Anthropomorphic representation methods and devices without interaction

Abstract

This invention provides a method and apparatus for anthropomorphic behavior without interaction, relating to the field of robotics. The method includes: acquiring the operating state of a device, and controlling the device to enter an autonomous activity state when the operating state meets preset idle conditions; after the device enters the autonomous activity state, determining a preset default behavior as the first target anthropomorphic behavior; after determining the first target anthropomorphic behavior, randomly selecting a behavior different from the previously determined target anthropomorphic behavior from a preset set of behaviors as the next target anthropomorphic behavior, and repeating the random selection to obtain multiple target anthropomorphic behaviors; controlling the device to execute the first target anthropomorphic behavior and the multiple target anthropomorphic behaviors sequentially during autonomous movement.

Description

Technical Field

[0001] This invention relates to the field of robotics, and in particular to a method and apparatus for anthropomorphic representation without interaction. Background Technology

[0002] Child companion robots are intelligent interactive devices designed specifically for young children. Through functions such as voice dialogue, facial expression interaction, motion sensing, and content playback, they provide children with emotional companionship, early education, and safety monitoring. These devices typically integrate technologies such as voice recognition, sensors, and cameras, enabling them to tell stories, teach knowledge, remind schedules, and provide simple emotional responses. They can also connect with parents' mobile devices for remote monitoring.

[0003] Currently, companion robots with autonomous walking capabilities, such as pet robots, have been launched on the market. Pet robots can map and move around indoors, offering more interactive possibilities compared to devices that can only be placed on a table.

[0004] However, these pet robots typically remain stationary on their charging docks unless actively interacted with by their owners, and cannot engage in activities like real pets when unattended. This results in pet robots lacking sentience, resembling lifeless objects, which hinders the establishment of a deep emotional connection between the pet robot and its owner. Summary of the Invention

[0005] This invention provides a method, device, robot, electronic device, and storage medium for anthropomorphic performance without interaction, in order to solve the defects of existing pet robots that remain still and lack intelligence when no one interacts with them, making it difficult to establish a deep emotional connection between humans and devices.

[0006] This invention provides a method for anthropomorphic representation without interaction, comprising: The device's operating status is acquired, and when the operating status meets preset idle conditions, the device is controlled to enter an autonomous activity state; wherein, the idle conditions include no human interaction input on the device and no tasks to be executed, and the autonomous activity state is the state in which the device moves autonomously within a preset space; After the device enters the autonomous activity state, the preset default behavior is determined as the first target anthropomorphic behavior; After determining the first target anthropomorphic expression, a different expression from the previously determined target anthropomorphic expression is randomly selected from a preset set of behaviors as the next target anthropomorphic expression, and the random selection is repeated to obtain multiple target anthropomorphic expressions; wherein, the set of behaviors includes a walking expression mode and a fun behavior mode, the walking expression mode is the device outputting audio information during autonomous movement, and the fun behavior mode is the device performing fun actions during autonomous movement; During autonomous movement, the device is controlled to execute the first target anthropomorphic representation and the subsequent anthropomorphic representations of multiple targets in sequence.

[0007] According to a non-interactive anthropomorphic performance method provided by the present invention, the fun behavior mode includes multiple fun actions, which are divided into a humorous mode, a life simulation mode, and a physiological simulation mode. When the randomly selected target anthropomorphic performance is the fun behavior mode, the method further includes: randomly selecting a fun action that is different from the fun action performed previously from all the fun actions corresponding to the humorous mode, the life simulation mode, and the physiological simulation mode, and controlling the device to perform the selected fun action.

[0008] According to the present invention, a method for anthropomorphic performance without interaction is provided, wherein determining a preset default performance as the first target anthropomorphic performance includes: acquiring a triggering scenario before the device enters the autonomous activity state; when the triggering scenario is automatically triggered under unmanned interaction conditions, determining a first type of voice information matching the scenario automatically triggered under unmanned interaction conditions as the default performance; and when the triggering scenario is triggered after an interaction ends, determining a second type of voice information matching the scenario triggered after an interaction ends as the default performance.

[0009] According to the present invention, a non-interactive anthropomorphic representation method is provided, wherein the walking expression mode includes self-narration walking and humming walking; the method further includes: when the randomly selected target anthropomorphic representation is self-narration walking, controlling the device to output voice information matching the current scene of the device during autonomous movement; and when the randomly selected target anthropomorphic representation is humming walking, controlling the device to output humming or singing audio information during autonomous movement.

[0010] According to a non-interactive anthropomorphic performance method provided by the present invention, the method further includes: before the device is in the autonomous activity state and the movement direction of the device is determined, controlling the device to output direction selection voice information; wherein, the direction selection voice information is used to characterize the device's intention to select a movement direction.

[0011] According to the anthropomorphic representation method without interaction provided by the present invention, the amusing mode corresponds to at least one of the following fun actions: raising limbs, leaping into the air, twisting the body, making a cute pose, rotating and making a cool pose, pounding the ground, continuous rotation, nodding, and looking around; the life simulation mode corresponds to at least one of the following fun actions: playing ball, drawing, drumming, searching for food, and moving with the light; the physiological simulation mode corresponds to at least one of the following fun actions: sneezing, exhaling, smiling, yawning, meditating, and smelling objects.

[0012] According to the present invention, a method for anthropomorphic representation without interaction is provided, wherein the step of acquiring the operating state of the device and controlling the device to enter an autonomous activity state when the operating state meets a preset idle condition includes: when the device is in the preset space and it is detected that there is no human interaction input and no task to be executed within a preset time period, controlling the device to leave the stationary position and enter the preset space for autonomous movement, and determining that the device is in the autonomous activity state.

[0013] The present invention also provides a non-interactive anthropomorphic performance device, the device comprising: The status control module is used to acquire the operating status of the device and control the device to enter an autonomous activity state when the operating status meets the preset idle conditions; wherein, the idle conditions include that the device has no human interaction input and no tasks to be executed, and the autonomous activity state is the state in which the device moves autonomously within a preset space; The first line of the determination module is used to determine the preset default behavior as the first target anthropomorphic behavior after the device enters the autonomous activity state. The second behavior determination module is used to, after determining the first target anthropomorphic behavior, randomly select a behavior from a preset behavior set that is different from the previously determined target anthropomorphic behavior as the next target anthropomorphic behavior, and repeat the random selection to obtain multiple target anthropomorphic behaviors; wherein, the behavior set includes a walking expression mode and a fun behavior mode, the walking expression mode is the device outputting audio information during autonomous movement, and the fun behavior mode is the device performing fun actions during autonomous movement; The execution control module is used to control the device to execute the first target anthropomorphic expression and the multiple target anthropomorphic expressions sequentially during autonomous movement.

[0014] The present invention also provides a robot, the robot comprising: The robot itself; A mobile component, disposed on the robot body, is used to drive the robot body to move within a preset space; An audio output component, located on the robot body, is used to output audio information; An action execution component, located on the robot body, is used to perform fun actions; The controller is connected to the moving component, the audio output component, and the motion execution component, respectively. The controller is configured to: acquire the operating status of the robot, and when the operating status meets a preset idle condition, control the mobile component to drive the robot body to move autonomously within the preset space, so that the robot enters an autonomous activity state; wherein, the idle condition includes that the robot has no human interaction input and no task to be executed; The controller is further configured to: after the robot enters the autonomous activity state, determine a preset default behavior as the first target anthropomorphic behavior; after determining the first target anthropomorphic behavior, randomly select a behavior different from the previously determined target anthropomorphic behavior from a preset behavior set as the next target anthropomorphic behavior, and repeat the random selection to obtain multiple target anthropomorphic behaviors; wherein, the behavior set includes a walking expression mode and a fun behavior mode, the walking expression mode is to output audio information through the audio output component during autonomous movement, and the fun behavior mode is to perform fun actions through the action execution component during autonomous movement; The controller is also configured to: during the process of the mobile component driving the robot body to move autonomously, control the audio output component and the motion execution component to execute sequentially according to the order of the first target anthropomorphic expression and the order of the multiple target anthropomorphic expressions.

[0015] The controller is also configured to perform the anthropomorphic representation method without interaction described in any of the preceding descriptions.

[0016] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the anthropomorphic performance method without interaction as described in any of the preceding claims.

[0017] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the anthropomorphic representation method without interaction as described in any of the preceding claims.

[0018] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the anthropomorphic representation method without interaction as described in any of the preceding claims.

[0019] This invention provides a method and apparatus for anthropomorphic behavior without interaction. By actively triggering the device to enter an autonomous activity state when there is no interactive input and no task to be performed, the device can move autonomously within a preset space even when unattended, thus overcoming the rigid state of the device being stationary in a fixed position when idle. In the autonomous activity state, a preset default behavior is used as the first target anthropomorphic behavior. Then, a different behavior is randomly selected from a set of behaviors including walking expression patterns and fun behavior patterns as the subsequent target anthropomorphic behaviors, and executed in sequence. This allows the device to continuously present rich anthropomorphic behaviors such as vocalizations and movements during autonomous movement, with no repetition between adjacent movements. This simulates the self-entertaining behavior of a real pet when alone, avoiding a mechanical feel due to monotonous and repetitive behaviors, thereby enhancing the device's fun and anthropomorphism and facilitating a deeper emotional connection between humans and the device. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating the anthropomorphic representation method without interaction provided by the present invention. Figure 2 This is a schematic diagram illustrating the composition of the set of behaviors provided in the embodiments of this application; Figure 3 This is a schematic diagram of the anthropomorphic representation device without interaction provided in the embodiments of this application; Figure 4 This is a schematic diagram of the structure of the robot provided in the embodiments of this application; Figure 5 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0023] The anthropomorphic representation method without interaction provided in this application can be executed by a device with autonomous mobility, by a server, cloud platform, or terminal connected to the device, or by the device and server working together. Devices with autonomous mobility include various mobile intelligent devices such as pet robots, child companion robots, and electronic pets. When executed by the device itself, the specific execution component can be a built-in controller, processor, or control system.

[0024] For ease of explanation, the following embodiments use the built-in controller of the pet robot as the execution subject, and the application of the pet robot in the home indoor environment is used as an example throughout the text. Those skilled in the art will understand that the following description is also applicable to other execution subjects and other application scenarios.

[0025] Figure 1 This is a flowchart illustrating the anthropomorphic representation method without interaction provided by the present invention, as shown below. Figure 1 As shown, the method includes the following: Step S110: Obtain the operating status of the device, and when the operating status meets the preset idle conditions, control the device to enter the autonomous activity state.

[0026] Specifically, the operating status refers to the status information that reflects the current working condition of the device. The operating status can include the device's interaction status and task status. The interaction status is used to characterize whether there is currently any interactive input between the device and the user, while the task status is used to characterize whether there is currently any task to be executed.

[0027] The controller can obtain the running status by periodically reading the device's interaction records and task queue, or by reading when an interaction end event or task completion event is triggered. This embodiment does not limit the method of obtaining the status.

[0028] The idle condition includes no user interaction input and no pending tasks. No user interaction input means that no interaction request is detected from the user to the device at any given time, including but not limited to voice, touch, buttons, and remote control. No pending tasks means that there are no tasks such as storytelling, content playback, or schedule reminders waiting to be processed in the device's task queue. When the interaction state indicates no user interaction input and the task state indicates no pending tasks, the controller determines that the operating state meets the idle condition and then controls the device to enter the autonomous activity state.

[0029] Autonomous activity state refers to the state in which the device moves autonomously within a preset space. The preset space refers to a pre-defined physical space that allows the device to move, such as the entire indoor space of a home, or a part of the indoor space of a home, such as the living room area.

[0030] Autonomous movement of the device in autonomous activity mode can be achieved based on an environmental map pre-built within a preset space. The device plans its movement route according to the environmental map and avoids obstacles during movement. The autonomous movement route can be generated randomly or according to a preset patrol route. In one example, after the owner leaves the home, the pet robot has neither interactive input nor playback tasks. The controller determines that the idle condition is met, so it controls the pet robot to start moving autonomously indoors, entering autonomous activity mode.

[0031] Step S120: After the device enters the autonomous activity state, the preset default behavior is determined as the first target anthropomorphic behavior.

[0032] Specifically, target anthropomorphic performance refers to the performance content to be executed by the device in autonomous activity state, which is used to simulate the behavior of real pets or anthropomorphic characters. Multiple target anthropomorphic performances will be determined and executed in sequence during a single autonomous activity.

[0033] The default behavior is a pre-configured behavior that is the first action executed each time the device enters an autonomous activity state. The default behavior can be a voice output, an action output, or a combination of both. The specific content of the default behavior can be preset at the factory or configured by the user in the accompanying application. Fixing the default behavior as the first target anthropomorphic behavior ensures that the device exhibits a stable and context-appropriate initial behavior each time it begins autonomous activity.

[0034] Step S130: After determining the first target anthropomorphic expression, randomly select an expression from the preset behavior set that is different from the previously determined target anthropomorphic expression as the next target anthropomorphic expression, and repeat the above random selection to obtain multiple target anthropomorphic expressions.

[0035] Specifically, a behavior set is a pre-built collection of various behaviors that a device can perform in an autonomous activity state. Behavior sets include two categories: movement expression patterns and fun behavior patterns.

[0036] The movement expression mode is when the device outputs audio information during autonomous movement. The audio information can be either voice-based or melody-based. The fun behavior mode is when the device performs fun actions during autonomous movement. Fun actions refer to the fun and expressive gestures made by the device through its body, limbs, lights, and other output components.

[0037] Each random selection is based on the anthropomorphic representation of the target determined in the previous instance as the basis for deduplication. In other words, the representation selected from the behavior set in this instance is different from the representation determined in the previous instance, so the representation content of two consecutive executions will not be repeated.

[0038] Random selection can be implemented by first removing the previously determined behaviors from the behavior set and then drawing the remaining behaviors with equal probability, or by first drawing randomly and then drawing again when the drawn result is the same as the previously determined behavior, until the drawn result is different from the previously determined behavior.

[0039] The aforementioned random selection is repeated during the device's autonomous operation. Each completed performance triggers the next selection, resulting in a series of anthropomorphic target performances. The timing of the selection can also be set according to a preset time interval, such as triggering a selection at regular intervals. The time interval can be a fixed value or randomly selected within a preset range to further enhance the naturalness of the behavior.

[0040] In step S140, during the autonomous movement process, the control device executes the anthropomorphic representation of the first target and the anthropomorphic representation of multiple targets in sequence.

[0041] Specifically, the controller sequentially calls the output resources corresponding to the anthropomorphic representation of each target in a predetermined order. The output resources include at least one of the audio resources and the sequence of motion control instructions. The device synchronously completes audio playback or motion display during movement.

[0042] The execution method can be to perform while moving, such as the device outputting audio information while moving; or it can pause at the current position briefly while performing some fun actions, and continue moving after the actions are completed. The two methods can be flexibly selected according to the type of content being presented.

[0043] In one example, the pet robot moves autonomously in the living room, first executing the default voice output as the first target anthropomorphic expression, and then, based on the random selection results, executing a humming output and a fun action in sequence, with natural transitions between the various expressions.

[0044] Using the above implementation method, the device no longer remains stationary on the charging dock when there is no human interaction or task. Instead, it automatically enters an autonomous activity state. Through a mechanism that fixes the first expression and selects subsequent expressions one by one to avoid repetition, it continuously outputs non-repeating anthropomorphic expressions during movement. This avoids the dullness caused by mechanical repetition of the expression content, so that the device presents a spirituality close to that of a real pet, which is conducive to establishing a deeper emotional connection between the device and the user.

[0045] Optionally, the fun behavior pattern includes multiple fun actions, which are divided into humorous patterns, life simulation patterns, and physiological simulation patterns. When the randomly selected target's anthropomorphic manifestation conforms to the aforementioned interesting behavioral pattern, the method further includes: From all the fun actions corresponding to the humorous mode, the life simulation mode, and the physiological simulation mode, randomly select a fun action that is different from the fun action performed previously, and control the device to perform the selected fun action.

[0046] Based on the above embodiments, the fun behavior pattern includes multiple fun actions, which are divided into a humorous mode, a life simulation mode, and a physiological simulation mode. Figure 2 This is a schematic diagram illustrating the composition of the set of behaviors provided in the embodiments of this application, such as... Figure 2 As shown, the fun behavior patterns in the behavior set are divided into the above three types, and each type corresponds to several fun actions.

[0047] The "funny" mode refers to action categories aimed at amusing users and creating a lively atmosphere; the "life simulation" mode refers to action categories that simulate the daily life behaviors of pets or anthropomorphic characters; and the "physiological simulation" mode refers to action categories that simulate biological physiological reactions. Categorizing fun actions into these three categories facilitates the organization and management of action resources and makes it easier to expand the action library according to these categories in the future.

[0048] When the randomly selected anthropomorphic representation of the target is a fun behavior pattern, the controller further randomly selects a different fun action from all the fun actions corresponding to the humorous, life simulation, and physiological simulation modes, and controls the device to execute the selected fun action. The deduplication here is based on the previously executed fun action, and the selection range covers all fun actions corresponding to the three modes; that is, the selection is not limited by category boundaries, and each fun action in the three modes has an equal chance of being selected.

[0049] The deduplication method is similar to the random selection in step S130. It can either remove the previously performed fun actions before extraction, or extract the actions and compare them before deciding whether to extract again. In one example, the pet robot's previous fun action was nodding. Nodding is excluded in this selection. The controller randomly selects the body twisting action from the remaining fun actions and controls the pet robot to perform it.

[0050] By adopting the above implementation method, deduplication at the action level is further realized on the basis of deduplication at the mode level, forming two levels of deduplication selection, which further reduces the possibility of repetition of adjacent performance content, making the interesting actions of the device more diverse and enhancing the anthropomorphism and fun of the device.

[0051] Optionally, determining the preset default behavior as the first target anthropomorphic behavior includes: Obtain the triggering scenario before the device enters the autonomous activity state; When the triggering scenario is automatically triggered under unmanned interaction conditions, the first type of voice information that matches the scenario automatically triggered under unmanned interaction conditions is determined as the default performance; When the triggering scenario is triggered after an interaction ends, the second type of voice information that matches the scenario triggered after the interaction ends is determined as the default performance.

[0052] In this application, the triggering scenario is used to characterize the cause of the device entering the autonomous activity state. The controller can determine the triggering scenario based on the interaction records within a preset time window before entering the autonomous activity state. If there are no interaction records within the preset time window, the triggering scenario is determined to be automatically triggered under the condition of no human interaction. If there are completed interaction records within the preset time window, the triggering scenario is determined to be triggered after an interaction ends.

[0053] When the triggering scenario is automatically triggered under unmanned interaction conditions, the first type of voice information matching the scenario is determined as the default behavior. The first type of voice information is pre-recorded or synthesized voice content that semantically matches the device's active exploration activity. Examples include the voice saying "Who says robots can only stay still? I'm the all-around little wandering king!" or "Exploration time! Let's see if there are any new discoveries at home!" Multiple first-type voice information can be configured; the default behavior is determined by randomly selecting one from these multiple first-type voice information.

[0054] When the triggering scenario is triggered after an interaction ends, the second type of voice information that matches the scenario triggered after the interaction ends is determined as the default performance.

[0055] The second type of voice information semantically corresponds to the context where the interaction has just ended and the device has switched to its own activity. For example, the semantics of the voice message is "I'll play by myself for a while," or the semantics of "Why is no one here? I'll go wander around by myself." Multiple voice messages of this second type can also be configured and randomly selected.

[0056] Using the above implementation method, the anthropomorphic performance of the first target can be adaptively determined according to the triggering scenario, so that the voice content output when the device starts to operate autonomously corresponds to the cause of entering the autonomous operation state, and the behavior is more coherent and natural in the context, further improving the anthropomorphism of the device.

[0057] Optionally, the marching expression mode includes self-narration marching and humming marching; the method further includes: When the randomly selected target is anthropomorphically represented as self-narrating, the device is controlled to output voice information that matches the current scene of the device during autonomous movement. When the randomly selected target is anthropomorphized and moves while humming, the device is controlled to output humming or singing audio information during autonomous movement.

[0058] When the randomly selected target is anthropomorphized and moves in a self-narrating manner, the controller controls the device to output voice information that matches the current scene of the device during the autonomous movement.

[0059] The current scene can be determined based on at least one of the device's movement process, location, and surrounding environment information. The voice information matching the current scene semantically aligns with the device's ongoing activity, giving the auditory effect of the device talking to itself. The voice information can be retrieved from a pre-built voice library according to scene tags, or it can be synthesized in real time based on scene information.

[0060] When the randomly selected target is anthropomorphized and moves while humming, the controller controls the device to output humming or singing audio information during autonomous movement.

[0061] The audio information for humming or singing can be randomly selected from a preset music library. The music library can store multiple humming and singing audio tracks, such as several preset humming tracks and several children's songs. Each time the humming process is executed, one track is selected from the music library for playback.

[0062] Using the above implementation method, the walking expression mode is subdivided into self-talk walking and humming walking. The sound performance of the device during movement is more diverse, simulating the behavior characteristics of real pets or children talking to themselves and humming tunes when they are alone, thus enhancing the vividness of the device's behavior.

[0063] Optionally, the method further includes: Before the device is in the autonomous activity state and the direction of movement of the device is determined, the device is controlled to output direction selection voice information; wherein, the direction selection voice information is used to represent the device's intention to select the desired direction of movement.

[0064] Specifically, during autonomous movement, the equipment will constantly face opportunities to make decisions about its direction of movement, such as when it reaches an intersection, needs to turn when it encounters an obstacle, or needs to plan the next route after completing a section of the route.

[0065] Before the direction of movement is determined, the controller controls the device to play direction selection voice information through the audio output component. The direction selection voice information is used to represent the device's intention to select the direction of movement. For example, the voice with the semantic meaning is "Where should we go?" or "Which way should we go?", or the voice with the semantic meaning is "Left or right?", or the voice with the semantic meaning is "Let me see what fun things are around here".

[0066] After the direction selection voice message has finished playing, or in parallel with the playback process, the controller determines the direction of movement and controls the device to continue moving.

[0067] By adopting the above implementation method, the device externalizes the selection process in the direction decision-making stage through voice, making the originally silent path planning process appear as a behavior similar to biological thinking and looking around, further weakening the mechanical feel of the device and enhancing the overall anthropomorphic feel of the autonomous movement process.

[0068] Optionally, the fun actions corresponding to the funny mode include at least one of the following: raising limbs, leaping into the air, twisting the body, making a cute pose, spinning and making a cool pose, pounding the ground, continuous spinning, nodding, and looking around. The fun actions corresponding to the life simulation mode include at least one of the following: playing ball, drawing, drumming, finding food, and moving with the light. The fun actions corresponding to the physiological simulation mode include at least one of the following: sneezing, exhaling, smiling, yawning, meditative posture, and smelling objects.

[0069] The fun actions corresponding to the humorous mode include at least one of the following: raising limbs, leaping into the air, twisting the body, making a cute pose, spinning and making a cool pose, pounding the ground, continuous spinning, nodding, and looking around.

[0070] Taking the twisting of the machine body as an example, the controller sends a sequence of control commands to the machine body drive component to swing left and right alternately, so that the machine body presents a twisting effect; taking looking around as an example, the controller controls the head rotating component of the machine to rotate back and forth within a preset angle range to simulate the behavior of looking around.

[0071] The fun actions corresponding to the life simulation mode include at least one of the following: playing ball, drawing, drumming, finding food, and moving with the light.

[0072] Taking food locator as an example, the device moves while sniffing, simulating a pet's foraging behavior; taking light-based motion as an example, the device plays rhythmic audio while controlling the lighting components to change lighting effects and move in sync with the body.

[0073] The fun actions corresponding to the physiological simulation mode include at least one of the following: sneezing, exhaling, smiling, yawning, meditative posture, and smelling objects.

[0074] Physiological simulation-based fun actions are usually achieved by combining sound effects with physical movements. For example, when yawning, the device outputs a yawning sound effect while simultaneously displaying an open mouth or a stretched-out posture; when sneezing, the device outputs a sneezing sound effect while simultaneously displaying a forward-leaning and shaking posture.

[0075] Using the above implementation methods, the three modes cover behavioral performance in three dimensions: playful interaction, daily life, and physiological reactions. The fun action library is rich in content and closely resembles the behavioral characteristics of real pets, making the device's performance in autonomous activity state more three-dimensional and full.

[0076] Optionally, the step of acquiring the operating status of the device and controlling the device to enter an autonomous activity state when the operating status meets a preset idle condition includes: When the device is within the preset space and no human interaction input or pending task is detected within a preset time period, the device is controlled to move autonomously from its stationary position into the preset space, and the device is determined to be in the autonomous activity state.

[0077] When the device is within a preset space and no new interactive input or pending task is detected within a preset time period, the controller moves the device autonomously from its stationary position into the preset space, confirming that the device is in an autonomous activity state. The preset time period is a pre-configured idle time threshold. The controller starts timing from the moment the most recent interaction ends or the most recent task is completed. When the preset time period is reached and no new interactive input or new pending task is detected during this period, the idle condition is determined to be met.

[0078] The preset duration can be set at the factory or by the user according to their usage habits.

[0079] A stationary position refers to the location where the device is parked when it is not in use, such as the location of the charging dock. Once the idle condition is met, the controller will control the device to move away from the charging dock and enter the preset space for autonomous movement.

[0080] In one example, the pet robot is parked on a charging dock in the living room. After a conversation with its owner, a timer starts. Once the timer reaches a preset duration and there are no new interactions or tasks during that time, the controller moves the pet robot away from the charging dock and begins to move autonomously indoors.

[0081] By adopting the above implementation method, the idle condition is determined by continuous detection for a preset duration, which avoids the device from being mistakenly judged as idle during interaction gaps or task gaps, thus preventing frequent start-stop autonomous activities and making the triggering of autonomous activity state more stable and reasonable.

[0082] The anthropomorphic representation device without interaction provided by the present invention is described below. The anthropomorphic representation device without interaction described below and the anthropomorphic representation method without interaction described above can be referred to in correspondence.

[0083] Figure 3 This is a schematic diagram of the anthropomorphic representation device without interaction provided in the embodiments of this application, as shown below. Figure 3 As shown, the device includes: The status control module 310 is used to acquire the operating status of the device, and when the operating status meets the preset idle conditions, control the device to enter the autonomous activity state; wherein, the idle conditions include that the device has no human interaction input and no task to be executed, and the autonomous activity state is the state in which the device moves autonomously within a preset space; The first behavior determination module 320 is used to determine the preset default behavior as the first target anthropomorphic behavior after the device enters the autonomous activity state; The second behavior determination module 330 is used to, after determining the first target anthropomorphic behavior, randomly select a behavior from a preset behavior set that is different from the previously determined target anthropomorphic behavior as the next target anthropomorphic behavior, and repeat the random selection to obtain multiple target anthropomorphic behaviors; wherein, the behavior set includes a walking expression mode and a fun behavior mode, the walking expression mode is the device outputting audio information during autonomous movement, and the fun behavior mode is the device performing fun actions during autonomous movement; The execution control module 340 is used to control the device to execute the first target anthropomorphic expression and the multiple target anthropomorphic expressions in sequence during autonomous movement.

[0084] Figure 4 This is a schematic diagram of the robot structure provided in the embodiments of this application, such as... Figure 4 As shown, the robot includes a robot body 91, a movement component 92, an audio output component 93, a motion execution component 94, and a controller 95.

[0085] A mobility component is located on the robot body and is used to drive the robot body to move within a preset space. The mobility component can be a wheeled drive structure or a legged drive structure. The wheeled drive structure includes drive wheels and drive motors, while the legged drive structure includes leg mechanisms and corresponding joint drive components. An audio output component is located on the robot body and is used to output audio information. The audio output component can include a speaker and audio processing circuitry. A motion execution component is located on the robot body and is used to perform fun actions. The motion execution component can include at least one of a head rotation mechanism, a limb drive mechanism, a body swing mechanism, and a lighting component. Different fun actions are performed by the corresponding mechanisms in the motion execution component. A controller is connected to the mobility component, audio output component, and motion execution component respectively. The connection method can be an electrical connection or a bus communication connection.

[0086] The controller is configured to acquire the robot's operating status and, when the operating status meets preset idle conditions, control the motion component to drive the robot body to move autonomously within a preset space, thus enabling the robot to enter an autonomous activity state. Idle conditions include no human-interactive input and no pending tasks. The controller is also configured to, after the robot enters the autonomous activity state, determine a preset default behavior as the first target anthropomorphic behavior. After determining the first target anthropomorphic behavior, it randomly selects a behavior different from the previously determined target anthropomorphic behavior from a preset behavior set as the next target anthropomorphic behavior. This random selection is repeated to obtain multiple target anthropomorphic behaviors. The walking expression mode in the behavior set outputs audio information through the audio output component during autonomous movement, while the fun behavior mode performs fun actions through the action execution component during autonomous movement. The controller is also configured to, during the autonomous movement of the robot body driven by the motion component, control the audio output component and the action execution component to execute sequentially according to the order of the first target anthropomorphic behavior and the multiple target anthropomorphic behaviors.

[0087] Furthermore, the controller can also be configured to execute the anthropomorphic performance method without interaction in any of the foregoing method embodiments, such as executing the acquisition of the trigger scene and the adaptive determination of the default performance, or executing the action-level deduplication selection of fun actions. For specific implementation methods, please refer to the description of the corresponding embodiments for the foregoing, which will not be repeated here.

[0088] Using the above implementation method, the robot achieves human-like behavior without interaction through a combination of hardware and software. The mobile component, audio output component and motion execution component work together under the unified scheduling of the controller, so that the robot exhibits continuous and non-repetitive human-like behavior when there is no human interaction. The technical effect achieved at the whole machine level is the same as that of the aforementioned method embodiment.

[0089] Figure 5This is a schematic diagram of the structure of the electronic device provided by the present invention, such as... Figure 5 As shown, the electronic device may include a processor 510, a communications interface 520, a memory 530, and a communication bus 540. The processor 510, communications interface 520, and memory 530 communicate with each other via the communication bus 540. The processor 510 can call logical instructions in the memory 530 to execute a non-interactive anthropomorphic performance method. This method includes: acquiring the device's operating state, and when the operating state meets preset idle conditions, controlling the device to enter an autonomous activity state; wherein the idle conditions include no interactive input and no tasks to be executed on the device, and the autonomous activity state is a state in which the device moves autonomously within a preset space. After the device enters the autonomous activity state, the preset default behavior is determined as the first target anthropomorphic behavior; After determining the first target anthropomorphic expression, a different expression from the previously determined target anthropomorphic expression is randomly selected from a preset set of behaviors as the next target anthropomorphic expression, and the random selection is repeated to obtain multiple target anthropomorphic expressions; wherein, the set of behaviors includes a walking expression mode and a fun behavior mode, the walking expression mode is the device outputting audio information during autonomous movement, and the fun behavior mode is the device performing fun actions during autonomous movement; During autonomous movement, the device is controlled to execute the first target anthropomorphic representation and the subsequent anthropomorphic representations of multiple targets in sequence.

[0090] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0091] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the anthropomorphic performance method without interaction provided by the above methods. The method includes: acquiring the operating state of the device, and when the operating state meets a preset idle condition, controlling the device to enter an autonomous activity state; wherein, the idle condition includes that the device has no interactive input and no task to be executed, and the autonomous activity state is the state in which the device moves autonomously within a preset space. After the device enters the autonomous activity state, the preset default behavior is determined as the first target anthropomorphic behavior; After determining the first target anthropomorphic expression, a different expression from the previously determined target anthropomorphic expression is randomly selected from a preset set of behaviors as the next target anthropomorphic expression, and the random selection is repeated to obtain multiple target anthropomorphic expressions; wherein, the set of behaviors includes a walking expression mode and a fun behavior mode, the walking expression mode is the device outputting audio information during autonomous movement, and the fun behavior mode is the device performing fun actions during autonomous movement; During autonomous movement, the device is controlled to execute the first target anthropomorphic representation and the subsequent anthropomorphic representations of multiple targets in sequence.

[0092] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the anthropomorphic performance method without interaction provided by the above methods. The method includes: acquiring the operating state of the device, and when the operating state meets a preset idle condition, controlling the device to enter an autonomous activity state; wherein, the idle condition includes that the device has no interactive input and no task to be executed, and the autonomous activity state is a state in which the device moves autonomously within a preset space. After the device enters the autonomous activity state, the preset default behavior is determined as the first target anthropomorphic behavior; After determining the first target anthropomorphic expression, a different expression from the previously determined target anthropomorphic expression is randomly selected from a preset set of behaviors as the next target anthropomorphic expression, and the random selection is repeated to obtain multiple target anthropomorphic expressions; wherein, the set of behaviors includes a walking expression mode and a fun behavior mode, the walking expression mode is the device outputting audio information during autonomous movement, and the fun behavior mode is the device performing fun actions during autonomous movement; During autonomous movement, the device is controlled to execute the first target anthropomorphic representation and the subsequent anthropomorphic representations of multiple targets in sequence.

[0093] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0094] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention 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; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for anthropomorphic representation without interaction, characterized in that, The method includes: The device's operating status is acquired, and when the operating status meets preset idle conditions, the device is controlled to enter an autonomous activity state; wherein, the idle conditions include no human interaction input on the device and no tasks to be executed, and the autonomous activity state is the state in which the device moves autonomously within a preset space; After the device enters the autonomous activity state, the preset default behavior is determined as the first target anthropomorphic behavior; After determining the first target anthropomorphic expression, a different expression from the previously determined target anthropomorphic expression is randomly selected from a preset set of behaviors as the next target anthropomorphic expression, and the random selection is repeated to obtain multiple target anthropomorphic expressions; wherein, the set of behaviors includes a walking expression mode and a fun behavior mode, the walking expression mode is the device outputting audio information during autonomous movement, and the fun behavior mode is the device performing fun actions during autonomous movement; During autonomous movement, the device is controlled to execute the first target anthropomorphic representation and the subsequent anthropomorphic representations of multiple targets in sequence.

2. The anthropomorphic representation method without interaction according to claim 1, characterized in that, The fun behavior patterns include multiple fun actions, which are divided into humorous patterns, life simulation patterns, and physiological simulation patterns. When the randomly selected target's anthropomorphic manifestation conforms to the aforementioned interesting behavioral pattern, the method further includes: From all the fun actions corresponding to the humorous mode, the life simulation mode, and the physiological simulation mode, randomly select a fun action that is different from the fun action performed previously, and control the device to perform the selected fun action.

3. The anthropomorphic representation method without interaction according to claim 1, characterized in that, The step of determining the preset default behavior as the first target anthropomorphic behavior includes: Obtain the triggering scenario before the device enters the autonomous activity state; When the triggering scenario is automatically triggered under unmanned interaction conditions, the first type of voice information that matches the scenario automatically triggered under unmanned interaction conditions is determined as the default performance; When the triggering scenario is triggered after an interaction ends, the second type of voice information that matches the scenario triggered after the interaction ends is determined as the default performance.

4. The anthropomorphic representation method without interaction according to claim 1, characterized in that, The marching expression modes include self-narration marching and humming marching; the method further includes: When the randomly selected target is anthropomorphically represented as self-narrating, the device is controlled to output voice information that matches the current scene of the device during autonomous movement. When the randomly selected target is anthropomorphized and moves while humming, the device is controlled to output humming or singing audio information during autonomous movement.

5. The anthropomorphic representation method without interaction according to claim 1, characterized in that, The method further includes: Before the device is in the autonomous activity state and the direction of movement of the device is determined, the device is controlled to output direction selection voice information; wherein, the direction selection voice information is used to represent the device's intention to select the desired direction of movement.

6. The anthropomorphic representation method without interaction according to claim 2, characterized in that, The funny actions corresponding to the humorous mode include at least one of the following: raising limbs, leaping into the air, twisting the body, making a cute pose, spinning and making a cool pose, pounding the ground, continuous spinning, nodding, and looking around. The fun actions corresponding to the life simulation mode include at least one of the following: playing ball, drawing, drumming, finding food, and moving with the light. The fun actions corresponding to the physiological simulation mode include at least one of the following: sneezing, exhaling, smiling, yawning, meditative posture, and smelling objects.

7. The anthropomorphic representation method without interaction according to claim 1, characterized in that, The step of acquiring the operating status of the device and controlling the device to enter an autonomous activity state when the operating status meets preset idle conditions includes: When the device is within the preset space and no human interaction input or pending task is detected within a preset time period, the device is controlled to move autonomously from its stationary position into the preset space, and the device is determined to be in the autonomous activity state.

8. A non-interactive anthropomorphic performance device, characterized in that, The device includes: The status control module is used to acquire the operating status of the device and control the device to enter an autonomous activity state when the operating status meets the preset idle conditions; wherein, the idle conditions include that the device has no human interaction input and no tasks to be executed, and the autonomous activity state is the state in which the device moves autonomously within a preset space; The first line of the determination module is used to determine the preset default behavior as the first target anthropomorphic behavior after the device enters the autonomous activity state; The second behavior determination module is used to, after determining the first target anthropomorphic behavior, randomly select a behavior from a preset behavior set that is different from the previously determined target anthropomorphic behavior as the next target anthropomorphic behavior, and repeat the random selection to obtain multiple target anthropomorphic behaviors; wherein, the behavior set includes a walking expression mode and a fun behavior mode, the walking expression mode is the device outputting audio information during autonomous movement, and the fun behavior mode is the device performing fun actions during autonomous movement; The execution control module is used to control the device to execute the first target anthropomorphic expression and the multiple target anthropomorphic expressions sequentially during autonomous movement.

9. A robot, characterized in that, The robot includes: The robot itself; A mobile component, disposed on the robot body, is used to drive the robot body to move within a preset space; An audio output component, located on the robot body, is used to output audio information; An action execution component, located on the robot body, is used to perform fun actions; The controller is connected to the moving component, the audio output component, and the motion execution component, respectively. The controller is configured to: acquire the operating status of the robot, and when the operating status meets a preset idle condition, control the mobile component to drive the robot body to move autonomously within the preset space, so that the robot enters an autonomous activity state; wherein, the idle condition includes that the robot has no human interaction input and no task to be executed; The controller is further configured to: after the robot enters the autonomous activity state, determine a preset default behavior as the first target anthropomorphic behavior; after determining the first target anthropomorphic behavior, randomly select a behavior different from the previously determined target anthropomorphic behavior from a preset behavior set as the next target anthropomorphic behavior, and repeat the random selection to obtain multiple target anthropomorphic behaviors; wherein, the behavior set includes a walking expression mode and a fun behavior mode, the walking expression mode is to output audio information through the audio output component during autonomous movement, and the fun behavior mode is to perform fun actions through the action execution component during autonomous movement; The controller is also configured to: during the process of the mobile component driving the robot body to move autonomously, control the audio output component and the motion execution component to execute sequentially according to the order of the first target anthropomorphic expression and the order of the multiple target anthropomorphic expressions.

10. The robot according to claim 9, characterized in that, The controller is also configured to perform the anthropomorphic representation method without interaction as described in any one of claims 2 to 7.

11. 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, when executing the computer program, implements the non-interactive anthropomorphic representation method as described in any one of claims 1 to 7.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the non-interactive anthropomorphic performance method as described in any one of claims 1 to 7.

Images