Control method and intelligent mobile device

Abstract

The invention discloses a control method and intelligent mobile equipment, and the method comprises the steps: responding to a target triggering event, and controlling the intelligent mobile equipment to be switched from a current first following mode to a second following mode; and based on the position information and the motion information of the target following object, controlling a movement parameter of the intelligent mobile device so as to control the intelligent mobile device to move to a first relative position relationship with the target following object, wherein under the first relative position relation, the intelligent mobile device can collect front image data and / or side image data of the target following object; in the first following mode, the intelligent mobile device only locates the position of the target following object or only collects rear data of the target following object.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and more specifically, to a control method and a smart mobile device. Background Technology

[0002] Currently, smart mobile devices have become an integral part of more and more users' daily lives, providing them with convenience and services. For example, home robots, in certain scenarios, enter a follow mode, meaning they follow behind the user and record video content. Because the robot follows behind the user, it often fails to capture the user's facial expressions and body movements, reducing the value of the recorded video and thus impacting the user experience. Summary of the Invention

[0003] In view of the above, this application provides the following technical solution:

[0004] The first aspect of this application provides a control method, including:

[0005] In response to a target trigger event, control the smart mobile device to switch from the current first follow mode to the second follow mode; and,

[0006] The movement parameters of the smart mobile device are controlled based on the position and motion information of the target object to control the smart mobile device to move to a position with a first relative positional relationship with the target object.

[0007] In the first relative positional relationship, the smart mobile device is able to collect frontal image data and / or side image data of the target object being followed.

[0008] In the first follow mode, the smart mobile device only locates the position of the target object to be followed or only collects data behind the target object to be followed.

[0009] In one possible implementation, controlling the smart mobile device to switch from the current first follow mode to the second follow mode in response to a target trigger event includes at least one of the following:

[0010] In response to receiving a first mode switching instruction from a target user, the smart mobile device is controlled to switch from the first follow mode to the second follow mode, wherein the target user is or is not the target follow object;

[0011] In response to the state data of the target object being followed satisfying the corresponding triggering condition, the smart mobile device is controlled to switch from the first following mode to the second following mode, wherein the triggering condition corresponding to the target object being followed is different in different activity states;

[0012] In response to a change in the number of target objects being followed by the smart mobile device, the smart mobile device is controlled to switch from the first following mode to the second following mode.

[0013] In response to a change in the spatial environment data of the smart mobile device, the smart mobile device is controlled to switch from the first follow mode to the second follow mode.

[0014] In one possible implementation, the response to the state data of the target following object satisfying a corresponding triggering condition includes at least one of the following:

[0015] The emotional state data of the target object being followed satisfies the corresponding first triggering condition, wherein the first triggering condition includes at least one preset emotional type.

[0016] The activity status data of the target object being followed satisfies the corresponding second triggering condition, wherein the second triggering condition includes at least one preset activity type and / or at least one interaction scenario;

[0017] The target object's body state data satisfies the corresponding third trigger condition, which includes at least one preset body state type and / or physiological parameter range.

[0018] In one possible implementation, the response to the state data of the target following object satisfying a corresponding triggering condition includes at least one of the following:

[0019] When the target object is in a moving state, the emotional state represented by the obtained sound data and / or image data of the target object is analyzed using an emotion analysis model. If the emotional state belongs to the target emotion type, the first triggering condition is determined to be met.

[0020] When the target object is in a relatively stationary state, the scene analysis model is used to analyze the activity state represented by the image data of the target object. If the activity state belongs to the target activity type, it is determined that the second triggering condition is met.

[0021] When the target following object is in an interactive state, the interaction data between the target following object and the target interactive object is analyzed using a scene analysis model. If the analysis shows that the interaction data belongs to the target interactive scene, it is determined that the second triggering condition is met.

[0022] If the target physiological parameters of the target object being followed exceed the corresponding physiological parameter range, the third triggering condition is determined to be met.

[0023] In one possible implementation, controlling the movement parameters of the smart mobile device based on the position and motion information of the target object to be followed includes:

[0024] Predict the destination information of the target object based on its motion and location information;

[0025] The movement parameters of the smart mobile device are determined based on the destination information and the current location information of the smart mobile device.

[0026] The intelligent mobile device is controlled to move according to the movement parameters to a position relative to the target object being followed, thus establishing a first relative positional relationship.

[0027] In one possible implementation, determining the movement parameters of the smart mobile device based on the destination information and the current location information of the smart mobile device includes:

[0028] Based on the destination information, the destination and movement trajectory of the target object being followed are obtained;

[0029] Based on the current location information, the destination and movement trajectory of the target object being followed, at least one of the following is determined: the movement path, movement speed, and movement mode of the smart mobile device.

[0030] or,

[0031] Based on the destination information and the current location information, determine the available space range between the smart mobile device and the target object being followed;

[0032] Based on the available space range and the movement trajectory of the target object being followed, at least one of the following is determined: the movement path, movement speed, and movement mode of the smart mobile device.

[0033] In one possible implementation, determining the movement parameters of the smart mobile device based on the destination information and the current location information of the smart mobile device includes at least one of the following:

[0034] When it is determined based on the current location information that there is a second relative positional relationship between the smart mobile device and the target following object, and the target following object is in a moving state, at least one of the moving path, moving speed, and moving mode of the smart mobile device is determined based on the moving trajectory of the target following object, so as to control the smart mobile device to switch from the second relative positional relationship with the target following object to the first relative positional relationship;

[0035] When it is determined that there is a second relative positional relationship between the smart mobile device and the target object being followed based on the current location information, and the target object being followed is in a relatively stationary state, the movement path and / or movement mode of the smart mobile device are determined based on the available space range between the current location information and the target object being followed.

[0036] If, based on the current location information, it is determined that there is a third relative positional relationship between the smart mobile device and the target object being followed, the movement parameters of the smart mobile device are controlled to keep it relatively stationary with respect to the target object being followed, or the smart mobile device is controlled to move from the third relative positional relationship with the target object to a first relative positional relationship.

[0037] One possible implementation also includes at least one of the following:

[0038] In response to the smart mobile device moving to a position with a first relative position to the target object being followed, the camera module of the smart mobile device is controlled to acquire frontal image data and / or side image data of the target object being followed;

[0039] The image data collected by the smart mobile device during its movement to a positional relationship with the target object being followed is processed to generate frontal and / or side image data of the target object being followed.

[0040] The system obtains time information indicating when the smart mobile device moves to a position with a first relative position to the target object it is following, and acquires image data of the target object from the target acquisition device based on the time information.

[0041] One possible implementation also includes at least one of the following:

[0042] The image data of the target object collected by the smart mobile device is input into the target processing model to generate the movement parameters of the smart mobile device;

[0043] After switching to the second follow mode, the movement parameters of the smart mobile device are controlled based on the position and motion information of the target object being followed;

[0044] In response to switching from the first follow mode to the second follow mode, the movement parameters of the smart mobile device are controlled based on the position and motion information of the target follow object.

[0045] A second aspect of this application provides a smart mobile device, including a camera module, at least one processor, and a memory connected to the processor, wherein:

[0046] The camera module is used to capture images;

[0047] The memory is used to store computer programs;

[0048] The processor is used to execute the computer program to enable the smart mobile device to perform the following operations:

[0049] In response to a target trigger event, control the smart mobile device to switch from the current first follow mode to the second follow mode; and,

[0050] The movement parameters of the smart mobile device are controlled based on the position and motion information of the target object to control the smart mobile device to move to a position with a first relative positional relationship with the target object.

[0051] In the first relative positional relationship, the smart mobile device is able to collect frontal image data and / or side image data of the target object being followed.

[0052] In the first follow mode, the smart mobile device only locates the position of the target object to be followed or only collects data behind the target object to be followed. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of this application 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 only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0054] Figure 1 This is a flowchart of a control method disclosed in an embodiment of this application;

[0055] Figure 2 These are comparative example diagrams of different follow modes disclosed in the embodiments of this application;

[0056] Figure 3 This is a flowchart illustrating the movement parameters of a smart mobile device as disclosed in an embodiment of this application;

[0057] Figure 4 This is an example diagram illustrating the movement of a smart mobile device via flight as disclosed in the embodiments of this application;

[0058] Figure 5 This is an example diagram of a smart mobile device moving around a target object from the side, as disclosed in an embodiment of this application.

[0059] Figure 6This is an example diagram illustrating how a smart mobile device moves around the side of a target-following object when the target and the object are stationary, as disclosed in an embodiment of this application.

[0060] Figure 7 This is a schematic diagram of a movement path planning logic disclosed in an embodiment of this application;

[0061] Figure 8 This is a schematic diagram of another movement path planning logic disclosed in an embodiment of this application;

[0062] Figure 9 This is a schematic diagram of another movement path planning logic disclosed in an embodiment of this application;

[0063] Figure 10 This is a schematic diagram of the structure of a smart mobile device disclosed in an embodiment of this application. Detailed Implementation

[0064] 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 some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0065] This application discloses a control scheme for controlling smart mobile devices. The scheme can be applied to smart mobile devices or other devices capable of controlling them. Specifically, the executing entity of the control scheme disclosed in this application can be the smart mobile device itself, or other processing devices in the smart mobile device application scenario. This processing device can obtain data information from the smart mobile device and information about the following object (the object that the smart mobile device needs to serve or follow), perform corresponding calculations, and generate instructions for controlling the smart mobile device.

[0066] The executing entities of the control scheme include, but are not limited to, robots, smart pets, drones, smartphones, and smart wearable devices. This application does not impose fixed restrictions on the product form of the executing entity of the control scheme, and it can be selected according to application requirements. For ease of understanding, the following embodiments will be described using a smart mobile device itself as the executing entity of the control scheme as an example.

[0067] Figure 1 This is a flowchart illustrating a control method disclosed in an embodiment of this application. See also... Figure 1 As shown, the control method may include:

[0068] Step 101: In response to the target trigger event, control the smart mobile device to switch from the current first follow mode to the second follow mode.

[0069] The target triggering event can be an actively triggered event. When a mobile smart device detects a specific event or scenario, such as monitoring a user (the follower) talking to someone, establishing a video call with someone, reading a book, watching a movie, playing with building blocks, playing with toys, or fiddling with figurines, the smart mobile device actively controls the switch from the first follower mode to the second follower mode.

[0070] Alternatively, the target triggering event can also be a passive triggering event, such as receiving a follow mode switching command or a change in the follow object. The follow mode switching command can be an instruction input by the follow object or other objects, and the input methods include, but are not limited to, voice, gesture, input device input, and remote control.

[0071] The first following mode can be a traditional rear-view following mode, where the smart mobile device follows behind the subject. In this mode, the smart mobile device can essentially only capture the user's back view and cannot capture the subject's face, thus missing much valuable information. The second following mode can be understood as a front-view following mode or a side-view following mode. In this mode, the smart mobile device is always positioned in front of or to the side of the subject at a certain distance and angle, allowing it to capture the subject's face and better record images or videos containing facial information.

[0072] Figure 2 The top image shows an example of the first follow mode, and the bottom image shows an example of the second follow mode. These can be combined. Figure 2 Understand the positional relationship between the followed object and the smart mobile device in both the first and second follow modes.

[0073] Step 102: Control the movement parameters of the smart mobile device based on the position and motion information of the target object to control the smart mobile device to move to a position with a first relative positional relationship with the target object.

[0074] Step 102 can be control logic triggered by the follow mode switch, that is, when controlling the smart mobile device to switch to follow mode, the content of step 102 is implemented synchronously; or, step 102 can also be control logic executed after switching to the second follow mode, that is, after the smart mobile device successfully switches from the first follow mode to the second follow mode, the content of step 102 is implemented.

[0075] The target object to be followed includes, but is not limited to, people, animals, or other mobile devices. The location and motion information of the target object can be used to predict its trajectory and / or destination. After determining the trajectory and / or destination, the movement parameters of the smart mobile device can be determined based on this information. These movement parameters include, but are not limited to, movement path, movement direction, movement speed, and movement mode. The movement mode refers to application scenarios where smart mobile devices have different movement modes, such as some smart mobile devices that simultaneously possess land-based and flight movement capabilities.

[0076] Understandably, in the first follow mode, the smart mobile device is positioned behind the target object. However, in the second follow mode, the smart mobile device needs to be positioned in front of or to the side of the target object. Therefore, after the smart control device switches from the first follow mode to the second follow mode, the smart mobile device does not immediately move to the front of the target object. Instead, it needs to move from behind the target object to the front of it. In other words, after switching follow modes, the smart mobile device needs to first move from behind the target object to the front or side-front of it, and then maintain its position in front of or side-front of the target object to ensure that the mobile smart device can capture the front or side view of the target object.

[0077] The first relative positional relationship ensures that the smart mobile device is always within the target distance range of the side front or directly front of the target object, such as always being within the radiation range of -70 degrees to 70 degrees in the frontal direction of the target object. Under the first relative positional relationship, the smart mobile device is able to acquire frontal image data and / or side image data of the target object. The image data here can be image frames, live images, or video data.

[0078] In the first follow mode, the smart mobile device only locates the position of the target object or only collects data from behind the target object. Locating the target object's position can be achieved through methods such as ultrasonic positioning or UWB antenna positioning, thus enabling intelligent following from behind. Collecting data from behind the target object includes, but is not limited to, collecting image data of the target object's rear, map data of the surrounding environment, and data of other objects behind it. Compared to the first follow mode, in the second follow mode, the smart mobile device can move from behind the target object to in front of or to the side of the target object, capturing facial images. This allows for better recording of the target object's behavior and helps in better understanding its emotions and intentions, thereby providing better service to the target object or user.

[0079] It should be noted that the path of a smart mobile device moving from behind to in front of or to the side of the target object must avoid the target object's movement range to prevent interfering with its movement. In other words, the smart mobile device's movement path should be curved, bypassing the user's side to reach the front of the target object.

[0080] The control method described in this embodiment automatically controls the smart mobile device to switch from a first follow mode to a second follow mode when a target trigger event is detected. This allows the smart mobile device to move from behind the target object to a position where it can capture a frontal and / or side image of the target object, thereby acquiring more meaningful images containing the facial content of the target object.

[0081] In one implementation, controlling a smart mobile device to switch from a current first follow mode to a second follow mode in response to a target trigger event may include: controlling the smart mobile device to switch from the first follow mode to the second follow mode in response to receiving a first mode switching instruction from a target user, wherein the target user is or is not the target follow object.

[0082] In this implementation, the switching of the follow mode is triggered by the reception of a passive command, as described in the previous embodiment. The command can be a voice command, an action command, or can be triggered by a physical or virtual switch on a smart mobile device or a machine capable of controlling a smart mobile device. The command can be issued by the target object being followed, such as the target object issuing a voice command like "I want to make a video call now, please record a video for me"; or the command can be issued by other objects, such as parents wanting the home robot to record their child playing games, they can control the home robot to switch from the first follow mode to the second follow mode by pressing the relevant button on the home robot or through a third-party device such as a mobile phone.

[0083] In another implementation, in response to a target trigger event, controlling the smart mobile device to switch from the current first follow mode to the second follow mode includes: in response to the state data of the target follow object satisfying the corresponding trigger condition, controlling the smart mobile device to switch from the first follow mode to the second follow mode, wherein the trigger condition corresponding to the target follow object is different in different activity states.

[0084] In this implementation, the switching of the follow mode is actively triggered, that is, when the corresponding triggering conditions are detected, the smart mobile device is automatically controlled to switch from the first follow mode to the second follow mode.

[0085] The status data can be activity status, including but not limited to movement status, stationary status, game status, motion status, meeting status, etc. For example, if a child is detected playing with a Rubik's Cube, the system can automatically switch from the first follow mode to the second follow mode, so that the smart mobile device moves from behind the child to their side and front to capture images or videos of them focusing on playing with the Rubik's Cube.

[0086] Status data can also be emotional or physical states, such as happiness, frustration, sadness, fatigue, excitement, etc. For example, if a user (the target being followed) says, "I'm so busy today, I'm exhausted," then it's determined that the user is in a fatigued state, and the system automatically switches to the second following mode to capture images or videos containing the user's facial features.

[0087] Status data can also represent work or study status. In this state, the smart mobile device can run relevant applications to provide corresponding functions. For example, if the robot has a built-in elementary school curriculum knowledge base and the user (the target being followed) says, "What is the next line after 'The lotus leaves stretch to the sky, an endless expanse of green'?", the robot determines that the user is in a learning state and will switch to a second following mode, circling around to the user's side and collecting the user's learning process. At the same time, it will activate the elementary school knowledge base application to answer the user's questions.

[0088] The triggering conditions for the target object differ depending on its state. Responding to the target object's state data satisfying the corresponding triggering condition may include: the target object's emotional state data satisfying a corresponding first triggering condition, where the first triggering condition includes at least one preset emotion type.

[0089] During implementation, the voice and / or image data of the target being followed needs to be monitored in real time. The emotional state is obtained through the recognition and analysis of this data. Emotional state data can also be sounds representing emotional states, such as crying or laughing. The emotional state data of the target being followed satisfies the corresponding first trigger condition, that is, it matches a preset emotion type. The emotion type can be a mood state or emotional state, including happiness, sadness, frustration, etc.

[0090] That is, when the target object is in a moving state, the emotional state represented by the obtained sound data and / or image data of the target object is analyzed using an emotion analysis model, and if the emotional state belongs to the target emotion type, the first triggering condition is determined to be met.

[0091] For example, the state data could be emotional state, and the triggering condition could be detecting that the user is laughing, crying, or speaking emotionally charged words. In specific implementation, for scenarios where the user speaks emotionally charged words, after collecting voice data such as "This is really good news," the collected voice data can be sent to a speech recognition model, and the recognized text content can be input into a sentiment analysis model. Simultaneously, the image collected by the robot can be sent to a visual recognition model. If the sentiment analysis result is "happy" and the visual recognition result is a "smiling face," then it can be determined that a pre-following mode (second follow mode) needs to be executed. Of course, there might be situations where the robot's original image does not contain the user's face and cannot identify whether it is a "smiling face." In such cases, based on the sentiment analysis result of "happy," the robot can perform curved movements around the user until it can capture the user's facial expression.

[0092] In response to the target following object's state data satisfying the corresponding triggering condition, it may include: the target following object's activity state data satisfying the corresponding second triggering condition, the second triggering condition including at least one preset activity type and / or at least one interaction scenario.

[0093] The activity status can include work status, study status, exercise status, entertainment activities, etc. If the identification result of the activity status data matches the preset activity scenario, it can be considered that the second trigger condition is met. Activity types include fitness, doing crafts, reading, playing games, etc.; interaction scenarios include communicating with people, playing with pets, controlling other devices, etc.

[0094] That is, when the target object is in a relatively static state, the activity state represented by the image data of the target object obtained by the scene analysis model is analyzed, and if the activity state belongs to the target activity type, the second triggering condition is determined to be met.

[0095] For example, camera data is fed into a visual recognition model; the visual recognition results are analyzed and then fed into a scene analysis model to analyze what the currently followed target is doing; if the analysis results indicate that the followed target is in a relatively "static" scene, such as playing with building blocks, then it is determined that a forward-following mode is needed.

[0096] Alternatively, when the target following object is in an interactive state, the interaction data between the target following object and the target interactive object is analyzed using a scene analysis model. If the analysis shows that the interaction data belongs to the target interactive scene, it is determined that the second triggering condition is met.

[0097] For example, the robot inputs the content captured by the camera into the visual recognition model, analyzes the visual recognition results, and sends the results to the scene analysis model to analyze what the target object is currently doing. If the analysis results indicate that the target object is talking to someone else, it can be determined that the forward follow mode needs to be executed.

[0098] In response to the target following object's state data satisfying the corresponding triggering condition, it may include: the target following object's body state data satisfying the corresponding third triggering condition, the third triggering condition including at least one preset body state type and / or physiological parameter range.

[0099] Body status data can be obtained through smart wearable devices, or through images or sounds of the target being followed. The body status data must meet a third trigger condition, which can be a match with a preset body status, such as detecting fatigue, high heart rate, high body temperature, injury, etc. The physiological parameter range is preset and can include blood pressure range, heart rate range, etc.; for example, a normal heart rate is 60-110. If the smart wearable device detects that the target being followed has a heart rate of 118, exceeding the preset parameter range, then the third trigger condition is determined to be met. In other words, the third trigger condition is determined to be met when the target physiological parameters of the target being followed exceed the corresponding physiological parameter range.

[0100] In another implementation, in response to a target triggering event, controlling the smart mobile device to switch from the current first follow mode to the second follow mode includes: in response to the smart mobile device's target follow object switching from the current first object to the second object or the number of target follow objects changing, controlling the smart mobile device to switch from the first follow mode to the second follow mode.

[0101] If the target of the tracking changes, such as switching from following an adult to following a baby or child, or from a person to a pet, it may be necessary to capture more precious moments of the child or pet. For example, if the original target of the tracking was the mother, and the mother approaches the child with a toy and hands it to the child, then the target of the tracking has changed from the mother to the child, and it is necessary to switch to the front-follow mode.

[0102] The number of objects being followed changes, such as switching from only object A to having two objects, A and B. For example, if user A (the object being followed) walks towards user B, they may need to take a photo together. The smart mobile device needs to move around to the front of the user to take the photo, thus confirming the execution of the front-follow mode.

[0103] In another implementation, in response to a target triggering event, controlling the smart mobile device to switch from the current first follow mode to the second follow mode includes: in response to a change in the spatial environment data of the smart mobile device, controlling the smart mobile device to switch from the first follow mode to the second follow mode.

[0104] Among them, the spatial environment data changes. For example, when a yoga teacher brings a classroom assistant robot to the classroom, the classroom assistant robot is in the first follow mode in the corridor before entering the classroom, moving behind the yoga teacher. After the yoga teacher enters the classroom, the classroom assistant robot switches to the second follow mode, goes around to the front of the yoga teacher, and collects video of the yoga teacher's teaching process in real time.

[0105] Furthermore, changes in road conditions within the spatial environment may also trigger a switch in the following mode. For example, if the target object is initially in a cluttered and confined space, the robot will initially operate in the first following mode, following behind the target object to avoid hindering its movement. Once the target object enters a more spacious area, the robot can switch to the second following mode, circling around to the front of the target object to capture a frontal image.

[0106] The above content details the specific implementation of controlling a smart mobile device to switch from the current first follow mode to the second follow mode in response to a target trigger event. However, the above content does not constitute a fixed limitation on the implementation of switching follow modes. In practical applications, different follow mode switching trigger conditions can be configured based on requirements to adapt to different scenario needs and better serve users.

[0107] Figure 3 This is a flowchart illustrating the movement parameters of a smart mobile device as disclosed in an embodiment of this application. (In conjunction with...) Figure 3 As shown, controlling the movement parameters of the smart mobile device based on the position and motion information of the target object to be followed may include:

[0108] Step 301: Predict the destination information of the target object based on its motion information and location information.

[0109] The motion information includes motion direction, motion state, and motion speed. Specifically, the movement trajectory and destination of the target being followed can be predicted based on the target's motion direction, motion state, motion speed, and current position.

[0110] Step 302: Determine the movement parameters of the smart mobile device based on the destination information and the current location information of the smart mobile device.

[0111] Determining the movement parameters of a smart mobile device requires considering the destination of the target object, its movement trajectory, information about other objects in the space they occupy, and the available space. Furthermore, it's necessary to consider the motion information of the target object, such as whether it is stationary and its speed. These considerations are made to ensure that the smart mobile device does not interfere with the target object during movement, preventing contact, collisions, or blocking its path. Furthermore, considering information about other objects in the space they occupy and the available space helps avoid mutual interference between the smart mobile device and other objects, and also assists in planning the shortest possible movement path.

[0112] The current location information of a smart mobile device is used to determine whether it is in front of, to the side of, or behind the target object it is following, thereby determining the movement path and speed of the smart mobile device.

[0113] Step 303: Control the smart mobile device to move according to the movement parameters to a position with a first relative positional relationship with the target object being followed.

[0114] The movement parameters include, but are not limited to, movement path, movement speed, and movement mode. After determining the movement parameters, the intelligent mobile device is directly controlled to move according to the movement parameters to a position with a first relative position to the target object, thereby achieving forward following of the target object and acquiring images of the front and / or side of the target object.

[0115] In this implementation, the destination information of the target object is first predicted based on the motion and position information of the target object. Then, the movement parameters of the smart mobile device are determined based on the destination information and the current position information of the smart mobile device. The smart mobile device is then controlled to move based on the movement parameters. This implementation process fully considers the movement state of the target object, thereby enabling the smart mobile device to move to a position with a first relative position relationship with the target object according to a more reasonable and accurate movement path.

[0116] In one implementation, determining the movement parameters of the smart mobile device based on the destination information and the current location information of the smart mobile device includes: obtaining the destination and movement trajectory of the target following object based on the destination information; and determining at least one of the movement path, movement speed, and movement mode of the smart mobile device based on the current location information, the destination and movement trajectory of the target following object.

[0117] In other words, the robot's movement path, speed, and mode of movement are determined based on the positional relationship and trajectory of the target object and the intelligent mobile device. For example, if the target object moves forward in a straight line to a location 'a' meters in front of it, and the intelligent mobile device is located 'b' meters behind the target object, the intelligent mobile device's movement path needs to avoid the target object, thus requiring it to detour around to the front or side of the target object. Since the target object is constantly moving forward, the intelligent mobile device's speed needs to be greater than the target object's speed in order to detour around to the front or side of the target object. Furthermore, when the target object is moving in a relatively narrow space, if the mobile intelligent device simultaneously supports land and air movement, it can be controlled to move from behind the target object to in front of it via air movement. Figure 4 This diagram illustrates an example of a smart mobile device moving by flight, which can be combined with... Figure 4 Understand the relevant content.

[0118] In another implementation, determining the movement parameters of the smart mobile device based on the destination information and the current location information of the smart mobile device includes: determining the available space range between the smart mobile device and the target following object based on the destination information and the current location information; and determining at least one of the movement path, movement speed, and movement mode of the smart mobile device based on the available space range and the movement trajectory of the target following object.

[0119] This implementation determines the movement path of the smart mobile device by defining the available space range. For example, if the target following device is moving forward in a straight line, and the smart mobile device is behind the target following object, it needs to go around to the front of the target following object; if the space on the right side of the target following object is narrow and the smart mobile device cannot pass through, while the space on the left side is wide, the smart mobile device can be controlled to go around to the front or side-front of the target following object from the left side. Figure 5 This diagram illustrates an example of a smart mobile device moving around a target object from the side, which can be combined with... Figure 5 Understand the relevant content.

[0120] In one implementation, determining the movement parameters of the smart mobile device based on the destination information and the current location information of the smart mobile device includes: when it is determined based on the current location information that there is a second relative positional relationship between the smart mobile device and the target following object, and the target following object is in a moving state, determining at least one of the movement path, movement speed, and movement mode of the smart mobile device based on the movement trajectory of the target following object, so as to control the smart mobile device to switch from the second relative positional relationship with the target following object to the first relative positional relationship.

[0121] The second relative positional relationship refers to the smart mobile device being located within a certain distance behind the target object. Since the smart mobile device is moving, the movement path needs to be planned based on the target object's movement trajectory to move from the second relative positional relationship to the first relative positional relationship. (See also...) Figure 5 Understand the content of this implementation.

[0122] In another implementation, determining the movement parameters of the smart mobile device based on the destination information and the current location information of the smart mobile device includes: when it is determined based on the current location information that there is a second relative positional relationship between the smart mobile device and the target following object, and the target following object is in a relatively stationary state, determining the movement path and / or movement mode of the smart mobile device based on the available space range between the current location information and the target following object.

[0123] In this implementation, if the smart mobile device is behind the target object and the target object is stationary, the smart mobile device only needs to move to the front or side of the target object. The path and movement method can be planned by only considering the obstacle information within the space between the two. Figure 6 An example diagram is shown where a smart mobile device moves around the side of the target object while the target and the object are stationary, which can be used for understanding.

[0124] In another implementation, determining the movement parameters of the smart mobile device based on the destination information and the current location information of the smart mobile device includes: if it is determined based on the current location information that there is a third relative positional relationship between the smart mobile device and the target following object, controlling the movement parameters of the smart mobile device to keep it relatively stationary with respect to the target following object, or controlling the smart mobile device to move from the third relative positional relationship with the target following object to having the first relative positional relationship.

[0125] The third relative positional relationship can be that the smart mobile device is located in front of or to the side of the target object. If the smart mobile device and the target object are already in this third relative positional relationship, it is sufficient to maintain a relatively stationary state between them.

[0126] Furthermore, considering that although the smart mobile device is in front of or to the side of the target object, there may be situations where the distance between the two is too far or too close, in other implementations, even when the target object and the smart mobile device have a third relative positional relationship, the smart mobile device will still be controlled to move from the third relative positional relationship with the target object to the first relative positional relationship.

[0127] In implementation, after triggering the follow mode switch, the movement path of the smart mobile device can be planned in real time. The specific process includes: determining the current position coordinates of the smart mobile device as the starting position; determining the target position of the smart mobile device based on the position coordinates of the target object to be followed and the movement parameters of the target object to be followed, wherein the movement parameters include at least the movement direction and the movement speed; and planning the movement path based on the starting position and the target position.

[0128] The method of planning a following path based on the starting position and the target position includes at least one of the following: if the video captured by the smart mobile device contains the frontal facial features of the target object, a movement path of the smart mobile device is planned based on the movement parameters of the target object; if the video captured by the smart mobile device contains the back view features of the target object, an available space range is determined based on the starting position and the target position, coordinate point interpolation is performed within the available space range to obtain a set of coordinate points, and a movement path of the smart mobile device is planned based on the set of coordinate points, wherein the available space range is a range through which the smart mobile device can move without intersecting with the movement space of the target object; if the video captured by the smart mobile device contains the side facial features of the target object, an available space range is determined based on the starting position and the target position; based on the orientation of the smart mobile device relative to the user, coordinate point interpolation is performed within the available space range to obtain a set of coordinate points; and a movement path is planned based on the set of coordinate points.

[0129] In a specific implementation, the planning logic for the movement path of a smart mobile device in the lead-follow mode is as follows:

[0130] 1. The main control module sends camera data to the visual model and motion trajectory prediction model in real time;

[0131] 2. The visual model performs image reasoning to infer the presence of a human face / back view / side profile (left / right side) in the image.

[0132] 3. The motion trajectory model performs image reasoning to infer the direction of motion of the target in the image;

[0133] 4. The main control module determines its current position based on the inference results of the visual model:

[0134] The image contains all human faces—the robot is positioned directly in front of the target it is following, so there is no need to adjust its orientation.

[0135] The image only shows the robot's back—the robot is positioned in the opposite direction of the target it is following, and its following orientation needs to be adjusted.

[0136] The image contains some facial data—the robot is located to the side of the target it is following, and its following orientation needs to be adjusted.

[0137] 5. The main control module obtains the direction and speed of motion of the target based on the reasoning results of the motion trajectory model;

[0138] 6. Based on the direction of movement of the target being followed, predict the coordinates of the target's destination and set the coordinates of the user's own destination as the position ahead of the target's destination coordinates;

[0139] 7. Use your own position coordinates as the starting coordinates for path planning, and combine them with the destination coordinates calculated in step 6;

[0140] 8. If the robot is in the forward direction of the target it is following, it plans its own running path in real time. The corresponding movement path planning logic is illustrated as follows: Figure 7 ;

[0141] 9. If the robot is positioned in the opposite direction of the target it is following, calculate the available spatial coordinate range between the starting point and the target point (avoiding the coordinate range of the target object), interpolate intermediate coordinate points, and then use this set of coordinate points to plan its own running path in real time. The corresponding movement path planning logic is illustrated below. Figure 8 ;

[0142] 10. If the robot is located to the side of the target it is following, calculate the available spatial coordinate range between the starting point and the target point (avoiding the target's coordinate range), as well as the robot's lateral orientation relative to the target (selecting coordinate points in the lateral orientation direction). Perform intermediate coordinate point interpolation, and then use this set of coordinate points to plan its own running path in real time. The corresponding movement path planning logic is illustrated as follows: Figure 9 ;

[0143] 11. In steps 9 and 10, calculate the radian value of the planned path. During the robot's movement, combine its real-time position and the distance to the target to calculate the angle that the head needs to rotate. Rotate the head in real time so that the camera can be aligned to capture images of the target.

[0144] 12. Move in real time according to the planned movement path.

[0145] The above content details various implementations of determining the movement parameters of the smart mobile device based on the destination information of the target object being followed and the current location information of the smart mobile device, which helps those skilled in the art to better understand and implement the technical solution of this application.

[0146] In other implementations, in addition to the steps disclosed in the foregoing embodiments, the control method may also include: in response to the smart mobile device moving to a position with a first relative positional relationship with the target object being followed, controlling the camera module of the smart mobile device to acquire frontal image data and / or side image data of the target object being followed.

[0147] After acquiring frontal and / or side image data of the target object, the image data can be saved automatically or according to default / user settings, such as saving only the image data of the user's actions and expressions.

[0148] In other implementations, the control method may further include: generating image data collected by the smart mobile device during its movement to a position with the target object being followed, thereby obtaining frontal and / or side image data of the target object being followed.

[0149] For example, as the robot moves from behind the user (the target being followed) to in front of or to the side of the user, the image data collected by the robot may only include the user's back and the back of their head, without including the user's facial data. In order to make the image data more vivid and complete, this part of the image data that does not include the user's face can be processed so that the images collected after the follow mode is switched will all include the user's facial content.

[0150] In practice, facial content can be added to images that do not contain facial content based on an image generation model or an image processing model.

[0151] In one example, a photo of the target object to be followed can be input by the user and fed into the model, allowing the model to learn the facial contour data of the target object in advance. During the robot's forward following motion, a "partial" expression image of the target object is captured and fed into the model. The model analyzes that the facial part in the expression data is "incomplete" and needs to be "completed". Based on the previously learned facial contour data of the target object, the model "completes" the facial image in the expression image and adjusts the acquisition angle of the expression image to capture a frontal view.

[0152] In another example, after entering the front-follow mode, the video data recorded and saved after entering the front-follow mode is processed so that all image frames in the video data contain at least some of the user's facial features. In implementation, based on pre-stored user facial features, the first image frame containing partial facial features, acquired by the image acquisition module during the process of the smart mobile device moving from behind the target object to having a first relative position with the target object, is processed so that the first image frame contains the user's complete facial features; other display content in the first image frame besides the facial features is adjusted so that the visual acquisition angle of the first image frame corresponds to the user's frontal face acquisition angle; the processed first image frame replaces the original, unprocessed first image frame. Specifically, adjusting other display content in the first image frame besides the facial features can be achieved by adjusting the image content other than the facial features in the second image frame acquired after the smart mobile device moves to a first relative position with the target object.

[0153] In other implementations, the control method may further include: obtaining time information of the smart mobile device moving to a position with a first relative positional relationship with the target object being followed, and acquiring image data of the target object being followed from a target acquisition device based on the time information.

[0154] In practical applications, smart mobile devices, such as robots, are used in scenarios involving other recording devices, such as home security cameras, personal mobile phones, and digital video cameras. The robot connects to the same home network as these devices and can share the recorded data via a personal mobile phone. Therefore, images containing the user's (target's) face captured by other recording devices can be used to supplement or complete the time periods where the smart mobile device did not capture the user's face. Specifically, the time points when the robot triggers the pre-following event and when the robot completes the pre-following action can be recorded; the content of other recording devices can be accessed to find the video content within the corresponding time points; the video content found can be analyzed using a recognition model to determine if it contains the frontal face of the person being followed; if it does, this data segment is sent to the robot; the robot integrates this data and merges it into the captured best video.

[0155] In one example, a smart mobile device can send a data request to other connected recording devices. The data request includes time period information, which corresponds to the period from when the smart mobile device enters the front-follow mode to when it moves to a first relative position with the target object. The device can also receive video content from other devices that contains at least some facial features of the target object during the specified time period. The device can then stitch the video content together with video content recorded after the smart mobile device moves to the first relative position with the target object and save the resulting video data.

[0156] The above embodiments describe the supplementary processing of images that do not contain the front or side view of the target object after the smart mobile device triggers the follow mode switch, so that all content of the images / videos captured from the moment the follow mode is switched includes the facial content of the target object, thereby better recording the past events of the target object.

[0157] In other implementations, the control method may further include at least one of the following: inputting image data of the target object collected by the smart mobile device into a target processing model to generate motion parameters of the smart mobile device; after switching to the second following mode, controlling the motion parameters of the smart mobile device based on the position information and motion information of the target object; and in response to switching from the first following mode to the second following mode, controlling the motion parameters of the smart mobile device based on the position information and motion information of the target object.

[0158] The process of inputting the image data of the target object collected by the smart mobile device into the target processing model to generate the movement parameters of the smart mobile device is to determine the movement information of the target object in real time, including but not limited to the movement direction and movement speed, so as to optimize and correct the movement parameters of the smart mobile device in real time based on the movement information of the target object.

[0159] In practice, the AI ​​big model (target processing model) can be directly used to generate the movement trajectory, movement speed, and movement mode of the smart mobile device. That is, based on the position, orientation, movement speed of the target object and the obstacle information between the smart mobile device and the target object, the AI ​​big model can be used to plan the movement path and movement speed of the smart mobile device.

[0160] The process of controlling the movement parameters of the smart mobile device based on the position and motion information of the target object can be done without relying on a large model. Instead, it can be based on the built-in algorithm logic to predict the movement trajectory and destination of the target object when it is in motion. Then, it can move to the front or side of the target object by controlling its own movement path and speed. In the implementation, obstacle information and map information can also be further considered.

[0161] Furthermore, the movement parameters of the smart mobile device can be controlled based on the location and motion information of the target object being followed. This can be done from the moment the follow mode switch is triggered, or it can be done after the second follow mode is successfully switched. This application does not impose any fixed restrictions on this, and the specific configuration can be set based on the actual application scenario.

[0162] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0163] The methods described in the above-disclosed embodiments of this application are detailed in terms of their implementation. The methods of this application can be implemented using various forms of apparatus. Therefore, this application also discloses an apparatus, which will be described below.

[0164] This application discloses a control device, including:

[0165] The mode switching module is used to control the smart mobile device to switch from the current first follow mode to the second follow mode in response to a target trigger event.

[0166] The motion control module is used to control the motion parameters of the smart mobile device based on the position information and motion information of the target object being followed, so as to control the smart mobile device to move to a position with a first relative positional relationship with the target object being followed.

[0167] In the first relative positional relationship, the smart mobile device can collect frontal image data and / or side image data of the target object being followed; in the first following mode, the smart mobile device only locates the position of the target object being followed or only collects rear data of the target object being followed.

[0168] The control device described in this embodiment automatically controls the smart mobile device to switch from the first follow mode to the second follow mode when a target trigger event is detected, so that the smart mobile device can move from behind the target object to a position where a frontal and / or side image of the target object can be captured, thereby acquiring a more meaningful image containing the facial content of the target object.

[0169] In one implementation, the mode switching module is used for at least one of the following: in response to receiving a first mode switching instruction from a target user, controlling the smart mobile device to switch from a first follow mode to a second follow mode, wherein the target user is or is not the target follow object; in response to the state data of the target follow object satisfying a corresponding trigger condition, controlling the smart mobile device to switch from the first follow mode to the second follow mode, wherein the trigger condition corresponding to the target follow object is different in different activity states; in response to the target follow object of the smart mobile device switching from the current first object to the second object or the number of target follow objects changing, controlling the smart mobile device to switch from the first follow mode to the second follow mode; in response to a change in the spatial environment data of the smart mobile device, controlling the smart mobile device to switch from the first follow mode to the second follow mode.

[0170] In one implementation, in response to the target following object's state data satisfying a corresponding trigger condition, including at least one of the following: the target following object's emotional state data satisfying a corresponding first trigger condition, the first trigger condition including at least one preset emotion type; the target following object's activity state data satisfying a corresponding second trigger condition, the second trigger condition including at least one preset activity type and / or at least one interaction scenario; the target following object's physical state data satisfying a corresponding third trigger condition, the third trigger condition including at least one preset physical state type and / or physiological parameter range.

[0171] In one implementation, in response to the state data of the target following object satisfying a corresponding trigger condition, at least one of the following is determined: when the target following object is in a moving state, the emotional state represented by the obtained sound data and / or image data of the target following object is analyzed using an emotion analysis model, and if the emotional state belongs to the target emotion type, a first trigger condition is determined to be satisfied; when the target following object is in a relatively stationary state, the activity state represented by the obtained image data of the target following object is analyzed using a scene analysis model, and if the activity state belongs to the target activity type, a second trigger condition is determined to be satisfied; when the target following object is in an interactive state, the interaction data between the target following object and the target interactive object is analyzed using a scene analysis model, and if the analysis shows that the interaction data belongs to the target interactive scene, a second trigger condition is determined to be satisfied; and when the target physiological parameters of the target following object exceed the corresponding physiological parameter range, a third trigger condition is determined to be satisfied.

[0172] In one implementation, the motion control module includes: a prediction processing module, used to predict the destination information of the target following object based on the motion information and position information of the target following object; a parameter determination module, used to determine the motion parameters of the smart mobile device based on the destination information and the current position information of the smart mobile device; and a motion control submodule, used to control the smart mobile device to move according to the motion parameters to a position with a first relative positional relationship with the target following object.

[0173] In one implementation, the parameter determination module can specifically be used to: obtain the destination and movement trajectory of the target object based on the destination information; determine at least one of the movement path, movement speed, and movement mode of the smart mobile device based on the current location information, the destination and movement trajectory of the target object; or,

[0174] Based on the destination information and the current location information, determine the available space range between the smart mobile device and the target object being followed; based on the available space range and the movement trajectory of the target object being followed, determine at least one of the following: the movement path, movement speed, and movement mode of the smart mobile device.

[0175] In one implementation, the parameter determination module can be used for at least one of the following: when it is determined based on the current location information that there is a second relative positional relationship between the smart mobile device and the target following object, and the target following object is in a moving state, determining at least one of the movement path, movement speed, and movement mode of the smart mobile device based on the movement trajectory of the target following object, so as to control the smart mobile device to switch from the second relative positional relationship with the target following object to the first relative positional relationship; when it is determined based on the current location information that there is a second relative positional relationship between the smart mobile device and the target following object, and the target following object is in a relatively stationary state, determining the movement path and / or movement mode of the smart mobile device based on the available space range between the current location information and the target following object; when it is determined based on the current location information that there is a third relative positional relationship between the smart mobile device and the target following object, controlling the movement parameters of the smart mobile device to keep it relatively stationary with the target following object, or controlling the smart mobile device to move from the third relative positional relationship with the target following object to the first relative positional relationship.

[0176] In one implementation, the control device may further include: an image processing module, configured to: in response to the smart mobile device moving to a position relative to the target object, control the camera module of the smart mobile device to acquire frontal and / or side image data of the target object; generate and process the image data acquired by the smart mobile device during its movement to the position relative to the target object to obtain frontal and / or side image data of the target object; obtain time information of the smart mobile device moving to the position relative to the target object, and acquire image data of the target object from a target acquisition device based on the time information.

[0177] In one implementation, the control device may further include: a parameter control module, configured to: input image data of the target object being followed, acquired by the smart mobile device, into a target processing model to generate motion parameters of the smart mobile device; control the motion parameters of the smart mobile device based on the position information and motion information of the target object being followed after switching to the second following mode; and control the motion parameters of the smart mobile device based on the position information and motion information of the target object being followed in response to switching from the first following mode to the second following mode.

[0178] The specific implementation of the above-mentioned control device and its various modules can be found in the corresponding sections of the method embodiments, and will not be repeated here.

[0179] Any of the control devices described in the above embodiments includes a processor and a memory. The mode switching module, motion control module, prediction processing module, parameter determination module, motion control submodule, image processing module, parameter control module, etc. in the above embodiments are all stored as program modules in the memory, and the processor executes the above program modules stored in the memory to realize the corresponding functions.

[0180] The processor contains a kernel, which retrieves the corresponding program modules from memory. One or more kernels can be configured, and the processing of backtracking data can be achieved by adjusting kernel parameters.

[0181] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0182] In an exemplary embodiment, a computer-readable storage medium is also provided, which can be directly loaded into the internal memory of a computer, and contains software code. After being loaded and executed by the computer, the computer program can implement the steps shown in any of the embodiments of the control method described above.

[0183] In an exemplary embodiment, a computer program product is also provided, which can be directly loaded into the internal memory of a computer and contains software code. After being loaded and executed by the computer, the computer program can implement the steps shown in any embodiment of the control method described above.

[0184] Furthermore, this application provides a smart mobile device. Figure 10 This is a schematic diagram of the structure of a smart mobile device disclosed in an embodiment of this application. See also... Figure 10 As shown, the smart mobile device 100 includes a camera module 1001, at least one processor 1002, and at least one memory 1003 and a bus 1004 connected to the processor; wherein, the camera module can be a panoramic camera module, or a monocular camera or a spotlight camera; the processor and the memory communicate with each other through the bus; the processor is used to call program instructions in the memory to execute the above control method.

[0185] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0186] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0187] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0188] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A control method, comprising: In response to a target trigger event, control the smart mobile device to switch from the current first follow mode to the second follow mode; as well as, The movement parameters of the smart mobile device are controlled based on the position and motion information of the target object to control the smart mobile device to move to a position with a first relative positional relationship with the target object. In the first relative positional relationship, the smart mobile device is able to collect frontal image data and / or side image data of the target object being followed. In the first follow mode, the smart mobile device only locates the position of the target object to be followed or only collects data behind the target object to be followed.

2. The method according to claim 1, wherein controlling the smart mobile device to switch from the current first follow mode to the second follow mode in response to the target triggering event includes at least one of the following: In response to receiving a first mode switching instruction from a target user, the smart mobile device is controlled to switch from the first follow mode to the second follow mode, wherein the target user is or is not the target follow object; In response to the target object's status data satisfying the corresponding trigger condition, the smart mobile device is controlled to switch from the first following mode to the second following mode, wherein... The triggering conditions for the target object to follow are different in different activity states; In response to a change in the number of target objects being followed by the smart mobile device, the smart mobile device is controlled to switch from the first following mode to the second following mode. In response to a change in the spatial environment data of the smart mobile device, the smart mobile device is controlled to switch from the first follow mode to the second follow mode.

3. The method according to claim 2, wherein, The response is that the state data of the target following object satisfies the corresponding triggering condition, including at least one of the following: The emotional state data of the target object being followed satisfies the corresponding first triggering condition, wherein the first triggering condition includes at least one preset emotional type. The activity status data of the target object being followed satisfies the corresponding second triggering condition, wherein the second triggering condition includes at least one preset activity type and / or at least one interaction scenario; The target object's body state data satisfies the corresponding third trigger condition, which includes at least one preset body state type and / or physiological parameter range.

4. The method according to claim 2, wherein, The response is that the state data of the target following object satisfies the corresponding triggering condition, including at least one of the following: When the target object is in a moving state, the emotional state represented by the obtained sound data and / or image data of the target object is analyzed using an emotion analysis model. If the emotional state belongs to the target emotion type, the first triggering condition is determined to be met. When the target object is in a relatively stationary state, the scene analysis model is used to analyze the activity state represented by the image data of the target object. If the activity state belongs to the target activity type, it is determined that the second triggering condition is met. When the target following object is in an interactive state, the interaction data between the target following object and the target interactive object is analyzed using a scene analysis model. If the analysis shows that the interaction data belongs to the target interactive scene, it is determined that the second triggering condition is met. If the target physiological parameters of the target object being followed exceed the corresponding physiological parameter range, the third triggering condition is determined to be met.

5. The method according to claim 1, wherein controlling the movement parameters of the smart mobile device based on the position information and motion information of the target following object includes: Predict the destination information of the target object based on its motion and location information; The movement parameters of the smart mobile device are determined based on the destination information and the current location information of the smart mobile device. The intelligent mobile device is controlled to move according to the movement parameters to a position relative to the target object being followed, thus establishing a first relative positional relationship.

6. The method according to claim 5, wherein determining the movement parameters of the smart mobile device based on the destination information and the current location information of the smart mobile device includes: Based on the destination information, the destination and movement trajectory of the target object being followed are obtained; Based on the current location information, the destination and movement trajectory of the target object being followed, at least one of the following is determined: the movement path, movement speed, and movement mode of the smart mobile device. or, Based on the destination information and the current location information, determine the available space range between the smart mobile device and the target object being followed; Based on the available space range and the movement trajectory of the target object being followed, at least one of the following is determined: the movement path, movement speed, and movement mode of the smart mobile device.

7. The method according to claim 5, wherein determining the movement parameters of the smart mobile device based on the destination information and the current location information of the smart mobile device includes at least one of the following: When it is determined based on the current location information that there is a second relative positional relationship between the smart mobile device and the target following object, and the target following object is in a moving state, at least one of the moving path, moving speed, and moving mode of the smart mobile device is determined based on the moving trajectory of the target following object, so as to control the smart mobile device to switch from the second relative positional relationship with the target following object to the first relative positional relationship; When it is determined that there is a second relative positional relationship between the smart mobile device and the target object being followed based on the current location information, and the target object being followed is in a relatively stationary state, the movement path and / or movement mode of the smart mobile device are determined based on the available space range between the current location information and the target object being followed. If, based on the current location information, it is determined that there is a third relative positional relationship between the smart mobile device and the target object being followed, the movement parameters of the smart mobile device are controlled to keep it relatively stationary with respect to the target object being followed, or the smart mobile device is controlled to move from the third relative positional relationship with the target object to a first relative positional relationship.

8. The method of claim 1, further comprising at least one of the following: In response to the smart mobile device moving to a position with a first relative position to the target object being followed, the camera module of the smart mobile device is controlled to acquire frontal image data and / or side image data of the target object being followed; The image data collected by the smart mobile device during its movement to a positional relationship with the target object being followed is processed to generate frontal and / or side image data of the target object being followed. The system obtains time information indicating when the smart mobile device moves to a position with a first relative position to the target object it is following, and acquires image data of the target object from the target acquisition device based on the time information.

9. The method of claim 1, further comprising at least one of the following: The image data of the target object collected by the smart mobile device is input into the target processing model to generate the movement parameters of the smart mobile device; After switching to the second follow mode, the movement parameters of the smart mobile device are controlled based on the position and motion information of the target object being followed; In response to switching from the first follow mode to the second follow mode, the movement parameters of the smart mobile device are controlled based on the position and motion information of the target follow object.

10. A smart mobile device, comprising a camera module, at least one processor, and a memory connected to the processor, wherein: The camera module is used to capture images; The memory is used to store computer programs; The processor is used to execute the computer program to enable the smart mobile device to perform the following operations: In response to a target trigger event, control the smart mobile device to switch from the current first follow mode to the second follow mode; and, The movement parameters of the smart mobile device are controlled based on the position and motion information of the target object to control the smart mobile device to move to a position with a first relative positional relationship with the target object. In the first relative positional relationship, the smart mobile device is able to collect frontal image data and / or side image data of the target object being followed. In the first follow mode, the smart mobile device only locates the position of the target object to be followed or only collects data behind the target object to be followed.

Images