected from the multiple candidate preference values ​​as the target preference value; and a target bionic action corresponding to the target preference value is determined.

[0122] For example, please refer to Table 2. Taking the preset number of 2 as an example, the total preference values ​​1, 2, and 3 can be arranged in order from large to small, and then the first two total preference values, namely, total preference value 3 and total preference value 2, are selected as candidate preference values; and then the total preference value 2 is randomly selected from the total preference value 2 and the total preference value 3 as the target preference value, and the "shaking head" corresponding to the target preference value is used as the target bionic action.

[0123] A preset number of multiple candidate preference values ​​can be screened out from the total preference values ​​corresponding to multiple lighting effects, the minimum preference value among the multiple screened candidate preference values ​​being greater than the maximum preference value among the unscreened preference values; a candidate preference value is randomly selected from the multiple candidate preference values ​​as the target preference value; and a target lighting effect corresponding to the target preference value is determined.

[0124] For example, please refer to Table 2. Taking the preset number of 2 as an example, the total preference values ​​0, 2, and 3 can be arranged in order from large to small, and then the first two total preference values, namely total preference value 3 and total preference value 2, are selected as candidate preference values; and then the total preference value 3 is randomly selected from the total preference value 2 and the total preference value 3 as the target preference value, and the "flash" corresponding to the target preference value is used as the target lighting effect.

[0125] After randomly selecting "Good morning" from multiple interactive sounds, randomly selecting "shaking head" from multiple bionic actions, and randomly selecting "flashing" from multiple lighting effects, you can control the smart device to say "good morning" in the current interactive scenario, shake its head, and flash the lights.

[0126] Through the above technical scheme, when facing the same interaction scenario, the smart device can randomly select a target bionic behavior corresponding to a candidate preference value from multiple candidate preference values ​​to execute, that is, the smart device will execute different target bionic behaviors when facing the same interaction scenario, thereby improving the user's sense of freshness when using the smart device, and thus improving the user experience; and the candidate preference value is large, and the number of times the user triggers the bionic behavior corresponding to the candidate preference value is also relatively frequent, so the bionic behavior corresponding to the candidate preference value randomly selected from the candidate preference value is also frequently triggered by the user, and the bionic behavior corresponding to the non-candidate preference value that is not frequently triggered by the user will not be displayed to the user, thereby further improving the user experience.

[0127] In a specific embodiment, the above scheme can enable the smart device to execute the target bionic behavior that is frequently triggered by the user in different current interaction scenarios corresponding to the same user, that is, the smart device can realize personalized display in different interaction scenarios facing the same user; and the same smart device may be used by different users. Therefore, the following scheme will specifically explain that the smart device executes the target bionic behavior that is frequently triggered by the user in different current interaction scenarios corresponding to different users, that is, the smart device realizes personalized display in different interaction scenarios facing different users.

[0128] In step S21, target identity information is determined from a plurality of historical identity information.

[0129] The historical identity information of different users can be established in the smart device, which includes the user's face, voiceprint and other biometric information; and for multiple different users, the bionic behavior of the smart device and the total preference value corresponding to the bionic behavior in multiple historical interaction scenarios between each user and the smart device are recorded.

[0130] After being awakened by the current user, the smart device can first collect the current user's face through an image acquisition device, or collect the current user's voiceprint through an audio acquisition device, and then determine the current user's identity; then determine the current user's target identity information from multiple stored historical identity information.

[0131] In step S22, the target interaction scene is determined from the multiple historical interaction scenes corresponding to the target identity information.

[0132] After determining the target identity information, determine multiple historical interaction scenes corresponding to the target user indicated by the target identity information, and determine the target interaction scene consistent with the current interaction scene in which the target user is currently located from the multiple historical interaction scenes. After obtaining the target interaction scene, the target bionic behavior frequently triggered by the target user can be determined according to the above steps S11 to S14, and the smart device can be controlled to execute the target bionic behavior.

[0133] Through the above technical solution, the historical identity information of different users can be established in the smart device to identify different users. Since the historical interaction scenarios between different users and the smart device are different, the mapping tables of the historical interaction scenarios corresponding to different users are different. Then the smart device will exhibit different bionic behaviors according to the mapping tables of the historical interaction scenarios of different users, thereby realizing personalized display for different users.

[0134] Figure 2 is a block diagram of a smart device control apparatus according to an exemplary embodiment. Figure 2, the intelligent device control device 200 includes: a total preference value determination module 210, a scene screening module 220, a preference value screening module 230 and a control module 240;

[0135] The total preference value determination module 210 is configured to record the bionic behavior of the smart device and the total preference value of the user for the bionic behavior in multiple historical interaction scenarios between the user and the smart device;

[0136] A scene screening module 220 is configured to determine a target interaction scene consistent with the current interaction scene from the plurality of historical interaction scenes;

[0137] The preference value screening module 230 is configured to select a target bionic behavior corresponding to a target preference value from the total preference values ​​corresponding to the multiple bionic behaviors in the target interaction scenario, wherein the target bionic behavior is a bionic behavior that the user likes;

[0138] The control module 240 is configured to control the smart device to execute the target bionic behavior.

[0139] Optionally, the total preference value determination module 210 includes:

[0140] The first total preference value determination submodule is configured to, for each of the multiple historical interaction scenarios, accumulate the preference values ​​of the bionic behaviors indicated by the interaction behaviors according to the user's instructions for the smart device to perform the bionic behaviors, and obtain the user's total preference value for the bionic behaviors.

[0141] Optionally, the first total preference value determination submodule includes:

[0142] The second total preference value determination submodule is configured to, for each of the multiple historical interaction scenarios, accumulate the preference values ​​of the bionic behaviors indicated by the interaction behaviors according to the number of interaction behaviors of the user, to obtain the total preference value; wherein the number of interaction behaviors is directly proportional to the total preference value.

[0143] Optionally, the bionic behavior includes at least one of interactive sound, bionic action and lighting effect; the total preference value determination module 210 includes a third total preference value determination submodule, and the third total preference value determination submodule is configured as at least one of the following:

[0144] Recording a plurality of different interactive sounds and corresponding total preference values;

[0145] Recording a plurality of different bionic actions and corresponding total preference values;

[0146] A plurality of different lighting effects and corresponding total preference values ​​are recorded.

[0147] Optionally, the bionic behavior includes at least one of interactive sound, bionic action and lighting effect; the preference value screening module 230 includes a first screening submodule, and the first screening submodule is configured as at least one of the following:

[0148] Selecting a target interactive sound corresponding to a target preference value from a plurality of total preference values ​​corresponding to the interactive sounds;

[0149] Selecting a target bionic action corresponding to a target preference value from the total preference values ​​corresponding to a plurality of different bionic actions;

[0150] A target lighting effect corresponding to a target preference value is selected from the total preference values ​​corresponding to a plurality of different lighting effects.

[0151] Optionally, the preference value screening module 230 includes:

[0152] A second screening submodule is configured to screen out a preset number of candidate preference values ​​from the plurality of total preference values, wherein a minimum preference value among the plurality of screened candidate preference values ​​is greater than a maximum preference value among the unscreened preference values;

[0153] A third screening submodule is configured to randomly select a candidate preference value from the plurality of candidate preference values ​​as the target preference value;

[0154] The first determination submodule is configured to determine the target bionic behavior corresponding to the target preference value.

[0155] Optionally, the preference value screening module 230 includes:

[0156] a fourth screening submodule, configured to select a maximum preference value from the plurality of total preference values ​​as the target preference value;

[0157] The second determination submodule is configured to determine the target bionic behavior corresponding to the target preference value.

[0158] Optionally, the scene screening module 220 includes:

[0159] A third determination submodule is configured to determine target identity information from multiple historical identity information;

[0160] The scene screening submodule is configured to determine the target interaction scene from the multiple historical interaction scenes corresponding to the target identity information.

[0161] Optionally, the interactive behavior includes at least one of an action instruction, a voice instruction and an interactive instruction.

[0162] Optionally, the historical interaction scene or the current interaction scene includes at least one of the following information:

[0163] The time period when the user interacts with the smart device, the environment information when the user interacts with the smart device, and the status information of the user.

[0164] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0165] The present disclosure also provides a computer-readable storage medium on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the smart device control method provided by the present disclosure are implemented.

[0166] Figure 3 8 is a block diagram of an intelligent device 800 according to an exemplary embodiment. For example, the intelligent device 800 may be a human-machine interactive device such as a robot or a robot dog.

[0167] Reference Figure 3 , the smart device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output interface 812 , a sensor component 814 , and a communication component 816 .

[0168] The processing component 802 generally controls the overall operation of the smart device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned smart device control method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0169] The memory 804 is configured to store various types of data to support operations on the smart device 800. Examples of such data include instructions for any application or method operating on the smart device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0170] The power supply component 806 provides power to the various components of the smart device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the smart device 800.

[0171] The multimedia component 808 includes a screen that provides an output interface between the smart device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the smart device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0172] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the smart device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0173] The input / output interface 812 provides an interface between the processing component 802 and the peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0174] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the smart device 800. For example, the sensor assembly 814 can detect the open / closed state of the smart device 800, the relative positioning of the components, such as the display and keypad of the smart device 800, and the sensor assembly 814 can also detect the position change of the smart device 800 or a component of the smart device 800, the presence or absence of user contact with the smart device 800, the orientation or acceleration / deceleration of the smart device 800, and the temperature change of the smart device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0175] The communication component 816 is configured to facilitate wired or wireless communication between the smart device 800 and other devices. The smart device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0176] In an exemplary embodiment, the smart device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the above-mentioned smart device control method.

[0177] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by the processor 820 of the smart device 800 to complete the above-mentioned smart device control method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0178] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0179] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for controlling an intelligent device, characterized in that: include: Recording the bionic behaviors of the smart device and the user's total preference value for the bionic behaviors in multiple historical interaction scenarios of the interaction between the user and the smart device, wherein the bionic behaviors are the behaviors fed back by the smart device after the user interacts with the smart device, the historical interaction scenarios include the time period when the user interacts with the smart device, the environment information when the user interacts with the smart device, and the user's state information, wherein the user's state information includes the user's emotions; the environment information includes the sound environment and light environment when the user interacts with the smart device; Determine a target interaction scene consistent with the current interaction scene from the plurality of historical interaction scenes; Selecting a target bionic behavior corresponding to a target preference value from the total preference values ​​corresponding to a plurality of bionic behaviors in the target interaction scenario; Control the smart device to execute the target bionic behavior.

2. The method according to claim 1, characterized in that: Recording the bionic behaviors of the smart device and the user's total preference value for the bionic behaviors in multiple historical interaction scenarios between the user and the smart device, including: For each of the multiple historical interaction scenarios, according to the interaction behavior in which the user instructs the smart device to perform the bionic behavior, the preference value of the bionic behavior indicated by the interaction behavior is accumulated to obtain the user's total preference value for the bionic behavior.

3. The method according to claim 2, characterized in that For each of the plurality of historical interaction scenarios, according to the interaction behavior in which the user instructs the smart device to perform the bionic behavior, accumulating the preference value of the bionic behavior indicated by the interaction behavior to obtain the user's total preference value for the bionic behavior, including: For each of the multiple historical interaction scenarios, the preference values ​​of the bionic behaviors indicated by the interaction behaviors are accumulated according to the number of interaction behaviors of the user to obtain the total preference value; wherein the number of interaction behaviors is proportional to the total preference value.

4. The method according to claim 1, characterized in that: The bionic behavior includes at least one of interactive sound, bionic action and lighting effect; recording the bionic behavior of the smart device and the user's total preference value for the bionic behavior includes at least one of the following: Recording a plurality of different interactive sounds and corresponding total preference values; Recording a plurality of different bionic actions and corresponding total preference values; A plurality of different lighting effects and corresponding total preference values ​​are recorded.

5. The method according to claim 1, characterized in that The bionic behavior includes at least one of interactive sound, bionic action and lighting effect; and the target bionic behavior corresponding to the target preference value is selected from the total preference values ​​corresponding to the multiple bionic behaviors in the target interactive scene, including at least one of the following: Selecting a target interactive sound corresponding to a target preference value from a plurality of total preference values ​​corresponding to the interactive sounds; Selecting a target bionic action corresponding to a target preference value from the total preference values ​​corresponding to a plurality of different bionic actions; A target lighting effect corresponding to a target preference value is selected from the total preference values ​​corresponding to a plurality of different lighting effects.

6. The method according to claim 1, characterized in that Selecting a target bionic behavior corresponding to a target preference value from the total preference values ​​corresponding to a plurality of bionic behaviors in the target interaction scenario includes: Screening out a preset number of candidate preference values ​​from the plurality of total preference values, wherein a minimum preference value among the plurality of screened candidate preference values ​​is greater than a maximum preference value among the unscreened preference values; Randomly selecting a candidate preference value from the plurality of candidate preference values ​​as the target preference value; Determine the target bionic behavior corresponding to the target preference value.

7. The method according to claim 1, characterized in that Selecting a target bionic behavior corresponding to a target preference value from the total preference values ​​corresponding to a plurality of bionic behaviors in the target interaction scenario includes: Selecting a maximum preference value from the plurality of total preference values ​​as the target preference value; Determine the target bionic behavior corresponding to the target preference value.

8. The method according to claim 1, characterized in that Determining a target interaction scene consistent with the current interaction scene from the plurality of historical interaction scenes includes: Determining target identity information from multiple historical identity information; The target interaction scene is determined from the plurality of historical interaction scenes corresponding to the target identity information.

9. The method according to any one of claims 1 to 8, characterized in that: The interactive behavior includes at least one of an action instruction, a voice instruction, and an interactive instruction.

10. A smart device control device, characterized in that: include: a total preference value determination module, configured to record the bionic behaviors of the smart device and the total preference value of the user for the bionic behaviors in multiple historical interaction scenarios of the interaction between the user and the smart device, wherein the bionic behaviors are the behaviors fed back by the smart device after the user interacts with the smart device, the historical interaction scenarios include the time period when the user interacts with the smart device, the environment information when the user interacts with the smart device, and the state information of the user, wherein the state information of the user includes the emotions of the user; and the environment information includes the sound environment and the light environment when the user interacts with the smart device; A scene screening module is configured to determine a target interaction scene that is consistent with the current interaction scene from the plurality of historical interaction scenes; a preference value screening module configured to select a target bionic behavior corresponding to a target preference value from the total preference values ​​corresponding to a plurality of bionic behaviors in the target interaction scenario; The control module is configured to control the smart device to execute the target bionic behavior.

11. A smart device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: Execute the steps of any one of the methods of claims 1 to 9.

12. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the steps of the method described in any one of claims 1 to 9 are implemented.