Intelligent interaction method and system, terminal and storage medium

Abstract

The invention discloses an intelligent interaction method and system, a terminal and a storage medium, and relates to the technical field of equipment interaction, and the method comprises the steps: obtaining a current use scene and a target user portrait corresponding to a user through at least one first terminal in a plurality of preset terminals; determining first interaction guide data for at least one second terminal in the plurality of preset terminals according to the current use scene and the target user portrait, and controlling the second terminal to provide an initial interaction guide service for the user according to the first interaction guide data; obtaining feedback data of the user for the initial interaction guide service; and according to the feedback data, adjusting the first interaction guide data to generate second interaction guide data, and according to the second interaction guide data, controlling the second terminal to provide a target interaction guide service for the user. Therefore, the user can better use the interaction function, and the interaction effect and the user interaction experience can be improved.

Description

Technical Field

[0001] This application relates to the field of device interaction technology, and in particular to an intelligent interaction method, system, terminal and storage medium. Background Technology

[0002] With the development of science and technology, especially the continuous progress and development of interconnection and interaction technologies, users have increasingly higher requirements for device interaction. Currently, voice-activated intelligent agents can provide interactive services to users, thereby enhancing the user experience.

[0003] In existing technologies, terminal devices typically only respond to user-initiated interactions after the user has actively initiated an interaction. For example, the user may need to ask a question via voice before the terminal device can answer. However, users may not be familiar with the terminal device's interactive functions and therefore may not know what interactive features it offers, thus affecting their ability to use these features. Therefore, the problem with existing technologies is that they typically require users to initiate interactions, hindering the user's ability to utilize the terminal device's interactive functions and negatively impacting the interaction effect and user experience.

[0004] Therefore, the relevant technologies still need to be improved and developed. Summary of the Invention

[0005] The main purpose of this application is to provide an intelligent interaction method, system, terminal and storage medium, which aims to solve the technical problem in related technologies that interaction operations can usually only be initiated by the user, which affects the user's use of the interactive functions of the terminal device and is not conducive to improving the interaction effect and user interaction experience.

[0006] To achieve the above objectives, the first aspect of this application provides an intelligent interaction method, wherein the method includes: Obtain the target user profile corresponding to the current usage scenario and the user through at least one of multiple preset terminals; Based on the current usage scenario and the target user profile, first interactive guidance data is determined for at least one second terminal among the multiple preset terminals, and the second terminal is controlled to provide initial interactive guidance services to the user based on the first interactive guidance data. Obtain the feedback data of the user regarding the initial interactive guidance service, wherein the feedback data includes explicit feedback data and implicit feedback data, the explicit feedback data includes interactive operation instructions and / or feedback voice, and the implicit feedback data includes behavioral intention features and / or facial expression features. Based on the feedback data, the first interactive guidance data is adjusted to generate the second interactive guidance data, and the second terminal is controlled to provide the target interactive guidance service to the user based on the second interactive guidance data.

[0007] Optionally, the above-mentioned acquisition of the target user profile corresponding to the current usage scenario and the user through at least one of multiple preset terminals includes: Environmental perception data, device status data, and user identity data are acquired through at least one first terminal among multiple preset terminals. Based on the above environmental perception data and the above device status data, the current usage scenario is determined; Based on the aforementioned user identity data, the target user profile corresponding to each user is determined.

[0008] Optionally, the above-mentioned determination of the target user profile corresponding to the user based on the aforementioned user identity data includes: Based on the aforementioned user identity data, target user profiles matching the aforementioned users are determined from a pre-set user profile database; The user profiles in the aforementioned user profile database are constructed based on user behavior logs collected through the aforementioned preset terminals.

[0009] Optionally, before determining the first interactive guidance data for at least one second terminal among the plurality of preset terminals based on the current usage scenario and the target user profile, the method further includes: Based on the current usage scenario and the target user profile described above, determine whether the preset cross-platform collaboration triggering conditions are met. If the above cross-terminal collaboration triggering conditions are met, then based on the above current usage scenario, the above target user profile and the above device capability information corresponding to the above preset terminal, at least one second terminal different from the above first terminal is determined from the above multiple preset terminals. If the above cross-terminal collaboration triggering conditions are not met, then the first terminal will be used as the second terminal. The aforementioned cross-terminal collaboration triggering conditions are pre-set based on the aforementioned preset state logic relationship between terminals.

[0010] Optionally, the aforementioned first interactive guidance data includes interactive guidance content and interactive guidance type; The aforementioned interactive guidance type is used to control the way the second terminal outputs the aforementioned interactive guidance content.

[0011] Optionally, the above-mentioned adjustment of the first interactive guidance data to generate the second interactive guidance data based on the above-mentioned feedback data includes: Multi-source feedback analysis was performed on the above feedback data to obtain the corresponding demand data of the above users; Based on the aforementioned requirement data, at least one of the interactive guidance content and interactive guidance type of the first interactive guidance data is adjusted to generate the second interactive guidance data.

[0012] Optionally, the above method further includes: Obtain the interactive behavior of the aforementioned users in response to the aforementioned target interactive guidance service; Update the target user profile in the user profile database that matches the user mentioned above based on the above interactive behavior.

[0013] A second aspect of this application provides an intelligent interactive system, wherein the system includes: The data acquisition module is used to acquire the target user profile corresponding to the current usage scenario and the user through at least one of multiple preset terminals. The first control module is used to determine first interactive guidance data for at least one second terminal among the multiple preset terminals based on the current usage scenario and the target user profile, and to control the second terminal to provide initial interactive guidance services to the user based on the first interactive guidance data. The feedback acquisition module is used to acquire the user's feedback data on the initial interactive guidance service. The feedback data includes explicit feedback data and implicit feedback data. The explicit feedback data includes interactive operation instructions and / or feedback voice, and the implicit feedback data includes behavioral intention features and / or facial expression features. The second control module is used to adjust the first interactive guidance data according to the feedback data to generate the second interactive guidance data, and to control the second terminal to provide the target interactive guidance service to the user according to the second interactive guidance data.

[0014] A third aspect of this application provides a terminal, 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 any of the steps of the aforementioned intelligent interaction method.

[0015] A fourth aspect of this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of any of the above-described intelligent interaction methods.

[0016] As can be seen from the above, the present application provides an intelligent interaction method. Specifically, it involves obtaining the current usage scenario and the target user profile corresponding to the user through at least one first terminal among multiple preset terminals; determining first interaction guidance data for at least one second terminal among the multiple preset terminals based on the current usage scenario and the target user profile, and controlling the second terminal to provide initial interaction guidance services to the user based on the first interaction guidance data; obtaining feedback data from the user regarding the initial interaction guidance service, wherein the feedback data includes explicit feedback data and implicit feedback data, the explicit feedback data includes interactive operation instructions and / or feedback voice, and the implicit feedback data includes behavioral intention features and / or facial expression features; adjusting the first interaction guidance data based on the feedback data to generate second interaction guidance data, and controlling the second terminal to provide target interaction guidance services to the user based on the second interaction guidance data.

[0017] Thus, the first terminal obtains the current usage scenario and the target user profile corresponding to the user, thereby determining the first interaction guidance data for the second terminal. Based on the first interaction guidance data, the second terminal is controlled to provide initial interaction guidance services to the user, achieving proactive interaction guidance services for the user. Furthermore, user feedback data regarding the initial interaction guidance service can be obtained. Based on the feedback data, the first interaction guidance data is adjusted to obtain second interaction guidance data, and then based on the second interaction guidance data, a more user-specific target interaction guidance service is provided. In this way, the terminal device can proactively provide interaction guidance to the user, allowing the user to better utilize the interactive functions. Moreover, the interaction guidance can be adjusted in real time based on user feedback, which helps improve the interaction effect and user experience. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating an intelligent interaction method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the constituent modules of an intelligent interactive system provided in an embodiment of this application; Figure 3 This is a schematic diagram of the overall architecture of an intelligent interactive system provided in an embodiment of this application; Figure 4This is a block diagram illustrating the internal structure of a terminal provided in an embodiment of this application. Detailed Implementation

[0020] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of this application with unnecessary detail.

[0021] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0022] It should also be understood that the terminology used in this application specification is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this application specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0023] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0024] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to classification." Similarly, the phrases "if determined" or "if classified to [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once classified to [the described condition or event]," or "in response to classification to [the described condition or event]."

[0025] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0026] Many specific details are set forth in the following description in order to provide a full understanding of this application. However, this application may also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the spirit of this application. Therefore, this application is not limited to the specific embodiments disclosed below.

[0027] Currently, various terminal devices are being used more and more widely, and users have increasingly higher requirements for device interaction. However, in existing technologies, interaction can usually only be initiated by the user, which affects the user's use of the terminal device's interactive functions and is not conducive to improving the interaction effect and user experience.

[0028] Taking voice interaction as an example, with the popularization of smart terminal devices and the development of voice interaction technology, voice intelligent agents have become the core interaction entry point of terminal devices. However, there are many defects in the current related technologies, resulting in poor user experience and difficulty in fully realizing the service value of intelligent agents.

[0029] In existing technologies, the utilization rate of intelligent agents is extremely low, with many hidden functions remaining untapped due to user cognitive blind spots and ingrained habits. Feedback mechanisms are simplistic, relying solely on explicit feedback such as user clicks and voice replies to adjust service strategies, neglecting implicit user behavioral intentions (such as frequent category switching and dwell time) and emotional states (such as frowning or smiling), leading to a disconnect between guidance strategies and users' actual needs. Cross-platform experiences are fragmented, only achieving multi-terminal data synchronization without implementing cross-platform scene collaborative triggering and dynamic device resource adaptation. For example, collaborative triggering between in-vehicle navigation and TV pre-heating services, or simultaneous adaptation of older devices and augmented reality (AR) devices, results in gaps in scene transitions, causing interaction solutions to be out of touch with users' actual needs. Scene adaptation is rigid, lacking real-time scene perception and dynamic strategy adjustment capabilities, employing a "one-size-fits-all" approach that cannot adapt to the differentiated needs of different scenarios (such as immersive movie-watching scenarios and family gathering scenarios). Privacy and personalization are imbalanced, lacking a privacy-level management mechanism, leading users to refuse data authorization due to privacy concerns or to raise security concerns due to excessive data use. At the same time, the service loop is missing, and a full-link iterative mechanism of "guidance-use-effect-optimization" has not been formed, resulting in low iteration efficiency of the intelligent agent and difficulty in quickly responding to changes in user needs.

[0030] The aforementioned issues prevent voice-activated agents from accurately matching user needs and achieving end-to-end device interaction encompassing "multi-feedback perception, cross-device collaboration, dynamic scene adaptation, and service closed loop." This results in insufficient service targeting and a significant need to improve user engagement and overall user experience. Therefore, a smart interaction method capable of integrating multi-feedback data and enabling cross-device collaboration and dynamic adaptation is urgently needed to address these problems.

[0031] To address at least one of the aforementioned technical problems, this application proposes an intelligent interaction method. Specifically, it involves obtaining a target user profile corresponding to the current usage scenario and the user through at least one first terminal among multiple preset terminals; determining first interaction guidance data for at least one second terminal among the multiple preset terminals based on the current usage scenario and the target user profile; controlling the second terminal to provide initial interaction guidance services to the user based on the first interaction guidance data; obtaining feedback data from the user regarding the initial interaction guidance service, wherein the feedback data includes explicit feedback data and implicit feedback data, the explicit feedback data including interactive operation instructions and / or feedback voice, and the implicit feedback data including behavioral intention features and / or facial expression features; adjusting the first interaction guidance data to generate second interaction guidance data based on the feedback data; and controlling the second terminal to provide target interaction guidance services to the user based on the second interaction guidance data.

[0032] Thus, the first terminal obtains the current usage scenario and the target user profile corresponding to the user, thereby determining the first interaction guidance data for the second terminal. Based on the first interaction guidance data, the second terminal is controlled to provide initial interaction guidance services to the user, achieving proactive interaction guidance services for the user. Furthermore, user feedback data regarding the initial interaction guidance service can be obtained. Based on the feedback data, the first interaction guidance data is adjusted to obtain second interaction guidance data, and then based on the second interaction guidance data, a more user-specific target interaction guidance service is provided. In this way, the terminal device can proactively provide interaction guidance to the user, allowing the user to better utilize the interactive functions. Moreover, the interaction guidance can be adjusted in real time based on user feedback, which helps improve the interaction effect and user experience.

[0033] like Figure 1 As shown in the figure, this application provides an intelligent interaction method, which specifically includes the following steps: Step S100: Obtain the target user profile corresponding to the current usage scenario and the user through at least one first terminal among multiple preset terminals; Step S200: Based on the current usage scenario and the target user profile, determine first interaction guidance data for at least one second terminal among the multiple preset terminals, and control the second terminal to provide initial interaction guidance service to the user based on the first interaction guidance data. Step S300: Obtain the user's feedback data for the initial interactive guidance service. The feedback data includes explicit feedback data and implicit feedback data. The explicit feedback data includes interactive operation instructions and / or feedback voice. The implicit feedback data includes behavioral intention features and / or facial expression features. Step S400: Based on the feedback data, adjust the first interactive guidance data to generate second interactive guidance data, and control the second terminal to provide the target interactive guidance service to the user based on the second interactive guidance data.

[0034] The aforementioned preset terminal is a pre-set terminal device that can provide intelligent interaction. For example, the preset terminal may include a television, a mobile terminal, a mobile smart screen, an in-vehicle terminal, etc., and may also include other smart terminals, which are not specifically limited here.

[0035] It should be noted that the above-mentioned intelligent interaction method can be deployed in various preset terminals or executed based on an intelligent interaction system. In this embodiment, the example of execution based on an intelligent interaction system is used for illustration, but it is not intended as a specific limitation.

[0036] Specifically, the above-mentioned acquisition of the current usage scenario and the target user profile corresponding to the user through at least one of multiple preset terminals includes: Environmental perception data, device status data, and user identity data are acquired through at least one first terminal among multiple preset terminals. Based on the above environmental perception data and the above device status data, the current usage scenario is determined; Based on the aforementioned user identity data, the target user profile corresponding to each user is determined.

[0037] The primary terminal, acting as the data acquisition entity, simultaneously acquires three core data types through its built-in multimodal acquisition modules (such as cameras, microphones, and sensors) and device status monitoring modules: environmental perception data, device status data, and user identity data. Environmental perception data includes information such as noise intensity, light intensity, and spatial layout of the current environment, which can be collected through the terminal's environmental sensors and camera. Device status data includes the primary terminal's operating status (such as whether it is playing music, battery level, and performance parameters), network connection status, and the online status of associated terminals, which are monitored and reported by the terminal in real time. User identity data is used to identify the user and can be obtained through biometric recognition (such as facial recognition and voice recognition), account login information, or preset role tags (such as child, parent, or elderly).

[0038] The current usage scenario is determined by scene fusion based on the acquired environmental perception data and device status data. For example, when the environmental perception data shows that the light is dim and the noise is low, and the device status data shows that the terminal is in video playback mode, the current scenario can be determined as an "immersive movie viewing scenario"; when the device status data shows that the mobile phone is in navigation mode and the TV is in standby mode, and the environmental perception data shows that the mobile phone is moving towards the home area, the current scenario can be determined as a "vehicle-TV cross-terminal connection scenario".

[0039] Furthermore, based on the aforementioned user identity data, the target user profile corresponding to the user is determined, including: Based on the aforementioned user identity data, target user profiles matching the aforementioned users are determined from a pre-set user profile database; The user profiles in the aforementioned user profile database are constructed based on user behavior logs collected through the aforementioned preset terminals.

[0040] In this embodiment, based on user identity data, a target user profile matching the user is determined from a pre-set user profile database. The user profiles in the database are constructed based on user behavior logs collected over a long period through pre-set terminals, covering dimensions such as user behavior habits (e.g., viewing preferences, operation frequency), preference tags (e.g., favorite film and television genres, interaction methods), emotional characteristics (e.g., behavioral expressions corresponding to common emotional states), and role attributes (e.g., content preferences for children, operation habits for the elderly). Once user identity data is obtained, the system uses a feature matching algorithm to filter out the target user profile from the database that best matches the user's identity characteristics, providing data support for subsequent interactive guidance services.

[0041] In this embodiment of the application, before determining the first interactive guidance data for at least one second terminal among the plurality of preset terminals based on the current usage scenario and the target user profile, the method further includes: Based on the current usage scenario and the target user profile described above, determine whether the preset cross-platform collaboration triggering conditions are met. If the above cross-terminal collaboration triggering conditions are met, then based on the above current usage scenario, the above target user profile and the above device capability information corresponding to the above preset terminal, at least one second terminal different from the above first terminal is determined from the above multiple preset terminals. If the above cross-terminal collaboration triggering conditions are not met, then the first terminal will be used as the second terminal. The aforementioned cross-terminal collaboration triggering conditions are pre-set based on the aforementioned preset state logic relationship between terminals.

[0042] It should be noted that, in the embodiments of this application, the aforementioned first terminal can be one or more, and the aforementioned second terminal can also be one or more. When the cross-terminal collaborative triggering condition is met, and multiple second terminals are determined from multiple preset terminals, at least one second terminal is a terminal that is different from all the first terminals. That is, the second terminal may include some (or all) of the first terminals, and at least one new terminal.

[0043] In some application scenarios, the system determines whether to activate cross-platform collaboration services based on the current usage scenario and target user profile, combined with preset cross-platform collaboration trigger conditions. These cross-platform collaboration trigger conditions are pre-defined based on the state logic relationships between preset terminals. For example, scenario association rules such as "Mobile phone completes movie ticket purchase → TV starts preheating service" and "Car navigation shows distance to home is less than 1 kilometer → TV automatically turns on and prepares personalized content" can all serve as preset cross-platform collaboration trigger conditions.

[0044] If the judgment result meets the cross-terminal collaboration triggering conditions, the system, based on the current usage scenario, target user profile, and device capability information corresponding to the preset terminals, determines at least one second terminal different from the first terminal from multiple preset terminals. Device capability information is stored in a preset device capability library, including the terminal's hardware performance (such as the device's computing power, AR device display capabilities), supported interaction methods (such as pop-ups, floating cards, AR virtual human guidance), etc. For example, in the "mobile ticket purchase → TV pre-heating" scenario, the first terminal is a mobile phone. Based on the device capability library, the system knows that a TV has superior video display capabilities, therefore determining the TV as the second terminal. If the user is a child, the target user profile shows a preference for animated guidance, and the mobile smart screen supports AR virtual human functionality, then the mobile smart screen can be determined as the second terminal.

[0045] If the determination result indicates that the cross-platform collaboration triggering conditions are not met, then the first terminal of the data collection entity will be directly designated as the second terminal, and it will be responsible for providing subsequent interactive guidance services. For example, if the user is only performing routine browsing operations on their mobile phone and has not triggered any cross-platform association rules, then the mobile phone will serve as the second terminal to provide interactive guidance services.

[0046] Furthermore, the aforementioned first interactive guidance data includes interactive guidance content and interactive guidance type; the interactive guidance type is used to control the way the aforementioned second terminal outputs the aforementioned interactive guidance content.

[0047] After identifying the second terminal, the system determines the first interactive guidance data for the second terminal based on the current usage scenario and the target user profile, and controls the second terminal to provide the user with initial interactive guidance services based on the data.

[0048] The first interactive guidance data includes interactive guidance content and interactive guidance type. Interactive guidance content consists of core service information matched to the scenario and user needs, while interactive guidance type controls how the second terminal outputs the interactive guidance content. For example, in the "boot-up scenario," if the target user profile is elderly (preferring simple operation and large font prompts), the first interactive guidance content can be set to "Directly play the opera program you didn't finish watching yesterday," and the interactive guidance type can be set to "Large font pop-up + voice broadcast." In the "child companionship scenario," if the target user profile is a child, the interactive guidance content can be set to "Recommended animation update for today: 'A Animation,' do you want to watch it?", and the interactive guidance type can be set to "AR cartoon character voice guidance + graphic card."

[0049] After receiving the first interactive guidance data, the second terminal calls its corresponding output module (such as display screen, speaker, AR component, etc.) to perform service provision operations according to the interactive guidance type, so as to ensure that the user can clearly perceive and obtain the initial interactive guidance service.

[0050] In this embodiment of the application, adjusting the first interactive guidance data based on the feedback data to generate the second interactive guidance data includes: Multi-source feedback analysis was performed on the above feedback data to obtain the corresponding demand data of the above users; Based on the aforementioned requirement data, at least one of the interactive guidance content and interactive guidance type of the first interactive guidance data is adjusted to generate the second interactive guidance data.

[0051] After the second terminal provides the initial interactive guidance service, the system obtains the user's feedback data on the service through the multimodal acquisition module and the associated data monitoring module of the second terminal. This feedback data covers both explicit and implicit feedback data, enabling a comprehensive understanding of the user's needs.

[0052] Explicit feedback data refers to user-initiated feedback information that directly expresses the user's intentions, including interactive operation commands and / or feedback voice. Interactive operation commands include actions such as clicking the "Confirm" or "Cancel" buttons in the guidance pop-up window, or swiping to select recommended content; feedback voice includes voice commands such as "Play this program" or "No need" spoken by the user to the guidance service, which are collected by the terminal's microphone and converted into text data.

[0053] Implicit feedback data refers to indirect feedback information that users do not actively express but can reflect their true needs and emotional states. This includes behavioral intention characteristics and / or facial expression characteristics. Behavioral intention characteristics can be obtained through analysis of user actions. For example, if a user frequently switches recommended categories after seeing the initial introductory content, this can be extracted as a behavioral intention characteristic of "hesitation in selecting content"; if a user stays on a particular recommended content for more than a preset threshold, this can be extracted as a behavioral intention characteristic of "interest". Facial expression characteristics are obtained by capturing user facial images through the terminal's camera and analyzing them using emotion recognition algorithms. For example, recognizing a user frowning can be extracted as a facial expression characteristic of "impatience," while recognizing a smile can be extracted as a facial expression characteristic of "satisfaction." In addition, the user's voice tone characteristics (such as rapid or calm) can also be used as part of implicit feedback data to help determine the user's emotional state.

[0054] After acquiring feedback data, the system performs in-depth analysis and processing. Based on the analysis results, it adjusts the first interactive guidance data to generate the second interactive guidance data, thereby controlling the second terminal to provide the user with the target interactive guidance service, achieving dynamic service optimization. The specific process is as follows: First, multi-source feedback analysis is performed on the feedback data to obtain the user's corresponding demand data. The system uses a multi-feedback processing module to fuse and analyze explicit and implicit feedback data, eliminating the limitations of a single feedback dimension. For example, if a user clicks "Cancel" in the initial guidance pop-up (explicit feedback) but simultaneously exhibits frequent scrolling of the recommendation list (implicit feedback: hesitation in selecting a movie), the multi-source feedback analysis result is "The user is not interested in the current guidance content but has a viewing need; other types of content need to be recommended." If the user replies "Wait a moment" via voice (explicit feedback) and their facial expression is a frown (implicit feedback: impatience), the analysis result is "The user is currently busy; guidance interference needs to be reduced, and service should be postponed."

[0055] Subsequently, based on the obtained demand data, at least one of the interactive guidance content and interactive guidance type of the first interactive guidance data is adjusted to generate the second interactive guidance data. For example, for the demand data of "hesitating to select a program", the first interactive guidance content is changed from "whether to play the opera program" to "We recommend 3 types of popular content for you: opera, storytelling, and square dance tutorials. Click to watch". At the same time, the interactive guidance type is changed from "pop-up" to "lightweight floating card" to avoid excessive interference. For the demand data of "busy status", the interactive guidance content is changed to "Your demand has been recorded. We will remind you again in 10 minutes". The interactive guidance type is changed to "text notification only, no voice broadcast".

[0056] Finally, based on the second interaction guidance data, the second terminal provides users with a target interaction guidance service. This service can more accurately match users' real needs and improve the effectiveness of the interaction and user satisfaction.

[0057] In some application scenarios, the above methods also include: Obtain the interactive behavior of the aforementioned users in response to the aforementioned target interactive guidance service; Update the target user profile in the user profile database that matches the user mentioned above based on the above interactive behavior.

[0058] To achieve long-term optimization and precise adaptation of services, after providing the target interaction guidance service on the second terminal, the system obtains the user's interaction behavior for the service (such as whether to click to view, operation duration, whether to provide secondary feedback, etc.), and updates the target user profile in the user profile library that matches the user based on the interaction behavior.

[0059] For example, if a user frequently clicks on square dance tutorials within a target interactive guidance service, the system will reinforce the "preference for square dancing" tag in their user profile; if a user repeatedly rejects pop-up guidance and prefers lightweight notifications during movie viewing, their "interaction preference" will be updated to "low-interference guidance." Through continuous profile iteration, the system ensures that subsequent interactive guidance services can be generated based on the latest user needs data, further improving service accuracy.

[0060] This application provides an intelligent interaction method. Specifically, it involves obtaining the current usage scenario and the target user profile corresponding to the user through at least one first terminal among multiple preset terminals; determining first interaction guidance data for at least one second terminal among the multiple preset terminals based on the current usage scenario and the target user profile, and controlling the second terminal to provide initial interaction guidance services to the user based on the first interaction guidance data; obtaining feedback data from the user regarding the initial interaction guidance service, wherein the feedback data includes explicit feedback data and implicit feedback data, the explicit feedback data including interactive operation instructions and / or feedback voice, and the implicit feedback data including behavioral intention features and / or facial expression features; adjusting the first interaction guidance data based on the feedback data to generate second interaction guidance data, and controlling the second terminal to provide target interaction guidance services to the user based on the second interaction guidance data.

[0061] Thus, the first terminal obtains the current usage scenario and the target user profile corresponding to the user, thereby determining the first interaction guidance data for the second terminal. Based on the first interaction guidance data, the second terminal is controlled to provide initial interaction guidance services to the user, achieving proactive interaction guidance services for the user. Furthermore, user feedback data regarding the initial interaction guidance service can be obtained. Based on the feedback data, the first interaction guidance data is adjusted to obtain second interaction guidance data, and then based on the second interaction guidance data, a more user-specific target interaction guidance service is provided. In this way, the terminal device can proactively provide interaction guidance to the user, allowing the user to better utilize the interactive functions. Moreover, the interaction guidance can be adjusted in real time based on user feedback, which helps improve the interaction effect and user experience.

[0062] like Figure 2 As shown, corresponding to the above-described intelligent interaction method, this application embodiment also provides an intelligent interaction system, which includes: Data acquisition module 210 is used to acquire the target user profile corresponding to the current usage scenario and the user through at least one first terminal among multiple preset terminals; The first control module 220 is used to determine first interactive guidance data for at least one second terminal among the multiple preset terminals based on the current usage scenario and the target user profile, and to control the second terminal to provide initial interactive guidance services to the user based on the first interactive guidance data. The feedback acquisition module 230 is used to acquire the user's feedback data on the initial interactive guidance service. The feedback data includes explicit feedback data and implicit feedback data. The explicit feedback data includes interactive operation instructions and / or feedback voice. The implicit feedback data includes behavioral intention features and / or facial expression features. The second control module 240 is used to adjust the first interactive guidance data according to the feedback data to generate the second interactive guidance data, and to control the second terminal to provide the target interactive guidance service to the user according to the second interactive guidance data.

[0063] Thus, the first terminal obtains the current usage scenario and the target user profile corresponding to the user, thereby determining the first interaction guidance data for the second terminal. Based on the first interaction guidance data, the second terminal is controlled to provide initial interaction guidance services to the user, achieving proactive interaction guidance services for the user. Furthermore, user feedback data regarding the initial interaction guidance service can be obtained. Based on the feedback data, the first interaction guidance data is adjusted to obtain second interaction guidance data, and then based on the second interaction guidance data, a more user-specific target interaction guidance service is provided. In this way, the terminal device can proactively provide interaction guidance to the user, allowing the user to better utilize the interactive functions. Moreover, the interaction guidance can be adjusted in real time based on user feedback, which helps improve the interaction effect and user experience.

[0064] It should be noted that the specific structure and implementation of the above-mentioned intelligent interactive system and its various modules or units can be referred to the corresponding descriptions in the above method embodiments, and will not be repeated here.

[0065] It should be further noted that the division of the various modules of the above-mentioned intelligent interaction system is not unique and is not intended as a specific limitation.

[0066] In this embodiment, the above-mentioned intelligent interaction scheme is further described based on a specific application scenario. It should be noted that this embodiment uses voice interaction as an example for specific explanation, but this is not intended to limit the scope of the application.

[0067] Figure 3 This is a schematic diagram of the overall architecture of an intelligent interactive system provided in an embodiment of this application, such as... Figure 3 As shown, the system architecture is divided into four layers from top to bottom. Each layer works together to achieve proactive voice services driven by multiple feedbacks, cross-terminal collaboration, and dynamic adaptation to multiple scenarios.

[0068] User layer: Covers multiple roles in the family (elderly, children, parents) and typical scenarios such as powering on, watching movies, idle time, children's companionship, powering off, and cross-platform scene connection (in-vehicle terminal-TV, mobile terminal-TV). It also includes the collection of explicit user feedback (click / voice reply), implicit behavior (frequent switching of categories, operation duration) and emotional state (facial expression, tone of voice), and is the main body for receiving and interacting with services.

[0069] Terminal layer: Includes multiple terminal devices such as TVs, mobile terminals, mobile smart screens, and in-vehicle terminals. It has a built-in terminal service software development kit (SDK), device capability detection module, and multimodal acquisition module (camera, microphone). It is responsible for collecting scene data (playback history, device performance parameters), user feedback data (explicit + implicit), displaying service content (pop-ups, floating cards, AR virtual humans), and executing interaction commands. It also supports local cache calls in extreme scenarios.

[0070] Service Layer: The core modules include a trigger-based proactive service module, a push-based proactive service module, an agent training module, a log monitoring module (Behavior Log Kafka Service), a multi-feedback processing module (explicit + implicit feedback parsing), a cross-terminal collaborative triggering module (multi-terminal state linkage), a multi-scenario dynamic adaptation module (scenario awareness + strategy adjustment), a privacy classification management module, and a service effect attribution module, realizing scenario recognition, feedback parsing, cross-terminal linkage, dynamic guidance, and service closed-loop optimization.

[0071] Data layer: Stores user profiles (such as behavioral habits, preference tags, emotional characteristics, role attributes), scene data, interaction logs (explicit and implicit feedback), script template library, device capability library (terminal performance parameters, hardware supported functions) and privacy permission configuration library, providing data support for the service layer.

[0072] Specifically, the problems in existing technologies are solved through technologies such as multi-feedback driven, cross-terminal collaboration and device adaptation, multi-scenario dynamic adaptation, intelligent agent tunability, balance between privacy and personalization, and service closed-loop optimization.

[0073] Multi-feedback driven technology: Simultaneously collect explicit user feedback (clicking "OK" / voice "No need") and implicit feedback (behavioral intent: frequent switching of categories indicates hesitation in selecting movies; emotional state: camera recognition of frowning indicates impatience). The multi-feedback processing module analyzes the user's real needs and dynamically adjusts the guidance content and the degree of interference (such as switching to a soft prompt if the user is impatient).

[0074] Cross-terminal collaboration and device adaptation technology: leverage Kafka service to achieve multi-terminal data synchronization and build a unified user profile; trigger services based on multi-terminal status linkage (such as mobile ticketing → TV preheating) through the cross-terminal collaboration trigger module; combine device capability library to dynamically adapt service forms (such as lightweight text guidance, virtual human guidance, etc.) according to terminal performance (such as the different performance of old devices and AR devices) and scenario characteristics (such as driving scenarios, home entertainment scenarios).

[0075] Multi-scenario dynamic adaptation technology: Based on time, device status, user behavior, environmental data and other multi-dimensional real-time perception of scenarios (such as immersive movie watching, family gathering, idle time), the multi-scenario dynamic adaptation module adjusts the guidance type (forced / semi-forced / weak guidance) and guidance frequency and display format. For example, in the movie watching scenario, pop-ups are closed and only text-to-speech (TTS) is retained.

[0076] Intelligent agent trainable platform: provides a full-process tool for "scene creation - trigger rule setting - guidance and execution action design - simulation testing - release and launch - data collection - iterative optimization", sets up AI automatic optimization suggestion function, and generates dialogue or rule adjustment plan based on data collection results.

[0077] Privacy and personalization balance technology: Users can customize the scope of data use through the privacy classification management module (such as only using movie viewing records for recommendations, and only using children's data for children's mode). The system automatically blocks unauthorized data transfers, ensuring personalized services while complying with privacy settings.

[0078] Service closed-loop optimization technology: Track the entire chain of data from "guide-response-use-exit" through the service effect attribution module. If a user responds to the recommended content and then quickly exits, it is determined that the user's needs do not match, and the recommendation type will be adjusted accordingly. The user profile is dynamically iterated based on long-term data to avoid profile solidification.

[0079] In some specific application scenarios, intelligent interactive services are provided to users based on steps such as data initialization and user profile construction, scene awareness and cross-terminal collaborative triggering, multi-feedback collection and parsing, dynamic guidance strategy generation and execution, service effect tracking and strategy iteration, extreme scenarios and privacy adaptation.

[0080] Data initialization and user profile construction: Multiple terminal devices upload user behavior logs, device capability parameters, and privacy permission configurations to the data layer through the terminal service SDK, and combine user operation records, role tags, and emotional characteristics to build a unified user profile across multiple terminals.

[0081] Scene awareness and cross-terminal collaboration triggering: The log monitoring module captures terminal data in real time, and the multi-scene dynamic adaptation module identifies the current scene based on multi-dimensional data (such as family gatherings, immersive movie watching); the cross-terminal collaboration triggering module judges the linkage of multiple terminal statuses (such as the in-vehicle terminal navigation displaying "almost home") and matches the corresponding service scene.

[0082] Multi-feedback collection and analysis: The terminal collects explicit user feedback (clicks / voice replies) and implicit feedback (behavioral + emotional) through the multi-modal collection module, and the multi-feedback processing module analyzes the feedback intent.

[0083] Dynamic guidance strategy generation and execution: Based on scenario type, user profile, feedback intent and device capabilities, the multi-scenario dynamic adaptation module generates personalized guidance strategies (guidance type, content, display format), calls the script template library to generate guidance content, and executes guidance through terminal display (pop-up window, AR virtual human) or TTS broadcast. The number of guidance rounds and the complexity of guidance content can be set. For example, the number of guidance rounds can be set to no more than 3, and the guidance content can be quickly understood by the user.

[0084] Service performance tracking and strategy iteration: The service performance attribution module analyzes user data (such as browsing time and operation behavior) after the user response, determines the service matching degree and optimizes the attribution; the operations staff can view the data dashboard and AI optimization suggestions through the intelligent agent tuning platform, adjust the scene rules or wording content, and then launch it in a gray or full range after simulation testing.

[0085] Extreme scenarios and privacy adaptation: When the network is interrupted, the terminal calls the locally cached guide content; when the privacy permission is configured to "only allow basic data use", the system only pushes content based on the viewing history and blocks the access of sensitive data such as location and emotion.

[0086] Thus, in this embodiment of the application, a voice-active service system and method are provided that integrates multi-feedback driving (explicit and implicit feedback), cross-terminal collaboration (data synchronization and scene linkage), and multi-scenario dynamic adaptation (real-time scene perception and dynamic strategy adjustment). It is applicable to multiple terminal devices such as TVs, mobile terminals, mobile smart screens, and in-vehicle terminals. It can realize personalized and accurate proactive service push and interactive guidance for multiple users in the family (elderly, children, and parents) in scenarios such as power-on, watching movies, idle time, and cross-terminal scene connection, while taking into account privacy protection and extreme scenario adaptation.

[0087] Specifically, a multi-feedback driven dynamic guidance mechanism is implemented: simultaneously collecting explicit and implicit feedback, and dynamically adjusting guidance content, interference level, and frequency through a feedback analysis model, unlike existing single-feedback mechanisms. A cross-platform collaboration and dynamic device capability adaptation mechanism is also established: achieving multi-terminal data synchronization and scene-based triggering, adapting service formats based on device performance and scene characteristics, overcoming the limitations of existing cross-platform mechanisms that only synchronize data. A multi-scene dynamic adaptation system is constructed: based on real-time scene perception using multi-dimensional data, dynamically adjusting guidance types, display formats, and frequencies (e.g., closing pop-ups in movie-watching scenarios), addressing the shortcomings of existing "one-size-fits-all" guidance. Furthermore, a fully configurable intelligent agent training and AI optimization platform is provided: offering full-process tools such as scene creation and rule editing, setting up AI automatic optimization suggestion functions, and supporting rapid strategy iteration to solve the problem of low iteration efficiency in existing systems. Finally, a privacy-leveling and personalized balance mechanism is implemented: users define the scope of data use, and the system automatically blocks unauthorized data flow, which is conducive to achieving privacy protection and improving data usage security. A closed-loop optimization mechanism for the entire service lifecycle has been established: tracking data across the entire chain from "guidance-response-use" to "effects", attributing and optimizing services and dynamically iterating user profiles to avoid profile solidification and improve the long-term adaptability of services.

[0088] In this way, the utilization rate of intelligent agent capabilities is improved: through multi-feedback perception, cross-terminal collaboration and dynamic scene guidance, user cognitive blind spots and habit solidification are broken, allowing hidden functions (movie list recommendations, children's mode settings) to be perceived and used by users.

[0089] Optimize cross-platform and scenario adaptation experience: cross-platform collaborative triggering enables seamless connection between scenarios such as "travel-home", device capability adaptation avoids fragmented experience, and dynamic scenario guidance ensures accurate and non-intrusive service (such as closing pop-ups in movie-watching scenarios).

[0090] Balancing privacy and personalization: Privacy-tiered management addresses user security concerns, enabling precise services while adhering to privacy settings and increasing user willingness to grant permissions.

[0091] Reduce operating and iteration costs: The standardized tuning platform, combined with AI-powered automatic optimization suggestions, eliminates the need for modifications to the underlying code. The closed-loop service makes iterations more precise and improves the efficiency of strategy implementation.

[0092] Enhance user stickiness: By adapting to multiple family roles, dynamic personas, and predictive services (such as Friday suspense drama reminders), establish an emotional connection between users and the intelligent agent, and increase long-term dependence.

[0093] Wider compatibility: Supports multiple terminals such as TV, mobile devices, and in-vehicle terminals, covering all scenarios such as family entertainment, parent-child companionship, and cross-terminal connection, and is compatible with devices of different performance and extreme scenarios.

[0094] It should be noted that in some application scenarios, the dimensions of feedback data can be expanded. For example, feedback data can also include environmental feedback data (such as noise intensity and light brightness), such as automatically increasing the TTS volume when there is high noise and decreasing the brightness of the pop-up window when the light is dim. The aforementioned preset terminals can also include smart speakers, smart home control centers, smartwatches, and other terminals. For example, a smartwatch can detect the user's movement status and then push a tutorial video on the TV for guidance. Furthermore, other guidance and interaction methods can be adopted. For example, VR guidance can be used (such as showing interactive game rules through VR devices during family gatherings) and gesture interaction guidance (such as waving to close the guidance pop-up). For cross-terminal collaborative use scenarios, it can also be extended from entertainment scenarios to office scenarios (computer meeting ends → mobile phone pushes minutes and voice reminders), education scenarios (tablet learning → TV pushes expanded knowledge point guidance), and other scenarios. Regarding privacy protection issues, temporary authorization functions (such as using location data only for this service) and data anonymization processing (fuzzy positioning for regional content recommendation) can also be set up to enhance privacy and security. Furthermore, it can also upgrade AI optimization capabilities. For example, it can set up a user demand prediction model and, based on multiple feedback data and scenario linkage, push potential needs that users have not expressed in advance (such as parents working overtime → automatically pushing bedtime story guidance for children).

[0095] Based on the above embodiments, this application also provides a terminal, the principle block diagram of which can be as follows: Figure 4 As shown. The terminal includes a processor, memory, network interface, and display screen connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements the steps of any of the above-described intelligent interaction methods. The display screen can be a liquid crystal display (LCD) or an e-ink display.

[0096] Those skilled in the art will understand that Figure 4 The block diagram shown is only a partial structural diagram related to the solution of this application and does not constitute a limitation on the terminal on which the solution of this application is applied. The specific terminal may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements.

[0097] In one embodiment, a terminal is provided, the terminal including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of any of the intelligent interaction methods provided in the embodiments of this application.

[0098] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of any of the intelligent interaction methods provided in this application.

[0099] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0100] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the above device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above device can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0101] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0102] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0103] In the embodiments provided in this application, it should be understood that the disclosed systems / terminal devices and methods can be implemented in other ways. For example, the system / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units described above is merely a logical functional division, and in actual implementation, it can be divided in other ways. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0104] If the integrated modules / units described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, and software distribution media, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0105] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions are not in essence a departure from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. An intelligent interaction method, characterized in that, The method includes: Obtain the target user profile corresponding to the current usage scenario and the user through at least one of multiple preset terminals; Based on the current usage scenario and the target user profile, first interaction guidance data is determined for at least one second terminal among the plurality of preset terminals, and the second terminal is controlled to provide initial interaction guidance services to the user based on the first interaction guidance data; Obtain the user's feedback data for the initial interactive guidance service, wherein the feedback data includes explicit feedback data and implicit feedback data, the explicit feedback data includes interactive operation instructions and / or feedback voice, and the implicit feedback data includes behavioral intention features and / or facial expression features; Based on the feedback data, the first interactive guidance data is adjusted to generate the second interactive guidance data, and the second terminal is controlled to provide the target interactive guidance service to the user based on the second interactive guidance data.

2. The intelligent interaction method according to claim 1, characterized in that, The step of obtaining the target user profile corresponding to the current usage scenario and the user through at least one first terminal among multiple preset terminals includes: Environmental perception data, device status data, and user identity data are acquired through at least one first terminal among multiple preset terminals. Based on the environmental perception data and the device status data, the current usage scenario is determined; Based on the user identity data, determine the target user profile corresponding to the user.

3. The intelligent interaction method according to claim 2, characterized in that, The step of determining the target user profile corresponding to the user based on the user identity data includes: Based on the user identity data, a target user profile matching the user is determined from a preset user profile database; The user profiles in the user profile database are constructed based on user behavior logs collected through the preset terminal.

4. The intelligent interaction method according to claim 1, characterized in that, Before determining the first interactive guidance data for at least one second terminal among the plurality of preset terminals based on the current usage scenario and the target user profile, the method further includes: Based on the current usage scenario and the target user profile, determine whether the preset cross-platform collaboration triggering conditions are met; If the cross-terminal collaboration triggering condition is met, then based on the current usage scenario, the target user profile, and the device capability information corresponding to the preset terminal, at least one second terminal different from the first terminal is determined from the plurality of preset terminals; If the cross-terminal collaboration triggering condition is not met, then the first terminal will be used as the second terminal; The cross-terminal collaboration triggering conditions are preset based on the state logic relationship between the preset terminals.

5. The intelligent interaction method according to claim 1, characterized in that, The first interactive guidance data includes interactive guidance content and interactive guidance type; The interactive guidance type is used to control how the second terminal outputs the interactive guidance content.

6. The intelligent interaction method according to claim 5, characterized in that, The step of adjusting the first interactive guidance data to generate the second interactive guidance data based on the feedback data includes: Multi-source feedback analysis is performed on the feedback data to obtain the user's corresponding demand data; Based on the required data, at least one of the interactive guidance content and interactive guidance type of the first interactive guidance data is adjusted to generate the second interactive guidance data.

7. The intelligent interaction method according to claim 3, characterized in that, The method further includes: Acquire the user's interaction behavior with the target interaction guidance service; Update the target user profile in the user profile library that matches the user based on the interaction behavior.

8. An intelligent interactive system, characterized in that, The system includes: The data acquisition module is used to acquire the target user profile corresponding to the current usage scenario and the user through at least one of multiple preset terminals. The first control module is used to determine first interaction guidance data for at least one second terminal among the plurality of preset terminals according to the current usage scenario and the target user profile, and to control the second terminal to provide initial interaction guidance service to the user according to the first interaction guidance data; The feedback acquisition module is used to acquire the user's feedback data for the initial interaction guidance service, wherein the feedback data includes explicit feedback data and implicit feedback data, the explicit feedback data includes interactive operation instructions and / or feedback voice, and the implicit feedback data includes behavioral intention features and / or facial expression features. The second control module is used to adjust the first interactive guidance data to generate second interactive guidance data based on the feedback data, and to control the second terminal to provide the target interactive guidance service to the user based on the second interactive guidance data.

9. A terminal, characterized in that, The terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the intelligent interaction method as described in any one of claims 1 to 7.

10. 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 intelligent interaction method as described in any one of claims 1 to 7.

Images