Interactive control method and device, electronic equipment and computer readable storage medium

Abstract

Embodiments of the present application disclose an interactive control method and device, electronic equipment and computer readable storage medium, and relate to the technical field of robots. The method comprises: a robot obtaining an interactive request of a target user, responding to the interactive request based on a target personality model to obtain an interactive response result, wherein the target personality model is obtained by adjusting an original personality model based on interactive frequency information, and the target personality model and the original personality model are used to control the personality of the robot when interacting with the target user. The personality model of the robot is adjusted based on the interactive frequency information, so as to realize dynamic adjustment of the personality of the robot. Furthermore, the personality of the robot is adjusted based on the interactive frequency information, so that the adjustment of the personality of the robot is more in line with the needs of the user, and the rationality of the adjustment of the personality of the robot is improved.

Description

Technical Field

[0001] This application relates to the field of robotics, specifically to an interactive control method, device, electronic device, and computer-readable storage medium. Background Technology

[0002] With the development of robotics technology, there are more and more scenarios for interaction between robots and users, such as navigation, consultation, dialogue or companionship. Users can interact with robots to obtain the information they need or have a good experience.

[0003] As user demands increase, robots with different personalities have become a necessity for development. Currently, although there are strategies for setting or generating robot personalities, robot personalities are mainly set in a fixed way, making it difficult to dynamically adjust them. Summary of the Invention

[0004] This application provides an interactive control method, device, electronic device, and computer-readable storage medium that can dynamically adjust the robot's personality and improve the user experience.

[0005] In a first aspect, embodiments of this application provide an interactive control method applied to a robot, the method comprising:

[0006] Obtain interaction requests from the target user;

[0007] The interaction response result is obtained based on the target personality model in response to the interaction request;

[0008] The target personality model is obtained by adjusting the original personality model based on interaction frequency information. The target personality model and the original personality model are used to control the robot's personality when interacting with the target user.

[0009] Secondly, embodiments of this application also provide an interactive control device for use with a robot, the device comprising:

[0010] The acquisition module is used to acquire interaction requests from the target user;

[0011] The response module is used to respond to the interaction request based on the target personality model and obtain the interaction response result;

[0012] The target personality model is obtained by adjusting the original personality model based on interaction frequency information. The target personality model and the original personality model are used to control the robot's personality when interacting with the target user.

[0013] Optionally, in some embodiments of this application, before obtaining the interaction request of the target user, the apparatus further includes:

[0014] Acquire interaction frequency information for the target user, the interaction frequency information including the interaction frequency between the robot and the target user;

[0015] Determine the robot's original personality model, which is obtained by performing personality initialization processing on the robot;

[0016] The original personality model is optimized based on the interaction frequency information to obtain the target personality model.

[0017] Optionally, in some embodiments of this application, the original personality model includes several personality weight parameters for representing at least one personality trait.

[0018] The step of optimizing the original personality model based on the interaction frequency information to obtain the target personality model includes:

[0019] The target personality model is obtained by optimizing the personality weight parameters in the original personality model based on the interaction frequency information.

[0020] Optionally, in some embodiments of this application, the personality includes extraversion, affinity, emotional stability, and quiet companionship, and the personality weight parameters include a first personality weight parameter for extraversion, a second personality weight parameter for affinity, a third personality weight parameter for emotional stability, and a fourth personality weight parameter for quiet companionship.

[0021] The step of optimizing each of the personality weight parameters in the original personality model based on the interaction frequency information to obtain the target personality model includes:

[0022] If the interaction frequency corresponding to the interaction frequency information is higher than the frequency threshold, then the first personality weight parameter and the second personality weight parameter are increased to obtain the target personality model.

[0023] If the interaction frequency corresponding to the interaction frequency information is lower than the frequency threshold, then the weight parameters of the third personality and the fourth personality are increased to obtain the target personality model.

[0024] Optionally, in some embodiments of this application, optimizing the personality weight parameters in the original personality model based on the interaction frequency information to obtain the target personality model includes:

[0025] Obtain the frequency-personality correspondence, which is the correspondence between interaction frequency and several personality parameters obtained based on reinforcement learning;

[0026] Based on the frequency-personality correspondence, the target personality parameters for each personality weight parameter are determined according to the interaction frequency information.

[0027] The target personality model is obtained by adjusting the weight parameters of each personality in the original personality model according to the target personality parameters.

[0028] Optionally, in some embodiments of this application, the apparatus further includes:

[0029] The robot's predictive personality model is predicted at a future target time point using a machine learning model that utilizes historical user data.

[0030] Output the personality identifier for the predicted personality model;

[0031] In response to receiving personality optimization configuration information, the optimization of the original personality model based on the interaction frequency information is controlled according to the personality optimization configuration information.

[0032] Optionally, in some embodiments of this application, the step of responding to the interaction request based on the target personality model and obtaining the interaction response result includes:

[0033] Determine the current use case;

[0034] The target personality model is adjusted according to the usage scenario to obtain a scenario-based personality model;

[0035] Based on the scenario personality model, respond to the interaction request corresponding to the usage scenario to obtain the interaction response result.

[0036] Thirdly, embodiments of this application also provide an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps in the above-described interactive control method.

[0037] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in the above-described interactive control method.

[0038] Fifthly, embodiments of this application also provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations described in embodiments of this application.

[0039] In summary, the robot in this application embodiment acquires the interaction request of the target user, responds to the interaction request based on the target personality model, and obtains the interaction response result. The target personality model is obtained by adjusting the original personality model based on the interaction frequency information. The target personality model and the original personality model are used to control the robot's personality when interacting with the target user.

[0040] In this embodiment, the robot's personality model is adjusted using interaction frequency information, enabling dynamic adjustment of the robot's personality. Adjusting the robot's personality through interaction frequency information also makes the personality adjustment more aligned with user needs, enhancing the rationality of the adjustment process. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a schematic diagram of a scenario where a robot executes the interactive control method according to an embodiment of this application;

[0043] Figure 2 This is a flowchart illustrating the interactive control method provided in an embodiment of this application;

[0044] Figure 3 This is a schematic diagram of the structure of the interactive control device provided in the embodiments of this application;

[0045] Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application.

[0046] Explanation of icon numbers:

[0047] 101-Robot; 301-Acquisition module; 302-Response module; 401-Processor; 402-Memory; 403-Power supply; 404-Input unit. Detailed Implementation

[0048] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] In the description of the embodiments of this application, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Furthermore, the terms "first," "second," "third," and "fourth" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first," "second," "third," and "fourth" may explicitly or implicitly include one or more features. In the description of the present invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0050] In this application, the term "exemplary" is used to mean "serving as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0051] This application provides an interactive control method, apparatus, electronic device, and computer-readable storage medium. Specifically, this application provides an interactive control apparatus suitable for electronic devices (e.g., robots), including interactive robots such as emotional robots and companion robots.

[0052] For example, please see Figure 1 , Figure 1 This is a schematic diagram of a scenario where a robot executes the interactive control method according to an embodiment of this application. Specifically, the execution process of the robot executing the interactive control method is as follows:

[0053] Robot 101 acquires the interaction request from the target user, responds to the interaction request based on the target's personality model, and obtains the interaction response result.

[0054] The target personality model is obtained by adjusting the original personality model based on interaction frequency information. The target personality model and the original personality model are used to control the robot's personality when interacting with the target user.

[0055] For example, after a user interacts with the robot via voice, touch, or proximity, the number of interactions and the time intervals between them are recorded. The interaction frequency is then calculated, and the robot's original personality model is adjusted based on this frequency to obtain a target personality model. When the user makes a new interaction request, the robot responds to the request based on the adjusted target personality model, resulting in an interaction response.

[0056] In summary, the embodiments of this application adjust the robot's personality model by using interaction frequency information, thereby achieving dynamic adjustment of the robot's personality. Adjusting the robot's personality through interaction frequency information also makes the personality adjustment more aligned with user needs, improving the rationality of the adjustment.

[0057] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the priority of the embodiments.

[0058] Please see Figure 2 , Figure 2 This is a flowchart illustrating the interactive control method provided in an embodiment of this application. Although a logical order is shown in the flowchart, in some cases, the steps shown or described can be performed in a different order than that shown in the flowchart. Specifically, this interactive control method is applied to a robot, and the specific flow of the interactive control method is as follows:

[0059] S201. Obtain the interaction request from the target user.

[0060] Interaction requests refer to requests from users that they expect the robot to provide targeted feedback. These requests may include navigation requests, dialogue requests, or requests for companionship. It is understood that these interaction requests can be obtained by receiving the user's voice, receiving the user's text input, detecting the user's distance, capturing the user's image, or recognizing the user's gestures.

[0061] S202. Respond to the interaction request based on the target personality model to obtain the interaction response result.

[0062] The target personality model is obtained by adjusting the original personality model based on interaction frequency information. The target personality model and the original personality model are used to control the robot's personality when interacting with the target user.

[0063] The target personality model corresponds to the robot's current personality parameters, reflecting the robot's personality when interacting with others. For example, the robot's personality can be extroverted, friendly, emotionally stable, or quiet and companionable. Specifically, an extroverted robot is lively and cheerful, a friendly robot is gentle and considerate, an emotionally stable robot is calm and reliable, and a quiet and companionable robot is less proactive and more inclined to listen quietly.

[0064] Responding to the interaction request based on the target personality model can be understood as engaging in dialogue with the user according to the personality corresponding to the target personality model. For example, engaging in dialogue with the user using an extroverted personality makes the user feel the robot's liveliness; engaging in dialogue with the user using an approachable personality enhances the warmth of the conversation, etc.

[0065] Interaction frequency information refers to the frequency of interactions between the robot and the user, reflecting the speed of these interactions. This interaction frequency information can be used to adjust the robot's personality, improving the rationality of these adjustments. For example, a higher interaction frequency can lead to a more extroverted and friendly robot personality, while a lower interaction frequency can result in a more emotionally stable robot personality.

[0066] In summary, the embodiments of this application adjust the robot's personality model by using interaction frequency information, thereby achieving dynamic adjustment of the robot's personality. Adjusting the robot's personality through interaction frequency information also makes the personality adjustment more aligned with user needs, improving the rationality of the adjustment.

[0067] Optionally, in this embodiment, the robot's personality can be adjusted in real time when responding to user interaction requests, or it can be pre-adjusted based on the previously calculated interaction frequency. For example, taking the pre-adjustment of personality as an example, before the step "obtaining the target user's interaction request", the method further includes:

[0068] Acquire interaction frequency information for the target user, the interaction frequency information including the interaction frequency between the robot and the target user;

[0069] Determine the robot's original personality model, which is obtained by performing personality initialization processing on the robot;

[0070] The original personality model is optimized based on the interaction frequency information to obtain the target personality model.

[0071] Understandably, the original personality model is obtained by initializing the robot's personality, that is, the initial personality model, which reflects the robot's personality in the initial state. For example, the original personality model includes emotional stability or affinity.

[0072] This application embodiment adjusts the original personality model by acquiring interaction frequency information to obtain the robot's target personality model.

[0073] In this embodiment, the robot's personality can be comprehensively represented by multiple personality weight parameters. Furthermore, the robot's personality model can be adjusted by adjusting these various personality weight parameters. Optionally, in some embodiments of this application, the original personality model includes several personality weight parameters representing at least one personality trait. The step "optimizing the original personality model based on the interaction frequency information to obtain the target personality model" includes:

[0074] The target personality model is obtained by optimizing the personality weight parameters in the original personality model based on the interaction frequency information.

[0075] For example, by increasing or decreasing the personality weight parameter, the robot's personality model can be adjusted, thereby changing the robot's personality when conversing with users.

[0076] Specifically, taking personality traits including extroversion, agreeableness, emotional stability, and quiet companionship as an example, the adjustment of robot personality is explained. Specifically, the personality weight parameters include a first personality weight parameter for extroversion, a second personality weight parameter for agreeableness, a third personality weight parameter for emotional stability, and a fourth personality weight parameter for quiet companionship. The step "optimizing each of the personality weight parameters in the original personality model based on the interaction frequency information to obtain the target personality model" includes:

[0077] If the interaction frequency corresponding to the interaction frequency information is higher than the frequency threshold, then the first personality weight parameter and the second personality weight parameter are increased to obtain the target personality model.

[0078] If the interaction frequency corresponding to the interaction frequency information is lower than the frequency threshold, then the weight parameters of the third personality and the fourth personality are increased to obtain the target personality model.

[0079] For example, during high-frequency interactions, extraversion and affinity can be enhanced, while emotional stability, quiet companionship, and other qualities can be diminished; conversely, during low-frequency interactions, emotional stability and quiet companionship can be enhanced, while extraversion and affinity can be diminished.

[0080] In this embodiment of the application, the enhancement or reduction magnitude can be calculated based on the interaction frequency and weighting factor. That is, optionally, in some embodiments of this application, the step "if the interaction frequency corresponding to the interaction frequency information is higher than the frequency threshold, then increase the first personality weight parameter and the second personality weight parameter to obtain the target personality model" includes:

[0081] If the interaction frequency corresponding to the interaction frequency information is higher than the frequency threshold, then the first weight compensation parameter is calculated based on the interaction frequency and the first weight factor, and the second weight compensation parameter is calculated based on the interaction frequency and the second weight factor.

[0082] The enhanced first personality weight parameter is obtained based on the first personality weight parameter and the first weight compensation parameter.

[0083] The enhanced second personality weight parameters are obtained based on the second personality weight parameters and the second weight compensation parameters.

[0084] The target personality model is obtained based on the enhanced first personality weight parameter and the enhanced second personality weight parameter.

[0085] In this embodiment, the first weighting factor and the second weighting factor are the factors influencing the outwardness and affinity of the interaction frequency during high-frequency interaction. The first weighting factor and the second weighting factor can be the same or different. For example, the product of the first weighting factor and the interaction frequency is used as the first weighting compensation parameter, and the product of the second weighting factor and the interaction frequency is used as the second weighting compensation parameter. That is, the first weighting compensation parameter... Second weighting compensation parameter ,in, and These are the weighting factors for the influence of extraversion and affinity during high-frequency interactions. E corresponds to the first personality weighting parameter for extraversion, A corresponds to the second personality weighting parameter for affinity, and F corresponds to the interaction frequency.

[0086] For example, the sum of the first personality weight parameter and the first weight compensation parameter is calculated to obtain the enhanced first personality weight parameter; the sum of the second personality weight parameter and the second weight compensation parameter is calculated to obtain the enhanced second personality weight parameter.

[0087] Similarly, the step "If the interaction frequency corresponding to the interaction frequency information is lower than the frequency threshold, then increase the weight parameters of the third personality and the fourth personality to obtain the target personality model" includes:

[0088] If the interaction frequency corresponding to the interaction frequency information is lower than the frequency threshold, then the third weight compensation parameter is calculated based on the interaction frequency and the third weight factor, and the fourth weight compensation parameter is calculated based on the interaction frequency and the fourth weight factor.

[0089] The enhanced third personality weight parameters are obtained based on the third personality weight parameters and the third weight compensation parameters.

[0090] The enhanced fourth personality weight parameters are obtained based on the fourth personality weight parameters and the fourth weight compensation parameters.

[0091] The target personality model is obtained based on the enhanced third personality weight parameter and the enhanced fourth personality weight parameter.

[0092] In this embodiment of the application, the third weighting factor and the fourth weighting factor are the factors that affect the frequency of interaction on emotional stability and quiet companionship during low-frequency interaction. The third weighting factor and the fourth weighting factor can be the same or different.

[0093] Since the frequency of interaction is inversely proportional to emotional stability and quiet companionship characteristics (i.e., the lower the frequency of interaction, the higher the emotional stability and the higher the quiet companionship characteristics), in this embodiment, the frequency of interaction is normalized to between 0 and 1, and the difference between 1 and the frequency of interaction is used as the basis for adjustment. High-frequency interaction is close to 1, and low-frequency interaction is close to 0. For example, the product of the third weighting factor and the difference is used as the third weighting compensation parameter, and the product of the fourth weighting factor and the difference is used as the fourth weighting compensation parameter.

[0094] That is, the third weighting compensation parameter Fourth weighting compensation parameter ,in, and These are the weighting factors for the impact of low-frequency interaction on emotional stability and quiet companionship, respectively. S corresponds to the third personality weighting parameter for emotional stability, Q corresponds to the fourth personality weighting parameter for quiet companionship, and F corresponds to the interaction frequency.

[0095] For example, the sum of the third personality weight parameter and the third weight compensation parameter is calculated to obtain the enhanced third personality weight parameter; the sum of the fourth personality weight parameter and the fourth weight compensation parameter is calculated to obtain the enhanced fourth personality weight parameter.

[0096] In this embodiment of the application, the first weight factor, the second weight factor, the third weight factor, and the fourth weight factor can be dynamically set based on the robot's design style, regional cultural attributes, or application scenario. For example, the first and second weight factors are larger for robots with interactive companion design styles or interactive scenarios, while the first and second weight factors are smaller for business tools such as robots with business or cleaning design styles or office scenarios.

[0097] Optionally, in some embodiments of this application, the personality weight parameters of the original personality model can be adjusted according to the mapping relationship between interaction frequency and personality parameters. That is, optionally, in some embodiments of this application, the step "optimizing each of the personality weight parameters in the original personality model according to the interaction frequency information to obtain the target personality model" includes:

[0098] Obtain the frequency-personality correspondence, which is the correspondence between interaction frequency and several personality parameters obtained based on reinforcement learning;

[0099] Based on the frequency-personality correspondence, the target personality parameters for each personality weight parameter are determined according to the interaction frequency information.

[0100] The target personality model is obtained by adjusting the weight parameters of each personality in the original personality model according to the target personality parameters.

[0101] For example, based on the frequency-personality correspondence, the personality parameters corresponding to the current interaction frequency are determined. Then, the personality weight parameters of the original personality model are adjusted to these personality parameters to obtain the target personality model. The frequency-personality correspondence is obtained using reinforcement learning, for example, by accumulating rewards for each personality adjustment based on user feedback and subsequent interactions, and then using these rewards to optimize the frequency-personality correspondence.

[0102] For example, taking a value range of 1-100 for each personality weight parameter, the personality parameters for each personality weight parameter are determined according to the frequency-personality correspondence. For example, the first personality weight parameter for extroversion is 80, the second personality weight parameter for affinity is 60, the third personality weight parameter for emotional stability is 50, and the fourth personality weight parameter for quiet companionship is 40. Then, the personality weight parameters of the original personality model are adjusted to 80, 60, 50, and 40 respectively to obtain the target personality model.

[0103] In this application embodiment, interaction frequency and personality adjustment records can also be used to predict the robot's future personality change trend, and the personality adjustment mechanism can be optimized in response to user behavior data or feedback. That is, optionally, in some embodiments of this application, the method further includes:

[0104] The robot's predictive personality model is predicted at a future target time point using a machine learning model that utilizes historical user data.

[0105] Output the personality identifier for the predicted personality model;

[0106] In response to receiving personality optimization configuration information, the optimization of the original personality model based on the interaction frequency information is controlled according to the personality optimization configuration information.

[0107] The user's historical data includes interaction behavior, frequency, duration, and personality adjustment records from different historical periods. A machine learning model is used to predict the robot's future personality model based on these interactions and personality adjustments. For example, this machine learning model may include an LSTM model.

[0108] Among them, the personality label is used to identify the robot's current personality. For example, the personality label includes text labels such as "extroversion" and "affability", or it can be an animated or graphic label that represents extroversion or affability. There is no limitation here.

[0109] The personality optimization configuration information refers to control information for adjusting personality based on interaction frequency. For example, this information includes the optimized frequency-personality correspondence, the adjustment range of personality weight parameters, the upper and lower limits of adjustment, etc., used to adjust the robot's personality model more refinedly, accurately, and reasonably, further improving the rationality of the robot's personality adjustment. Optionally, in this embodiment, the personality adjustment mechanism can also be optimized through voice evaluation, questionnaires, or receiving user personality preference settings.

[0110] Optionally, in some embodiments of this application, the robot's personality can be adjusted according to the robot's usage scenario. That is, optionally, in some embodiments of this application, the step "responding to the interaction request based on the target personality model and obtaining the interaction response result" includes:

[0111] Determine the current use case;

[0112] The target personality model is adjusted according to the usage scenario to obtain a scenario-based personality model;

[0113] Based on the scenario personality model, respond to the interaction request corresponding to the usage scenario to obtain the interaction response result.

[0114] The usage scenario can be determined based on the actual environment in which the robot is located. For example, if the robot is located in a home, then the usage scenario is a home scenario. The usage scenario can also be determined based on the purpose or content of the interaction. For example, when interacting with medical-related content, the usage scenario is a medical scenario; when conducting learning consultations, the usage scenario is an educational scenario.

[0115] It's understandable that adjusting a robot's personality based on usage scenarios can improve the match between the robot's personality and user needs, thus enhancing the rationality of personality adjustments. For example, family scenarios require increased friendliness and extroversion, medical scenarios require increased emotional stability and quiet companionship, and educational scenarios require increased initiative.

[0116] It is understood that, in the embodiments of this application, the personality model adjustment based on the usage scenario can also be based on the mapping relationship between the scenario and the personality parameters. For example, the personality parameters corresponding to the current usage scenario are determined according to the mapping relationship between the scenario and the personality parameters, and the personality weight parameters in the robot's personality model are adjusted according to the personality parameters to obtain a scenario personality model suitable for the usage scenario.

[0117] Furthermore, in this embodiment, historical dialogue information can be combined to analyze user personality preferences. These preferences, along with interaction frequency, can be used to adjust the robot's personality model. For example, feature extraction can be performed on historical dialogue information to identify the user's language style (e.g., formal / informal, humorous / serious), topic preferences (e.g., technology, entertainment, health), interaction rhythm (e.g., quick response or thoughtful consideration), and emotional tendency (e.g., positive / negative / neutral). Then, classification models in machine learning or deep learning (e.g., SVM, random forest, BERT) can be used to predict the user's preferred personality type. Finally, the personality weight parameters of the original personality model are adjusted according to preset weights, taking into account personality preferences and interaction frequency, to obtain the target personality model.

[0118] Furthermore, in this embodiment, in addition to the interaction frequency, the robot's personality model can be adjusted by incorporating the user's emotions. This allows the robot to better cater to the user's emotions. For example, if the user's emotions are analyzed to be negative, the robot's emotional stability and quiet companionship can be enhanced to alleviate the user's negative emotions during interaction. Specifically, in this embodiment, a pre-trained model (e.g., VADER, RoberTa) can be used to analyze the emotional polarity (positive / negative / neutral) of the user's input information (text or voice), or a camera can be used to capture the user's facial expressions, and the user's emotions can be comprehensively analyzed based on facial expressions and user input information.

[0119] In this embodiment, the interaction frequency information includes not only the interaction frequency between the user and the robot, but also the interaction frequency between the user and other devices associated with the user. For example, the interaction frequency information may also include the frequency with which the user operates their mobile phone, checks the time on their watch, and receives notifications. It is understood that these interaction frequencies with other devices can also reflect the user's current emotions, and adjusting the robot's personality through these interaction frequencies can help obtain a target personality model that matches the user's real-time state. In this embodiment, the user's interaction frequencies with other devices can be stored in the cloud, downloaded from the cloud after recognizing the user's face, or stored locally on the other device. When the user approaches the robot, the robot establishes a short-range communication (such as Bluetooth) connection with the device to obtain the interaction frequency data.

[0120] In summary, the robot in this application embodiment acquires the interaction request of the target user, responds to the interaction request based on the target personality model, and obtains the interaction response result. The target personality model is obtained by adjusting the original personality model based on the interaction frequency information. The target personality model and the original personality model are used to control the robot's personality when interacting with the target user.

[0121] In this embodiment, the robot's personality model is adjusted using interaction frequency information, enabling dynamic adjustment of the robot's personality. Adjusting the robot's personality through interaction frequency information also makes the personality adjustment more aligned with user needs, enhancing the rationality of the adjustment process.

[0122] To facilitate better implementation of the interactive control method of this application, this application also provides an application processing device based on the above-described interactive control method. The meanings of the terms used are the same as in the above-described interactive control method, and specific implementation details can be found in the descriptions of the method embodiments.

[0123] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of the interactive control device provided in an embodiment of this application, wherein the interactive control device is applied to a robot, and the interactive control device can be specifically as follows:

[0124] Module 301 is used to acquire interaction requests from the target user;

[0125] Response module 302 is used to respond to the interaction request based on the target personality model and obtain the interaction response result;

[0126] The target personality model is obtained by adjusting the original personality model based on interaction frequency information. The target personality model and the original personality model are used to control the robot's personality when interacting with the target user.

[0127] Optionally, in some embodiments of this application, before obtaining the interaction request of the target user, the apparatus further includes:

[0128] Acquire interaction frequency information for the target user, the interaction frequency information including the interaction frequency between the robot and the target user;

[0129] Determine the robot's original personality model, which is obtained by performing personality initialization processing on the robot;

[0130] The original personality model is optimized based on the interaction frequency information to obtain the target personality model.

[0131] Optionally, in some embodiments of this application, the original personality model includes several personality weight parameters for representing at least one personality trait.

[0132] The step of optimizing the original personality model based on the interaction frequency information to obtain the target personality model includes:

[0133] The target personality model is obtained by optimizing the personality weight parameters in the original personality model based on the interaction frequency information.

[0134] Optionally, in some embodiments of this application, the personality includes extraversion, affinity, emotional stability, and quiet companionship, and the personality weight parameters include a first personality weight parameter for extraversion, a second personality weight parameter for affinity, a third personality weight parameter for emotional stability, and a fourth personality weight parameter for quiet companionship.

[0135] The step of optimizing each of the personality weight parameters in the original personality model based on the interaction frequency information to obtain the target personality model includes:

[0136] If the interaction frequency corresponding to the interaction frequency information is higher than the frequency threshold, then the first personality weight parameter and the second personality weight parameter are increased to obtain the target personality model.

[0137] If the interaction frequency corresponding to the interaction frequency information is lower than the frequency threshold, then the weight parameters of the third personality and the fourth personality are increased to obtain the target personality model.

[0138] Optionally, in some embodiments of this application, optimizing the personality weight parameters in the original personality model based on the interaction frequency information to obtain the target personality model includes:

[0139] Obtain the frequency-personality correspondence, which is the correspondence between interaction frequency and several personality parameters obtained based on reinforcement learning;

[0140] Based on the frequency-personality correspondence, the target personality parameters for each personality weight parameter are determined according to the interaction frequency information.

[0141] The target personality model is obtained by adjusting the weight parameters of each personality in the original personality model according to the target personality parameters.

[0142] Optionally, in some embodiments of this application, the apparatus further includes:

[0143] The robot's predictive personality model is predicted at a future target time point using a machine learning model that utilizes historical user data.

[0144] Output the personality identifier for the predicted personality model;

[0145] In response to receiving personality optimization configuration information, the optimization of the original personality model based on the interaction frequency information is controlled according to the personality optimization configuration information.

[0146] Optionally, in some embodiments of this application, the step of responding to the interaction request based on the target personality model and obtaining the interaction response result includes:

[0147] Determine the current use case;

[0148] The target personality model is adjusted according to the usage scenario to obtain a scenario-based personality model;

[0149] Based on the scenario personality model, respond to the interaction request corresponding to the usage scenario to obtain the interaction response result.

[0150] In this embodiment of the application, the acquisition module 301 first acquires the interaction request of the target user, and the response module 302 responds to the interaction request based on the target personality model to obtain the interaction response result;

[0151] The target personality model is obtained by adjusting the original personality model based on interaction frequency information. The target personality model and the original personality model are used to control the robot's personality when interacting with the target user.

[0152] In summary, the embodiments of this application adjust the robot's personality model by using interaction frequency information, thereby achieving dynamic adjustment of the robot's personality. Adjusting the robot's personality through interaction frequency information also makes the personality adjustment more aligned with user needs, improving the rationality of the adjustment.

[0153] In addition, this application also provides an electronic device, such as Figure 4 As shown, it illustrates a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Specifically:

[0154] The electronic device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will understand that... Figure 4 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0155] The processor 401 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 402, and by calling data stored in the memory 402, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. Optionally, the processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 401.

[0156] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0157] The electronic device also includes a power supply 403 that supplies power to the various components. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 may also include one or more DC or AC power supplies, recharging systems, power equipment debugging circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0158] The electronic device may also include an input unit 404, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0159] Although not shown, the electronic device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the electronic device loads the executable files corresponding to the processes of one or more applications into the memory 402 according to the following instructions, and the processor 401 runs the applications stored in the memory 402, thereby implementing the steps in any of the interactive control methods provided in the embodiments of this application.

[0160] The robot in this application embodiment acquires the interaction request of the target user, responds to the interaction request based on the target personality model, and obtains the interaction response result. The target personality model is obtained by adjusting the original personality model based on the interaction frequency information. The target personality model and the original personality model are used to control the robot's personality when interacting with the target user.

[0161] In this embodiment, the robot's personality model is adjusted using interaction frequency information, enabling dynamic adjustment of the robot's personality. Adjusting the robot's personality through interaction frequency information also makes the personality adjustment more aligned with user needs, enhancing the rationality of the adjustment process.

[0162] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0163] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0164] To this end, this application provides a computer-readable storage medium storing a computer program that can be loaded by a processor to execute the steps of any of the interactive control methods provided in this application.

[0165] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0166] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0167] Since the instructions stored in the computer-readable storage medium can execute the steps of any of the interactive control methods provided in this application, the beneficial effects that any of the interactive control methods provided in this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0168] The interactive control method, apparatus, electronic device, and computer-readable storage medium provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. An interactive control method, characterized in that, Applied to robots, the method includes: Obtain interaction requests from the target user; The interaction response result is obtained based on the target personality model in response to the interaction request; The target personality model is obtained by adjusting the original personality model based on interaction frequency information. The target personality model and the original personality model are used to control the robot's personality when interacting with the target user. Before obtaining the interaction request from the target user, the method further includes: The original personality model is optimized based on the interaction frequency information to obtain the target personality model; The method further includes: The robot's predictive personality model is predicted at a future target time point using a machine learning model that utilizes historical user data. Output the personality identifier for the predicted personality model; In response to receiving personality optimization configuration information, the optimization of the original personality model based on the interaction frequency information is controlled according to the personality optimization configuration information; The personality optimization configuration information is control information for adjusting personality based on interaction frequency. The personality optimization configuration information includes at least one of the following: optimized frequency-personality correspondence, adjustment range of personality weight parameters, adjustment upper limit or adjustment lower limit.

2. The interactive control method according to claim 1, characterized in that, Before obtaining the interaction request from the target user, the method further includes: Acquire interaction frequency information for the target user, the interaction frequency information including the interaction frequency between the robot and the target user; The robot's original personality model is determined, which is obtained by performing personality initialization processing on the robot.

3. The interactive control method according to claim 2, characterized in that, The original personality model includes several personality weight parameters for representing at least one personality trait. The step of optimizing the original personality model based on the interaction frequency information to obtain the target personality model includes: The target personality model is obtained by optimizing the personality weight parameters in the original personality model based on the interaction frequency information.

4. The interactive control method according to claim 3, characterized in that, The personality traits include extraversion, affinity, emotional stability, and quiet companionship. The personality weighting parameters include a first personality weighting parameter for extraversion, a second personality weighting parameter for affinity, a third personality weighting parameter for emotional stability, and a fourth personality weighting parameter for quiet companionship. The step of optimizing each of the personality weight parameters in the original personality model based on the interaction frequency information to obtain the target personality model includes: If the interaction frequency corresponding to the interaction frequency information is higher than the frequency threshold, then the first personality weight parameter and the second personality weight parameter are increased to obtain the target personality model. If the interaction frequency corresponding to the interaction frequency information is lower than the frequency threshold, then the weight parameters of the third personality and the fourth personality are increased to obtain the target personality model.

5. The interactive control method according to claim 3, characterized in that, The step of optimizing each of the personality weight parameters in the original personality model based on the interaction frequency information to obtain the target personality model includes: Obtain the frequency-personality correspondence, which is the correspondence between interaction frequency and several personality parameters obtained based on reinforcement learning; Based on the frequency-personality correspondence, the target personality parameters for each personality weight parameter are determined according to the interaction frequency information. The target personality model is obtained by adjusting the weight parameters of each personality in the original personality model according to the target personality parameters.

6. The interactive control method according to claim 1, characterized in that, The interaction response result obtained by responding to the interaction request based on the target personality model includes: Determine the current use case; The target personality model is adjusted according to the usage scenario to obtain a scenario-based personality model; Based on the scenario personality model, respond to the interaction request corresponding to the usage scenario to obtain the interaction response result.

7. An interactive control device, characterized in that, The device, applied to robots, includes: The acquisition module is used to acquire interaction requests from the target user; The response module is used to respond to the interaction request based on the target personality model and obtain the interaction response result; The target personality model is obtained by adjusting the original personality model based on interaction frequency information. The target personality model and the original personality model are used to control the robot's personality when interacting with the target user. Before acquiring the interaction request from the target user, the device further includes: The original personality model is optimized based on the interaction frequency information to obtain the target personality model; The device further includes: The robot's predictive personality model is predicted at a future target time point using a machine learning model that utilizes historical user data. Output the personality identifier for the predicted personality model; In response to receiving personality optimization configuration information, the optimization of the original personality model based on the interaction frequency information is controlled according to the personality optimization configuration information; The personality optimization configuration information is control information for adjusting personality based on interaction frequency. The personality optimization configuration information includes at least one of the following: optimized frequency-personality correspondence, adjustment range of personality weight parameters, adjustment upper limit or adjustment lower limit.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the interactive control method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the interactive control method as described in any one of claims 1-6.

Images