A function adjustment method and related apparatus

Abstract

The embodiment of the application discloses a function adjusting method, the method comprises: acquiring first radar data, and starting a fine adjustment function when a duration of a first gesture indicated by the first radar data exceeds a first threshold value, and fine adjustment of a target function can be performed based on a second gesture indicated by second radar data. The application uses the duration of the gesture as the basis for whether to start the fine adjustment mode, so that the gesture category used by the independent gesture function and the wake-up gesture can be overlapped, and the gesture category required when the gesture implemented function is adjusted can be reduced.

Description

Technical Field

[0001] This application relates to the field of radar, and more particularly to a function adjustment method and related apparatus. Background Technology

[0002] With societal progress and rapid development in material life, people's demand for more intelligent and convenient human-computer interaction methods is becoming increasingly strong. Human-computer interaction is a discipline that studies the interactive relationship between a system and its users. The system can be various types of machines, as well as computerized systems and software. Human-computer interaction technology has extremely high development potential and application value in future terminals, smart cockpits, and other application scenarios.

[0003] Human-computer interaction methods are constantly evolving and can be divided into contact-based and contactless interaction. Initially, keyboard or physical button interaction offered high accuracy and no redundant operations, but it was not intuitive and required complex device interfaces to cover all operations. The advent of graphical user interfaces (GUIs) eliminated abstract commands; the interaction device was typically a mouse. However, mouse control and the displayed area were separate, requiring users to perform indirect interactions, further increasing the difficulty of interaction. Touchscreen interfaces enabled direct interaction, retaining some tactile feedback while further reducing the learning and cognitive costs for users. However, clicking on a touchscreen often makes it difficult to precisely control the landing point; the granularity of the input signal is far lower than the granularity of the interactive element's response, and the interaction form remains a two-dimensional interface. Currently, contactless interaction mainly includes voice control and motion control. Voice control, however, is limited by its stringent requirements for noisy environments, restricting its application scenarios.

[0004] Gesture recognition, as a crucial method of human-computer interaction, has become a research hotspot and has been widely applied in various fields. For example, in in-vehicle environments, due to excessive ambient noise and the potential for multiple people to talk inside the vehicle, the accuracy of speech recognition is often unsatisfactory. With touchscreens, drivers must shift their gaze to operate, affecting driving safety. Therefore, in in-vehicle environments, gesture recognition, as a contactless interaction method that allows for blind operation, is in high demand.

[0005] Traditional gesture recognition technology primarily utilizes optical cameras. While optical images can clearly represent the shape and texture of gestures, they also have significant limitations. First, optical cameras perform poorly in strong or dim lighting conditions. Second, they are limited by viewing distance; users must perform the gesture within a specific space, and there can be no obstacles. Furthermore, the storage and computational costs of optical images are relatively high. Additionally, optical technology carries a significant risk of privacy breaches and cannot guarantee security. In contrast, millimeter-wave-based gesture recognition demonstrates its advantages. It is unaffected by lighting conditions, has a significantly wider range of applications, and its low power consumption allows for easy integration without compromising user privacy.

[0006] Radar-based gesture recognition boasts high accuracy, smoothness, strong environmental adaptability, and privacy protection, making it suitable for precise, remote adjustments and holding significant application value in smart cockpits and future terminals. Current single-mode millimeter-wave gesture recognition systems can only perform single-command operations and cannot achieve precise two-way adjustments to certain device functions. However, future applications will also require gesture-based fine-tuning functions such as volume control and map zooming. Summary of the Invention

[0007] In a first aspect, this application provides a functional adjustment method, the method comprising:

[0008] Acquire first radar data;

[0009] It should be understood that the first radar data in the embodiments of this application may refer to the reflected signal received by the receiving antenna in the radar system at the analog processing circuit, and the reflected signal is an analog signal. After obtaining the analog signal, the analog signal can be transmitted to the analog-to-digital converter circuit and digitized by the circuit to obtain a digital signal.

[0010] It should be understood that the analog signal obtained by the analog processing circuit can be transmitted to the analog-to-digital converter circuit and digitized by the circuit to obtain a digital signal. The first radar data in the embodiments of this application may also refer to the digital signal obtained by the above digitization, but this is not limited here.

[0011] Based on the first radar data indicating the first gesture, and the duration of the first gesture exceeding the first threshold, the adjustment function for the target function is activated;

[0012] The first gesture can be a preset type of gesture (that is, a pre-configured gesture type that can enable fine adjustment), such as a hover gesture, etc.

[0013] After acquiring the first radar data, the motion characteristics (such as distance, speed, angle, etc.) of the user's gesture indicated by the first radar data can be analyzed from the signal layer. When the duration of the user's gesture exceeds the first threshold and the motion characteristics can indicate the first gesture, the adjustment function for the target function is activated.

[0014] After acquiring the first radar data, when the duration of the user's gesture exceeds the first threshold, a portion of the radar data can be extracted from the first radar data, and gesture recognition can be performed on the portion of the radar data through a pre-trained neural network (or other gesture category recognition methods). When the recognition result is the first gesture, the adjustment function for the target function is activated.

[0015] In one possible implementation, the first threshold is greater than 0.7 seconds and less than 1.5 seconds.

[0016] In this application, the radar gestures (e.g., the first gesture, the second gesture, and the third gesture) are radar-based touch-independent gestures, also known as "3D gestures." A radar gesture refers to a gesture that is spatially distant from the electronic device (e.g., the gesture does not require the user to touch the device, although the gesture does not exclude touch). While radar gestures themselves may typically only have two-dimensional activity information components, such as a radar gesture consisting of a swipe from the upper left to the lower right, because radar gestures are a certain distance from the electronic device ("third dimension" or depth), the radar gestures in this application can generally be considered three-dimensional.

[0017] In one possible implementation, some or all of the data in the first radar data can be radar data corresponding to the first gesture. After acquiring the first radar data, it is necessary to identify the radar data related to the user's gesture, and then perform relevant processing on the first gesture using this identified radar data (such as determining the gesture category, determining the gesture duration, etc.).

[0018] Fine-tuning can include activating functions and adjusting the degree of function adjustment. This degree of adjustment can include increasing or decreasing values, adjusting the orientation of the display position, scaling the display area, and adjusting the position or shape of hardware. For example, fine-tuning can include adjusting volume, display brightness, scaling the displayed image, moving the display interface, adjusting the window height, and adjusting the fore-and-aft position of the seats in the vehicle cabin. Because it involves adjusting the degree of function adjustment, fine-tuning gestures need to be held for a certain period of time to select the degree of adjustment, and this holding time is relatively long.

[0019] In one possible implementation, timing can be started when gesture data is detected, and if the duration of the gesture data does not exceed a first threshold before terminating, an independent gesture adjustment mode can be enabled.

[0020] The independent gesture adjustment mode can include turning a function on or off. Since it does not involve adjusting the degree of function, the independent gesture can be a single gesture and the duration is very short, such as waving left or right.

[0021] When the duration of the first gesture indicated by the first radar data exceeds a first threshold, the radar data related to the first gesture in the first radar data can be used to identify the gesture category (that is, to identify the gesture category of the first gesture). The reason for identifying the gesture category of the first gesture is that it is necessary to determine the function type of subsequent fine adjustment (that is, to determine the target function) based on the gesture category of the first gesture. It should be understood that the gesture category here can be understood as the hand shape category, and the hand shape characteristics of gestures in different gesture categories are different.

[0022] Acquire second radar data;

[0023] Specifically, the processor can acquire second radar data, which can be obtained from the reflected signal of the user's gesture (second gesture);

[0024] In response to the activation of the adjustment function for the target function, the second gesture indicated by the second radar data and the motion characteristics of the second gesture are determined based on the second radar data.

[0025] It should be understood that there is also a preset mapping relationship between the first gesture and the second gesture. Specifically, the first gesture can be used to activate the adjustment mode of the target function corresponding to the gesture type of the first gesture. When the adjustment mode of the target function is activated, the user can only adjust the target function based on the gesture type (the gesture type of the second gesture) corresponding to the adjustment mode of the target function.

[0026] Based on the motion characteristics, adjustment information is determined, including at least one of adjustment amplitude, adjustment direction, and adjustment speed, and the target function is adjusted based on the adjustment information.

[0027] Among them, the adjustment range indicates the size of the fine adjustment, such as the volume adjustment or the height of the window. The adjustment direction indicates the direction of the fine adjustment, such as the volume increasing or decreasing, or the vehicle rising or falling. The adjustment speed indicates the size of the adjustment per unit time, that is, the rate of change of the adjusted value, such as the rate of change of the volume during adjustment or the rate of the window rising.

[0028] In the scenario of fine adjustment, the above-mentioned adjustment information can be combined with each other;

[0029] It should be noted that in some fine-tuning implementations, fine-tuning can be performed based solely on the adjustment direction. For example, waving to the left indicates increasing the volume to an adjacent fixed position (e.g., 100 is the maximum volume, and the fixed positions can be 0, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100). Each left wave can increase the volume to an adjacent position (e.g., from 10 to 20). Waving to the right indicates decreasing the volume to an adjacent fixed position.

[0030] In this embodiment, the duration of the gesture indicated by the first radar data is used as the basis for whether to enable the fine adjustment mode. This part of the radar data may not be used as the basis for determining the degree of adjustment when fine adjustment is performed later, but only as the trigger condition for whether to enable fine adjustment (which can also be called the wake-up gesture in this embodiment). Enabling fine adjustment based on the gesture duration has the following advantages: Since the gesture types are limited, as the types of functions continue to increase in the future, the gesture types used as the basis for enabling fine adjustment functions may not be enough (independent gesture functions occupy a part of the gesture types, and wake-up gestures occupy another part of the gesture types. The two cannot overlap, otherwise errors will occur). However, by using the gesture duration as the basis for whether to enable the fine adjustment mode, the gesture categories used by independent gesture functions and wake-up gestures can overlap, thereby reducing the number of gesture categories required when adjusting the functions implemented by gestures. Furthermore, in scenarios involving gesture-based function adjustments, especially fine-tuning, it's crucial to ensure the overall gesture design remains continuous. When users attempt fine-tuning based on gestures, they subconsciously anticipate a continuous series of gestures over a given period. If the rule for activating the fine-tuning function is also defined based on the duration of the gesture, users will perceive this activation gesture as seamless. Using the duration of the gesture indicated by the first radar data as the basis for activating fine-tuning mode aligns better with user thought processes and habits, reducing the learning curve for users.

[0031] In one possible implementation, the first radar data is acquired before the second radar data.

[0032] In one possible implementation, the first radar data and the second radar data are radar data acquired continuously in the time domain; or, the first radar data and the second radar data are radar data acquired at time intervals of a target time period, the duration of which is less than a second threshold. The second threshold can be the time during which the processor performs relevant processing on the first radar data, within which the adjustment function for the target function has not yet been activated.

[0033] In one possible implementation, the first gesture and the second gesture can also be continuous gestures by the user. Continuous gestures can be understood as the first gesture and the second gesture having the same hand shape (or very similar hand shape). Optionally, the first gesture can be a stationary gesture or a gesture with a movement range less than a threshold. Since the second gesture needs to adjust the target function to a certain extent, the second gesture can be a gesture with a movement range greater than a threshold.

[0034] In this embodiment, the first gesture and the second gesture have the same hand shape, so that the gesture used by the user when waking up the function for fine adjustment is the same hand shape as the gesture used when making fine adjustment, which allows the user to accurately adjust the function with a very small learning cost.

[0035] In one possible implementation, the first gesture is a pinching gesture, and the second gesture is a gesture of keeping the fingers pinched and dragging; or, the first gesture is a palm-hanging gesture, and the second gesture is an upward or downward gesture; or, the first gesture is a palm-hanging gesture, and the second gesture is a left-right waving gesture; or, the first gesture is a palm-hanging gesture, and the second gesture is a forward-backward pushing gesture; or, the first gesture is a fist-clenching gesture, and the second gesture is a gesture of keeping the fist clenched and moving; or, the first gesture is a slight palm-shaking gesture, and the second gesture is an upward or downward gesture; or, the first gesture is a fist-clenching gesture with the thumb extended, and the second gesture is a gesture of keeping the fist clenched with the thumb extended and pushing forward-backward. The gesture semantic alignment adjustment function of the above-mentioned second gesture conforms to user habits and can help reduce the learning cost.

[0036] In one possible implementation, before activating the adjustment function for the target function, the method further includes: determining, based on a preset correspondence, that the gesture type of the first gesture corresponds to the target function, wherein the preset correspondence includes a mapping between gesture types and functions.

[0037] In one possible implementation, the first gesture is a pinch of fingers, and the target function is adjusting the playback progress of a video or audio file; or...

[0038] The first gesture is a circle drawing, and the target function is volume adjustment; or,

[0039] The first gesture is a palm hover, and the target function is to adjust the display brightness or adjust the scaling of the displayed image; or,

[0040] The first gesture is a clenched fist, and the target function is to adjust the movement of the display interface; or,

[0041] The first gesture is a slight waving of the hand, and the target function is adjusting the window height; or,

[0042] The first gesture is a clenched fist with the thumb extended, and the target function is the fore-and-aft adjustment of the seat in the vehicle cabin.

[0043] Specifically, the processor can identify a user's gesture within the radar system's monitoring area at a certain moment, and determine that the duration of the user's gesture exceeds a first threshold. It can then identify the user's gesture as a finger pinch, and enable the function adjustment mode for adjusting the progress of the video or audio played by the application.

[0044] Specifically, the processor can identify a user's gesture within the radar system's monitoring area at a certain moment, and determine that the duration of the user's gesture exceeds a first threshold. It can then identify the user's gesture as a circle and activate the volume adjustment function.

[0045] Specifically, the processor can identify a user's gesture within the radar system's monitoring area at a certain moment, and determine that the duration of the user's gesture exceeds a first threshold. It can then identify the user's gesture as a hand hover, and activate the function adjustment mode for adjusting display brightness or scaling of the displayed image.

[0046] Specifically, the processor can identify a user's gesture within the radar system's monitoring area at a certain moment, and determine that the duration of the user's gesture exceeds a first threshold. It can then identify the user's gesture as a clenched fist, and activate the motion adjustment function mode for the display interface.

[0047] Specifically, the processor can identify a user's gesture within the radar system's monitoring area at a certain moment, and determine that the duration of the user's gesture exceeds a first threshold. It can then identify the user's gesture as a slight hand shake, and activate the window height adjustment function.

[0048] Specifically, the processor can identify a user's gesture within the radar system's monitoring area at a certain moment, and determine that the duration of the user's gesture exceeds a first threshold. It can then identify the user's gesture as a clenched fist with an extended thumb, and activate the function adjustment mode for adjusting the fore-and-aft position of the seats in the vehicle cabin.

[0049] In this embodiment of the application, when a first gesture is determined to exist based on the first radar data and the duration of the first gesture exceeds a first threshold, the adjustment function for the target function can be activated.

[0050] Specifically, when the adjustment function for the target function is enabled, certain feedback information can be presented, which can indicate that the adjustment function for the target function has been enabled. Specifically, when the adjustment function for the target function is enabled, the target corresponding to the target function can be displayed, which is used to indicate that the adjustment function for the target function has been enabled.

[0051] In one possible implementation, the target presentation may include: a control display for adjusting the target function. In smart home applications, the target presentation can be performed on an electronic device with a display screen; in smart cockpit applications, the target presentation can be performed on the central control screen in the vehicle cabin.

[0052] Taking the target function as adjusting the progress of video or audio played by the application as an example, the target presentation can be the display of a progress bar.

[0053] Taking volume adjustment as an example, the target display could be the volume adjustment control.

[0054] Taking the target function as display brightness adjustment as an example, the target presentation can be the display of the display brightness adjustment control.

[0055] Taking the target function of adjusting the scaling of the displayed image as an example, the target presentation can be the display of the image scaling control.

[0056] Taking the target function as the movement adjustment of the display interface as an example, the target presentation can be the display of the movement control on the display interface.

[0057] In one possible implementation, the target presentation may include vibration cues from hardware associated with the target function; for example, in a smart cabin scenario, the target presentation may be vibration cues from the seat.

[0058] Taking the target function of adjusting the fore-and-aft position of the seats in the cabin as an example, the target display can be a vibration prompt for the seat whose position needs to be adjusted.

[0059] In one possible implementation, the target presentation may include: an audio prompt, which may contain a voice indicating that the adjustment function for the target function has been enabled. For example, if the target function is adjusting the playback progress of a video or audio file played by an application, the target presentation may be the voice message "The playback progress function for the video or audio file played by the application has been enabled"; if the target function is adjusting the volume, the target presentation may be the voice message "The volume adjustment function has been enabled"; if the target function is adjusting the display brightness, the target presentation may be the voice message "The display brightness adjustment function has been enabled"; if the target function is adjusting the zoom of a displayed image, the target presentation may be the voice message "The image zoom function has been enabled"; if the target function is adjusting the window height, the target presentation may be the voice message "The window height adjustment function has been enabled"; if the target function is adjusting the fore-and-aft position of the seat in the vehicle cabin, the target presentation may be the voice message "The fore-and-aft position adjustment function of the seat in the vehicle cabin has been enabled".

[0060] In one possible implementation, indicating a first gesture based on the first radar data, and the duration of the first gesture exceeding a first threshold, includes: indicating a user's gesture based on the first radar data, and the duration of the user's gesture exceeding the first threshold; determining the user's gesture as a first gesture based on the first radar data; and the first gesture being used to indicate the activation of the adjustment function.

[0061] In one possible implementation, a portion of radar data can be extracted from the first radar data, and the user's gesture can be determined as a first gesture based on this portion of radar data. Optionally, the portion of radar data consists of the first N radar data points from the first radar data. Unlike gesture detection, gesture extraction involves capturing a portion of the gesture of appropriate length during the gesture action for gesture recognition. Therefore, the extraction length is crucial; extracting too short or too long a portion will cause the gesture recognition to fail. Optionally, gesture extraction can be performed using time-based extraction and gesture feature extraction methods.

[0062] The time-based segmentation method aligns with the idea of ​​independent gesture recognition. It extracts N radar data points (e.g., N chirp signals) from the start of the gesture, and then uses these extracted signals for gesture recognition. The time-based segmentation method is simple, direct, and effective, its effectiveness stemming from several aspects: First, in subsequent gesture category determination, a gesture recognition algorithm based on a multi-dimensional feature fusion network with a self-attention mechanism can be used. This algorithm is insensitive to changes in gesture signal length; for similar gesture features, slight differences in duration (i.e., the speed of the gesture) have minimal impact on the recognition result, and the length of the same gesture varies between different users. Second, if the length of an independent gesture is shorter than the first threshold, the duration-based judgment ensures that the independent gesture will not be segmented, thus not affecting its recognition.

[0063] Gesture feature extraction refers to analyzing the characteristic changes of a specific gesture to extract the gesture. The extraction length is not fixed and varies depending on the gesture. For example, hovering gestures can be extracted from changes in distance or speed, and the first circle in a continuous circling motion can be extracted from changes in distance, angle, and speed. Gesture feature extraction can solve the problem of the impact of gesture length differences caused by different users and different gestures on the extraction, and the extraction of individual gestures is more accurate.

[0064] Based on the above description, the time-based extraction method is suitable for situations where different wake-up gestures have similar durations; while the gesture feature extraction method is suitable for different wake-up gestures that share a common feature, allowing for the extraction of different wake-up gestures using a single feature. In practical applications, the appropriate extraction method can be selected based on a comprehensive consideration of the type and characteristics of the wake-up gesture.

[0065] In one possible implementation, motion features are single salient features of a gesture (such as distance, speed, or angle). Analyzing these features allows for the recognition of a specific type of gesture. Gesture type recognition based on motion features only requires partial feature analysis, eliminating the need for feature fusion and neural networks. This simplifies some aspects of gesture recognition, reduces computational load, and improves real-time performance.

[0066] In one possible implementation, determining the user's gesture as a first gesture based on the first radar data includes: acquiring the motion features of the user's gesture based on the first radar data, and determining the user's gesture as a first gesture based on the motion features of the user's gesture; or, determining the user's gesture as a first gesture based on the first radar data using a pre-trained gesture classification network.

[0067] In one possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include: distance information of the second gesture, the distance information including at least one of the following: the change of distance between the second gesture and the radar system over time, the rate of change of the distance, and the direction of change of the distance.

[0068] In one possible implementation, the second radar data is obtained based on the reflection of a user's gesture in a radar field provided by the radar system, and the motion characteristics of the second gesture include: rate information of the second gesture, the rate information including the magnitude of the change in the movement rate of the second gesture in the radar field over time.

[0069] In one possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include: angle information of the second gesture, the angle information including the change of the angle between the second gesture and the radar system over time, the angle including azimuth and / or elevation angle.

[0070] This application's embodiments, based on gesture feature extraction, perform fine quantification of gesture features, including distance, speed, horizontal angle, and pitch angle. By acquiring variables reflecting the direction, magnitude, and speed of feature changes, it is possible to achieve bidirectional, varying amplitudes and speeds, with high stability and strong generalization.

[0071] In one possible implementation, after adjusting the target function based on the adjustment information, the method further includes: acquiring third radar data; instructing a third gesture based on the third radar data to disable the adjustment function for the target function; the third gesture is a withdrawal gesture or a hovering gesture.

[0072] Secondly, this application provides a function adjustment method, the method comprising:

[0073] Acquire target radar data, which is obtained based on the reflection of the user's target gesture in the radar field provided by the radar system; wherein, in the design where a wake-up gesture exists, the target radar data can be the second radar data described in the first aspect;

[0074] Based on the target radar data, the motion characteristics of the target gesture are determined; the motion characteristics of the target gesture include at least two of the following: distance information, velocity information, or angle information. The distance information includes the change of distance between the target gesture and the radar system over time. The velocity information includes the change of relative velocity between the target gesture and the radar system over time. The angle information includes the change of angle of the target gesture in the radar field over time. The angle includes azimuth and / or elevation angle.

[0075] Based on the motion characteristics, adjustment information is determined, including at least one of adjustment amplitude, adjustment direction, and adjustment speed, and the target function is adjusted based on the adjustment information.

[0076] In existing implementations, time-of-flight (TOF) is used for fine-tuning. However, due to hardware limitations associated with TOF, the sensitivity and accuracy of fine-tuning are very low. This application's embodiment uses radar (e.g., millimeter-wave radar) for fine-tuning, which improves operational accuracy. Furthermore, during fine-tuning, the adjustment action must exhibit at least one significantly changing characteristic, such as distance, angle, or speed. This application's embodiment, based on the extraction of gesture motion features, performs fine-quantification of these features, including distance, speed, horizontal angle, and pitch angle. Variables reflecting the direction, magnitude, and speed of feature changes are obtained, thereby enabling bidirectional, multi-amplitude, multi-speed, highly stable, and strongly generalizable fine-tuning.

[0077] In one possible implementation, the change of distance over time includes:

[0078] At least one of the following: the numerical value of the distance change over time, the rate of change of the distance over time, or the direction of change of the distance over time;

[0079] The adjustment range is related to the change in distance over time, the adjustment speed is related to the rate of change of distance over time, and the adjustment direction is related to the direction of change of distance over time.

[0080] In one possible implementation, the target gesture is a periodic gesture, and the change in relative velocity over time is used to determine the number of gesture cycles of the target gesture;

[0081] The adjustment range is related to the number of cycles, and the adjustment speed is related to the number of gesture cycles of the target gesture within a fixed time.

[0082] It should be understood that other types of motion features can be used for fine-tuning of periodic gestures, and this is not a limitation here.

[0083] In one possible implementation, the change of the angle over time includes:

[0084] At least one of the following: the numerical value of the angle change over time, the rate of change of the angle over time, or the direction of change of the angle over time;

[0085] The adjustment range is related to the change value of the angle over time, the adjustment speed is related to the rate of change of the angle over time, and the adjustment direction is related to the direction of change of the angle over time.

[0086] In one possible implementation, before determining the motion characteristics of the target gesture based on the target radar data, the method further includes:

[0087] When the target gesture is a periodic gesture or a gesture whose relative speed with the radar system changes continuously, the feature type for determining the motion characteristics of the target gesture includes the speed information;

[0088] When the target gesture is a gesture whose distance to the radar system is constantly changing, the feature type for determining the motion characteristics of the target gesture includes the distance information;

[0089] When the target gesture is a gesture with constantly changing angles in the radar field, the feature type for determining the motion characteristics of the target gesture includes the angle information.

[0090] For different gesture categories, corresponding motion feature types can be obtained, which reduces the amount of data processing while ensuring accurate recognition.

[0091] Thirdly, this application provides a function adjustment device, the device comprising:

[0092] The acquisition module is used to acquire the first radar data;

[0093] The function activation module is used to activate the adjustment function for the target function based on the first radar data indicating the first gesture and the duration of the first gesture exceeding the first threshold.

[0094] The acquisition module is also used to acquire second radar data;

[0095] A function adjustment module, configured to, in response to the activation of the adjustment function for the target function, determine, based on the second radar data, the second gesture indicated by the second radar data, and the motion characteristics of the second gesture; and,

[0096] Based on the motion characteristics, adjustment information is determined, including at least one of adjustment amplitude, adjustment direction, and adjustment speed, and the target function is adjusted based on the adjustment information.

[0097] In this embodiment, the duration of the gesture indicated by the first radar data is used as the basis for whether to enable the fine adjustment mode. This part of the radar data may not be used as the basis for determining the degree of adjustment when fine adjustment is performed later, but only as the trigger condition for whether to enable fine adjustment (which can also be called the wake-up gesture in this embodiment). Enabling fine adjustment based on the gesture duration has the following advantages: Since the gesture types are limited, as the types of functions continue to increase in the future, the gesture types used as the basis for enabling fine adjustment functions may not be enough (independent gesture functions occupy a part of the gesture types, and wake-up gestures occupy another part of the gesture types. The two cannot overlap, otherwise errors will occur). However, by using the gesture duration as the basis for whether to enable the fine adjustment mode, the gesture categories used by independent gesture functions and wake-up gestures can overlap, thereby reducing the number of gesture categories required when adjusting the functions implemented by gestures. Furthermore, in scenarios involving gesture-based function adjustments, especially fine-tuning, it's crucial to ensure the overall gesture design remains continuous. When users attempt fine-tuning based on gestures, they subconsciously anticipate a continuous series of gestures over a given period. If the rule for activating the fine-tuning function is also defined based on the duration of the gesture, users will perceive this activation gesture as seamless. Using the duration of the gesture indicated by the first radar data as the basis for activating fine-tuning mode aligns better with user thought processes and habits, reducing the learning curve for users.

[0098] In one possible implementation, the first threshold is greater than 0.7 seconds and less than 1.5 seconds.

[0099] In one possible implementation, the first radar data is acquired before the second radar data.

[0100] In one possible implementation, the first radar data and the second radar data are radar data acquired continuously in the time domain; or,

[0101] The first radar data and the second radar data are radar data acquired in the time domain at target time intervals, wherein the duration of the target time interval is less than a threshold.

[0102] In one possible implementation, the first gesture and the second gesture are consecutive gesture actions of the user.

[0103] In one possible implementation, the first gesture and the second gesture are of the same gesture type, wherein the first gesture is a stationary gesture or a gesture with a movement amplitude less than a threshold, and the second gesture is a gesture with a movement amplitude greater than a threshold.

[0104] In one possible implementation, the first gesture is a pinching gesture, and the second gesture is a gesture of maintaining the pinched fingers while dragging; or...

[0105] The first gesture is a hand-holding gesture, and the second gesture is an upward or downward gesture; or...

[0106] The first gesture is a hand-holding gesture, and the second gesture is a left-right waving gesture; or...

[0107] The first gesture is a hand-holding gesture, and the second gesture is a pushing gesture; or...

[0108] The first gesture is a clenched fist gesture, and the second gesture is a gesture that maintains the clenched fist while moving; or,

[0109] The first gesture is a slight shaking of the palm, and the second gesture is an upward or downward gesture; or...

[0110] The first gesture is a fist with the thumb extended, and the second gesture is a gesture of keeping the fist clenched and the thumb extended while pushing back and forth.

[0111] In one possible implementation, the first gesture and the second gesture are of the same gesture type as the first gesture, and both the first gesture and the second gesture are gestures with a movement amplitude greater than a threshold.

[0112] In one possible implementation, both the first gesture and the second gesture are circling gestures.

[0113] In one possible implementation, the function activation module is further configured to:

[0114] Before activating the adjustment function for the target function, based on a preset correspondence, the gesture type of the first gesture is determined to correspond to the target function, wherein the preset correspondence includes a mapping between gesture type and function.

[0115] In one possible implementation, the first gesture is a pinch of fingers, and the target function is adjusting the playback progress of a video or audio file; or...

[0116] The first gesture is a circle drawing, and the target function is volume adjustment; or,

[0117] The first gesture is a palm hover, and the target function is to adjust the display brightness or adjust the scaling of the displayed image; or,

[0118] The first gesture is a clenched fist, and the target function is to adjust the movement of the display interface; or,

[0119] The first gesture is a slight waving of the hand, and the target function is adjusting the window height; or,

[0120] The first gesture is a clenched fist with the thumb extended, and the target function is the fore-and-aft adjustment of the seat in the vehicle cabin.

[0121] In one possible implementation, the device further includes:

[0122] The presentation module is used to present a target corresponding to the target function before adjusting the target function based on the adjustment information. The target presentation is used to indicate that the adjustment function for the target function has been enabled.

[0123] In one possible implementation, the target presentation includes at least one of the following:

[0124] The control display for adjusting the target function;

[0125] Vibration alerts from hardware related to the target function; and,

[0126] Sound prompt.

[0127] In one possible implementation, the step of instructing a first gesture based on the first radar data, and the duration of the first gesture exceeding a first threshold, includes:

[0128] Based on the first radar data indicating the user's gesture, and the duration of the user's gesture exceeds a first threshold, the user's gesture is determined to be a first gesture according to the first radar data, and the first gesture is used to indicate the activation of the adjustment function.

[0129] In one possible implementation, determining the user's gesture as a first gesture based on the first radar data includes:

[0130] Extract a portion of the radar data from the first radar data;

[0131] Based on the radar data, the user's gesture is determined to be the first gesture.

[0132] In one possible implementation, the partial radar data is the first N radar data in the first radar data.

[0133] In one possible implementation, determining the user's gesture as a first gesture based on the first radar data includes:

[0134] Based on the first radar data, the motion characteristics of the user's gesture are obtained, and the user's gesture is determined to be a first gesture based on the motion characteristics of the user's gesture; or,

[0135] Based on the first radar data, the user's gesture is determined to be the first gesture through a pre-trained gesture classification network.

[0136] In one possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include:

[0137] The distance information of the second gesture includes at least one of the following: the change in distance between the second gesture and the radar system over time, the rate of change of the distance, and the direction of change of the distance.

[0138] In one possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include:

[0139] The rate information of the second gesture includes the magnitude of the change in the movement rate of the second gesture in the radar field over time.

[0140] In one possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include:

[0141] The angle information of the second gesture includes the change of the angle between the second gesture and the radar system over time, and the angle includes azimuth and / or elevation angle.

[0142] In one possible implementation, the acquisition module is further configured to:

[0143] After adjusting the target function based on the adjustment information, third radar data is acquired;

[0144] The device further includes:

[0145] The function shutdown module is used to disable the adjustment function for the target function based on the third gesture indicated by the third radar data; the third gesture is a hand withdrawal gesture or a hovering gesture.

[0146] Fourthly, this application provides a function adjustment device, the device comprising:

[0147] The acquisition module is used to acquire target radar data, which is obtained based on the reflection of the user's target gesture in the radar field provided by the radar system.

[0148] A motion feature determination module is used to determine the motion features of the target gesture based on the target radar data; the motion features of the target gesture include at least two of the following: distance information, velocity information, or angle information; the distance information includes the change of distance between the target gesture and the radar system over time; the velocity information includes the change of relative velocity between the target gesture and the radar system over time; and the angle information includes the change of angle of the target gesture in the radar field over time, wherein the angle includes azimuth and / or elevation angle.

[0149] The function adjustment module is used to determine adjustment information based on the motion characteristics, the adjustment information including at least one of adjustment amplitude, adjustment direction and adjustment speed, and to adjust the target function based on the adjustment information.

[0150] When performing fine-tuning of functions, the adjustment actions all have at least one significantly changing characteristic, such as distance, angle, or speed. Based on the extraction of gesture motion features, this application's embodiments perform fine-tuning of gesture features, including distance, speed, horizontal angle, and pitch angle. By acquiring variables reflecting the direction, amount, and speed of feature changes, bidirectional, varying amplitudes, different speeds, high stability, and strong generalization of fine-tuning can be achieved.

[0151] In one possible implementation, the change of distance over time includes:

[0152] At least one of the following: the numerical value of the distance change over time, the rate of change of the distance over time, or the direction of change of the distance over time;

[0153] The adjustment range is related to the change in distance over time, the adjustment speed is related to the rate of change of distance over time, and the adjustment direction is related to the direction of change of distance over time.

[0154] In one possible implementation, the target gesture is a periodic gesture, and the change in relative velocity over time is used to determine the number of gesture cycles of the target gesture;

[0155] The adjustment range is related to the number of cycles, and the adjustment speed is related to the number of gesture cycles of the target gesture within a fixed time.

[0156] In one possible implementation, the change of the angle over time includes:

[0157] At least one of the following: the numerical value of the angle change over time, the rate of change of the angle over time, or the direction of change of the angle over time;

[0158] The adjustment range is related to the change value of the angle over time, the adjustment speed is related to the rate of change of the angle over time, and the adjustment direction is related to the direction of change of the angle over time.

[0159] In one possible implementation, the motion feature determination module is further configured to: before determining the motion feature of the target gesture based on the target radar data, determine the feature type of the motion feature of the target gesture to include the speed information when the target gesture is a periodic gesture or a gesture with a constantly changing relative rate with the radar system;

[0160] When the target gesture is a gesture whose distance to the radar system is constantly changing, the feature type for determining the motion characteristics of the target gesture includes the distance information;

[0161] When the target gesture is a gesture with constantly changing angles in the radar field, the feature type for determining the motion characteristics of the target gesture includes the angle information.

[0162] Fifthly, this application provides a function adjustment device, comprising: one or more processors and a memory; wherein the memory stores computer-readable instructions;

[0163] The one or more processors read the computer-readable instructions to cause the computer device to implement the first aspect and any optional method thereof, and the second aspect and any optional method thereof.

[0164] In one possible implementation, the device further includes a radar system for:

[0165] Provide radar field;

[0166] Sensing reflections from users within the radar field;

[0167] Analyze the reflections from the user in the radar field; and

[0168] Radar data is provided based on the analysis of the reflections.

[0169] In a sixth aspect, embodiments of this application provide a computer-readable storage medium, characterized in that it includes computer-readable instructions, which, when executed on a computer device, cause the computer device to perform the methods of the first aspect and any optional method thereof, as well as the methods of the second aspect and any optional method thereof.

[0170] In a seventh aspect, embodiments of this application provide a computer program product, characterized in that it includes computer-readable instructions, which, when executed on a computer device, cause the computer device to perform the first aspect and any optional method thereof, as well as the second aspect and any optional method thereof.

[0171] Eighthly, this application provides a chip system including a processor for supporting an execution device or training device in implementing the functions involved in the foregoing aspects, such as transmitting or processing data involved in the foregoing methods; or, information. In one possible design, the chip system further includes a memory for storing program instructions and data necessary for the execution device or training device. The chip system may be composed of chips or may include chips and other discrete devices.

[0172] Ninthly, this application provides a vehicle, including: one or more processors and a memory; wherein the memory stores computer-readable instructions;

[0173] The one or more processors read the computer-readable instructions to cause the computer device to implement the first aspect and any optional method thereof, and the second aspect and any optional method thereof;

[0174] The vehicle's cabin also includes a radar system for:

[0175] Provide radar field;

[0176] Sensing reflections from users within the radar field;

[0177] Analyze the reflections from the user in the radar field; and

[0178] Radar data is provided based on the analysis of the reflections.

[0179] In one possible implementation, the vehicle cabin further includes a driver's seat, a passenger seat, and a steering wheel fixed in front of the driver's seat; wherein,

[0180] The radar system includes:

[0181] A first radar system, the first radar system including a first radar integrated circuit, the first radar integrated circuit including:

[0182] At least one first transmitting antenna;

[0183] At least one first receiving antenna;

[0184] The first radar integrated circuit is located on the side of the steering wheel near the passenger seat, wherein the steering wheel is not being rotated by the user.

[0185] In one possible implementation, the at least one first transmitting antenna is used to provide a radar field to at least one of the following regions:

[0186] The area of ​​the driver's seat near the passenger seat; and

[0187] The area between the driver's seat and the passenger seat.

[0188] In one possible implementation, the cabin also includes a driver's seat, a passenger seat, and a center console;

[0189] The radar system includes:

[0190] A second radar system, the second radar system including a second radar integrated circuit, the second radar integrated circuit including:

[0191] At least one second transmitting antenna;

[0192] At least one second receiving antenna;

[0193] The second radar integrated circuit is located on the side of the center console facing away from the front of the vehicle.

[0194] In one possible implementation, the at least one second transmitting antenna is used to provide a radar field to at least one of the following regions:

[0195] The area in the driver's seat near the passenger seat;

[0196] The area of ​​the passenger seat closest to the driver's seat; and

[0197] The area between the driver's seat and the passenger seat.

[0198] In one possible implementation, the vehicle cabin further includes a driver's seat, a passenger seat, and an armrest box, the armrest box being fixed in the area between the driver's seat and the passenger seat;

[0199] The radar system includes:

[0200] A third radar system, the third radar system including a third radar integrated circuit, the third radar integrated circuit including:

[0201] At least one third transmitting antenna;

[0202] At least one third receiving antenna;

[0203] The third radar integrated circuit is located on the armrest box on the side facing the main control panel.

[0204] In one possible implementation, the at least one third transmitting antenna is used to provide a radar field to at least one of the following regions:

[0205] The area in the driver's seat near the passenger seat;

[0206] The area of ​​the passenger seat closest to the driver's seat; and

[0207] The area between the driver's seat and the passenger seat.

[0208] The radar system located on the right side of the steering wheel (such as the first radar system in this embodiment) has its radar beam illuminating diagonally to the right. This deployment position is mainly aimed at the driver's operation and can significantly reduce signal interference caused by the driver's body and arm movements when operating the steering wheel.

[0209] Among them, the radar beam of the radar system deployed near the center console (such as the second radar system in the embodiment of this application) shines in the middle, which can be used by the driver and the front passenger at the same time, with little interference to the passenger's body.

[0210] The radar system located in the armrest box (such as the third radar system in this embodiment) has its radar beam pointing upwards, which can be used by both the driver and the front passenger at the same time, with minimal physical interference to the passengers.

[0211] The embodiments of this application allow users to complete gesture control under conditions of no contact, no eye shift, and short arm movement distance, ensuring driving safety and ease of operation.

[0212] In one possible implementation, the vehicle further includes: a seat;

[0213] The one or more processors are also configured to read the computer-readable instructions in order to control the seat to provide a vibration alert when the adjustment function for the target function is activated.

[0214] In a tenth aspect, this application provides a vehicle, including: a vehicle compartment; the vehicle compartment includes a radar system;

[0215] The radar system is used for:

[0216] Provide radar field;

[0217] Sensing reflections from users within the radar field;

[0218] Analyze the reflections from the user in the radar field; and

[0219] Radar data is provided based on the analysis of the reflections;

[0220] The radar system includes:

[0221] A first radar system, the first radar system including a first radar integrated circuit, the first radar integrated circuit including:

[0222] At least one first transmitting antenna;

[0223] At least one first receiving antenna;

[0224] The first radar integrated circuit is located on the side of the steering wheel near the passenger seat, wherein the steering wheel is not being rotated by the user.

[0225] In one possible implementation, the at least one first transmitting antenna is used to provide a radar field to at least one of the following regions:

[0226] The area of ​​the driver's seat near the passenger seat; and

[0227] The area between the driver's seat and the passenger seat.

[0228] In one possible implementation, the cabin also includes a driver's seat, a passenger seat, and a center console;

[0229] The radar system includes:

[0230] A second radar system, the second radar system including a second radar integrated circuit, the second radar integrated circuit including:

[0231] At least one second transmitting antenna;

[0232] At least one second receiving antenna;

[0233] The second radar integrated circuit is located on the side of the center console facing away from the front of the vehicle.

[0234] In one possible implementation, the at least one second transmitting antenna is used to provide a radar field to at least one of the following regions:

[0235] The area in the driver's seat near the passenger seat;

[0236] The area of ​​the passenger seat closest to the driver's seat; and

[0237] The area between the driver's seat and the passenger seat.

[0238] In one possible implementation, the vehicle cabin further includes a driver's seat, a passenger seat, and an armrest box, the armrest box being fixed in the area between the driver's seat and the passenger seat;

[0239] The radar system includes:

[0240] A third radar system, the third radar system including a third radar integrated circuit, the third radar integrated circuit including:

[0241] At least one third transmitting antenna;

[0242] At least one third receiving antenna;

[0243] The third radar integrated circuit is located on the armrest box on the side facing the main control panel.

[0244] In one possible implementation, the at least one third transmitting antenna is used to provide a radar field to at least one of the following regions:

[0245] The area in the driver's seat near the passenger seat;

[0246] The area of ​​the passenger seat closest to the driver's seat; and

[0247] The area between the driver's seat and the passenger seat.

[0248] The radar system located on the right side of the steering wheel (such as the first radar system in this embodiment) has its radar beam illuminating diagonally to the right. This deployment position is mainly aimed at the driver's operation and can significantly reduce signal interference caused by the driver's body and arm movements when operating the steering wheel.

[0249] Among them, the radar beam of the radar system deployed near the center console (such as the second radar system in the embodiment of this application) shines in the middle, which can be used by the driver and the front passenger at the same time, with little interference to the passenger's body.

[0250] The radar system located in the armrest box (such as the third radar system in this embodiment) has its radar beam pointing upwards, which can be used by both the driver and the front passenger at the same time, with minimal physical interference to the passengers.

[0251] The embodiments of this application allow users to complete gesture control under conditions of no contact, no eye shift, and short arm movement distance, ensuring driving safety and ease of operation.

[0252] This application provides a function adjustment method, the method comprising: acquiring first radar data; based on the first radar data indicating a first gesture and the duration of the first gesture exceeding a first threshold, activating an adjustment function for a target function; acquiring second radar data; in response to the activation of the adjustment function for the target function, determining, based on the second radar data, a second gesture indicated by the second radar data and the motion characteristics of the second gesture; determining adjustment information based on the motion characteristics, the adjustment information including at least one of adjustment amplitude, adjustment direction, and adjustment speed, and adjusting the target function based on the adjustment information. In this embodiment, the duration of the gesture indicated by the first radar data is used as the basis for whether to enable the fine adjustment mode. This part of the radar data may not be used as the basis for determining the degree of adjustment when fine adjustment is performed later, but only as the trigger condition for whether to enable fine adjustment (which can also be called the wake-up gesture in this embodiment). Enabling fine adjustment based on the gesture duration has the following advantages: Since the gesture types are limited, as the types of functions continue to increase in the future, the gesture types used as the basis for enabling fine adjustment functions may not be enough (independent gesture functions occupy a part of the gesture types, and wake-up gestures occupy another part of the gesture types. The two cannot overlap, otherwise errors will occur). However, by using the gesture duration as the basis for whether to enable the fine adjustment mode, the gesture categories used by independent gesture functions and wake-up gestures can overlap, thereby reducing the number of gesture categories required when adjusting the functions implemented by gestures. Furthermore, in scenarios involving gesture-based function adjustments, especially fine-tuning, it's crucial to ensure the overall gesture design remains continuous. When users attempt fine-tuning based on gestures, they subconsciously anticipate a continuous series of gestures over a given period. If the rule for activating the fine-tuning function is also defined based on the duration of the gesture, users will perceive this activation gesture as seamless. Using the duration of the gesture indicated by the first radar data as the basis for activating fine-tuning mode aligns better with user thought processes and habits, reducing the learning curve for users. Attached Figure Description

[0253] Figure 1a This is a schematic diagram of a scenario provided for an embodiment of this application;

[0254] Figure 1b This is a schematic diagram of a scenario provided for an embodiment of this application;

[0255] Figure 1c This is a schematic diagram of a scenario provided for an embodiment of this application;

[0256] Figure 2 This is a schematic diagram of a scenario provided for an embodiment of this application;

[0257] Figure 3 This is a schematic diagram of a scenario provided for an embodiment of this application;

[0258] Figure 4 This is a schematic diagram of a scenario provided for an embodiment of this application;

[0259] Figure 5 This is a schematic diagram of a scenario provided for an embodiment of this application;

[0260] Figure 6 A flowchart illustrating a function adjustment method provided in an embodiment of this application;

[0261] Figure 7a This is a schematic diagram of a scenario provided for an embodiment of this application;

[0262] Figure 7b A radar signal illustration provided for an embodiment of this application;

[0263] Figure 8 A schematic diagram of radar data processing provided for an embodiment of this application;

[0264] Figure 9 A schematic diagram of radar data processing provided for an embodiment of this application;

[0265] Figure 10 A gesture data illustration provided for an embodiment of this application;

[0266] Figure 11a A gesture data illustration provided for an embodiment of this application;

[0267] Figure 11b A gesture data illustration provided for an embodiment of this application;

[0268] Figure 11c A schematic diagram of radar data processing provided for an embodiment of this application;

[0269] Figure 12a A gesture illustration provided for an embodiment of this application;

[0270] Figure 12b A flowchart illustrating a function adjustment method provided in an embodiment of this application;

[0271] Figure 13 A schematic diagram of radar data processing provided for an embodiment of this application;

[0272] Figure 14 A gesture data illustration provided for an embodiment of this application;

[0273] Figure 15 A gesture data illustration provided for an embodiment of this application;

[0274] Figure 16 A gesture data illustration provided for an embodiment of this application;

[0275] Figure 17 A gesture data illustration provided for an embodiment of this application;

[0276] Figure 18 A gesture data illustration provided for an embodiment of this application;

[0277] Figure 19 A schematic diagram of a radar antenna provided for an embodiment of this application;

[0278] Figure 20 A gesture data illustration provided for an embodiment of this application;

[0279] Figure 21 A radar angle illustration provided for an embodiment of this application;

[0280] Figure 22 A gesture data illustration provided for an embodiment of this application;

[0281] Figure 23 A gesture data illustration provided for an embodiment of this application;

[0282] Figure 24a A flowchart illustrating a function adjustment method provided in an embodiment of this application;

[0283] Figure 24b A flowchart illustrating a function adjustment method provided in an embodiment of this application;

[0284] Figure 25 A schematic diagram of the structure of the function adjustment device provided in the embodiments of this application;

[0285] Figure 26 A schematic diagram of the structure of the function adjustment device provided in the embodiments of this application;

[0286] Figure 27 A schematic diagram of the structure of the function adjustment device provided in the embodiments of this application;

[0287] Figure 28 This is a schematic diagram of a chip structure provided in an embodiment of this application. Detailed Implementation

[0288] The embodiments of this application are described below with reference to the accompanying drawings. The terminology used in the implementation section of this application is for explaining specific embodiments only and is not intended to limit the scope of this application.

[0289] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the description of embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of units is not necessarily limited to those units, but may include other units not explicitly listed or inherent to those processes, methods, products, or apparatuses.

[0290] The embodiments of this application will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems. First, the application scenarios of the embodiments of this application will be introduced:

[0291] The embodiments of this application can be applied to scenarios that require functional adjustments, such as smart homes and smart cockpits.

[0292] Next, we will describe the architecture of the above application scenarios in conjunction with the product architecture included in the scenarios.

[0293] Scenario 1: Smart Home

[0294] refer to Figure 1a , Figure 1a A schematic diagram of the structure of a smart home system provided in an embodiment of this application is shown. Figure 1a As shown, the smart home system may include: an electronic device 100 (optional), one or more smart home devices 200, and a cloud server 300 (optional).

[0295] Regarding electronic devices 100:

[0296] The electronic device 100 can be a portable electronic device such as a mobile phone, tablet computer, personal digital assistant (PDA), or wearable device. Exemplary embodiments of the portable electronic device include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of this application, the electronic device 100 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0297] Electronic device 100 may have an application (APP) installed for managing smart home devices, or electronic device 100 may access a World Wide Web (web) page for managing smart home devices. The application or web page for managing smart home devices may be developed and provided by the smart home device manufacturer (e.g., a smart router manufacturer such as Huawei).

[0298] Regarding smart home devices 200:

[0299] Smart home devices refer to intelligent devices capable of exchanging information via wireless communication technology and even learning autonomously. They provide convenient and efficient services to users, reducing their workload. Smart home devices 200 may include smart sockets, smart door locks, smart lights, smart fans, smart air conditioners, smart curtains, smart TVs, smart rice cookers, smart routers, etc. For example, such as... Figure 1a As shown, the smart home device 200 may include a smart light fixture 201, a smart TV 202, and a smart speaker 203. The smart light fixture 201 can control changes in lighting, such as changes in color and brightness. The smart TV 202 can interact with the user via voice, for example, by receiving voice control commands to play the user's favorite TV programs. The smart speaker 203 can interact with the user via voice, for example, by receiving voice control commands to play the user's favorite songs. In some implementations, the smart speaker 203 may have an integrated voice assistant module, providing interactive voice dialogue or query functions via a "wake word" (e.g., "Hello, Xiaoyi").

[0300] Smart home device 200 can be configured with a radar system (the architecture of the radar system can be referenced). Figure 2 As shown), the radar system can transmit radar signals to the monitored area and receive the reflected signals of the radar signals (which can be referred to as radar data in this embodiment). By analyzing and processing the reflected signals, the system can determine the state of objects within the monitored area (e.g., moving state, sleeping state, stationary state, etc.) or recognize gesture information (e.g., determining the gesture category or the motion characteristics of the gesture).

[0301] Regarding the radar system:

[0302] Depending on the specific implementation of the radar system, the radar signal can have various carriers. For example, when the radar system is a microwave radar, the radar signal is a microwave signal; when the radar system is an ultrasonic radar, the radar signal is an ultrasonic signal; and when the radar system is a lidar, the radar signal is a laser signal. It should be noted that when the radar system integrates multiple different radars, the radar signal can be a collection of multiple radar signals, which is not limited here.

[0303] A radar system can generate radar signals and transmit them to the area it is monitoring. (See reference...) Figure 2 The generation and transmission of the signal can be achieved by a radio frequency (RF) signal generator 12, a radar transmitting circuit 14, and a transmitting antenna 32. The radar transmitting circuit 14 typically includes any circuitry required to generate the signal transmitted via the transmitting antenna 32, such as pulse shaping circuitry, transmit triggering circuitry, RF switching circuitry, or other suitable transmitting circuitry. The RF signal generator 12 and the radar transmitting circuit 14 can be controlled by a processor 20, which issues commands and control signals via control line 34 to cause the transmission of a desired RF signal with the desired configuration and signal parameters at the transmitting antenna 32.

[0304] The radar system can also receive returned radar signals via the receiving antenna 30 at the analog processing circuit 16. These returned radar signals may be referred to as "echoes," "radar data," "echo signals," or "reflected signals." The analog processing circuit 16 typically includes any circuitry required to process the signals received via the receiving antenna 30 (e.g., signal separation, mixing, heterodyne and / or homodyne conversion, amplification, filtering, receive signal triggering, signal switching and routing, and / or other suitable radar signal receiving functions). Therefore, the analog processing circuit 16 generates one or more analog signals, such as in-phase (I) and quadrature (Q) analog signals. The resulting analog signals are transmitted to and digitized by an analog-to-digital converter (ADC) circuit 18. The digitized signals are then forwarded to the processor 20 for reflected signal processing.

[0305] It should be understood that the aforementioned radar system may also be deployed independently of the smart home device 200, rather than within the smart home device 200.

[0306] For example, taking smart home device 200 as a smart screen, refer to... Figure 1b Radar systems can be deployed in, but are not limited to, locations where... Figure 1b The corner of the top bezel of the display shown is referenced. Figure 1cThe radar system can also be deployed independently of smart home devices 200, serving as an independent sensing unit within the smart home environment.

[0307] Regarding the processor:

[0308] Processor 20 can be one of various types of processors that perform the following functions: it is capable of processing digitized received signals and controlling RF signal generator 12 and radar transmitting circuit 14 to provide radar operation and functions for terminal device 100. Therefore, processor 20 can be a digital signal processor (DSP), microprocessor, microcontroller, or other such device.

[0309] In some implementations, processor 20 may include hardware circuits (such as application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), general-purpose processors, digital signal processors (DSPs), microprocessors or microcontrollers, etc.) or combinations of these hardware circuits. For example, processor 20 may be a hardware system with instruction execution capabilities, such as a CPU or DSP, or a hardware system without instruction execution capabilities, such as an ASIC or FPGA, or a combination of the aforementioned hardware systems without instruction execution capabilities and hardware systems with instruction execution capabilities.

[0310] In order to perform radar operation and functions of the radar system, the processor 20 interfaces via the system bus 22 with one or more other required circuits (e.g., one or more memory devices 24 consisting of one or more types of memory, any required peripheral circuits 26 identification, and any required input / output circuits 28).

[0311] As described above, processor 20 can interface with RF signal generator 12 and radar transmitting circuit 14 via control line 34. In an alternative embodiment, RF signal generator 12 and / or radar transmitting circuit 14 can be connected to bus 22, enabling them to communicate with one or more of processor 20, memory device 24, peripheral circuitry 26, and input / output circuitry 28 via bus 22.

[0312] The target object (e.g., the user's gesture in this embodiment) can be located within the monitoring area of ​​the radar system, so the radar system can receive the reflected signal after the target object reflects the radar signal (e.g., the first radar data, the second radar data, and the third radar data in this embodiment).

[0313] In one alternative implementation, after receiving radar data, the processor 20 can process the radar data to determine the gesture indicated by the reflected signal and gesture-related information, and perform related function control based on the gesture-related information.

[0314] It should be understood that a smart home system may include multiple smart home devices with data processing capabilities, and there are communication connections between the various smart home devices. Therefore, distributed computing can be achieved through multiple smart home devices in the smart home system, and thus the above-mentioned processing to determine the gesture indicated by the reflected signal and the gesture-related information can be implemented by multiple smart home devices in the smart home system.

[0315] In this embodiment, the processor 20 can obtain the code stored in the memory device 24 (or a memory device deployed separately from the processor 20) to implement the function adjustment method in this embodiment.

[0316] Specifically, the processor 20 can be a hardware system with instruction execution capabilities. The function adjustment method provided in this application embodiment can be software code stored in memory. The processor 20 can retrieve the software code from memory and execute the retrieved software code to implement the function adjustment method provided in this application embodiment.

[0317] It should be understood that the processor 20 can also be a combination of a hardware system without instruction execution capability and a hardware system with instruction execution capability. Some steps in the function adjustment method provided in the embodiments of this application can also be implemented by a hardware system in the processor 20 without instruction execution capability, which is not limited here.

[0318] In some possible implementations, the steps described above for determining the identity of the target object can also be implemented based on the interaction between the smart home device 200 and the cloud server 300.

[0319] The smart home device 200 can be equipped with a wireless communication module, and the smart home device 200 can establish a communication connection with the cloud server 300 through the wireless communication module.

[0320] Regarding the wireless communication module:

[0321] The wireless communication module can provide one or more of the following wireless communication methods for use in the smart home device 200: wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), near field communication (NFC), and infrared (IR). In some embodiments, the smart home device 200 may also be configured with a mobile communication module, which can provide solutions for wireless communication technologies such as 2G / 3G / 4G / 5G for use in the electronic device 100.

[0322] The smart home device 200 can connect to the network through the wireless communication module or mobile communication module, and then communicate with the cloud server 300 to receive data, instructions and other information from the cloud server 300. Alternatively, the smart home device 200 can report data, its own working status and working parameters to the cloud server 300.

[0323] In one alternative implementation, after receiving radar data, the processor 20 can transmit the radar data to the cloud server 300, whereby the server can process the radar data to determine the gesture indicated by the reflected signal and related information.

[0324] In an alternative implementation, the processor 20 may receive gestures indicated by reflected signals sent by the cloud server, as well as gesture-related information.

[0325] Regarding cloud server 300:

[0326] The cloud server 300 is a device that provides secure and reliable elastic computing services. It serves as a media platform to enable communication between internal and external control devices in the home, meeting the needs of remote control, monitoring, and information exchange. Understandably, the cloud server 300 may include one or more servers; for example, it can be a server cluster, with different servers providing different services. The cloud server 300 is associated with the manufacturer or service provider of the smart home device 200. For example, the cloud server 300 can automatically send software updates to the smart home device 200 or provide cloud services to it. In this embodiment, the cloud server 300 provides an interface for managing smart home devices through an application or web page. The cloud server 300 can receive instructions from the electronic device 100 for managing smart home devices through this interface, and send instructions to the corresponding smart home devices based on these instructions to manage them. For example, the cloud server 300 can instruct the smart light fixture 201 to turn on / off, adjust brightness, or adjust color temperature, etc., according to the instructions sent by the electronic device 100.

[0327] Scenario 2: Intelligent Cockpit

[0328] Figure 3 This is a schematic diagram of the interior structure of a car, provided as an embodiment of this application. Currently in the automotive field, in-vehicle terminals such as vehicle infotainment systems (also known as in-vehicle audio-visual entertainment systems) are fixedly located on the center console of the car, and their screens can also be called center console displays or center console screens. In addition, some high-end cars are gradually adopting fully digital displays in the cabin, with multiple or a single display screen installed to show content such as digital instrument clusters and in-vehicle entertainment systems. Figure 3 As shown, the cabin is equipped with multiple displays, such as the digital instrument display 101, the central control screen 102, the display 103 in front of the passenger in the front passenger seat (also known as the front passenger), the display 104 in front of the left rear passenger, and the display 105 in front of the right rear passenger.

[0329] Additionally, a radar system (which may be referred to simply as radar in subsequent embodiments) can be deployed inside the vehicle, although Figure 3 Only one radar 106 is shown near the A-pillar on the driver's side. Multiple radars can be installed inside the cabin, and their positions are flexible. For example, some cabin radars can be located above the vehicle's central control screen, some can be located to the left of the central control screen, some can be located on the A-pillar or B-pillar, and some can be located at the front of the cabin roof. For a detailed description of the radars, please refer to the above embodiments. Figure 2 Description of radar systems in China.

[0330] In order to recognize the hand gestures of the driver and passenger, the radar can be placed on the side of the steering wheel closest to the passenger seat, on the main console, and on the armrest between the driver and passenger seats.

[0331] For example, you can refer to Figure 4 ,in, Figure 4 This diagram illustrates the layout of a radar system within a vehicle cabin, such as... Figure 4 As shown, radar 1 can be installed on the side of the steering wheel near the passenger seat. The radar field provided by radar 1 can be directed towards the area of ​​the driver's seat near the passenger seat, as well as the area between the driver's seat and the passenger seat. In addition, radar 2 can be installed on the side of the center console facing the driver's seat and the passenger seat. The radar field provided by radar 2 can be directed towards the area of ​​the driver's seat near the passenger seat, the area of ​​the passenger seat near the driver's seat, and the area between the driver's seat and the passenger seat.

[0332] For example, you can refer to Figure 5 ,in, Figure 5 This diagram illustrates the layout of a radar system within a vehicle cabin, such as... Figure 4 As shown, radar 1 can be installed on the side of the steering wheel near the passenger seat. Radar 1 provides a radar field that can be directed towards the area near the passenger seat in the driver's seat, as well as the area between the driver and passenger seats. In addition, radar 2 can be installed on the side of the center console facing the driver and passenger seats. Radar 2 provides a radar field that can be directed towards the area near the passenger seat in the driver's seat, the area near the driver in the passenger seat, and the area between the driver and passenger seats. Furthermore, radar 3 can be installed on the side of the armrest between the driver and passenger seats facing the main console. Radar 3 provides a radar field that can be directed towards the area near the passenger seat in the driver's seat, the area near the driver in the passenger seat, and the area between the driver and passenger seats.

[0333] This application proposes three deployment locations for radar systems from the perspectives of facilitating passenger use, ensuring safety, reducing signal interference, and enhancing gesture characteristics.

[0334] The radar system located on the right side of the steering wheel (such as the first radar system in this embodiment) has its radar beam illuminating diagonally to the right. This deployment position is mainly aimed at the driver's operation and can significantly reduce signal interference caused by the driver's body and arm movements when operating the steering wheel.

[0335] Among them, the radar beam of the radar system deployed near the center console (such as the second radar system in the embodiment of this application) shines in the middle, which can be used by the driver and the front passenger at the same time, with little interference to the passenger's body.

[0336] The radar system located in the armrest box (such as the third radar system in this embodiment) has its radar beam pointing upwards, which can be used by both the driver and the front passenger at the same time, with minimal physical interference to the passengers.

[0337] The embodiments of this application allow users to complete gesture control under conditions of no contact, no eye shift, and short arm movement distance, ensuring driving safety and ease of operation.

[0338] The aforementioned vehicle 200 can be a car, truck, motorcycle, bus, ship, airplane, helicopter, lawnmower, recreational vehicle, amusement park vehicle, construction equipment, tram, golf cart, train, and handcart, etc., and this application embodiment does not impose any special limitations.

[0339] The embodiments of this application are described below with reference to the accompanying drawings. The terminology used in the implementation section of this application is for explaining specific embodiments only and is not intended to limit the scope of this application.

[0340] Reference Figure 6 , Figure 6 This is a schematic diagram illustrating an embodiment of a function adjustment method provided in this application. The function adjustment method provided in this application can be applied to electronic devices or servers, wherein the electronic device can be a vehicle-mounted device, computer, smartphone, or smartwatch, etc. Figure 6 As shown, the functional adjustment method provided in this application embodiment may include:

[0341] 601. Acquire the first radar data.

[0342] Taking smart home applications as an example, indoor users can perform radar gesture operations within the radar's detection range, and users can adjust specific functions in the smart home through radar gesture operations.

[0343] Taking the application scenario of smart cockpit as an example, passengers in the car (such as the driver and front passenger) can perform radar gesture operations within the radar's detection range. Users can adjust specific functions of the in-vehicle system through radar gesture operations.

[0344] In this application, the radar gestures (e.g., the first gesture, the second gesture, the third gesture, and the target gesture) are radar-based touch-independent gestures, also known as "3D gestures." A radar gesture refers to a gesture that is spatially distant from the electronic device (e.g., the gesture does not require the user to touch the device, although this gesture does not exclude touch). While radar gestures themselves may typically only have two-dimensional activity information components, such as a radar gesture consisting of a swipe from the upper left to the lower right, because the radar gesture is a certain distance from the electronic device ("third dimension" or depth), the radar gestures in this application can generally be considered three-dimensional.

[0345] In one possible implementation, when a user performs a gesture operation, the user's gesture may be within the monitoring area of ​​the radar system. The radar system can transmit radar signals to the monitored area and receive the reflected signals from the user's gesture. For example, signal generation and transmission can be achieved by the RF signal generator 12, radar transmitting circuit 14, and transmitting antenna 32 in the above embodiments.

[0346] The radar system can generate radar signals, and the types of radar signals can include, but are not limited to, continuous wave (CW) signals and chirp signals (or chirps).

[0347] Taking chirp signals as an example, a chirp signal is an electromagnetic signal whose frequency varies with time. Typically, the frequency of a rising chirp signal increases over time, while the frequency of a falling chirp signal decreases over time. The frequency variation of a chirp signal can take many different forms. For example, the frequency of a linear frequency modulated (LFM) signal varies linearly. Other forms of frequency variation in chirp signals include exponential variations. Besides chirp signals where the frequency varies continuously according to some predetermined function (i.e., a linear or exponential function), step-chirp signals can also be generated, where the frequency changes in steps. That is, a typical step-chirp signal consists of multiple frequency steps, where the frequency is constant for a predetermined duration at each step. Step-chirp signals can also be pulsed on and off, where the pulse is activated for a predetermined time period during each step of the chirp scan.

[0348] In one possible implementation, the radar system can transmit chirp signals, where the mathematical expression for a chirp signal can be exemplarily given as:

[0349]

[0350] in, B represents bandwidth. To fix the initial phase, t c Let A be the chirp signal period, A be the amplitude, and f0 be the starting frequency.

[0351] In one possible implementation, the radar system can transmit radar signals and receive reflected signals from the user's gestures.

[0352] The term "reflected signal from the user's gesture" can be understood as: a radar signal that impacts the user's gesture and is reflected back by the gesture. In a smart home scenario, this radar signal could be a radar signal impacting a walking target and being reflected back by that target. In a smart cockpit scenario, this radar signal could be a radar signal impacting a target object getting in or out of a vehicle and being reflected back by that target.

[0353] Furthermore, the processor can acquire the first radar data and, based on the first radar data, recognize the user's gestures and analyze the gesture information.

[0354] It should be understood that the first radar data in the embodiments of this application may refer to the reflected signal received by the receiving antenna in the radar system at the analog processing circuit, and the reflected signal is an analog signal. After obtaining the analog signal, the analog signal can be transmitted to the analog-to-digital converter circuit and digitized by the circuit to obtain a digital signal.

[0355] It should be understood that the analog signal obtained by the analog processing circuit can be transmitted to the analog-to-digital converter circuit and digitized by the circuit to obtain a digital signal. The first radar data in the embodiments of this application may also refer to the digital signal obtained by the above digitization, but this is not limited here.

[0356] The following describes the implementation of the processor acquiring the first radar data based on the processor and radar system deployment location:

[0357] 1. The radar system and processor are deployed in the same electronic device:

[0358] Among them, electronic devices can be a terminal in a smart home or an in-vehicle device in a smart cockpit;

[0359] In one possible implementation, the radar system can be deployed in an electronic device. After acquiring the first radar data, the radar system can transmit the first radar data to a processor in the electronic device (if the first radar data is an analog signal, the analog-to-digital converter circuit can convert the analog signal into a digital signal and then transmit the digital signal to the processor). The processor can then process the first radar data.

[0360] 2. The radar system and processor are deployed in different electronic devices (for ease of description, these different electronic devices will be referred to as electronic device A and electronic device B below):

[0361] In one possible implementation, the radar system can be deployed in electronic device A. After acquiring the first radar data, the radar system can transmit the first radar data to the processor in electronic device B. (If the first radar data is an analog signal, the analog-to-digital converter circuit in electronic device A can convert the analog signal into a digital signal and then transmit the digital signal to the processor in electronic device B. Alternatively, the analog signal can be transmitted to electronic device B, and the analog-to-digital converter circuit in the processor of electronic device B can convert the analog signal into a digital signal and then transmit the digital signal to the processor in electronic device B.) The processor in electronic device B can then process the first radar data.

[0362] 3. The radar system is deployed in electronic devices, while the processor is deployed on a cloud server:

[0363] In one possible implementation, the radar system can be deployed in an electronic device. After acquiring the first radar data, the radar system can transmit the first radar data to the processor in the cloud server (if the first radar data is an analog signal, the analog-to-digital converter circuit in the electronic device can convert the analog signal into a digital signal and then transmit the digital signal to the processor in the cloud server, or the analog signal can be transmitted to the cloud server, and the analog-to-digital converter circuit of the cloud server's processor can convert the analog signal into a digital signal). Then, the processor in the cloud server can process the first radar data.

[0364] Reference Figure 7a , Figure 7a An exemplary operation of radar system 102 is illustrated. Radar system 102 is implemented as a frequency-modulated continuous wave radar. In the environment, user 302 is located at a distance from the monitoring environment of radar system 102. To detect user 302, radar system 102 transmits radar transmission signal 306 (…). Figure 7a The description is as radar transmitted signal 306. At least a portion of radar transmitted signal 306 is reflected by user 302. This reflected portion represents reflected signal 308. Figure 7a The radar system 102 receives the reflected signal 308 (described as radar received signal 308). The radar system 102 receives the reflected signal 308 and processes it to extract data for radar-based application 206. As depicted, the amplitude of the reflected signal 308 is smaller than the amplitude of the radar transmitted signal 306 due to losses during propagation and reflection.

[0365] The radar transmission signal 306 comprises a sequence of chirps 310-1 to 310-N, where N represents a positive integer greater than one. The radar system 102 may transmit chirps 310-1 to 310-N in continuous bursts or as time-separated pulses. For example, the duration of each chirp 310-1 to 310-N may be on the order of tens or thousands of microseconds (e.g., between approximately 30 microseconds (μs) and 5 milliseconds (ms)).

[0366] The frequencies of chirps 310-1 to 310-N can increase or decrease over time. In the depicted example, radar system 102 employs a dual-slope cycle (e.g., triangular frequency modulation) to linearly increase and decrease the frequencies of chirps 310-1 to 310-N over time. The dual-slope cycle enables radar system 102 to measure the Doppler shift caused by the motion of user 302.

[0367] Typically, the emission characteristics (e.g., bandwidth, center frequency, duration, and emission power) of the chirps 310-1 to 310-N can be customized to achieve specific detection range, range resolution, or Doppler sensitivity to detect one or more features of user 302 or one or more gestures performed by user 302.

[0368] At radar system 102, the reflected signal 308 represents a delayed version of the radar transmitted signal 306. The amount of delay is proportional to the tilt range (e.g., distance) from the antenna array 212 of radar system 102 to user 302. Specifically, this delay represents the sum of the time it takes for the radar transmitted signal 306 to propagate from radar system 102 to user 302 and the time it takes for the reflected signal 308 to propagate from user 302 to radar system 102. If user 302 and / or radar system 102 are moving, the reflected signal 308 is offset in frequency relative to the radar transmitted signal 306 due to the Doppler effect. In other words, the characteristics of the reflected signal 308 depend on the movement of the hand and / or the movement of radar system 102. Similar to the radar transmitted signal 306, the reflected signal 308 consists of one or more chirps 310-1 to 310N.

[0369] In one possible implementation, motion information of objects in the radar field (such as the motion information of a user's gesture) can be extracted based on first radar data. This motion information can include, but is not limited to, distance, velocity, and angle information. The distance information is contained in the frequency of each echo pulse. By performing a Fast Fourier Transform (FFT) on a single pulse in a fast time domain, the distance information of the gesture within the current pulse time can be obtained. Integrating the distance information from each pulse yields the overall distance change information of the single gesture. After performing a Fast Fourier Transform (FFT) on the original gesture echo in the fast time domain, another FFT is performed in the slow time domain. The peak value reflects the Doppler frequency of the target, thus containing the target's velocity information. The slow time domain FFT must be performed within the same range gate. However, because the overall motion of the target involves distance migration, an FFT cannot be directly performed on a single range gate of the overall gesture. Instead, the number of accumulated pulses should be appropriately set so that the gesture truncation within each FFT operation has virtually no distance migration.

[0370] Specifically, after acquiring the first radar data, preliminary processing (e.g., Fast Fourier Transform, FFT) can be performed on the first radar data. Specifically, the processor can perform a one-dimensional (1D) Fast Fourier Transform (FFT) to obtain the Range-FFT spectrum, and a two-dimensional (2D) FFT to obtain the Range-Doppler spectrum. The following describes the 1D-FFT and 2D-FFT processes in detail:

[0371] In one possible implementation, the first radar data may include multiple chirp signals, each of which can be processed to obtain the corresponding range-FFT spectrum. For example, if r(n) is a digitized reflection signal, where n is the number of samples within a single chirp signal period, then an N1-point FFT (or 1D-FFT) can be performed on r(n) to obtain R(k):

[0372] R(k)=FFT(r(n), N1), N1≥n;

[0373] That is, a 1D-FFT can be performed on the reflected signal to obtain the corresponding Range-FFT, where the Range-FFT can be composed of multiple range points (Range-bins), and the range points (Range-bins) can be represented as... Where α i Given the modulus of R(k) in the positive frequency domain, the unit distance corresponding to a single distance point Range-bin can be defined as the distance resolution d. res Then the distance value di =α i ×d res The maximum detection range is The horizontal axis of the Range-FFT spectrum can be the aforementioned distance values, and the vertical axis can be the signal reflection intensity corresponding to each distance value. The signal reflection intensity can be defined as the magnitude of the complex signal (for example, if the complex signal is a+bj, then the signal reflection intensity can be expressed as...). The Range-FFT spectrum can include N1 / 2 distance values ​​and the signal reflection intensity corresponding to each distance value.

[0374] For example, you can refer to Figure 5 , Figure 5 This is a schematic diagram of a Range-FFT (Fourier Transform) spectrum, such as... Figure 5 As shown, the x-coordinate of the Range-FFT is the distance value d (inclusive). The vertical axis represents the signal reflection intensity.

[0375] In one possible implementation, after calculating the Range-FFT of a chirp signal, similarly, 1D-FFT processing can be performed on all K chirp signals within a frame to obtain K Range-FFTs.

[0376] In one possible implementation, the sequence of K values ​​on the same range-bin in the range-FFT can be subjected to another FFT (also known as 2D-FFT) to obtain the range-Doppler spectrum.

[0377] Taking radar data as chirp signals as an example, the first radar data may include multiple chirp signals, as shown in the reference. Figure 7b , Figure 7b Each row in the matrix shown represents a chirp signal, and multiple chirp signals are superimposed in rows to form gesture data (e.g., first radar data).

[0378] In one possible implementation, the radar system can have a long-range, wide-angle detection range, while its excellent radar performance makes it highly sensitive to minute movements. Interference information unrelated to gestures can be filtered out through range-dimensional filtering and velocity-dimensional filtering.

[0379] Among them, distance-dimensional filtering refers to filtering out targets outside the gesture area (including moving and static targets, such as driver body movements and driver breathing in a smart cockpit scenario). Figure 8As shown, the gesture and the human body are separated in terms of distance, and a distance-dimensional filter can be used to filter out other targets outside the gesture distance.

[0380] Among them, velocity-dimensional filtering refers to using a fourth-order feedback filter to filter out stationary targets and low-speed targets (such as in-vehicle displays, stationary or swaying ornaments, etc.) within the gesture area.

[0381] 602. Based on the first radar data indicating the first gesture, and the duration of the first gesture exceeding the first threshold, activate the adjustment function for the target function.

[0382] In this embodiment of the application, after obtaining the first radar data, gesture-related data analysis can be performed on the first radar data.

[0383] In one possible implementation, some or all of the data in the first radar data can be radar data corresponding to the first gesture. After acquiring the first radar data, it is necessary to identify the radar data related to the user's gesture, and then perform relevant processing on the first gesture using this identified radar data (such as determining the gesture category, determining the gesture duration, etc.).

[0384] In one possible implementation, the start and end times of the first gesture in the first radar data can be determined using variance detection. For example, the variance of each chirp of the gesture echo can be calculated. Since the echo variance increases significantly when there is a gesture compared to when there is no gesture, this characteristic can be used to determine the start and end times of a gesture. When there is a gesture, the echo variance increases; when the echo variance of a segment of radar signal data exceeds a set threshold θ, it is determined to be the start time of the gesture. Figure 9 The example shown is a segment of radar data. If the echo variance at a certain point is greater than a threshold θ, then the radar wave data starting from that point is determined to be gesture data. Figure 9 As shown in "gesture start point a". During the gesture termination determination process, due to the possibility of brief periods of stillness during the gesture, the variance may fall below the threshold for a certain time period (e.g., ...). Figure 9 The data segment shown (from point b to point c) would have redundant data if included in the radar signal data used for gesture recognition, increasing the computational load. Therefore, the end-of-gesture flag is set to ensure that the echo variance of n consecutive frames (e.g., approximately 1 / 30 s) is less than the threshold θ (e.g., ...). Figure 9 As shown, if the echo variance of n consecutive frames starting from point b is less than the threshold θ, then point b is marked as the gesture termination point. Determine the termination point n frames after receiving the echo of a gesture. Figure 9 Point c shown in the diagram is not used as the gesture termination point; instead, the last echo smaller than the threshold is used as the termination point of the gesture data. Figure 9 Point b shown in the diagram.

[0385] In this embodiment, timing can be started when gesture data is detected. If the duration of the gesture data exceeds a first threshold, a fine-tuning mode can be activated. The first threshold can be greater than 0.7 seconds and less than 1.5 seconds, for example, the first threshold can be 0.7 seconds, 0.8 seconds, 0.9 seconds, 1 second, 1.1 seconds, etc.

[0386] Fine-tuning can include activating functions and adjusting the degree of function adjustment. This degree of adjustment can include increasing or decreasing values, adjusting the orientation of the display position, scaling the display area, and adjusting the position or shape of hardware. For example, fine-tuning can include adjusting volume, display brightness, scaling the displayed image, moving the display interface, adjusting the window height, and adjusting the fore-and-aft position of the seats in the vehicle cabin. Because it involves adjusting the degree of function adjustment, fine-tuning gestures need to be held for a certain period of time to select the degree of adjustment, and this holding time is relatively long.

[0387] In one possible implementation, timing can be started when gesture data is detected, and if the duration of the gesture data does not exceed a first threshold before terminating, an independent gesture adjustment mode can be enabled.

[0388] The independent gesture adjustment mode can include turning a function on or off. Since it does not involve adjusting the degree of function, the independent gesture can be a single gesture and the duration is very short, such as waving left or right.

[0389] As interaction methods become more sophisticated, the number of gestures increases, and each gesture has distinct characteristics. Therefore, independent gestures and fine-tuning gestures share many overlapping features and are not easily distinguishable. Their biggest difference lies in the duration of the gesture; independent gestures are all single gestures with very short durations. Table 1 below shows an example of the duration statistics for continuous circling gestures, using circling as an example.

[0390] Table 1

[0391]

[0392] Table 1 takes continuous circling motion as an example. Considering individual gesture differences, the judgment threshold is set to 1 second. Under the radar parameter configuration in Table 1, 1 second corresponds to 1440 chirps. Gestures shorter than 1 second are judged as independent gestures, while gestures longer than 1 second are considered fine adjustment gestures. This ensures that the system can know that fine adjustment is in progress at the beginning of the second circling motion.

[0393] In this embodiment, the duration of the gesture indicated by the first radar data is used as the basis for whether to enable the fine adjustment mode. This part of the radar data may not be used as the basis for determining the degree of adjustment when fine adjustment is performed later, but only as the trigger condition for whether to enable fine adjustment (which can also be called the wake-up gesture in this embodiment). Enabling fine adjustment based on the gesture duration has the following advantages: Since the gesture types are limited, as the types of functions continue to increase in the future, the gesture types used as the basis for enabling fine adjustment functions may not be enough (independent gesture functions occupy a part of the gesture types, and wake-up gestures occupy another part of the gesture types. The two cannot overlap, otherwise errors will occur). However, by using the gesture duration as the basis for whether to enable the fine adjustment mode, the gesture categories used by independent gesture functions and wake-up gestures can overlap, thereby reducing the number of gesture categories required when adjusting the functions implemented by gestures. Furthermore, in scenarios involving gesture-related function adjustments, especially fine-tuning, it is necessary to ensure that the overall gesture design is as continuous as possible. When users want to make fine-tuning adjustments based on gestures, they will subconsciously know that the adjustment process requires gestures over a continuous period of time. If the rules for activating fine-tuning functions are also defined based on whether the duration is long enough, then users will perceive that the operation process of activating the gesture is continuous with the subsequent actions.

[0394] When the duration of the first gesture indicated by the first radar data exceeds a first threshold, the radar data related to the first gesture in the first radar data can be used to identify the gesture category (that is, to identify the gesture category of the first gesture). The reason for identifying the gesture category of the first gesture is that it is necessary to determine the function type of subsequent fine adjustment (that is, to determine the target function) based on the gesture category of the first gesture. It should be understood that the gesture category here can be understood as the hand shape category, and the hand shape characteristics of gestures in different gesture categories are different.

[0395] In one possible implementation, the processor can indicate the user's gesture based on the first radar data, and if the duration of the user's gesture exceeds a first threshold, the processor can determine the user's gesture as a first gesture based on the first radar data, and the first gesture is used to indicate the activation of the adjustment function.

[0396] In one possible implementation, a portion of radar data can be extracted from the first radar data, and the user's gesture can be determined as a first gesture based on this portion of radar data. Optionally, the portion of radar data consists of the first N radar data points from the first radar data. Unlike gesture detection, gesture extraction involves capturing a portion of the gesture of appropriate length during the gesture action for gesture recognition. Therefore, the extraction length is crucial; extracting too short or too long a portion will cause the gesture recognition to fail. Optionally, gesture extraction can be performed using time-based extraction and gesture feature extraction methods.

[0397] The time-based segmentation method aligns with the idea of ​​independent gesture recognition. It extracts N radar data points (e.g., N chirp signals) from the start of the gesture, and then uses these extracted signals for gesture recognition. The time-based segmentation method is simple, direct, and effective, its effectiveness stemming from several aspects: First, in subsequent gesture category determination, a gesture recognition algorithm based on a multi-dimensional feature fusion network with a self-attention mechanism can be used. This algorithm is insensitive to changes in gesture signal length; for similar gesture features, slight differences in duration (i.e., the speed of the gesture) have minimal impact on the recognition result, and the length of the same gesture varies between different users. Second, if the length of an independent gesture is shorter than the first threshold, the duration-based judgment ensures that the independent gesture will not be segmented, thus not affecting its recognition.

[0398] Taking continuous circular fine-tuning as an example, according to Table 1, the length of the first clockwise and counterclockwise wake-up gesture generally does not exceed 1000 chirps. Therefore, the truncated length N can be taken as 1000 chirps. (Refer to...) Figure 10 , Figure 10 This is a diagram illustrating the gesture of drawing two counter-clockwise circles before it is captured. (Refer to...) Figure 11a , Figure 11a This is a screenshot of the gesture of drawing two counterclockwise circles.

[0399] In the above example of continuous circle drawing for fine adjustment, when the gesture action reaches 1 second, the system determines that a fine adjustment operation is in progress. It extracts the first 1000 chirps of data in 1 second (1 second is 1440 chirps under the current radar parameter configuration, which is greater than 1000 chirps) for identification. The identification result is the category of the wake-up gesture.

[0400] Gesture feature extraction refers to analyzing the characteristic changes of a specific gesture to extract the gesture. The extraction length is not fixed and varies depending on the gesture. For example, hovering gestures can be extracted from changes in distance or speed, and the first circle in a continuous circling motion can be extracted from changes in distance, angle, and speed. Gesture feature extraction can solve the problem of the impact of gesture length differences caused by different users and different gestures on the extraction, and the extraction of individual gestures is more accurate.

[0401] Based on the above description, the time-based extraction method is suitable for situations where different wake-up gestures have similar durations; while the gesture feature extraction method is suitable for different wake-up gestures that share a common feature, allowing for the extraction of different wake-up gestures using a single feature. In practical applications, the appropriate extraction method can be selected based on a comprehensive consideration of the type and characteristics of the wake-up gesture.

[0402] After obtaining the aforementioned intercepted radar data, the motion characteristics of the user's gesture can be acquired based on the first radar data, and the user's gesture can be determined as a first gesture based on the motion characteristics of the user's gesture; or, based on the first radar data, the user's gesture can be determined as a first gesture through a pre-trained gesture classification network.

[0403] The following describes how to obtain the motion characteristics of the user's gesture based on the first radar data, and how to determine the user's gesture as the first gesture based on the motion characteristics of the user's gesture:

[0404] In one possible implementation, motion features are single salient features of a gesture (such as distance, speed, or angle). Analyzing these features allows for the recognition of a specific type of gesture. Gesture type recognition based on motion features only requires partial feature analysis, eliminating the need for feature fusion and neural networks. This simplifies some aspects of gesture recognition, reduces computational load, and improves real-time performance.

[0405] In wake-up gestures, taking hovering as an example, hovering is a stationary action where distance, speed, and angle characteristics remain unchanged, making it well-suited for judgment at the signal layer. Furthermore, considering that distance resolution is far higher than angle resolution under typical hardware performance, distance features are used to determine hovering actions. Specifically, the distance features of the currently received signal can be obtained, and the location of the maximum signal energy at each time point can be extracted. Using the signal's end position as a reference, the distance is continuously extended towards the signal's starting point until several consecutive times the distance difference between the gesture position and the reference position exceeds a threshold. At this point, it is considered not hovering, but rather a significant displacement. This method allows for the quantitative acquisition of hovering time. In addition, similar finer quantification can be achieved using distance features; when the slope of the fitted line of the first-order distance change remains consistently low over a certain period, it can be considered a hovering action.

[0406] Reference Figure 11b , Figure 11bFor an example of hover gesture signal layer judgment using the above method, the slope values ​​for each stage are -7.2967, -1.5059e-14, -2.8360, -1.5059e-14, 1.2219, -1.5059e-14, 0.1450, 0.5360, 0.5165, -0.0956, -0.7544, 2.3507, -0.8567, -0.6055, and 0.4787. If the slope judgment threshold is set to 3, it can be determined that the hover gesture lasts for approximately 2 seconds.

[0407] The following describes how, based on the first radar data, a pre-trained gesture classification network is used to determine that the user's gesture is the first gesture:

[0408] In one possible implementation, the pre-trained gesture classification network described above can be a network based on a multi-dimensional feature fusion recognition algorithm using convolutional layers combined with a self-attention mechanism. By fusing the distance, angle, and speed features of the gesture, the recognition result can be obtained. It should be understood that the pre-trained gesture classification network described above can also be applied to the recognition of independent gesture categories in independent gesture patterns.

[0409] The gesture recognition implementation mainly includes two methods: network recognition and signal layer recognition. Network layer recognition utilizes the multi-dimensional feature fusion recognition algorithm based on the attention mechanism proposed in this application. The overall architecture of the algorithm is as follows: Figure 11c As shown, the algorithm first stacks the three types of information from a single gesture to obtain information in a three-channel format, similar to the RGB image commonly used as input for deep learning algorithms in computer vision, serving as the data input for a single gesture. Then, feature extraction is performed on the input data, which is accomplished through multiple convolutional layers with a kernel size of 3. The feature extraction process reduces the data size and increases the number of channels. The data output undergoes a channel feature fusion step based on a self-attention mechanism, superimposing attention values ​​onto each channel. Subsequently, fully connected layers and a Softmax layer are used to one-dimensionalize the feature data and shorten its length to the number of gesture categories, outputting the predicted probability for each gesture category. Finally, the gesture category with the highest predicted probability can be taken as the gesture type of the first gesture.

[0410] The gesture type of the first gesture can be obtained through the above method, and then the gesture type of the first gesture can be determined to correspond to the target function based on a preset correspondence, wherein the preset correspondence includes the mapping between gesture type and function.

[0411] In other words, the type of the first gesture can be used to determine the target function (i.e., the object of adjustment) when subsequent fine-tuning is initiated.

[0412] In one possible implementation, the gesture type of the first gesture is a finger pinch (e.g., Figure 12a As shown), the target function is to adjust the progress of the video or audio being played by the application; or, if the gesture type of the first gesture is drawing a circle, the target function is to adjust the volume; or, if the gesture type of the first gesture is hovering the palm, the target function is to adjust the display brightness or the scaling of the displayed image; or, if the gesture type of the first gesture is clenching a fist, the target function is to adjust the movement of the display interface; or, if the gesture type of the first gesture is gently shaking the palm, the target function is to adjust the height of the car window; or, if the gesture type of the first gesture is clenching a fist and extending the thumb, the target function is to adjust the fore-and-aft position of the seat in the car cabin.

[0413] Specifically, the processor can identify a user's gesture within the radar system's monitoring area at a certain moment, and determine that the duration of the user's gesture exceeds a first threshold. It can then identify the user's gesture as a finger pinch, and enable the function adjustment mode for adjusting the progress of the video or audio played by the application.

[0414] Specifically, the processor can identify a user's gesture within the radar system's monitoring area at a certain moment, and determine that the duration of the user's gesture exceeds a first threshold. It can then identify the user's gesture as a circle and activate the volume adjustment function.

[0415] Specifically, the processor can identify a user's gesture within the radar system's monitoring area at a certain moment, and determine that the duration of the user's gesture exceeds a first threshold. It can then identify the user's gesture as a hand hover, and activate the function adjustment mode for adjusting display brightness or scaling of the displayed image.

[0416] Specifically, the processor can identify a user's gesture within the radar system's monitoring area at a certain moment, and determine that the duration of the user's gesture exceeds a first threshold. It can then identify the user's gesture as a clenched fist, and activate the motion adjustment function mode for the display interface.

[0417] Specifically, the processor can identify a user's gesture within the radar system's monitoring area at a certain moment, and determine that the duration of the user's gesture exceeds a first threshold. It can then identify the user's gesture as a slight hand shake, and activate the window height adjustment function.

[0418] Specifically, the processor can identify a user's gesture within the radar system's monitoring area at a certain moment, and determine that the duration of the user's gesture exceeds a first threshold. It can then identify the user's gesture as a clenched fist with an extended thumb, and activate the function adjustment mode for adjusting the fore-and-aft position of the seats in the vehicle cabin.

[0419] In this embodiment of the application, when a first gesture is determined to exist based on the first radar data and the duration of the first gesture exceeds a first threshold, the adjustment function for the target function can be activated.

[0420] Specifically, refer to Figure 12b When the adjustment function for the target function is enabled, certain feedback information can be presented. This feedback information can indicate that the adjustment function for the target function has been enabled. Specifically, when the adjustment function for the target function is enabled, the target corresponding to the target function can be displayed. The target display is used to indicate that the adjustment function for the target function has been enabled.

[0421] In one possible implementation, the target presentation may include: a control display for adjusting the target function. In smart home applications, the target presentation can be performed on an electronic device with a display screen; in smart cockpit applications, the target presentation can be performed on the central control screen in the vehicle cabin.

[0422] Taking the target function as adjusting the progress of video or audio played by the application as an example, the target presentation can be the display of a progress bar.

[0423] Taking volume adjustment as an example, the target display could be the volume adjustment control.

[0424] Taking the target function as display brightness adjustment as an example, the target presentation can be the display of the display brightness adjustment control.

[0425] Taking the target function of adjusting the scaling of the displayed image as an example, the target presentation can be the display of the image scaling control.

[0426] Taking the target function as the movement adjustment of the display interface as an example, the target presentation can be the display of the movement control on the display interface.

[0427] In one possible implementation, the target presentation may include vibration cues from hardware associated with the target function; for example, in a smart cabin scenario, the target presentation may be vibration cues from the seat.

[0428] Taking the target function of adjusting the fore-and-aft position of the seats in the cabin as an example, the target display can be a vibration prompt for the seat whose position needs to be adjusted.

[0429] In one possible implementation, the target presentation may include: an audio prompt, which may contain a voice indicating that the adjustment function for the target function has been enabled. For example, if the target function is adjusting the playback progress of a video or audio file played by an application, the target presentation may be the voice message "The playback progress function for the video or audio file played by the application has been enabled"; if the target function is adjusting the volume, the target presentation may be the voice message "The volume adjustment function has been enabled"; if the target function is adjusting the display brightness, the target presentation may be the voice message "The display brightness adjustment function has been enabled"; if the target function is adjusting the zoom of a displayed image, the target presentation may be the voice message "The image zoom function has been enabled"; if the target function is adjusting the window height, the target presentation may be the voice message "The window height adjustment function has been enabled"; if the target function is adjusting the fore-and-aft position of the seat in the vehicle cabin, the target presentation may be the voice message "The fore-and-aft position adjustment function of the seat in the vehicle cabin has been enabled".

[0430] 603. Acquire data from the second radar.

[0431] After activating the target function adjustment function (fine adjustment), the user can adjust the target function through gestures within the radar system's monitoring area.

[0432] Specifically, the processor can acquire second radar data, which can be obtained from the reflected signal of the user's gesture (second gesture). Regarding how the processor acquires the second radar data, please refer to the description of the acquisition method of the first radar data in the above embodiment, which will not be repeated here.

[0433] In one possible implementation, the first radar data is acquired before the second radar data.

[0434] In one possible implementation, the first radar data and the second radar data are radar data acquired continuously in the time domain; or, the first radar data and the second radar data are radar data acquired at time intervals of a target time period, the duration of which is less than a second threshold; wherein, the second threshold may be the time during which the processor performs relevant processing on the first radar data, during which the adjustment function for the target function has not yet been activated.

[0435] 604. In response to the activation of the adjustment function for the target function, determine the second gesture indicated by the second radar data and the motion characteristics of the second gesture based on the second radar data.

[0436] In this embodiment of the application, based on the activation of the adjustment function for the target function, the second gesture indicated by the second radar data and the motion characteristics of the second gesture can be determined according to the second radar data.

[0437] It should be understood that there is also a preset mapping relationship between the first gesture and the second gesture. Specifically, the first gesture can be used to activate the adjustment mode of the target function corresponding to the gesture type of the first gesture. When the adjustment mode of the target function is activated, the user can only adjust the target function based on the gesture type (the gesture type of the second gesture) corresponding to the adjustment mode of the target function.

[0438] The second radar gesture is the gesture used by the user when making fine adjustments. The first gesture is the gesture to wake up the fine adjustment function. The gestures can be quite different from the second gesture, which means that the first gesture and the second gesture can be considered as independent gestures.

[0439] In one possible implementation, the first gesture and the second gesture can also be continuous gestures by the user. Continuous gestures can be understood as the first gesture and the second gesture having the same hand shape (or very similar hand shape). Optionally, the first gesture can be a stationary gesture or a gesture with a movement range less than a threshold. Since the second gesture needs to adjust the target function to a certain extent, the second gesture can be a gesture with a movement range greater than a threshold.

[0440] In this embodiment, the first gesture and the second gesture have the same hand shape, so that the gesture used by the user when waking up the function for fine adjustment is the same hand shape as the gesture used when making fine adjustment, which allows the user to accurately adjust the function with very little learning cost.

[0441] In one possible implementation, the first gesture is a pinching gesture, and the second gesture is a gesture of keeping the fingers pinched and dragging; or, the first gesture is a palm-hanging gesture, and the second gesture is an upward or downward gesture; or, the first gesture is a palm-hanging gesture, and the second gesture is a left-right waving gesture; or, the first gesture is a palm-hanging gesture, and the second gesture is a forward-backward pushing gesture; or, the first gesture is a fist-clenching gesture, and the second gesture is a gesture of keeping the fist clenched and moving; or, the first gesture is a slight palm-shaking gesture, and the second gesture is an upward or downward gesture; or, the first gesture is a fist-clenching gesture with the thumb extended, and the second gesture is a gesture of keeping the fist clenched with the thumb extended and pushing forward-backward. The gesture semantic alignment adjustment function of the above-mentioned second gesture conforms to user habits and can help reduce the learning cost.

[0442] In one possible implementation, the first gesture and the second gesture are of the same gesture type as the first gesture, and both the first gesture and the second gesture are gestures with a movement amplitude greater than a threshold. For example, both the first gesture and the second gesture could be a circling gesture.

[0443] In this embodiment, the second radar data can be analyzed to determine the motion characteristics of the second gesture. These motion characteristics can be used to determine adjustment information during fine-tuning. The fine-tuning scheme does not require fine-quantification of all characteristics of each adjustment action. Based on the gesture characteristics, one or some motion characteristics of the gesture can be selected to achieve the fine-tuning function. Different gestures can employ different motion characteristics.

[0444] In one possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system. The motion characteristics of the second gesture may include: distance information of the second gesture, the distance information including at least one of the following: the change of distance between the second gesture and the radar system over time, the rate of change of the distance, and the direction of change of the distance.

[0445] Among them, the application of fine adjustment based on distance characteristics can be in situations where the relative distance between the hand gesture and the radar is constantly changing, and in situations where the area of ​​hand reflection points is relatively concentrated, which is conducive to distance detection.

[0446] For example, gestures suitable for fine quantification using distance features may include, but are not limited to: raising / pressing down the palm, waving left and right, moving forward and backward, etc.

[0447] The distance information is contained in the frequency of each echo pulse. By performing a fast Fourier transform on a single pulse in a fast time, the distance information of the gesture within the current pulse time can be obtained. By integrating the distance information of each pulse, the overall distance change information of a single gesture can be obtained.

[0448] The intermediate frequency signal can be simplified as follows:

[0449]

[0450] The signal spectrum can then be obtained using FFT, allowing you to pinpoint the spectral peaks.

[0451]

[0452] It is proportional to the target distance, so the target distance can be obtained as:

[0453]

[0454] Distance information extraction diagram as shown Figure 13Range resolution refers to the ability to distinguish between two nearby targets, that is, the minimum distance between targets that ensures no aliasing of echo signals, and it satisfies:

[0455]

[0456] Where c is the speed of light and B is the frequency modulation bandwidth of the chirp signal. The common bandwidth and distance resolution relationships in the 60GHz band are shown in Table 2 below.

[0457] Table 2

[0458]

[0459] Therefore, increasing the sweep bandwidth can improve the range resolution. At this point, the smallest scale for fine-tuning the range dimension is the range resolution. In this embodiment, the range resolution can also be improved by adjusting the Range-FFT during range feature extraction. Specifically, after Range-FFT processing, one spectral interval corresponds to one range gate unit, satisfying the following relationship:

[0460]

[0461] Where, N s N represents the number of sampling points for the I / Q channel Chirp signal. FFT This represents the number of FFT sampling points. Typically, N... s With N FFT Equal, at this time If N is increased FFT This will reduce 'a'.

[0462] For example: If N is set s 128, N FFT With a value of 512, the 128 sample points of the signal are used as the first 1 / 4 input of the FFT, and the remaining 3 / 4 are filled with 0s. At this point, the range gate spacing is reduced to 1 / 4 of its previous value. The minimum scale for fine-tuning the super-resolution can then be 1 / 4 of the range resolution.

[0463] In one possible implementation, a distance feature map can be obtained using range-FFT. The horizontal axis of the feature map corresponds to the number of chirp signals, which can represent time. The vertical axis represents distance, with each unit corresponding to a distance resolution R. resThe corresponding length. Due to the sensitivity of millimeter-wave radar to submillimeter-level displacement, echo signals with varying intensities exist at different distance gates on the same chirp signal. The location of the maximum energy within each chirp echo signal can then be extracted; the corresponding vertical axis value is the current position of the gesture. A very small number of abrupt position changes generally exist in the results, mainly due to noise. To reduce the impact of these abrupt changes, a sliding window averaging method is used for smoothing, which also smooths out jumps between distance points, facilitating subsequent processing. The sliding window length can be determined based on the length of the fine feature extraction time window (n frames). Then, a first-order fit can be performed on each segment of distance feature data, and the slope k of the first-order fit function can be extracted to obtain the distance adjustment basis information shown in Table 3 below:

[0464] Table 3

[0465]

[0466] Taking the upward and downward gestures as examples, for the upward movement, refer to... Figure 14 The upward movement lasts approximately 5-6 seconds, generating five slope values: -4.4657, 2.4895, 5.7985, 8.8039, and 12.5691. The first slope is negative because the process of reaching into the radar detection area involves a relative decrease in distance, with subsequent movements continuously moving away from the radar. The numerical values ​​reflect the rate of movement.

[0467] For the downward pressing action, refer to Figure 15 Conversely, the downward pressing motion represents a process where the relative distance continuously decreases. This motion also lasted approximately 5 / 6 seconds, with all slope values ​​being negative: -9.4675, -8.8054, -4.7695, -8.7964, and -6.6660. Similarly, the absolute value of the slope reflects the speed of the motion.

[0468] In one possible implementation, the second radar data is obtained based on the reflection of a user's gesture in a radar field provided by the radar system, and the motion characteristics of the second gesture may include: rate information of the second gesture, the rate information including the magnitude of the change in the movement rate of the second gesture in the radar field over time.

[0469] Fine-tuning based on velocity characteristics is suitable for processes with significant velocity changes, especially periodic motions. In these cases, velocity exhibits a clear sinusoidal relationship with time. Based on this analysis, gestures that utilize fine-quantification of velocity characteristics, such as clockwise and counterclockwise circular movements, continuous clicking, and sliding, are suitable for such applications.

[0470] In one possible implementation, after performing a fast-time FFT on the original gesture echo, a second FFT is performed in the slow-time dimension. The peak value reflects the target's Doppler frequency, thus containing the target's velocity information. The slow-time domain FFT must be performed within the same range gate. However, due to the range migration inherent in the target's overall motion, a direct FFT cannot be performed on a single range gate of the overall gesture. Instead, the number of accumulated pulses should be appropriately set to ensure that the gesture truncation within each FFT operation has virtually no range migration. This paper uses Short-Time Fourier Transform (SFT) to perform time-frequency analysis of the gesture signal, thereby extracting the gesture's Doppler information. Appropriately designing the number of accumulated pulses is equivalent to appropriately setting the window length of the SFT.

[0471] For the data processing in this paper, the distance information is first obtained by performing fast time FFT on the original signal. Then, the peak position data of each pulse is extracted and reassembled into a column. The time-frequency analysis of this column of data is performed using STFT to obtain the Doppler variation law of a single gesture.

[0472] If the target is in motion, then:

[0473]

[0474] The signal frequency contains both distance and velocity information, resulting in distance-velocity coupling, which cannot be directly obtained using a one-dimensional FFT. Let the signal sampling period be T. s The pulse repetition interval is T, the number of single-pulse sampling points is N, and L pulses are received. This can be rewritten as:

[0475]

[0476] Where n = 0, 1, 2, ..., N-1 represents the sampling point sequence of a single pulse, and l = 0, 1, 2, ..., L-1 represents the pulse sequence.

[0477] Observation shows that the phase component of the signal carries velocity information, and after a one-dimensional FFT, the phase component takes the form of the signal's complex envelope. Therefore, performing a second-dimensional FFT on the signal after the one-dimensional FFT (i.e., using the slow time lT as a variable) yields the signal's center frequency reflecting the target's velocity (i.e., the target's Doppler frequency):

[0478]

[0479] We can obtain:

[0480]

[0481] Time-frequency analysis of a signal refers to describing the composition of its frequency components across different time ranges. Since stationary signals are often ideal or artificially created, and signals are generally non-stationary, Fourier transform is insufficient for their analysis; time-frequency analysis is necessary. Short-time Fourier transform is a common method for time-frequency analysis.

[0482] The Short-Time Fourier Transform (STFT) represents the signal characteristics at a specific moment using a segment of the signal within a time window. In the STFT process, the time and frequency resolution of the time-frequency plot are determined by the window length. Increasing the window length leads to an increase in the length of the truncated signal, resulting in higher frequency resolution but lower time resolution, and vice versa. Specifically, the STFT first multiplies a function by a window function, and then performs a one-dimensional Fourier transform. By sliding the window function, a series of Fourier transform results are obtained. Arranging these results yields a two-dimensional representation with the time domain on the horizontal axis and the frequency domain on the vertical axis. Let s(t) be the signal to be analyzed, and STFT(t,ω) be the time-frequency analysis result of the signal. The STFT formula is as follows:

[0483] STFT(t,ω)=∫s(t′)ω(t′-t)e -jωt′ dt′;

[0484] As mentioned above, using STFT requires setting the window length, which affects both time and frequency resolution. High-frequency signals are suitable for small window lengths to achieve high time-domain resolution, while low-frequency signals are suitable for large window lengths to achieve high frequency-domain resolution. However, the STFT window length is fixed, thus its time-frequency analysis capabilities are somewhat limited. The STFT basis functions at different frequencies can be defined as follows: Figure 16 As shown in the diagram. A schematic diagram of Doppler information extraction can be seen as follows. Figure 17 As shown.

[0485] For example, when performing fine-tuning based on speed information, a speed feature map can be obtained, and the position of the maximum energy value within each chirp echo signal can be extracted. The vertical axis value corresponding to this position is the current gesture speed value. Local speed values ​​may fluctuate because the gesture cannot maintain an absolutely stable speed. To eliminate local fluctuations in the speed change curve, a sliding window averaging method is used for smoothing. The resulting speed curve can reflect the relatively uniformly accelerated motion of the gesture. Based on the shape characteristics of the obtained speed curve, variables reflecting the fine features of the gesture can be extracted. Taking a sinusoidal speed change curve as an example, the number of zeros of the sinusoidal speed curve can be determined using the intermediate value theorem: if the function is monotonic invariant in [a,b] and f(a)*f(b)<0, then the function f(x) has one and only one zero in [a,b]. One zero corresponds to 1 / 2 period. By taking the first derivative, the number of peaks and troughs that satisfy the derivative value of 0 can be determined. One peak to one trough corresponds to 1 / 2 period. Sine function fitting is performed to obtain the frequency of the speed transformation sinusoidal function. Wherein, the total duration of the gesture / the period of the sine function T = the number of periods.

[0486] Similar to distance features, the adjustment amplitude and speed can also be controlled solely based on changes in the velocity features in the transform domain. The adjustment direction can be determined either based on the wake-up gesture recognition result, such as drawing circles clockwise or counterclockwise, or by simultaneously utilizing angle features, for example, clockwise and counterclockwise angle changes are in opposite directions.

[0487] Taking the circling gesture as an example, based on the above analysis, circling clockwise and counterclockwise is a typical action that uses speed characteristics for fine adjustment. The periodic changes in speed information after passing through STFT are more obvious than the periodic fluctuations in distance.

[0488] Figure 18 The speed characteristic map shown is for a counter-clockwise 5-circle motion. After the above processing steps, the zero point count is 11 and the peak and trough count is 11. Based on the gesture classification result, it is determined to be counter-clockwise. Feedback can be given to the user every 1 / 4 cycle based on the peak and trough count and the zero point count. The speed of adjustment can be determined by the number of peaks and troughs within a fixed processing time interval.

[0489] In one possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system. The motion characteristics of the second gesture may include the angle information of the second gesture, which includes the change of the angle between the second gesture and the radar system over time, and the angle includes azimuth and / or elevation angles.

[0490] Among these, the fine-tuning based on angle features is applicable to gestures with minimal distance and speed fluctuations, especially those whose trajectories lie in the XOY plane at different heights in the diagram. For example, it can be applied to movements along different directions (currently limited by hardware performance and low angular resolution, the 360° plane can be divided into four regions, such as...). Figure 21 As shown in the diagram, the target angle is obtained based on multiple receiving antennas of the radar, by measuring the phase difference of each received echo. A schematic diagram of multi-antenna target echo reception is shown below. Figure 19 .

[0491] For example, a multiple signal classification (MUSIC) algorithm can be used, utilizing a radar four-antenna array to measure changes in the angle of a gesture. Unlike previous algorithms that directly process the covariance matrix of the array's received signals, the MUSIC algorithm performs eigenvalue decomposition on the covariance matrix of any array output data, thus obtaining a signal subspace corresponding to the signal components and a noise subspace orthogonal to the signal components. The orthogonality of these two subspaces is then used to estimate signal parameters such as the incident direction, polarization information, and signal strength. The MUSIC algorithm has broad applicability and advantages such as high accuracy and simultaneous measurement of multiple signals. The use of the MUSIC algorithm requires the radar element spacing to be no greater than half the carrier wavelength.

[0492] For example, if the number of elements in a radar linear array is K and the spacing is d, then the signal delay between two elements is dsinθ / c. Assume there are M targets with angles θ. m If m = 1, ..., M, then the received signals from M targets are:

[0493] S(t) = [S1(t), S2(t), ..., S M (t)] T ;

[0494] The direction vector of the signal is:

[0495]

[0496] in,

[0497]

[0498] Let the array element noise vector be:

[0499] N(t) = [n1(t), n2(t), ..., n K (t)] T ;

[0500] The received signal can then be obtained as:

[0501] X(t) = AS(t) + N(t);

[0502] Assuming the signals of each array element are uncorrelated, the covariance matrix of the received signal is:

[0503] R = E[XX] H ] = APA H +σ 2 I;

[0504] Where, P = E[SS] H ], where σ is the signal correlation matrix. 2 Let I be the noise power, and let I be a K×K identity matrix. Since R is a full-rank matrix with positive eigenvalues, we can obtain the eigenvector v by eigendecomposing R. i (i = 1, 2, ..., K), since the noise subspace is orthogonal to the signal subspace, a noise matrix is ​​constructed using the noise eigenvectors as columns:

[0505] E n =[v M+1 ,…,v K ];

[0506] Define the spatial spectral function:

[0507]

[0508] When a(θ) and E n When all columns are orthogonal, the denominator reaches its minimum value, therefore we can apply P... mu (θ) performs a spectral peak search and estimates the angle of arrival by finding the peaks.

[0509] Based on a radar multi-receiver antenna, the angle change during a gesture can be obtained using the MUSIC algorithm. In this paper, the number of pulses used for each angle calculation is 8, that is, the 8 original echo pulses from the single-channel received echo are first spliced ​​together.

[0510] X i =[x i1 ,x i2 ,…,x iN ];

[0511] Where N = 4096, which is the total length of 8 pulses, and i is the channel number. The four channel data are then concatenated to obtain the input matrix for the MUSIC algorithm:

[0512]

[0513] The gesture angle distribution corresponding to this segment of echo signal is obtained using the MUSIC algorithm. By performing the above operation on every 8 pulses of all echoes, the angle information of a single gesture across all stages can be obtained. A schematic diagram of angle information extraction is shown below. Figure 20 As shown.

[0514] Angular resolution characterizes the ability to distinguish two targets at the same distance, expressed as the included angle. Generally, the angular resolution of FMCW millimeter-wave angle measurements is related to the number of receiving antennas; more antennas result in higher accuracy. It satisfies the following:

[0515]

[0516] By using multiple transmitters, the angular resolution can be further improved. A series of transmit and receive antennas in a MIMO array can form a virtual array, at which point the angular resolution satisfies:

[0517]

[0518] Based on the above formulas, the angular resolution results for the two commonly used transceiver mechanisms are shown in Table 3 below:

[0519]

[0520] In summary, it can be seen that angular resolution can be significantly improved by enhancing radar hardware configuration.

[0521] When finely adjusting target functions based on angle features, angle feature extraction methods can be used to obtain angle feature maps. The distribution of scattering points in the angle feature maps can be divided into regions according to the angle. The direction of hand movement can be determined based on the change of angle over time. Then, the direction, magnitude, and speed of change of angle features can be determined. The adjustment direction of angle features can be reflected by the change of regions, the magnitude of adjustment can be reflected by the angle difference, and the speed of adjustment can be reflected by the angle difference per unit time.

[0522] For example, due to the current limitations of angular resolution, the radar detection area can be roughly divided into four parts (e.g. Figure 21 (As shown). With improved radar performance, regions can be divided more finely, resulting in more accurate direction determination. In the case of dividing the radar into four regions, each corresponding to 90°, the feature map obtained by moving a hand horizontally from Area 4 to Area 2 above the radar is shown below. Figure 22 As shown.

[0523] In addition, refer to Figure 23Furthermore, fine-tuning of target functions can be performed based on the aforementioned multiple motion characteristics. Specifically, when fine-tuning is required for various high-degree-of-freedom gestures, it is not easy to achieve this in a single dimension such as distance, speed, or angle (azimuth and elevation). In such cases, fine-tuning can be achieved by fusing features. By increasing the number of transceiver antennas or using virtual aperture technology, the radar's angular resolution and accuracy can be further improved. Angle features, distance features, and speed features can then be fused to achieve real-time spatial positioning and tracking of gestures, thereby realizing a function similar to air mouse movement.

[0524] Optionally, to ensure real-time performance, a short-interval feature fine quantization method can be adopted, in which fine features are extracted once every time window (nframes). The gesture data processed in each segment is not saved and is updated quickly. This small-scale data processing mode improves the feature feedback speed.

[0525] This application's embodiments, based on gesture feature extraction, perform fine quantification of gesture features, including distance, speed, horizontal angle, and pitch angle. By acquiring variables reflecting the direction, magnitude, and speed of feature changes, it is possible to achieve bidirectional, varying amplitudes and speeds, with high stability and strong generalization.

[0526] 605. Based on the motion characteristics, determine adjustment information, the adjustment information including at least one of adjustment amplitude, adjustment direction and adjustment speed, and adjust the target function based on the adjustment information.

[0527] Taking the progress adjustment of video or audio played by the application as an example, the adjustment range can indicate the size of the progress adjustment, the adjustment direction can indicate the direction of the progress adjustment (such as adjusting the progress forward or backward), and the adjustment speed can indicate the speed of the progress adjustment.

[0528] Taking volume adjustment as an example, the adjustment range can indicate the adjustment range, the adjustment direction can indicate the adjustment direction (e.g., forward or backward adjustment), and the adjustment speed can indicate the adjustment speed.

[0529] Taking the target function of display brightness adjustment as an example, the adjustment range can indicate the size of the adjustment progress, the adjustment direction can indicate the direction of the adjustment progress (such as adjusting the progress forward or backward), and the adjustment speed can indicate the speed of the adjustment progress.

[0530] Taking the target function of scaling the displayed image as an example, the adjustment range can indicate the scaling ratio of the displayed image, the adjustment direction can indicate whether it is zooming in or zooming out, and the adjustment speed can indicate the scaling adjustment speed.

[0531] Taking the movement adjustment with the target function as the display interface as an example, the adjustment range can indicate the size of the displacement during adjustment, the adjustment direction can indicate the direction of movement during adjustment, and the adjustment speed can indicate the speed of movement during adjustment.

[0532] Taking the target function of window height adjustment as an example, the adjustment range can indicate the size of the window height adjustment, the adjustment direction can indicate whether the window height is adjusted upwards or downwards, and the adjustment speed can indicate the speed of window height adjustment.

[0533] Taking the target function of adjusting the fore-and-aft position of the seats in the cabin as an example, the adjustment range can indicate the size of the adjustment of the fore-and-aft position of the seats in the cabin, the adjustment direction can indicate whether the seats in the cabin are adjusted forward or backward, and the adjustment speed can indicate the speed of the adjustment of the fore-and-aft position of the seats in the cabin.

[0534] In one possible implementation, the user can disable the fine-tuning function via a termination gesture (third gesture). Specifically, the processor can acquire third radar data and then, based on this data, instruct a third gesture to disable the adjustment function for the target function. This third gesture can be a release gesture or a hovering gesture. The stop action serves as a marker for fine-tuning, preventing unnecessary movements that could lead to erroneous adjustments. Most fine-tuning functions can be stopped directly by releasing the hand, while some functions sensitive to distance changes use a hovering stop. Optionally, the third gesture can have a strong continuity with the second gesture.

[0535] For example, you can refer to Figure 24a , Figure 24a This is a flowchart illustrating a function adjustment method provided in an embodiment of this application. Figure 24a As shown, the embodiments of this application can organically combine fine adjustment with gesture classification and recognition, ensuring that the gesture classification and recognition output results complete single-command operations, while also being compatible with using combined gestures or continuous repeated gestures to enter the fine adjustment function.

[0536] This application provides a function adjustment method, the method comprising: acquiring first radar data; based on the first radar data indicating a first gesture and the duration of the first gesture exceeding a first threshold, activating an adjustment function for a target function; acquiring second radar data; in response to the activation of the adjustment function for the target function, determining, based on the second radar data, a second gesture indicated by the second radar data and the motion characteristics of the second gesture; determining adjustment information based on the motion characteristics, the adjustment information including at least one of adjustment amplitude, adjustment direction, and adjustment speed, and adjusting the target function based on the adjustment information. In this embodiment, the duration of the gesture indicated by the first radar data is used as the basis for whether to enable the fine adjustment mode. This part of the radar data may not be used as the basis for determining the degree of adjustment when fine adjustment is performed later, but only as the trigger condition for whether to enable fine adjustment (which can also be called the wake-up gesture in this embodiment). Enabling fine adjustment based on the gesture duration has the following advantages: Since the gesture types are limited, as the types of functions continue to increase in the future, the gesture types used as the basis for enabling fine adjustment functions may not be enough (independent gesture functions occupy a part of the gesture types, and wake-up gestures occupy another part of the gesture types. The two cannot overlap, otherwise errors will occur). However, by using the gesture duration as the basis for whether to enable the fine adjustment mode, the gesture categories used by independent gesture functions and wake-up gestures can overlap, thereby reducing the number of gesture categories required when adjusting the functions implemented by gestures. Furthermore, in scenarios involving gesture-based function adjustments, especially fine-tuning, it's crucial to ensure the overall gesture design remains continuous. When users attempt fine-tuning based on gestures, they subconsciously anticipate a continuous series of gestures over a given period. If the rule for activating the fine-tuning function is also defined based on the duration of the gesture, users will perceive this activation gesture as seamless. Using the duration of the gesture indicated by the first radar data as the basis for activating fine-tuning mode aligns better with user thought processes and habits, reducing the learning curve for users.

[0537] Reference Figure 24b , Figure 24b This application provides a flowchart illustrating a function adjustment method, which may include:

[0538] 2401. Acquire target radar data, wherein the target radar data is obtained based on the reflection of the user's target gesture in the radar field provided by the radar system;

[0539] In the design where a wake-up gesture is present, the target radar data can be the second radar data described in the first aspect. The similarities will not be repeated here.

[0540] 2402. Based on the target radar data, determine the motion characteristics of the target gesture; the motion characteristics of the target gesture include at least two of the following: distance information, velocity information, or angle information; the distance information includes the change of distance between the target gesture and the radar system over time; the velocity information includes the change of relative velocity between the target gesture and the radar system over time; the angle information includes the change of angle of the target gesture in the radar field over time; the angle includes azimuth and / or elevation angle.

[0541] In one possible implementation, the change of distance over time includes:

[0542] At least one of the following: the numerical value of the distance change over time, the rate of change of the distance over time, or the direction of change of the distance over time;

[0543] The adjustment range is related to the change in distance over time, the adjustment speed is related to the rate of change of distance over time, and the adjustment direction is related to the direction of change of distance over time.

[0544] In one possible implementation, the target gesture is a periodic gesture, and the change in relative velocity over time is used to determine the number of gesture cycles of the target gesture;

[0545] The adjustment range is related to the number of cycles, and the adjustment speed is related to the number of gesture cycles of the target gesture within a fixed time.

[0546] In one possible implementation, the change of the angle over time includes:

[0547] At least one of the following: the numerical value of the angle change over time, the rate of change of the angle over time, or the direction of change of the angle over time;

[0548] The adjustment range is related to the change value of the angle over time, the adjustment speed is related to the rate of change of the angle over time, and the adjustment direction is related to the direction of change of the angle over time.

[0549] In one possible implementation, the feature type of the motion characteristics of the target gesture can be determined based on whether the target gesture is a periodic gesture or a gesture whose relative rate with respect to the radar system is constantly changing;

[0550] When the target gesture is a gesture whose distance to the radar system is constantly changing, the feature type for determining the motion characteristics of the target gesture includes the distance information;

[0551] When the target gesture is a gesture with constantly changing angles in the radar field, the feature type for determining the motion characteristics of the target gesture includes the angle information.

[0552] The embodiments of this application can obtain the corresponding motion feature types for different gesture categories, thereby reducing the amount of data processing while ensuring accurate recognition.

[0553] For more details on step 2402, please refer to the description of step 604 in the above embodiments, which will not be repeated here.

[0554] 2403. Based on the motion characteristics, determine adjustment information, the adjustment information including at least one of adjustment amplitude, adjustment direction and adjustment speed, and adjust the target function based on the adjustment information.

[0555] When performing fine-tuning of functions, the adjustment actions all have at least one significantly changing characteristic, such as distance, angle, or speed. Based on the extraction of gesture motion features, this application's embodiments perform fine-tuning of gesture features, including distance, speed, horizontal angle, and pitch angle. By acquiring variables reflecting the direction, amount, and speed of feature changes, bidirectional, varying amplitudes, different speeds, high stability, and strong generalization of fine-tuning can be achieved.

[0556] Reference Figure 25 , Figure 25 A schematic diagram of a function adjustment device provided in this application embodiment, wherein the device 2500 includes:

[0557] Acquisition module 2501 is used to acquire first radar data;

[0558] For a detailed description of the acquisition module 2501, please refer to steps 601 and 603. The similarities will not be repeated here.

[0559] The function activation module 2502 is used to activate the adjustment function for the target function based on the first radar data indicating the first gesture and the duration of the first gesture exceeding the first threshold.

[0560] The specific description of the function activation module 2502 can be found in step 602, and the similarities will not be repeated here.

[0561] The acquisition module 2501 is also used to acquire second radar data;

[0562] Function adjustment module 2503 is configured to, in response to the activation of the adjustment function for the target function, determine, based on the second radar data, the second gesture indicated by the second radar data, and the motion characteristics of the second gesture; and,

[0563] Based on the motion characteristics, adjustment information is determined, including at least one of adjustment amplitude, adjustment direction, and adjustment speed, and the target function is adjusted based on the adjustment information.

[0564] For a detailed description of the function adjustment module 2503, please refer to steps 604 and 605. The similarities will not be repeated here.

[0565] In one possible implementation, the first threshold is greater than 0.7 seconds and less than 1.5 seconds.

[0566] In one possible implementation, the first radar data is acquired before the second radar data.

[0567] In one possible implementation, the first radar data and the second radar data are radar data acquired continuously in the time domain; or,

[0568] The first radar data and the second radar data are radar data acquired in the time domain at target time intervals, wherein the duration of the target time interval is less than a threshold.

[0569] In one possible implementation, the first gesture and the second gesture are consecutive gesture actions of the user.

[0570] In one possible implementation, the first gesture and the second gesture are of the same gesture type, wherein the first gesture is a stationary gesture or a gesture with a movement amplitude less than a threshold, and the second gesture is a gesture with a movement amplitude greater than a threshold.

[0571] In one possible implementation, the first gesture is a pinching gesture, and the second gesture is a gesture of maintaining the pinched fingers while dragging; or...

[0572] The first gesture is a hand-holding gesture, and the second gesture is an upward or downward gesture; or...

[0573] The first gesture is a hand-holding gesture, and the second gesture is a left-right waving gesture; or...

[0574] The first gesture is a hand-holding gesture, and the second gesture is a pushing gesture; or...

[0575] The first gesture is a clenched fist gesture, and the second gesture is a gesture that maintains the clenched fist while moving; or,

[0576] The first gesture is a slight shaking of the palm, and the second gesture is an upward or downward gesture; or...

[0577] The first gesture is a fist with the thumb extended, and the second gesture is a gesture of keeping the fist clenched and the thumb extended while pushing back and forth.

[0578] In one possible implementation, the first gesture and the second gesture are of the same gesture type as the first gesture, and both the first gesture and the second gesture are gestures with a movement amplitude greater than a threshold.

[0579] In one possible implementation, both the first gesture and the second gesture are circling gestures.

[0580] In one possible implementation, the function activation module 2502 is further configured to:

[0581] Before activating the adjustment function for the target function, based on a preset correspondence, the gesture type of the first gesture is determined to correspond to the target function, wherein the preset correspondence includes a mapping between gesture type and function.

[0582] In one possible implementation, the first gesture is a pinch of fingers, and the target function is adjusting the playback progress of a video or audio file; or...

[0583] The first gesture is a circle drawing, and the target function is volume adjustment; or,

[0584] The first gesture is a palm hover, and the target function is to adjust the display brightness or adjust the scaling of the displayed image; or,

[0585] The first gesture is a clenched fist, and the target function is to adjust the movement of the display interface; or,

[0586] The first gesture is a slight waving of the hand, and the target function is adjusting the window height; or,

[0587] The first gesture is a clenched fist with the thumb extended, and the target function is the fore-and-aft adjustment of the seat in the vehicle cabin.

[0588] In one possible implementation, the device further includes:

[0589] The presentation module is used to present a target corresponding to the target function before adjusting the target function based on the adjustment information. The target presentation is used to indicate that the adjustment function for the target function has been enabled.

[0590] In one possible implementation, the target presentation includes at least one of the following:

[0591] The control display for adjusting the target function;

[0592] Vibration alerts from hardware related to the target function; and,

[0593] Sound prompt.

[0594] In one possible implementation, the step of instructing a first gesture based on the first radar data, and the duration of the first gesture exceeding a first threshold, includes:

[0595] Based on the first radar data indicating the user's gesture, and the duration of the user's gesture exceeds a first threshold, the user's gesture is determined to be a first gesture according to the first radar data, and the first gesture is used to indicate the activation of the adjustment function.

[0596] In one possible implementation, determining the user's gesture as a first gesture based on the first radar data includes:

[0597] Extract a portion of the radar data from the first radar data;

[0598] Based on the radar data, the user's gesture is determined to be the first gesture.

[0599] In one possible implementation, the partial radar data is the first N radar data in the first radar data.

[0600] In one possible implementation, determining the user's gesture as a first gesture based on the first radar data includes:

[0601] Based on the first radar data, the motion characteristics of the user's gesture are obtained, and the user's gesture is determined to be a first gesture based on the motion characteristics of the user's gesture; or,

[0602] Based on the first radar data, the user's gesture is determined to be the first gesture through a pre-trained gesture classification network.

[0603] In one possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include:

[0604] The distance information of the second gesture includes at least one of the following: the change in distance between the second gesture and the radar system over time, the rate of change of the distance, and the direction of change of the distance.

[0605] In one possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include:

[0606] The rate information of the second gesture includes the magnitude of the change in the movement rate of the second gesture in the radar field over time.

[0607] In one possible implementation, the second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system, and the motion characteristics of the second gesture include:

[0608] The angle information of the second gesture includes the change of the angle between the second gesture and the radar system over time, and the angle includes azimuth and / or elevation angle.

[0609] In one possible implementation, the acquisition module 2501 is further configured to:

[0610] After adjusting the target function based on the adjustment information, third radar data is acquired;

[0611] The device further includes:

[0612] The function shutdown module is used to disable the adjustment function for the target function based on the third gesture indicated by the third radar data; the third gesture is a hand withdrawal gesture or a hovering gesture.

[0613] In this embodiment, the duration of the gesture indicated by the first radar data is used as the basis for whether to enable the fine adjustment mode. This part of the radar data may not be used as the basis for determining the degree of adjustment when fine adjustment is performed later, but only as the trigger condition for whether to enable fine adjustment (which can also be called the wake-up gesture in this embodiment). Enabling fine adjustment based on the gesture duration has the following advantages: Since the gesture types are limited, as the types of functions continue to increase in the future, the gesture types used as the basis for enabling fine adjustment functions may not be enough (independent gesture functions occupy a part of the gesture types, and wake-up gestures occupy another part of the gesture types. The two cannot overlap, otherwise errors will occur). However, by using the gesture duration as the basis for whether to enable the fine adjustment mode, the gesture categories used by independent gesture functions and wake-up gestures can overlap, thereby reducing the number of gesture categories required when adjusting the functions implemented by gestures. Furthermore, in scenarios involving gesture-based function adjustments, especially fine-tuning, it's crucial to ensure the overall gesture design remains continuous. When users attempt fine-tuning based on gestures, they subconsciously anticipate a continuous series of gestures over a given period. If the rule for activating the fine-tuning function is also defined based on the duration of the gesture, users will perceive this activation gesture as seamless. Using the duration of the gesture indicated by the first radar data as the basis for activating fine-tuning mode aligns better with user thought processes and habits, reducing the learning curve for users.

[0614] Reference Figure 26 , Figure 26 A schematic diagram of a function adjustment device provided in this application embodiment, wherein the device 2600 includes:

[0615] The acquisition module 2601 is used to acquire target radar data, which is obtained based on the reflection of the user's target gesture in the radar field provided by the radar system.

[0616] For a detailed description of the acquisition module 2601, please refer to the description of step 2401 in the above embodiments, which will not be repeated here.

[0617] The motion feature determination module 2602 is used to determine the motion features of the target gesture based on the target radar data. The motion features of the target gesture include at least two of the following: distance information, velocity information, or angle information. The distance information includes the change in distance between the target gesture and the radar system over time. The velocity information includes the change in relative velocity between the target gesture and the radar system over time. The angle information includes the change in angle of the target gesture in the radar field over time. The angle includes azimuth and / or elevation angle.

[0618] For a detailed description of the motion feature determination module 2602, please refer to the description of step 2402 in the above embodiments, which will not be repeated here.

[0619] The function adjustment module 2603 is used to determine adjustment information based on the motion characteristics, the adjustment information including at least one of adjustment amplitude, adjustment direction and adjustment speed, and to adjust the target function based on the adjustment information.

[0620] For a detailed description of the function adjustment module 2603, please refer to the description of step 2403 in the above embodiments, which will not be repeated here.

[0621] In one possible implementation, the change of distance over time includes:

[0622] At least one of the following: the numerical value of the distance change over time, the rate of change of the distance over time, or the direction of change of the distance over time;

[0623] The adjustment range is related to the change in distance over time, the adjustment speed is related to the rate of change of distance over time, and the adjustment direction is related to the direction of change of distance over time.

[0624] In one possible implementation, the target gesture is a periodic gesture, and the change in relative velocity over time is used to determine the number of gesture cycles of the target gesture;

[0625] The adjustment range is related to the number of cycles, and the adjustment speed is related to the number of gesture cycles of the target gesture within a fixed time.

[0626] In one possible implementation, the change of the angle over time includes:

[0627] At least one of the following: the numerical value of the angle change over time, the rate of change of the angle over time, or the direction of change of the angle over time;

[0628] The adjustment range is related to the change value of the angle over time, the adjustment speed is related to the rate of change of the angle over time, and the adjustment direction is related to the direction of change of the angle over time.

[0629] In one possible implementation, the motion feature determination module 2602 is further configured to: before determining the motion feature of the target gesture based on the target radar data, determine the feature type of the motion feature of the target gesture to include the speed information when the target gesture is a periodic gesture or a gesture whose relative rate with the radar system is constantly changing;

[0630] When the target gesture is a gesture whose distance to the radar system is constantly changing, the feature type for determining the motion characteristics of the target gesture includes the distance information;

[0631] When the target gesture is a gesture with constantly changing angles in the radar field, the feature type for determining the motion characteristics of the target gesture includes the angle information.

[0632] When performing fine-tuning of functions, the adjustment actions all have at least one significantly changing characteristic, such as distance, angle, or speed. Based on the extraction of gesture motion features, this application's embodiments perform fine-tuning of gesture features, including distance, speed, horizontal angle, and pitch angle. By acquiring variables reflecting the direction, amount, and speed of feature changes, bidirectional, varying amplitudes, different speeds, high stability, and strong generalization of fine-tuning can be achieved.

[0633] The following describes a function adjustment device provided in an embodiment of this application. Please refer to [link to relevant documentation]. Figure 27 , Figure 27 This is a schematic diagram of a function adjustment device provided in an embodiment of this application. Specifically, the function adjustment device 2700 includes: a receiver 2701, a transmitter 2702, a processor 2703, and a memory 2704 (wherein the function adjustment device 2700 may have one or more processors 2703). Figure 27 (Taking a processor as an example), the processor 2703 may include an application processor 27031 and a communication processor 27032. In some embodiments of this application, the receiver 2701, transmitter 2702, processor 2703, and memory 2704 may be connected via a bus or other means.

[0634] Memory 2704 may include read-only memory and random access memory, and provides instructions and data to processor 2703. A portion of memory 2704 may also include non-volatile random access memory (NVRAM). Memory 2704 stores processor and operation instructions, executable modules, or data structures, or subsets thereof, or extended sets thereof, wherein the operation instructions may include various operation instructions for implementing various operations.

[0635] Processor 2703 controls the operation of the radar system (including antenna, receiver 2701, and transmitter 2702). In specific applications, the various components of the radar system are coupled together through a bus system, which may include a data bus, as well as a power bus, control bus, and status signal bus. However, for clarity, all buses are referred to as the bus system in the diagram.

[0636] The functional adjustment method disclosed in the above embodiments of this application ( Figure 6 and Figure 24b The processor 2703 (as shown) can be applied to or implemented by the processor 2703. The processor 2703 can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 2703 or by instructions in software form. The processor 2703 can be a general-purpose processor, a digital signal processor (DSP), a microprocessor, or a microcontroller, and may further include an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The processor 2703 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 2704. Processor 2703 reads the information in memory 2704 and, in conjunction with its hardware, completes the steps of the functional adjustment method provided in the above embodiments.

[0637] Receiver 2701 can be used to receive input digital or character information, and to generate signal inputs related to the settings and function control of the radar system. Transmitter 2702 can be used to output digital or character information through the first interface; transmitter 2702 can also be used to send instructions to the disk group through the first interface to modify the data in the disk group.

[0638] In one possible implementation, the device further includes a radar system for:

[0639] Provide radar field;

[0640] Sensing reflections from users within the radar field;

[0641] Analyze the reflections from the user in the radar field; and

[0642] Radar data is provided based on the analysis of the reflections.

[0643] Among them, the function adjustment device 2700 can be an in-vehicle device in a smart cockpit scenario, a terminal device in a smart home scenario, etc.

[0644] This application also provides a computer program product that, when run on a computer, causes the computer to perform the function adjustment method described in the above embodiments.

[0645] This application also provides a computer-readable storage medium storing a program for signal processing, which, when run on a computer, causes the computer to perform the function adjustment method described in the above embodiments.

[0646] The functional adjustment device provided in this application embodiment can specifically be a chip, which includes a processing unit and a communication unit. The processing unit can be, for example, a processor, and the communication unit can be, for example, an input / output interface, pins, or circuits. The processing unit can execute computer execution instructions stored in the storage unit to cause the chip in the execution device to execute the image enhancement method described in the above embodiment, or to cause the chip in the training device to execute the image enhancement method described in the above embodiment. Optionally, the storage unit can be a storage unit within the chip, such as a register or cache. The storage unit can also be a storage unit located outside the chip in the wireless access device, such as a read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, such as random access memory (RAM).

[0647] For details, please refer to Figure 28 , Figure 28This is a schematic diagram of a chip provided in an embodiment of this application. The chip can be represented as a neural network processor NPU280. The NPU280 is mounted as a coprocessor on the host CPU, and tasks are assigned by the host CPU. The core part of the NPU is the arithmetic circuit 2803, which is controlled by the controller 2804 to extract matrix data from the memory and perform multiplication operations.

[0648] In some implementations, the arithmetic circuit 2803 internally includes multiple processing engines (PEs). In some implementations, the arithmetic circuit 2803 is a two-dimensional pulsating array. The arithmetic circuit 2803 can also be a one-dimensional pulsating array or other electronic circuitry capable of performing mathematical operations such as multiplication and addition. In some implementations, the arithmetic circuit 2803 is a general-purpose matrix processor.

[0649] For example, suppose we have an input matrix A, a weight matrix B, and an output matrix C. The arithmetic circuit retrieves the corresponding data of matrix B from the weight memory 2802 and caches it in each PE of the arithmetic circuit. The arithmetic circuit retrieves the data of matrix A from the input memory 2801 and performs matrix operations with matrix B. The partial result or the final result of the obtained matrix is ​​stored in the accumulator 2808.

[0650] Unified memory 2806 is used to store input and output data. Weight data is directly transferred to weight memory 2802 via direct memory access controller (DMAC) 2805. Input data is also transferred to unified memory 2806 via DMAC.

[0651] BIU stands for Bus Interface Unit 2810, which is used for interaction between the AXI bus and the DMAC and the Instruction Fetch Buffer (IFB) 2809.

[0652] The Bus Interface Unit (BIU) 2810 is used by the instruction fetch memory 2809 to fetch instructions from external memory, and also by the memory access controller 2805 to fetch the original data of the input matrix A or the weight matrix B from external memory.

[0653] The DMAC is mainly used to move input data from external memory DDR to unified memory 2806, or to weight data to weight memory 2802, or to input data to input memory 2801.

[0654] The vector computation unit 2807 includes multiple arithmetic processing units that further process the output of the computation circuit as needed, such as vector multiplication, vector addition, exponential operations, logarithmic operations, size comparisons, etc. It is mainly used for computation in non-convolutional / fully connected layers of neural networks, such as batch normalization, pixel-level summation, and upsampling of feature planes.

[0655] In some implementations, the vector computation unit 2807 can store the processed output vector in the unified memory 2806. For example, the vector computation unit 2807 can apply linear and / or nonlinear functions to the output of the computation circuit 2803, such as performing linear interpolation on feature planes extracted by convolutional layers, or accumulating a vector of values ​​to generate activation values. In some implementations, the vector computation unit 2807 generates normalized values, pixel-level summed values, or both. In some implementations, the processed output vector can be used as activation input to the computation circuit 2803, for example, for use in subsequent layers of the neural network.

[0656] The instruction fetch buffer 2809 connected to the controller 2804 is used to store the instructions used by the controller 2804;

[0657] The unified memory 2806, input memory 2801, weighted memory 2802, and instruction fetch memory 2809 are all on-chip memories. External memory is proprietary to this NPU hardware architecture.

[0658] The processor mentioned above can be a general-purpose central processing unit, a microprocessor, an ASIC, or one or more integrated circuits used to control the execution of program related steps of the function adjustment method described in the above embodiments.

[0659] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and 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. In addition, in the accompanying drawings of the device embodiments provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0660] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of this application, 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 is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, training equipment, or network device, etc.) to execute the methods of the various embodiments of this application.

[0661] In the above embodiments, the implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, in the form of a computer program product.

[0662] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

Claims

1. A method for adjusting a function, characterized in that, The method includes: Acquire first radar data and extract Doppler features or range Doppler spectrum features from the first radar data; When gesture data is detected from the first radar data, based on the Doppler features or range Doppler spectrum features in the first radar data indicating the first gesture, the gesture type of the first gesture belonging to the first gesture category, and the duration of the first gesture exceeding the first threshold, the range gate unit, angle unit, or velocity unit of the target corresponding to the first gesture is determined, and the adjustment function for the target function is activated. Acquire second radar data; In response to the activation of the target function adjustment function, the target echo signal is extracted in at least one of the range gate unit, angle unit, or velocity unit based on the second radar data. The second gesture indicated by the second radar data is determined based on the Doppler characteristics or range-Doppler spectrum characteristics in the second radar data. The motion characteristics of the second gesture are determined based on the phase difference, Doppler frequency, angle change, and the slope or number of cycles of the Doppler frequency versus time curve of the target echo signal. The gesture type difference between the first gesture and the second gesture is greater than a threshold. A preset mapping relationship exists between the first gesture and the second gesture. The first gesture is used to activate the target function adjustment mode corresponding to the gesture type of the first gesture. When the target function adjustment mode is activated, the gesture type of the second gesture and the measured value of the motion characteristics of the second gesture are used to adjust the target function; or, the hand shape of the first gesture and the hand shape of the second gesture are the same. The feature type of the motion characteristics of the second gesture includes phase difference, Doppler frequency, angle change, and the slope or number of cycles of the Doppler frequency versus time curve. Based on the motion characteristics, adjustment information is determined, including at least one of adjustment amplitude, adjustment direction, and adjustment speed, and the target function is adjusted based on the adjustment information.

2. The method according to claim 1, characterized in that, The first threshold is greater than 0.7 seconds and less than 1.5 seconds.

3. The method according to claim 1 or 2, characterized in that, The first radar data and the second radar data are radar data acquired continuously in the time domain; or, The first radar data and the second radar data are radar data acquired in the time domain at target time intervals, wherein the duration of the target time interval is less than a second threshold.

4. The method according to any one of claims 1 to 3, characterized in that, The first gesture and the second gesture have the same hand shape. The first gesture is a stationary gesture or a gesture with a movement range less than a threshold, and the second gesture is a gesture with a movement range greater than a threshold.

5. The method according to claim 4, characterized in that, The first gesture is a pinching gesture, and the second gesture is a gesture of keeping the fingers pinched and dragging; or, The first gesture is a hand-holding gesture, and the second gesture is an upward or downward gesture; or... The first gesture is a hand-holding gesture, and the second gesture is a left-right waving gesture; or... The first gesture is a hand-holding gesture, and the second gesture is a pushing gesture; or... The first gesture is a clenched fist gesture, and the second gesture is a gesture that maintains the clenched fist while moving; or, The first gesture is a slight shaking of the palm, and the second gesture is an upward or downward gesture; or... The first gesture is a fist with the thumb extended, and the second gesture is a gesture of keeping the fist clenched and the thumb extended while pushing back and forth.

6. The method according to any one of claims 1 to 5, characterized in that, The first gesture was determined based on a portion of radar data extracted from the first radar data.

7. The method according to claim 6, characterized in that, The radar data mentioned above refers to the first N radar data points from the first radar data set.

8. The method according to any one of claims 1 to 7, characterized in that, The second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system. The motion characteristics of the second gesture include: The distance information of the second gesture includes at least one of the following: the change in distance between the second gesture and the radar system over time, the rate of change of the distance, and the direction of change of the distance; or, The rate information of the second gesture, the rate information including the magnitude of the change in the movement rate of the second gesture in the radar field over time; or, The angle information of the second gesture includes the change of the angle between the second gesture and the radar system over time, and the angle includes azimuth and / or elevation angle.

9. The method according to any one of claims 1 to 8, characterized in that, After adjusting the target function based on the adjustment information, the method further includes: Acquire third radar data; Based on the third radar data, a third gesture is given to disable the adjustment function for the target function; the third gesture is a withdrawal gesture or a hovering gesture.

10. The method according to any one of claims 1 to 9, characterized in that, Before activating the adjustment function for the target function, the method further includes: Based on a preset correspondence, the gesture type of the first gesture is determined to correspond to the target function, wherein the preset correspondence includes a mapping between gesture types and functions, and the preset correspondence includes at least one of the following: The first gesture is a pinching motion, and the target function is to adjust the playback progress of the video or audio being played by the application; or, The first gesture is a circle drawing, and the target function is volume adjustment; or, The first gesture is a palm hover, and the target function is to adjust the display brightness or adjust the scaling of the displayed image; or, The first gesture is a clenched fist, and the target function is to adjust the movement of the display interface; or, The first gesture is a slight waving of the hand, and the target function is adjusting the window height; or, The first gesture is a clenched fist with the thumb extended, and the target function is the fore-and-aft adjustment of the seat in the vehicle cabin.

11. A method for adjusting a function, characterized in that, The method includes: Acquire target radar data and extract Doppler features or range Doppler features from the target radar data, wherein the target radar data is obtained based on the reflection of the user's target gesture in the radar field provided by the radar system; Based on the Doppler features or range Doppler features in the target radar data, determine at least one of the following units: range gate, angle unit, or velocity unit corresponding to the target gesture. Extract the target echo signal from the target radar data within the range gate, angle unit, or velocity unit. Determine the motion characteristics of the target gesture based on the phase difference, Doppler frequency, angle change, and the slope or number of cycles of the Doppler frequency versus time curve of the target echo signal. The motion characteristics of the target gesture include velocity information and at least one of the following: range information or angle information. In one embodiment, the distance information includes the change in distance between the target gesture and the radar system over time; the velocity information includes the change in relative velocity between the target gesture and the radar system over time; and the angle information includes the change in angle of the target gesture in the radar field over time, wherein the angle includes azimuth and / or elevation angle. When the target function adjustment mode is activated, the gesture type of the target gesture and the measured values ​​of the motion characteristics of the target gesture are used to adjust the target function. The feature types of the motion characteristics of the target gesture include phase difference, Doppler frequency, angle change, and the slope or number of cycles of the Doppler frequency change curve over time. Based on the motion characteristics, adjustment information is determined, including at least one of adjustment amplitude, adjustment direction, and adjustment speed, and the target function is adjusted based on the adjustment information.

12. The method according to claim 11, characterized in that, The change in distance over time includes: At least one of the following: the numerical value of the distance change over time, the rate of change of the distance over time, or the direction of change of the distance over time; The adjustment range is related to the change in distance over time, the adjustment speed is related to the rate of change of distance over time, and the adjustment direction is related to the direction of change of distance over time.

13. The method according to claim 11 or 12, characterized in that, The target gesture is a periodic gesture, and the change in relative speed over time is used to determine the number of gesture cycles of the target gesture; The adjustment range is related to the number of gesture cycles, and the adjustment speed is related to the number of gesture cycles of the target gesture within a fixed time.

14. The method according to any one of claims 11 to 13, characterized in that, The change of the angle over time includes: At least one of the following: the numerical value of the angle change over time, the rate of change of the angle over time, or the direction of change of the angle over time; The adjustment range is related to the change value of the angle over time, the adjustment speed is related to the rate of change of the angle over time, and the adjustment direction is related to the direction of change of the angle over time.

15. The method according to any one of claims 11 to 14, characterized in that, Before determining the motion characteristics of the target gesture based on the target radar data, the method further includes: When the target gesture is a periodic gesture or a gesture with a constantly changing relative speed to the radar system, the feature type for determining the motion characteristics of the target gesture includes the speed information; or, When the target gesture is a gesture whose distance to the radar system is constantly changing, the feature type for determining the motion characteristics of the target gesture includes the distance information; or, When the target gesture is a gesture with constantly changing angles in the radar field, the feature type for determining the motion characteristics of the target gesture includes the angle information.

16. A function adjustment device, characterized in that, The device includes: The acquisition module is used to acquire first radar data and extract Doppler features or range Doppler features from the first radar data. The function activation module is used to, when the gesture data is detected from the first radar data, determine at least one of the following units of the target corresponding to the first gesture: the first gesture indicates a first gesture, the gesture type of the first gesture belongs to a first gesture category, and the duration of the first gesture exceeds a first threshold, and activate the adjustment function for the target function. The acquisition module is also used to acquire second radar data; A function adjustment module is configured to, in response to the activation of the target function adjustment function, extract the target echo signal in at least one of the following units: a range gate unit, an angle unit, or a velocity unit, based on the second radar data; determine the second gesture indicated by the second radar data based on the Doppler characteristics or range-Doppler spectrum characteristics in the second radar data; and determine the motion characteristics of the second gesture based on the phase difference, Doppler frequency, angle change, and the slope or number of cycles of the Doppler frequency versus time curve of the target echo signal. Specifically, the gesture type difference between the first gesture and the second gesture is greater than a threshold; a preset mapping relationship exists between the first gesture and the second gesture; the first gesture is used to activate the target function adjustment mode corresponding to the gesture type of the first gesture; when the target function adjustment mode is activated, the gesture type of the second gesture and the measured value of the motion characteristics of the second gesture are used to adjust the target function; or, the hand shape of the first gesture and the hand shape of the second gesture are the same; the feature type of the motion characteristics of the second gesture includes phase difference, Doppler frequency, angle change, and the slope or number of cycles of the Doppler frequency versus time curve; and... Based on the motion characteristics, adjustment information is determined, including at least one of adjustment amplitude, adjustment direction, and adjustment speed, and the target function is adjusted based on the adjustment information.

17. The apparatus according to claim 16, characterized in that, The first gesture and the second gesture have the same hand shape. The first gesture is a stationary gesture or a gesture with a movement range less than a threshold, and the second gesture is a gesture with a movement range greater than a threshold.

18. The apparatus according to claim 16 or 17, characterized in that, The first gesture was determined based on a portion of radar data extracted from the first radar data.

19. The apparatus according to any one of claims 16 to 18, characterized in that, The second radar data is obtained based on the reflection of the user's gesture in the radar field provided by the radar system. The motion characteristics of the second gesture include: The distance information of the second gesture includes at least one of the following: the change in distance between the second gesture and the radar system over time, the rate of change of the distance, and the direction of change of the distance; or, The rate information of the second gesture, the rate information including the magnitude of the change in the movement rate of the second gesture in the radar field over time; or, The angle information of the second gesture includes the change of the angle between the second gesture and the radar system over time, and the angle includes azimuth and / or elevation angle.

20. A function adjustment device, characterized in that, The device includes: The acquisition module is used to acquire target radar data and extract Doppler features or range Doppler features from the target radar data. The target radar data is obtained based on the reflection of the user's target gesture in the radar field provided by the radar system. The motion feature determination module is used to determine, based on the Doppler features or range Doppler features in the target radar data, at least one of the following units: range gate unit, angle unit, or velocity unit corresponding to the target gesture; extract the target echo signal within the target radar data at least one of the range gate unit, angle unit, or velocity unit; and determine the motion features of the target gesture based on the phase difference, Doppler frequency, angle change, and the slope or number of cycles of the Doppler frequency versus time curve of the target echo signal. The feature type of the motion feature of the target gesture includes velocity information, and the motion feature of the target gesture also includes range information or angle information. At least one of the following information: the distance information includes the change in distance between the target gesture and the radar system over time; the velocity information includes the change in relative velocity between the target gesture and the radar system over time; the angle information includes the change in angle of the target gesture in the radar field over time, the angle including azimuth and / or elevation angle; when the target function adjustment mode is enabled, the gesture type of the target gesture and the measured values ​​of the motion characteristics of the target gesture are used to adjust the target function; the feature types of the motion characteristics of the target gesture include phase difference, Doppler frequency, angle change, and the slope or number of cycles of the Doppler frequency change curve over time; The function adjustment module is used to determine adjustment information based on the motion characteristics, the adjustment information including at least one of adjustment amplitude, adjustment direction and adjustment speed, and to adjust the target function based on the adjustment information.

21. The apparatus according to claim 20, characterized in that, The change in distance over time includes: At least one of the following: the numerical value of the distance change over time, the rate of change of the distance over time, or the direction of change of the distance over time; The adjustment range is related to the change in distance over time, the adjustment speed is related to the rate of change of distance over time, and the adjustment direction is related to the direction of change of distance over time.

22. The apparatus according to claim 20 or 21, characterized in that, The change of the angle over time includes: At least one of the following: the numerical value of the angle change over time, the rate of change of the angle over time, or the direction of change of the angle over time; The adjustment range is related to the change value of the angle over time, the adjustment speed is related to the rate of change of the angle over time, and the adjustment direction is related to the direction of change of the angle over time.

23. The apparatus according to any one of claims 20 to 22, characterized in that, The motion feature determination module is further configured to: before determining the motion features of the target gesture based on the target radar data, determine that the feature type of the motion features of the target gesture includes the speed information when the target gesture is a periodic gesture or a gesture with a constantly changing relative speed to the radar system; or, When the target gesture is a gesture whose distance to the radar system is constantly changing, the feature type for determining the motion characteristics of the target gesture includes the distance information; or, When the target gesture is a gesture with constantly changing angles in the radar field, the feature type for determining the motion characteristics of the target gesture includes the angle information.

24. A function adjustment device, characterized in that, include: One or more processors and a memory; wherein the memory stores computer-readable instructions; The one or more processors read the computer-readable instructions to cause the computer device to perform the method as described in any one of claims 1 to 15.

25. The apparatus according to claim 24, characterized in that, The device also includes a radar system for: Provide radar field; Sensing reflections from users within the radar field; Analyze the reflections from the user in the radar field; and Radar data is provided based on the analysis of the reflections.

26. A vehicle, characterized in that, include: One or more processors and a memory; wherein the memory stores computer-readable instructions; The one or more processors read the computer-readable instructions to cause the computer device to perform the method as described in any one of claims 1 to 15; The vehicle's cabin also includes a radar system for: Provide radar field; Sensing reflections from users within the radar field; Analyze the reflections from the user in the radar field; and Radar data is provided based on the analysis of the reflections.

27. The vehicle according to claim 26, characterized in that, The vehicle cabin also includes a driver's seat, a passenger seat, and a steering wheel fixed in front of the driver's seat; wherein... The radar system includes: A first radar system, the first radar system including a first radar integrated circuit, the first radar integrated circuit including: At least one first transmitting antenna; At least one first receiving antenna; The first radar integrated circuit is located on the side of the steering wheel near the passenger seat, wherein the steering wheel is not being rotated by the user.

28. The vehicle according to claim 27, characterized in that, The at least one first transmitting antenna is used to provide a radar field to at least one of the following areas: The area of ​​the driver's seat near the passenger seat; and The area between the driver's seat and the passenger seat.

29. The vehicle according to any one of claims 26 to 28, characterized in that, The vehicle cabin also includes a driver's seat, a passenger seat, and a center console; The radar system includes: A second radar system, the second radar system including a second radar integrated circuit, the second radar integrated circuit including: At least one second transmitting antenna; At least one second receiving antenna; The second radar integrated circuit is located on the side of the center console facing away from the front of the vehicle.

30. The vehicle according to claim 29, characterized in that, The at least one second transmitting antenna is used to provide a radar field to at least one of the following areas: The area in the driver's seat near the passenger seat; The area of ​​the passenger seat closest to the driver's seat; and The area between the driver's seat and the passenger seat.

31. The vehicle according to any one of claims 26 to 30, characterized in that, The vehicle cabin also includes a driver's seat, a passenger seat, and an armrest box, the armrest box being fixed in the area between the driver's seat and the passenger seat; The radar system includes: A third radar system, the third radar system including a third radar integrated circuit, the third radar integrated circuit including: At least one third transmitting antenna; At least one third receiving antenna; The third radar integrated circuit is located on the side of the armrest box facing the main control panel.

32. The vehicle according to claim 31, characterized in that, The at least one third transmitting antenna is used to provide a radar field to at least one of the following areas: The area in the driver's seat near the passenger seat; The area of ​​the passenger seat closest to the driver's seat; and The area between the driver's seat and the passenger seat.

33. The vehicle according to any one of claims 26 to 32, characterized in that, The vehicle also includes: seats; The one or more processors are also configured to read the computer-readable instructions in order to control the seat to provide a vibration alert when the adjustment function for the target function is activated.

34. A computer-readable storage medium, characterized in that, Includes computer-readable instructions that, when executed on a computer device, cause the computer device to perform the method according to any one of claims 1 to 15.

35. A computer program product, characterized in that, Includes computer-readable instructions that, when executed on a computer device, cause the computer device to perform the method as described in any one of claims 1 to 15.

Images