Touch intention recognition device, method and vehicle

Abstract

The application relates to a touch intention recognition device and method and a vehicle, and relates to the technical field of vehicle human-computer interaction. The device comprises: a sensing module for acquiring sensing information collected by a two-dimensional matrix capacitive near-field sensing electrode assembly in an object approaching period; a touch intention recognition module for determining sensing features corresponding to the sensing information; determining whether a child touch intention exists in a touch area based on the sensing features; the sensing features include sensing speed, sensing area, sensing intensity and sensing trajectory; the sensing speed represents the speed of the object approaching the touch area; the sensing area represents the coverage area of the sensing area of the two-dimensional matrix capacitive near-field sensing electrode assembly when the object approaches the touch area; the sensing intensity represents the ratio between the target capacitance value and the coverage area; and the sensing trajectory represents the object moving trajectory sensed by the two-dimensional matrix capacitive near-field sensing electrode assembly when the object approaches the touch area, which can improve the recognition accuracy of the child touch intention and avoid triggering of non-expected functions to cause driving safety.

Description

Technical Field

[0001] This application relates to the field of vehicle human-machine interaction technology, specifically to a touch intent recognition device, method, and vehicle. Background Technology

[0002] With the rapid development of intelligent connected vehicles and multimodal human-machine interaction technologies, the intelligent cockpit has evolved from a single central control screen to a collaborative architecture of "front-row main control + rear-row distributed terminals." To optimize the rear passenger experience, more and more vehicles are integrating capacitive touch screens, linear motor touch strips, or hidden buttons into the rear armrests, door panels, and seat backs to enable convenient control of audio-visual, air conditioning, window, and seat functions.

[0003] However, in travel scenarios involving child occupants, the rear-seat distributed touch interaction system poses certain safety hazards: children's unconscious limb movements, arm swings while sleeping, clothing fluttering, or sudden actions can easily trigger erroneous operations such as sudden volume increases, video switching, unexpected window descent, and seat sudden movement, frequently interrupting the driver's attention and causing driving safety risks.

[0004] Current methods for preventing accidental touches in automotive touchscreens mostly employ single-capacitor proximity sensing technology. This involves placing sensors around the touch area and delaying the response to touch commands by detecting an approaching object. This approach relies solely on a single capacitive proximity signal, using a static "proximity equals delay" logic. It cannot distinguish between the physiological differences between children and adults, nor can it differentiate between unconscious limb movements and active actions. This often leads to adults being accidentally locked during normal operation, or children quickly penetrating the system through accidental touches, failing to meet the precise accidental touch prevention needs in complex scenarios. Summary of the Invention

[0005] In view of the shortcomings of the prior art, the purpose of this application is to provide a touch intent recognition device, method and vehicle that can improve the recognition accuracy of children's touch intent and avoid driving safety caused by unexpected function triggering.

[0006] In a first aspect, embodiments of this application provide a touch intent recognition device, which is deployed in an interactive touch terminal in the non-driver's seat occupant area of ​​a vehicle. A two-dimensional matrix capacitive near-field sensing electrode assembly is embedded below the touch area of ​​the interactive touch terminal. The device includes a sensing module and a touch intent recognition module; the sensing module and the touch intent recognition module are communicatively connected. The system includes a sensing module, which acquires sensing information collected by the two-dimensional matrix capacitive near-field sensing electrode assembly during the object's approach time and sends this information to the touch intent recognition module. The touch intent recognition module determines the sensing characteristics corresponding to the sensing information and determines whether a child's touch intent exists in the touch area based on these characteristics. The sensing characteristics include: sensing speed, sensing area, sensing intensity, and sensing trajectory. Sensing speed characterizes the speed at which the object approaches the touch area. Sensing area characterizes the coverage area of ​​the sensing region of the two-dimensional matrix capacitive near-field sensing electrode assembly when the object approaches the touch area. The sensing area is the region composed of capacitor cells whose capacitance changes. Sensing intensity characterizes the ratio between the target capacitance value and the coverage area. The target capacitance value is the difference between the maximum and minimum capacitance changes in the sensing area. The sensing trajectory characterizes the object's movement trajectory sensed by the two-dimensional matrix capacitive near-field sensing electrode assembly when the object approaches the touch area.

[0007] Based on the above technical solutions, existing technologies typically rely on capacitance changes after an object touches the touchscreen surface for detection, resulting in inherent physical response lag. This application, by embedding a two-dimensional matrix capacitive near-field sensing electrode assembly below the touch area, captures the sensing information of the object during the "approach period," enabling the recognition process to begin before the object actually touches the panel. This early perception mechanism not only shortens the user's subjective perception of operation latency and improves the smoothness of interaction, but also reserves a crucial time window for the subsequent execution of safety strategies. Furthermore, it utilizes sensing speed to capture the abrupt and poorly controlled movement characteristics of children; it uses sensing area to perform rapid initial screening based on physiological size differences; it uses sensing intensity (i.e., the ratio of the target capacitance value to the coverage area) to effectively eliminate interference caused by different contact areas, accurately reflecting the dielectric constant characteristics of the object itself, enhancing the ability to distinguish between human bodies (adults vs. children) and non-living objects (such as metal keys, clothing); and it uses sensing trajectory analysis to distinguish between purposeful clicks and unconscious random waving. By using the above-mentioned multi-feature joint decision, the shortcomings of single features being susceptible to noise interference are effectively overcome. Even in complex environments such as vehicle bumps and multiple occupants, the system can achieve high accuracy in recognizing children's touch intentions before the object actually touches the touch area, thereby improving the accuracy of children's touch intention recognition and avoiding driving safety issues caused by unexpected function triggers.

[0008] In one possible approach, the sensing module is further configured to acquire gravity sensing information from the gravity sensor array beneath the occupant seat bound to the interactive touch terminal; and send the gravity sensing information to the touch intent recognition module; the touch intent recognition module is further configured to determine the gravity load and center of gravity distribution of the occupant seat based on the gravity sensing information; and determine whether there is a child's touch intent in the touch area based on the sensing characteristics, gravity load, and center of gravity distribution.

[0009] Based on the above technical solution, this application integrates two-dimensional matrix capacitive near-field sensing with seat gravity sensing. It utilizes capacitive characteristics (sensing speed, area, intensity, and trajectory) to capture the dielectric properties and motion details of approaching objects, while simultaneously combining gravity load and center of gravity distribution to accurately determine the occupant's size and posture. Therefore, it can effectively eliminate misjudgments in single-modality scenarios such as adult waving, object dropping, or simple posture adjustments, significantly reducing the misjudgment rate, especially considering the characteristics of children's lighter weight, significant forward shift of center of gravity when leaning forward to retrieve objects, or non-human center of gravity distribution. This is achieved through multi-feature cross-validation. This solution upgrades the traditional "post-contact response" to "pre-contact prediction," enabling high-confidence identification of children's touch intentions before object contact, blocking the risk of accidental touches at the source. It is suitable for complex multi-occupant scenarios, providing proactive safety protection for in-vehicle touch terminals.

[0010] In one possible implementation, the touch intent recognition module includes a child recognition unit and a behavior intent recognition unit; the child recognition unit and the behavior intent recognition unit are communicatively connected. Specifically, the child recognition unit determines whether the object on the occupant seat is a human body based on the center of gravity distribution; if the object on the occupant seat is a human body, it determines whether the object is a child based on sensing speed, sensing area, and gravity load; if the object on the occupant seat is a child, it sends the child's seating information to the behavior intent recognition unit; the behavior intent recognition unit, upon receiving the child's seating information, determines whether the touch area contains a child's touch intent based on sensing intensity and sensing trajectory.

[0011] Based on the above technical solution, this application adopts a series architecture of a child recognition unit and a behavioral intent recognition unit to construct a hierarchical filtering mechanism: the child recognition unit first eliminates non-human interference based on the center of gravity distribution, and then quickly filters out adult operations by combining gravity load and sensing area. Only when it is confirmed to be a child is the behavioral intent recognition unit triggered to determine the specific touch intent based on the sensing intensity and sensing trajectory. This architecture, by determining "child riding information" and combining sensing intensity and sensing trajectory, ensures a high recognition rate of children's touch intent while also taking into account the smoothness of adult operations.

[0012] In one possible approach, the child identification unit is specifically used to: acquire baseline information on the child's physiological characteristics; wherein, the baseline information on the child's physiological characteristics includes: first baseline information and second baseline information; the first baseline information is used to characterize the theoretical speed range of the sensing speed and the theoretical area range of the sensing area when the child approaches the two-dimensional matrix capacitor near-field sensing electrode assembly; the second baseline information is used to characterize the theoretical weight range of the child; when the sensing speed is within the theoretical speed range, the sensing area is within the theoretical area range, and the gravitational load is within the theoretical weight range, the object carried on the occupant seat is determined to be a child.

[0013] Based on the above technical solution, this application uses pre-set physiological characteristic benchmark information including theoretical speed range, theoretical area range, and theoretical weight range. The first benchmark information is used to identify the child's dynamic physiological characteristics (fast movement speed, small hand area), and the second benchmark information is used to identify the child's static physiological characteristics (light weight). The child is only identified as such when all three characteristics (dynamic speed, area) and static characteristics (weight) simultaneously meet the preset range conditions. This coupling mechanism effectively distinguishes scenarios where a single characteristic can be confusing (e.g., an adult waving their hand quickly only meets the speed requirement, or a pet getting on a table only meets the weight requirement), avoiding systematic misjudgments caused by training data bias or unreasonable manually set thresholds.

[0014] In one possible embodiment, the behavioral intent recognition unit includes: a non-limb object interference recognition subunit and a child behavior interference recognition subunit; the non-limb object interference recognition subunit and the child behavior interference recognition subunit are communicatively connected; the non-limb object interference recognition subunit is used to send a target notification message to the child behavior interference recognition subunit when the sensing intensity is within a reference intensity range; wherein, the reference intensity range is the theoretical intensity range of the sensing intensity when a human limb approaches the two-dimensional matrix capacitor near-field sensing electrode assembly; the target notification message is used to indicate that the sensing is caused by a human limb, excluding interference from non-human limbs; the child behavior interference recognition subunit is used, after receiving the target notification message, to determine whether there is a child's touch intent in the touch area based on the sensing trajectory and at least one calibrated sensing trajectory; wherein, each of the at least one calibrated sensing trajectories corresponds to a movement behavior of a human without touch intent.

[0015] Based on the above technical solution, this application uses a non-limb object interference identification subunit to determine whether the signal is within the theoretical range of human body strength based on the sensing intensity (the ratio of capacitance change to coverage area), accurately identifies limb signals and sends a target notification message, effectively eliminating dielectric interference caused by non-human contact; the child behavior interference identification subunit only compares the sensing trajectory with the calibration trajectory representing "unconscious movement behavior" after receiving the target notification message, in order to reversely exclude unintentional action scenarios of children's touch operation.

[0016] In one possible approach, the child behavior interference identification subunit is specifically used to: determine whether the vibration interference condition has been met in the past when the sensing trajectory does not match any of the calibrated sensing trajectories; wherein, the vibration interference condition is that multiple instances of a child's touch intention were detected in the touch area within a first target time period, but no subsequent child touch action was performed; the first target time period is the time period consisting of the current moment and multiple moments preceding it; and if the vibration interference condition has not been met in the past, determine whether a child's touch intention exists in the touch area based on the vehicle's operating information.

[0017] Based on the above technical solution, the child behavior interference identification subunit of this application, after confirming that the sensing trajectory does not match any of the calibrated trajectories representing no touch intention, further searches for vibration interference conditions (i.e., typical bumpy characteristics of multiple short-term misjudgments as touch intention without subsequent action) based on historical identification records within the first target time period. If no match is found, the vibration interference condition is finally verified three times in conjunction with real-time vehicle operation information (such as vehicle speed, acceleration, and road surface spectrum data). This effectively filters out capacitive interference in the touch area caused by continuous vehicle bumps, while excluding unintentional touch by children. It solves the technical problem that single time slice analysis is difficult to distinguish between "intentional operation" and "road condition-induced vibration", significantly reduces the false touch alarm rate under complex road conditions, and ensures a strong correlation between the touch intention identification result and the actual driving state of the vehicle.

[0018] In one possible approach, the trajectory of an object's movement is represented by changes in the sensing area; at least one calibrated sensing trajectory includes: a first sensing trajectory, wherein the sensing area moves without a fixed direction under the first sensing trajectory; a second sensing trajectory, wherein the position offset range of the sensing unit in the sensing area under the second sensing trajectory is lower than a preset position offset range, and the capacitance value changes monotonically at a rate lower than a preset capacitance change rate; a third sensing trajectory, wherein the sensing area jumps from a first position to a second position under the third sensing trajectory; a fourth sensing trajectory, wherein the dwell time of the sensing signal at each position during the movement of the sensing area under the fourth sensing trajectory is lower than a preset dwell time; the preset dwell time is the minimum dwell time to be processed; and a fifth sensing trajectory, wherein the number of sensing areas under the fifth sensing trajectory is at least two, and all sensing areas move with the same direction and speed.

[0019] Based on the above technical solution, this application can quickly and accurately improve the touch intent recognition rate by pre-calibrating the sensing trajectory of non-child-controlled touch intent, and quickly and accurately determining whether the currently detected sensing trajectory matches the calibrated sensing trajectory.

[0020] In one possible approach, the operational information includes the vehicle's lateral acceleration, longitudinal acceleration, and vertical acceleration. Based on this, a child behavior interference identification subunit is specifically used to: determine if a child intends to touch the touch area when the operational information does not meet preset operational conditions; wherein the preset operational conditions at least satisfy one of the following: any one of the lateral, longitudinal, and vertical accelerations is greater than the steady-state maximum acceleration threshold for any one of the accelerations; the vertical acceleration undergoes alternating positive and negative transitions within a second target time period; the second target time period is a time period consisting of the current moment and multiple moments preceding it.

[0021] Based on the above technical solution, the child behavior interference recognition subunit of this application, after excluding unintentional actions from the sensing trajectory and excluding vibration interference from historical records, further utilizes a two-dimensional criterion of "steady-state threshold + dynamic jump" for scene recognition: On the one hand, by setting the maximum limit acceleration threshold for steady-state operation of lateral, longitudinal, and vertical acceleration, it ensures that the touch intention is confirmed only when the vehicle is not in extreme conditions exceeding steady-state operation, such as sharp turns, rapid acceleration and deceleration, or violent bumps, thus physically eliminating misjudgments caused by passive limb displacement due to inertial force; on the other hand, it specifically monitors the positive and negative reciprocating jump characteristics of vertical acceleration in the second target time period, accurately capturing the high-frequency vibration mode of the vehicle passing through continuous speed bumps or gravel roads, effectively distinguishing between high-frequency limb tremors caused by chassis excitation and touch actions initiated by the child.

[0022] In one possible embodiment, the touch intent recognition device further includes a processing module; the touch intent recognition module and the processing module are communicatively connected. The processing module is configured to lock the touch area when the touch intent recognition module sends an indication message indicating the presence of a child's touch intent in the touch area; after locking the touch area, the touch area becomes unresponsive to touch actions.

[0023] Based on the above technical solution, during vehicle operation, accidental touch by a child may cause abnormal window operation, extreme changes in air conditioning temperature, or sudden switching of the multimedia interface, severely distracting the driver. Upon receiving an indication that a child intends to touch the device, the processing module directly executes a hardware or underlying software blocking operation to lock the touch area. This mechanism ensures that even if the recognition module has a slight probability error, or if a child forcibly touches the device after it has been locked, the response link for the touch function will be physically severed.

[0024] In one possible approach, the processing module is further configured to: obtain the driver's driving status; if the driving status is not any of at least one of the calibrated driving statuses, send a child touch permission request to the vehicle's central control display device to obtain the driver's response to the child touch permission request; at least one calibrated driving status is a driving status that requires maintaining attention; and based on the response, unlock the touch area and manage permissions.

[0025] Based on the above technical solution, the processing module of this application first determines whether the driver is in a calibrated driving state that requires a high degree of centralization. Only in a non-calibrated state will it initiate a request for child touch permission to the central control device, granting the driver the final decision-making power, and performing differentiated unlocking and permission control based on the response result. In this way, the driver's focus can be guaranteed by silence and locking in critical moments, while the convenience of passengers can be taken into account by flexible authorization in safe scenarios.

[0026] Secondly, embodiments of this application provide a touch intent recognition method, applied to the touch intent recognition device of the first aspect. The method includes: acquiring sensing information collected by a two-dimensional matrix capacitor near-field sensing electrode assembly during the time period of an object approaching; determining the sensing features corresponding to the sensing information; and determining whether a child's touch intent exists in the touch area based on the sensing features. The sensing features include: sensing speed, sensing area, sensing intensity, and sensing trajectory. The sensing speed characterizes the speed at which an object approaches the touch area. The sensing area characterizes the coverage area of ​​the sensing region of the two-dimensional matrix capacitor near-field sensing electrode assembly when the object approaches the touch area. The sensing area is a region composed of capacitor units whose capacitance changes. The sensing intensity characterizes the ratio between a target capacitance value and the coverage area. The target capacitance value is the difference between the maximum and minimum capacitance changes in the sensing area. The sensing trajectory characterizes the object movement trajectory sensed by the two-dimensional matrix capacitor near-field sensing electrode assembly when the object approaches the touch area.

[0027] Based on the above technical solution, this application captures the sensing information of an object during its "approach period" by embedding a two-dimensional matrix capacitive near-field sensing electrode assembly below the touch area, enabling the recognition process to be initiated before the object actually touches the panel. This early perception mechanism not only shortens the user's subjective perception of the operation delay and improves the smoothness of interaction, but also reserves a critical time window for the subsequent execution of safety strategies. In addition, it uses sensing speed to capture the abrupt and poorly controlled movement characteristics of children; it uses sensing area to perform rapid initial screening based on physiological size differences; it uses sensing intensity (i.e., the ratio of the target capacitance value to the coverage area) to effectively eliminate interference caused by different contact areas, accurately reflecting the dielectric constant characteristics of the object itself, and enhancing the ability to distinguish between human bodies (adults vs. children) and non-living objects (such as metal keys and clothing); and it uses sensing trajectory analysis to analyze the kinematic patterns of objects, distinguishing between purposeful click operations and unconscious random waving. By using the above-mentioned multi-feature joint decision, the shortcomings of single features being susceptible to noise interference are effectively overcome. Even in complex environments such as vehicle bumps and multiple occupants, the system can achieve high accuracy in recognizing children's touch intentions before the object actually touches the touch area, thereby improving the accuracy of children's touch intention recognition and avoiding driving safety issues caused by unexpected function triggers.

[0028] Thirdly, embodiments of this application provide a vehicle that includes a touch intent recognition device according to the first aspect and any possible implementation thereof.

[0029] Fourthly, embodiments of this application provide an electronic device, including: a processor; and a memory for storing processor-executable instructions. The processor is configured to execute instructions to implement the touch intent recognition method of the second aspect described above and any possible implementation thereof.

[0030] Fifthly, this application provides a computer-readable storage medium that, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the touch intent recognition method described in the second aspect above and any possible implementation thereof.

[0031] Sixthly, embodiments of this application provide a computer program product, which includes computer instructions that, when executed on an electronic device, cause the electronic device to perform the touch intent recognition method described in the second aspect and any possible implementation thereof.

[0032] It should be noted that the technical effects of any of the implementation methods in aspects two through six can be found in the technical effects of the corresponding implementation methods in aspect one, and will not be repeated here.

[0033] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of this application or the background art, the accompanying drawings used in the embodiments of this application will be described below.

[0035] Figure 1 A schematic diagram illustrating the implementation environment of a touch intent recognition method provided in this application embodiment; Figure 2 A schematic diagram of a two-dimensional matrix capacitor near-field sensing electrode assembly provided in an embodiment of this application; Figure 3 A schematic diagram illustrating the deployment location of a gravity sensor array provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a touch intent recognition device provided in an embodiment of this application; Figure 5 A flowchart illustrating a touch intent recognition method provided in an embodiment of this application; Figure 6 This is a block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0036] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0037] It should be noted that 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 data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0038] In the embodiments of this application, the words "exemplarily," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplarily," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the words "exemplarily," "for example," or "for instance" is intended to present the relevant concepts in a specific manner.

[0039] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0040] like Figure 1 As shown, the implementation environment of a touch intent recognition method provided in this application embodiment includes: a touch intent recognition device 101 and a two-dimensional matrix capacitive near-field sensing electrode assembly 102 deployed in a vehicle 100. The touch intent recognition device 101 and the two-dimensional matrix capacitive near-field sensing electrode assembly 102 are communicatively connected.

[0041] The two-dimensional matrix capacitor near-field sensing electrode assembly 102 includes multiple miniature capacitor sensing units arranged in an N-row × M-column matrix, which are used to collect sensing information of the target object (i.e., the approaching object) and the spatial distribution characteristics of the activation electrode in real time.

[0042] For example, such as Figure 2 As shown, the two-dimensional matrix capacitive near-field sensing electrode assembly 102 adopts a cross-grid layout of mutual capacitance detection architecture, with driving electrodes (TX) in the horizontal direction and receiving electrodes (RX) in the vertical direction. The driving electrodes and receiving electrodes form miniature capacitive sensing units at the intersection nodes, thereby constructing a high-density capacitive sensing matrix.

[0043] In this embodiment of the application, see again. Figure 2 The two-dimensional matrix capacitive near-field sensing electrode assembly 102 can be embedded below the touch area of ​​the interactive touch terminal in the non-driver's seat passenger area of ​​the vehicle. The touch area may include, but is not limited to: the center armrest touch area, the door trim panel operation area, the seat side wing and the front edge of the seat cushion, the headliner control panel and the rear entertainment screen frame and table folding mechanism, and this application does not limit it.

[0044] The touch intent recognition device 101 is used to acquire the sensing information of the target object collected by the two-dimensional matrix capacitor near field sensing electrode assembly 102 from far to near within a time period, determine the sensing characteristics corresponding to the sensing information, and determine whether there is a child's touch intent in the touch area based on the sensing characteristics.

[0045] In this embodiment, the touch intent recognition device 101 can be deployed in the interactive touch terminal in the non-driver's seat passenger area of ​​the vehicle, such as the rear center armrest touch area, the rear door trim panel operation area, the passenger screen touch layer, the rear entertainment screen bezel, and other passenger-side human-machine interface nodes.

[0046] The non-driver's seat passenger area refers to the space within the vehicle cabin that is not within the driver's operating responsibility area but carries the body and interaction of passengers (front passenger, rear passenger, side passenger). This may include, but is not limited to, the area in front of the front passenger seat and the front passenger side of the dashboard (front passenger entertainment screen area), the rear seat area (rear center armrest, rear seat back front, and the area around the rear small table), the interior door panel operating area (touch strips and capacitive buttons on the rear door / front passenger door), the rear control panel on the roof, and other passenger-accessible areas. This application does not limit this area.

[0047] The interactive touch terminal refers to the hardware and software assembly located in the non-driver's seat area, which allows non-driver's seat passengers to initiate touch / proximity / gesture input. It may include, but is not limited to, a display screen with a touch module and a screenless pure touch panel. This application does not limit this.

[0048] Optionally, the touch intent recognition device 101 may include, but is not limited to: a capacitive touch sensing main control chip, an integrated microcontroller unit, a perception algorithm module in the vehicle cockpit domain controller, and a touch sub-unit in the door area controller. This application does not limit the scope of the application.

[0049] In some embodiments, combined with Figure 2 The content states that when an object (such as a passenger's hand) approaches the touch area (or operating area) of an interactive touch terminal, it changes the dielectric distribution of the near-field electric field between the driving electrode and the receiving electrode, causing dielectric disturbances in the mutual capacitance. Based on this, the touch intent recognition device 101 can periodically scan the driving electrode line by line and simultaneously collect the coupled charge of the receiving electrode, demodulate the capacitance change value of each intersection node in multiple intersection nodes of the driving electrode and the receiving electrode, and then generate a two-dimensional capacitance sensing matrix (also known as a sensing thermal map) reflecting the object's approach state. On this basis, the touch intent recognition device 101 can process and analyze the capacitance sensing matrix, extract the sensing features of the touch area, and determine whether there is a child's touch intent in the touch area based on the sensing features.

[0050] Optionally, the implementation environment of the touch intent recognition method provided in this application embodiment further includes: a gravity sensor array 103 deployed in the vehicle 100. The gravity sensor array 103 is communicatively connected to the touch intent recognition device 101.

[0051] The gravity sensor array 103 can be deployed at the bottom of each seat in the vehicle 100 to detect the seat gravity load (or load weight) and center of gravity distribution; and to send the seat gravity load and center of gravity distribution to the touch intent recognition device 101. Accordingly, the touch intent recognition device 101 is also used to determine whether there is an occupant sitting in the seat, and whether the occupant is a child or an adult, based on the seat gravity load and center of gravity distribution.

[0052] For example, such as Figure 3 As shown, independent gravity sensor arrays 103-L and 103-R are installed under the left rear seat L and right rear seat R, respectively. These arrays can be used to collect the gravity load of the left rear seat L and right rear seat R, respectively. Through a dual "space-load" binding logic, the attribution of the action can be accurately determined. For example, if the left rear seat L is for a child and the right rear seat R is for an adult, only the left touch area can be locked, while the right touch area remains functional, demonstrating intelligent and user-friendly design.

[0053] Optionally, the two-dimensional matrix capacitive near-field sensing electrode assembly 102 can be replaced with an infrared array or a millimeter-wave radar micro-sensing unit. The infrared array or millimeter-wave radar micro-sensing unit can also output an N×M dimensional near-field intensity map, which is then processed by the touch intent recognition device 101 using predetermined sensing feature extraction and intent classification logic, or combined with the two-dimensional matrix capacitive near-field sensing electrode assembly 102 to form multimodal feature extraction and fusion recognition.

[0054] Among them, the near-field intensity map output by the two-dimensional matrix capacitive near-field sensing electrode assembly 102 is a capacitive sensing matrix, and its element values ​​represent the change in mutual capacitance; the near-field intensity map output by the infrared array is a near-field intensity map in the thermal radiation domain, and its element values ​​represent the infrared thermal radiation temperature difference; the near-field intensity map output by the millimeter-wave radar micro-sensing unit is a near-field intensity map in the echo domain, and its element values ​​represent the electromagnetic wave echo energy. The touch intention recognition device 101 can extract sensing features and recognize the child's touch intention based on the numerical distribution characteristics of each element in the near-field intensity map.

[0055] The vehicle provided in this application embodiment can also be referred to as a vehicle, mobile carrier, electric vehicle (EV), hybrid electric vehicle (HEV), plug-in hybrid electric vehicle (PHEV), fuel cell vehicle (FCV), autonomous vehicle, intelligent and connected vehicle (ICV), driverless vehicle, etc.

[0056] In this embodiment, the vehicle can be a sedan, a sport utility vehicle (SUV), a truck, an electric vehicle, a motorcycle, a tricycle, a special vehicle (such as an ambulance, fire truck, police car, etc.), a driverless taxi, an intelligent connected bus, an autonomous logistics vehicle, an electric truck, etc. Furthermore, this method is also applicable to various special-purpose vehicles, such as agricultural vehicles, mining vehicles, forestry vehicles, airport vehicles, port vehicles, etc., and this application does not impose specific limitations on them.

[0057] The above describes the implementation of touch intent recognition between the touch intent recognition device 101 and the two-dimensional matrix capacitive near-field sensing electrode assembly 102. For ease of understanding, the touch intent recognition method implemented by the touch intent recognition device 101 in this embodiment will be specifically described below with reference to the accompanying drawings.

[0058] like Figure 4 As shown, a touch intent recognition device 101 provided in this application embodiment includes: a sensing module 401 and a touch intent recognition module 402, which are communicatively connected.

[0059] The sensing module 401 is used to acquire the sensing information collected by the two-dimensional matrix capacitor near-field sensing electrode assembly during the time when the object approaches, and send the sensing information to the touch intent recognition module.

[0060] In some embodiments, when an object (such as an occupant's hand) approaches the touch area (or operating area) of the interactive touch terminal, it changes the dielectric distribution of the near-field electric field between the driving electrode and the receiving electrode, causing dielectric disturbance of the mutual capacitance. The two-dimensional matrix capacitive near-field sensing electrode assembly can collect sensing information of the object gradually approaching the touch area in real time. This sensing information includes the capacitance change sequence (i.e., capacitance sensing matrix) of each microcapacitive sensing unit collected by the two-dimensional matrix capacitive near-field sensing electrode assembly at a preset frame rate during the object approaching period, as well as the sensing signal intensity matrix and active electrode distribution data obtained after preprocessing. Accordingly, the sensing module 401 can use the sensing information collected in real time by the two-dimensional matrix capacitive near-field sensing electrode assembly during the object approaching period and send the sensing information to the touch intent recognition device 101.

[0061] The touch intent recognition module 402 is used to determine the sensing features corresponding to the sensing information, and to determine whether there is a child's touch intent in the touch area based on the sensing features.

[0062] The sensing characteristics include: sensing speed, sensing area, sensing intensity, and sensing trajectory. The following sections will provide a detailed description of each of these characteristics.

[0063] 1-1. Sensing speed: Used to characterize the speed at which an object approaches the touch area.

[0064] In some embodiments, the touch intent recognition module 402 can periodically acquire the two-dimensional capacitance sensing matrix (i.e., sensing information) collected by the two-dimensional matrix capacitance near-field sensing electrode assembly according to a preset sampling frequency, and read the two-dimensional capacitance sensing matrix frame by frame. Sensing units in the two-dimensional capacitance sensing matrix whose capacitance change exceeds a preset threshold are identified as active units. Then, spatial clustering processing is performed on the active units, grouping active units with continuous spatial locations and consistent response characteristics into the same active electrode region / sensing region. Based on this, the touch intent recognition module 402 can calculate the centroid coordinates of each active electrode region in each frame, and determine the equivalent motion speed of the object approaching the touch area by using the centroid displacement of each active electrode region between adjacent frames and the preset sampling frequency.

[0065] Optionally, the preset sampling frequency can be set according to actual needs. For example, the preset sampling frequency can be 100 Hz, 150 Hz, or 200 Hz, etc., and this application does not limit it.

[0066] The sensing velocity is the ratio of the average displacement of the centroid of the sensing area at adjacent sampling times during the object's approach period to the time interval between adjacent sampling times.

[0067] For example, for the active electrode region A, the touch intent recognition module 402 can calculate the centroid displacement Δd and sampling interval Δt of the active electrode region A between two adjacent frames to obtain the sensing speed v=Δd / Δt.

[0068] 1-2. Sensing area: The area covered by the sensing region of the two-dimensional matrix capacitor near-field sensing electrode assembly when an object approaches the touch area; the sensing region is the area composed of capacitor units whose capacitance changes.

[0069] In some embodiments, the touch intent recognition module 402 can perform frame-by-frame scanning and connected component analysis on the two-dimensional capacitive sensing matrix (i.e., sensing information). Specifically, the touch intent recognition module 402 can traverse the capacitive sensing matrix row by row, extract sensing units whose capacitance changes exceed a preset threshold, and define active units. Subsequently, spatial clustering processing is performed on the active units (e.g., using a four-neighbor or eight-neighbor connected component labeling algorithm), grouping units with continuous spatial locations and consistent response characteristics into the same candidate contact cluster (i.e., active electrode region), thereby filtering out discrete noise points and calculating the equivalent coverage area of ​​each active electrode region.

[0070] For example, taking a single sensing unit area of ​​Ao (e.g., 4mm × 4mm) as an example, if the sensing area contains K consecutive activation units, then the coverage area S of the sensing area is S = K. Ao.

[0071] 1-3. Sensing intensity (also known as sensing signal intensity gradient): This value characterizes the ratio between the target capacitance value and the coverage area. The target capacitance value is the difference between the maximum and minimum capacitance changes in the sensing region.

[0072] In some embodiments, the touch intent recognition module 402 can determine the target capacitance value as the difference between the maximum and minimum capacitance changes in the sensing area. Then, the ratio between the target capacitance value and the coverage area is determined as the sensing intensity. This sensing intensity, along with a preset sensing intensity threshold, is then used as a criterion for determining whether a child's touch intent exists in the touch area.

[0073] 1-4. Sensing trajectory: Used to characterize the trajectory of an object's movement as it approaches the touch area, sensed by the two-dimensional matrix capacitive near-field sensing electrode assembly.

[0074] In some embodiments, the touch intent recognition module 402 can continuously acquire a two-dimensional capacitive sensing matrix at a preset sampling frequency, perform spatial clustering of the active electrode regions frame by frame, and calculate the capacitance-weighted centroid coordinates of each active electrode region. Then, an inter-frame nearest neighbor association algorithm (or a Kalman filter tracker) is used to determine that active electrode regions in adjacent frames with displacements less than a preset threshold and area changes within an allowable range are the same approaching target, and a unique tracking identifier is assigned to this target. Afterwards, the centroid coordinate sequence under this identifier can be stitched together in chronological order to obtain the sensing trajectory of the object approaching the touch area.

[0075] In summary, after determining the sensing speed, sensing area, sensing intensity, and sensing trajectory corresponding to the sensing information using the above methods, the touch intent recognition module can compare the sensing speed, sensing area, sensing intensity, and sensing trajectory with their respective theoretical ranges. Based on the comparison results, it can then determine whether a child's touch intent exists in the touch area. The specific determination process can be found in the following embodiments and will not be elaborated upon here.

[0076] Based on the above technical solution, this application captures the sensing information of an object during its "approach period" by embedding a two-dimensional matrix capacitive near-field sensing electrode assembly below the touch area, enabling the recognition process to be initiated before the object actually touches the panel. This early perception mechanism not only shortens the user's subjective perception of the operation delay and improves the smoothness of interaction, but also reserves a critical time window for the subsequent execution of safety strategies. In addition, it uses sensing speed to capture the abrupt and poorly controlled movement characteristics of children; it uses sensing area to perform rapid initial screening based on physiological size differences; it uses sensing intensity (i.e., the ratio of the target capacitance value to the coverage area) to effectively eliminate interference caused by different contact areas, accurately reflecting the dielectric constant characteristics of the object itself, and enhancing the ability to distinguish between human bodies (adults vs. children) and non-living objects (such as metal keys and clothing); and it uses sensing trajectory analysis to analyze the kinematic patterns of objects, distinguishing between purposeful click operations and unconscious random waving. By using the above-mentioned multi-feature joint decision, the shortcomings of single features being susceptible to noise interference are effectively overcome. Even in complex environments such as vehicle bumps and multiple occupants, the system can achieve high accuracy in recognizing children's touch intentions before the object actually touches the touch area, thereby improving the accuracy of children's touch intention recognition and avoiding driving safety issues caused by unexpected function triggers.

[0077] In one optional implementation, the sensing module can also acquire gravity sensing information from the gravity sensor array beneath the occupant seat bound to the interactive touch terminal, and send the gravity sensing information to the touch intent recognition module. Accordingly, the touch intent recognition module can determine the gravity load and center of gravity distribution of the occupant seat based on the gravity sensing information, and determine whether there is a child's touch intent in the touch area based on the sensing characteristics, gravity load, and center of gravity distribution.

[0078] In some embodiments, the interactive touch terminal has a one-to-one correspondence with the occupant seats in the vehicle's spatial layout and electronic architecture configuration, and a gravity sensor array is deployed under each occupant seat. Based on this, the sensing module can collect gravity sensing information of each occupant seat through the gravity sensor array under the occupant seat bound to the interactive touch terminal, and send the gravity sensing information to the touch intent recognition module.

[0079] In some embodiments, after receiving the gravity load and center of gravity distribution from the sensing module, the touch intent recognition module can determine whether a child's touch intent exists in the touch area based on the sensing speed, sensing area, sensing intensity and sensing trajectory, gravity load, and center of gravity distribution. Specifically, the touch intent recognition module includes a child recognition unit and a behavioral intent recognition unit. The child recognition unit and the behavioral intent recognition unit are communicatively connected.

[0080] The child identification unit is used to determine whether an object mounted on the occupant seat is a human body based on the center of gravity distribution. If the object on the occupant seat is a human body, it can determine whether the object is a child based on sensing speed, sensing area, and gravity load. Then, if the object on the occupant seat is a child, the child's seating information can be sent to the behavior intention recognition unit.

[0081] In this embodiment of the application, the child identification unit stores child physiological characteristic reference information, which includes: first reference information and second reference information; the first reference information is used to characterize the theoretical speed range of the sensing speed and the theoretical area range of the sensing area when the child approaches the two-dimensional matrix capacitor near-field sensing electrode assembly; the second reference information is used to characterize the child's theoretical weight range.

[0082] It should be noted that, based on extensive statistical data, the speed at which children aged 3 to 12 approach the touch area during unconscious limb movements (such as natural forearm swinging or arm sliding while prone) is generally less than 0.5 meters per second (m / s), mainly concentrated in the 0.1–0.4 m / s range; while the speed at which adults actively approach the touch area (such as tapping, patting, or swiping) is often greater than 0.5 m / s. Therefore, this application can set the theoretical speed range of the sensing speed to 0.1 m / s ≤ v ≤ 0.5 m / s. This can be used as a criterion for determining whether a child intends to touch the touch area. If the sensing speed is within the range of 0.1 m / s ≤ v ≤ 0.5 m / s, a "suspected child approaching the touch area" signal can be output.

[0083] In this application embodiment, extensive experimental calibration shows that when a child's forearm approaches the touch area in a natural swinging state, its equivalent diameter is concentrated between 3cm and 6cm, corresponding to a coverage area of ​​approximately 3cm² to 6cm²; while an adult's palm or forearm typically exceeds 6cm when approaching. Therefore, this application can set the theoretical area range of the sensing area to 3cm²-6cm². This can be used as a criterion for determining whether a child intends to touch the area. If the sensing area is within the range of 3cm²-6cm², a "suspected child approaching the touch area" signal can be output.

[0084] In this embodiment of the application, a large amount of statistical data shows that the theoretical weight range for children is 15–45 kilograms.

[0085] It should be noted that the center of gravity distribution of non-human objects on the seat gravity array usually exhibits the following characteristics: single-peak concentration, abnormal position (leaning forward / leaning at an angle / leaning to the side), no physiological micro-movement in static state, extremely low or abnormally high pressure variance, and does not conform to the biomechanical projection model of the human ischium-thigh dual support area.

[0086] Specifically, based on the above, the child recognition unit can analyze the center of gravity distribution on the occupant seat. If the analysis results meet the following conditions: the center of gravity does not exhibit a single-peak extreme concentration, there is no significant positional shift (forward, angular, or lateral), it possesses low-frequency micro-motion characteristics consistent with physiological features, and the pressure variance is within a preset human body fluctuation range (neither extremely low nor abnormally high), interference from rigid objects, piled-up soft objects, and abnormal loads can be eliminated, thus confirming that the object on the occupant seat is a human body. Subsequently, the child recognition unit can obtain internally stored baseline information on children's physiological characteristics, namely, the theoretical speed range, the theoretical area range of the sensing area, and the theoretical weight range corresponding to the child. If the currently measured sensing speed is within the theoretical speed range, the sensing area is within the theoretical area range, and the gravity load is within the theoretical weight range, then the object on the occupant seat is determined to be a child.

[0087] The behavioral intent recognition unit is used to determine whether there is a child's touch intent in the touch area based on the sensing intensity and sensing trajectory after receiving information about a child riding in the vehicle.

[0088] In some embodiments, the behavioral intent recognition unit includes a non-limb object interference recognition subunit and a child behavior interference recognition subunit. The non-limb object interference recognition subunit and the child behavior interference recognition subunit are communicatively connected.

[0089] The non-limb object interference recognition subunit is used to send a target notification message to the child behavior interference recognition subunit when the sensing intensity is within the reference intensity range.

[0090] The reference strength range is the theoretical strength range of the sensing intensity when a human limb approaches the two-dimensional matrix capacitor near-field sensing electrode assembly.

[0091] It should be noted that extensive experiments have shown that when a real limb approaches the touch area, due to the good conductivity of the human body, the near-field electric field energy is significantly absorbed and undergoes concentrated distortion, resulting in a high level of induction intensity in the activated area, generally greater than 0.8 volts per square centimeter (V / cm²). However, when fabric objects flutter (excluding interference from non-limb objects such as clothing and backpack straps), only a weak disturbance to the electric field is caused, resulting in a diffuse distribution of the induction signal with low energy density; its average induction intensity is typically less than 0.5 V / cm². Based on this, a baseline intensity range of greater than 0.8 V / cm² can be used as a criterion for determining the presence of a child's intention to touch the touch area. As shown in the figure, when the induction intensity is greater than 0.8 V / cm², a "suspected child approaching the touch area" signal can be output.

[0092] Among them, the target notification message is used to indicate that the sensing was caused by a human limb, excluding interference from the approach of non-human limbs.

[0093] The child behavior interference identification subunit is used to determine whether there is a child's touch intention in the touch area based on the sensing trajectory and at least one calibrated sensing trajectory after receiving the target notification message.

[0094] Each of the at least one calibration sensing trajectory corresponds to a movement behavior of the human body without conscious touch control.

[0095] In this application, the trajectory of an object's movement sensed by the two-dimensional matrix capacitive near-field sensing electrode assembly when the object approaches the touch area can be represented by changes in the sensing area. Based on this, at least one calibration sensing trajectory can include: 2-1, First Sensing Trajectory In the first sensing trajectory, the sensing area does not move in a fixed direction. That is, when an object approaches the touch area, it has no obvious directionality, and the sensing area "moves randomly," "drifts," or has no clear directional change within the two-dimensional capacitive sensing matrix. For example, specific scenarios represented by the first sensing trajectory include: a hand naturally hanging down and slightly shaking as it approaches the touch area; or a body shaking causing clothing or pocket fabric to accidentally brush against the touch area.

[0096] 2-2, Second Sensing Trajectory In the second sensing trajectory, the positional offset range of the sensing unit in the sensing area is lower than the preset positional offset range, and the capacitance value changes monotonically at a rate lower than the preset capacitance change rate. Specifically, in terms of spatial change, the sensing area remains almost stationary, only "trembling" slightly within a very small range; the sensing trajectory exhibits a slow downward trend. In terms of amplitude change, the capacitance value changes slowly, continuously, and unidirectionally (only increasing or only decreasing). For example, the second sensing trajectory is suitable for scenarios such as adjusting posture or slowly and vertically approaching the touch area with a finger.

[0097] Optionally, the preset position offset range and preset capacitance change rate can be obtained by pre-calibration in the experiment or set according to actual needs. This application does not limit these.

[0098] 2-3, Third Sensing Trajectory In the third sensing trajectory, the sensing area jumps from the first position to the second position. That is, the sensing trajectory sweeps rapidly or jumps, and the sensing area does not continuously migrate between adjacent electrodes, but rather changes in a "disappearance-reappearance" manner. The specific scenario for the third sensing trajectory is accidental contact or rubbing against the touch area by clothing.

[0099] 2-4, Fourth Sensing Trajectory In the fourth sensing trajectory, the dwell time of the sensing signal at each location during the movement of the sensing area is less than the preset dwell time. That is, the sensing area "sweeps" over each location, stays for a very short time, and moves away as soon as it is detected; the dwell time is less than the minimum effective time threshold set by the system, and is considered "too late to process". Specific scenarios for the fourth sensing trajectory include: a finger quickly gliding across the touch area (swiping, brushing), unintentional touch followed by immediate removal, or rubbing against clothing, etc.

[0100] Optionally, the preset residence time is the minimum residence time for processing. The preset residence time can be obtained by pre-calibration in the experiment or set according to actual needs. This application does not limit this.

[0101] 2-5, Fifth Sensor Trajectory The fifth sensing trajectory involves at least two sensing areas, all moving in the same direction and at the same speed. This means multiple independent sensing areas exist simultaneously, moving in the same direction and at the same speed, exhibiting a "synchronous motion" characteristic. Specifically, the fifth sensing trajectory is characterized by the simultaneous detection of objects approaching from the left and right in the same direction at similar speeds, resulting in the perception of a unified movement of the passengers.

[0102] In some embodiments, if the sensing trajectory does not match any of the calibrated sensing trajectories, it is determined whether the vibration interference conditions were met in the past. If the vibration interference conditions were not met in the past, the child behavior interference recognition subunit can determine whether there is a child's touch intention in the touch area based on the vehicle's operating information.

[0103] Among them, the vibration interference condition is that within the first target time period, the presence of a child's intention to touch the touch area is detected multiple times, but no child touch action is performed subsequently; the first target time period is the time period consisting of the current moment and multiple moments before it.

[0104] For example, when the occupant seat is under load (e.g., a weight change detected by a gravity sensor), if the number of approach behaviors detected in the touch area exceeds a preset threshold (e.g., 5 times) within a first target time period (e.g., 10 seconds), and the duration of each approach behavior is less than a first duration threshold (e.g., 0.5 seconds), and the time interval between two adjacent approach behaviors is less than a second duration threshold (e.g., 1 second), but no effective touch action is actually detected, it is determined to be high-frequency vibration interference. In this case, the detection sensitivity of the touch area can be reduced, and the touch area can be put into a "temporary shielding state" (e.g., for 10 seconds). During the shielding period, the touch area does not respond to any sensing signals to avoid continuous misjudgments. After the shielding state ends, the normal working mode is automatically restored, and the touch area is reassessed for the child's touch intention.

[0105] By using the above methods, when the sensing trajectory cannot match the existing calibrated trajectory, the system can more accurately distinguish between a child's true touch intention and non-intent interference such as vibration and accidental touch, by combining the vehicle's operating status and historical behavior characteristics, thereby improving the robustness and user experience of the in-vehicle touch system.

[0106] In some embodiments, the operational information may include the vehicle's lateral acceleration, longitudinal acceleration, and vertical acceleration. Based on this, the child behavior interference recognition subunit can determine that a child intends to touch the touch area if the operational information does not meet preset operational conditions.

[0107] Among them, the preset operating conditions must meet at least one of the following: 3-1. The maximum limiting acceleration threshold for steady-state operation where any one of the lateral, longitudinal, and vertical accelerations exceeds any other acceleration.

[0108] Optionally, the maximum steady-state acceleration threshold for any acceleration can be set according to actual conditions. For example, the maximum steady-state acceleration threshold for each of the lateral, longitudinal, and vertical accelerations can be 0.5g.

[0109] 3-2. The vertical acceleration undergoes alternating positive and negative jumps during the second target time period; the second target time period is the time period consisting of the current moment and multiple moments preceding it.

[0110] It is understandable that the vertical acceleration fluctuates between positive and negative during the second target time period, indicating that the vehicle is currently in a bumpy state, which confirms that there is no intention for a child to touch the touch area.

[0111] In summary, if it is determined that the object on the occupant seat is a child and the sensing is triggered by a human limb, excluding interference from non-human limbs, and the sensing trajectory does not match any of the calibrated sensing trajectories, the vibration interference condition has not been met in the past, and the operating information does not meet the preset operating conditions, it can be determined that there is a child's intention to touch the touch area. Conversely, if the sensing trajectory matches at least one calibrated sensing trajectory, the vibration interference condition has been met in the past, and / or the operating information meets the preset operating conditions, it can be determined that there is no child's intention to touch the touch area.

[0112] Based on the above technical solution, this application integrates two-dimensional matrix capacitive near-field sensing and seat gravity sensing. It utilizes capacitive characteristics (sensing speed, area, intensity, and trajectory) to capture the dielectric properties and motion details of approaching objects, while simultaneously combining gravity load and center of gravity distribution to accurately determine the occupant's size and posture. Addressing the characteristics of children's lighter weight and significant forward shift of their center of gravity when leaning forward to retrieve objects, this application effectively eliminates misjudgments under single-modality conditions such as adult waving, object drops, or simple posture adjustments through multi-physics field feature cross-validation, significantly reducing the misjudgment rate. This solution upgrades the traditional "post-contact response" to "pre-contact prediction," enabling high-confidence identification of children's touch intentions before object contact, blocking the risk of accidental touches at the source. It is suitable for complex multi-occupant scenarios, providing proactive safety protection for in-vehicle touch terminals.

[0113] In one optional embodiment, the touch intent recognition device further includes a processing module; the touch intent recognition module and the processing module are communicatively connected. The processing module is configured to lock the touch area when the touch intent recognition module sends an indication message indicating the presence of a child's touch intent in the touch area. After locking the touch area, the touch area becomes unresponsive to the occupant's touch actions.

[0114] In some embodiments, the processing module can acquire the driver's driving status through sensors (such as cameras, LiDAR, etc.). If the driving status is not one of at least one of the calibrated driving statuses, a child touch permission request can be sent to the vehicle's central control display device to obtain the driver's response to the request. The processing module can then unlock the touch area and manage access based on the response.

[0115] At least one of the calibrated driving states must be a driving state that requires sustained attention. At least one calibrated driving state may include, but is not limited to: lane changing driving state, turning driving state, and driving state where the driver's attention is diverted.

[0116] For example, if the driver's driving state is any of at least one of the calibrated driving states, indicating that the driver is currently in a state that requires high concentration, then a pop-up request for child touch permission on the vehicle's central control display screen may interfere with the driver and affect driving safety, so the pop-up time needs to be delayed; if the driving state is not any of at least one of the calibrated driving states, a child touch permission request can be sent to the vehicle's central control display device to obtain the driver's response to the child touch permission request.

[0117] Among these, children's touch permission requests may include, but are not limited to: permission to use the touch functions of the touch area and permission to use them for a specified period of time.

[0118] For example, when the processing module receives an indication message from the touch intent recognition module indicating that a child intends to touch the touch area, it can immediately cut off the interrupt signal input to the touch chip in that area, achieving hardware-level locking. Simultaneously, a child touch permission request is sent to the central control display device via the vehicle network. This can generate a pop-up prompt on the front central control screen: "A child has been detected approaching the touch area on the left side of the rear seat. Do you wish to temporarily authorize the operation?", or, if the driver grants authorization, a pop-up prompt can appear: "Please confirm the permitted usage duration."

[0119] For example, when the vehicle's central control display screen pops up a child touch permission request interface, the interface can provide at least four interactive options, including but not limited to: "Allow for 5 minutes" (default option), "Valid for this trip", "Allow only volume adjustment", and "Cancel". The pop-up window on the vehicle's central control display screen is time-sensitive; if no confirmation operation is received from the driver within 5 seconds, it will automatically close and maintain the rear seat touch lock state.

[0120] A secondary confirmation mechanism can be set up for permission granting operations. For example, when the driver selects "Allow for 5 minutes" and completes the secondary confirmation (such as clicking confirm again or long-pressing), the authorization time can be recorded and a countdown can be started (the default duration is 5 minutes). During this period, the rear seat touch restrictions are lifted, allowing associated operations. When the countdown ends, the system automatically returns to the rear seat locked state. If the driver does not perform secondary confirmation or make a selection during the pop-up window display period, the permission request is automatically canceled, and the locked state remains in effect.

[0121] Optionally, this application embodiment supports multiple authorization modes to meet the control requirements of different driving scenarios, as follows: 1. Temporary Open Mode (Limited-Time Authorization) This mode is valid for 5 minutes and is suitable for short-term adjustments. The driver can initiate authorization by clicking the corresponding button on the central control screen or by entering a voice command (such as "allow 5 minutes"). Once authorized, the rear touch area will have full access. The system will start a countdown, automatically reverting to the locked state after the countdown reaches zero. Alternatively, the driver can also terminate the authorization within the validity period.

[0122] 2. Itinerary Open Mode (Full-cycle Authorization) This mode remains valid throughout the current driving cycle and is suitable for scenarios requiring multiple operations, such as long-distance travel. The driver authorizes the vehicle by selecting a button on the central control screen or by entering a voice command (such as "This trip is valid"), and the system then grants full touch access. This authorization remains valid from the moment it takes effect until the vehicle is powered off or the doors are locked, at which point it automatically ends. The driver can also manually revoke this authorization during the trip.

[0123] 3. Functional tiered access mode (restricted authorization) This mode only allows volume adjustment permissions and is suitable for specific scenarios such as calming children. The default effective duration is 10 minutes, which the driver can manually terminate early. The system filters touch commands at the software logic layer, intercepting all operation commands except for volume control, thereby achieving fine-grained control over operation permissions.

[0124] The triggering methods for the aforementioned authorization modes are diverse, including but not limited to: the driver directly clicking the virtual button on the central control screen, inputting preset voice commands (such as "Allow rear seat operation", "Authorize for 5 minutes", etc.), or pressing the physical "Confirm" button on the multi-function steering wheel. Rear seat operation behavior is continuously monitored during the authorization period. If abnormal operation is detected, the authorization strategy will be dynamically adjusted. For example, when a forceful click (touch acceleration greater than 2g) or continuous accidental touches (triggered 3 non-target area operations within 5 seconds) are detected, the remaining valid time can be automatically shortened to 1 minute, or the authorization can be terminated directly, balancing convenience and driving safety.

[0125] Based on the above technical solution, during vehicle operation, accidental touch by a child may cause abnormal window operation, extreme changes in air conditioning temperature, or sudden switching of the multimedia interface, severely distracting the driver. Upon receiving an indication that a child intends to touch the device, the processing module directly executes a hardware or underlying software blocking operation to lock the touch area. This mechanism ensures that even if the recognition module has a slight probability error, or if a child forcibly touches the device after it has been locked, the response link for the touch function will be physically severed.

[0126] For ease of understanding, the touch intent recognition method provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0127] like Figure 5 As shown, the touch intent recognition method provided in this application embodiment is applied to the above-mentioned... Figure 4 The touch intent recognition device in the middle, the method includes: S501. Acquire sensing information collected by the two-dimensional matrix capacitor near-field sensing electrode assembly during the object approach time period.

[0128] When an object (such as a passenger's hand) approaches the touch area (or operating area) of the interactive touch terminal, it changes the dielectric distribution of the near-field electric field between the driving electrode and the receiving electrode, causing dielectric disturbances in the mutual capacitance. The two-dimensional matrix capacitive near-field sensing electrode assembly can collect in real-time sensing information as the object gradually approaches the touch area during the approach period. This sensing information includes the sequence of capacitance changes (i.e., the capacitance sensing matrix) of each microcapacitive sensing unit, collected by the two-dimensional matrix capacitive near-field sensing electrode assembly at a preset frame rate during the object's approach period, and the pre-processed sensing signal intensity matrix and active electrode distribution data. Correspondingly, the touch intent recognition device can use the sensing information collected in real-time by the two-dimensional matrix capacitive near-field sensing electrode assembly during the object's approach period. Specific acquisition methods can be found in the description of the above embodiments and will not be repeated here.

[0129] S502. Determine the sensing characteristics corresponding to the sensing information.

[0130] The sensing characteristics include: sensing speed, sensing area, sensing intensity, and sensing trajectory; sensing speed is used to characterize the speed at which an object approaches the touch area; sensing area is used to characterize the coverage area of ​​the sensing region of the two-dimensional matrix capacitor near-field sensing electrode assembly when an object approaches the touch area; the sensing area is the region composed of capacitor units whose capacitance changes; sensing intensity is used to characterize the ratio between the target capacitance value and the coverage area; the target capacitance value is the difference between the maximum and minimum capacitance changes in the sensing area; and the sensing trajectory is used to characterize the trajectory of the object movement sensed by the two-dimensional matrix capacitor near-field sensing electrode assembly when the object approaches the touch area.

[0131] The specific process for determining the sensing speed, sensing area, sensing intensity, and sensing trajectory can be referred to the description in the above embodiments, and will not be repeated here.

[0132] S503. Determine whether a child intends to touch the touch area based on sensing characteristics.

[0133] In some embodiments, the touch intent recognition device can compare the sensing speed, sensing area, sensing intensity, and sensing trajectory with their respective theoretical ranges, and then determine whether a child's touch intent exists in the touch area based on the comparison results. The specific determination process can be referred to the description in the above embodiments, and will not be repeated here.

[0134] Based on the above technical solution, this application captures the sensing information of an object during its "approach period" by embedding a two-dimensional matrix capacitive near-field sensing electrode assembly below the touch area, enabling the recognition process to be initiated before the object actually touches the panel. This early perception mechanism not only shortens the user's subjective perception of operation latency and improves the smoothness of interaction, but also reserves a critical time window for the subsequent execution of safety strategies. Furthermore, it utilizes sensing speed to capture the abrupt and poorly controlled movement characteristics of children; it uses sensing area to perform rapid initial screening based on physiological size differences; it uses sensing intensity (i.e., the ratio of the target capacitance value to the coverage area) to effectively eliminate interference caused by different contact areas, accurately reflecting the dielectric constant characteristics of the object itself, enhancing the ability to distinguish between human bodies (adults vs. children) and non-living objects (such as metal keys and clothing); and it uses sensing trajectory analysis to distinguish between purposeful clicks and unconscious random waving. By using the above-mentioned multi-feature joint decision, the shortcomings of single features being susceptible to noise interference are effectively overcome. Even in complex environments such as vehicle bumps and multiple occupants, the system can achieve high accuracy in recognizing children's touch intentions before the object actually touches the touch area, thereby improving the accuracy of children's touch intention recognition and avoiding driving safety issues caused by unexpected function triggers.

[0135] like Figure 6 As shown in the embodiments of this application, an electronic device includes, but is not limited to, a processor 601 and a memory 602.

[0136] The memory 602 described above is used to store the executable instructions of the processor 601. It is understood that the processor 601 is configured to execute instructions to implement the touch intent recognition method in the above embodiments.

[0137] It should be noted that those skilled in the art will understand that Figure 6 The electronic device structure shown does not constitute a limitation on the electronic device; the electronic device may include, but is not limited to, other electronic devices. Figure 6 This may indicate more or fewer components, or combinations of certain components, or different component arrangements.

[0138] Processor 601 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in memory 602, and by calling data stored in memory 602, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. Processor 601 may include one or more processing units. Optionally, processor 601 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into processor 601.

[0139] The memory 602 can be used to store software programs and various data. The memory 602 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required by at least one functional module (such as a determination unit, processing unit, etc.), etc. Furthermore, the memory 602 may include high-speed random access memory and may also include non-volatile memory. For example, the non-volatile memory may include at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0140] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 602 including instructions, which can be executed by a processor 601 of an electronic device to implement the methods in the above embodiments.

[0141] Optionally, the computer-readable storage medium may be a non-transitory computer-readable storage medium, such as a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0142] In an exemplary embodiment, this application also provides a computer program product including one or more instructions, which can be executed by a processor 601 of an electronic device to perform the methods described above.

[0143] It should be noted that when one or more instructions in the computer-readable storage medium or computer program product are executed by the processor of an electronic device, they implement the various processes of the above method embodiments and achieve the same technical effect as the above method. To avoid repetition, they will not be described again here.

[0144] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0145] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0146] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0147] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0148] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, essentially, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0149] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A touch intent recognition device, wherein the touch intent recognition device is deployed in an interactive touch terminal in a non-driver's seat occupant area of ​​a vehicle, and a two-dimensional matrix capacitive near-field sensing electrode assembly is embedded below the touch area of ​​the interactive touch terminal; characterized in that, The touch intent recognition device includes: a sensing module and a touch intent recognition module; the sensing module and the touch intent recognition module are communicatively connected. The sensing module is used to acquire sensing information collected by the two-dimensional matrix capacitor near-field sensing electrode assembly during the object approach period, and send the sensing information to the touch intent recognition module. The touch intent recognition module is used to determine the sensing features corresponding to the sensing information; and to determine whether a child's touch intent exists in the touch area based on the sensing features; wherein, the sensing features include: sensing speed, sensing area, sensing intensity, and sensing trajectory; the sensing speed is used to characterize the speed at which an object approaches the touch area; the sensing area is used to characterize the coverage area of ​​the sensing region of the two-dimensional matrix capacitor near-field sensing electrode assembly when the object approaches the touch area; the sensing region is a region composed of capacitor units whose capacitance changes; the sensing intensity is used to characterize the ratio between the target capacitance value and the coverage area; the target capacitance value is the difference between the maximum and minimum capacitance changes in the sensing region; and the sensing trajectory is used to characterize the object movement trajectory sensed by the two-dimensional matrix capacitor near-field sensing electrode assembly when the object approaches the touch area.

2. The touch intent recognition device according to claim 1, characterized in that, The sensing module is also used to acquire gravity sensing information from the gravity sensor array below the occupant seat bound to the interactive touch terminal; and send the gravity sensing information to the touch intent recognition module. The touch intent recognition module is also used to determine the gravity load and center of gravity distribution of the occupant seat based on the gravity sensing information; and to determine whether there is a child's touch intent in the touch area based on the sensing features, the gravity load, and the center of gravity distribution.

3. The touch intent recognition device according to claim 2, characterized in that, The touch intent recognition module includes: a child recognition unit and a behavior intent recognition unit; the child recognition unit and the behavior intent recognition unit are communicatively connected. The child identification unit is used to determine whether the object mounted on the passenger seat is a human body based on the center of gravity distribution; if the object mounted on the passenger seat is a human body, it determines whether the object mounted on the passenger seat is a child based on the sensing speed, the sensing area, and the gravity load; if the object mounted on the passenger seat is a child, it sends the child's riding information to the behavior intention recognition unit. The behavior intention recognition unit is used to determine whether there is a child's touch intention in the touch area based on the sensing intensity and the sensing trajectory after receiving the child's riding information.

4. The touch intent recognition device according to claim 3, characterized in that, The child identification unit is specifically used for: Obtain baseline information on children's physiological characteristics; wherein, the baseline information on children's physiological characteristics includes: first baseline information and second baseline information; the first baseline information is used to characterize the theoretical velocity range of the sensing speed and the theoretical area range of the sensing area when the child approaches the two-dimensional matrix capacitor near-field sensing electrode assembly; the second baseline information is used to characterize the child's theoretical weight range; If the sensing speed is within the theoretical speed range, the sensing area is within the theoretical area range, and the gravity load is within the theoretical weight range, then the object mounted on the occupant seat is determined to be a child.

5. The touch intent recognition device according to claim 3, characterized in that, The behavioral intent recognition unit includes: a non-limb object interference recognition subunit and a child behavior interference recognition subunit; the non-limb object interference recognition subunit and the child behavior interference recognition subunit are communicatively connected. The non-limb object interference identification subunit is used to send a target notification message to the child behavior interference identification subunit when the sensing intensity is within the reference intensity range; wherein, the reference intensity range is the theoretical intensity range of the sensing intensity when a human limb approaches the two-dimensional matrix capacitor near-field sensing electrode assembly; the target notification message is used to indicate that the sensing is caused by a human limb, excluding interference from the approach of non-human limbs. The child behavior interference identification subunit is used to determine whether there is a child's touch intention in the touch area based on the sensing trajectory and at least one calibrated sensing trajectory after receiving the target notification message; wherein, each of the at least one calibrated sensing trajectories corresponds to a movement behavior of a human without touch consciousness.

6. The touch intent recognition device according to claim 5, characterized in that, The child behavior interference identification subunit is specifically used for: If the sensing trajectory does not match any of the calibrated sensing trajectories, it is determined whether the vibration interference condition was met in the past; wherein, the vibration interference condition is that within a first target time period, multiple instances of a child's intention to touch the touch area were detected, but no subsequent child touch action was performed; the first target time period is a time period consisting of the current moment and multiple moments preceding it; In cases where the vibration interference conditions are not met in the past, the presence of a child's intention to touch the touch area is determined based on the vehicle's operating information.

7. The touch intent recognition device according to claim 5, characterized in that, The trajectory of the object's movement is represented by changes in the sensing area; The at least one calibration sensing trajectory includes: a first sensing trajectory, wherein the sensing area under the first sensing trajectory does not move in a fixed direction; Second sensing trajectory: wherein, the position offset range of the sensing unit in the sensing area under the second sensing trajectory is lower than the preset position offset range, and the capacitance value changes monotonically at a rate lower than the preset capacitance change rate; Third sensing trajectory: wherein the sensing area jumps from the first position to the second position under the third sensing trajectory; Fourth sensing trajectory: wherein, the dwell time of the sensing signal at each position during the movement of the sensing area under the fourth sensing trajectory is less than a preset dwell time; the preset dwell time is the minimum dwell time for processing; Fifth sensing trajectory: wherein the number of sensing areas under the fifth sensing trajectory is at least 2, and the sensing areas all move with the same direction and speed of travel.

8. The touch intent recognition device according to claim 6, characterized in that, The operational information includes the vehicle's lateral acceleration, longitudinal acceleration, and vertical acceleration; the child behavior interference identification subunit is specifically used for: If the operating information does not meet the preset operating conditions, it is determined that the touch area has a child's touch intention; The preset operating conditions must satisfy at least one of the following: If any one of the lateral acceleration, the longitudinal acceleration, and the vertical acceleration exceeds the steady-state maximum limiting acceleration threshold of the aforementioned acceleration; The vertical acceleration undergoes alternating positive and negative jumps during the second target time period; the second target time period is the time period consisting of the current moment and multiple moments preceding it.

9. The touch intent recognition device according to any one of claims 1-8, characterized in that, The touch intent recognition device further includes: a processing module; the touch intent recognition module and the processing module are communicatively connected; The processing module is used to lock the touch area when the touch intention recognition module sends an indication message indicating that the touch area has a child's touch intention; wherein, after the touch area is locked, the touch area does not respond to touch actions.

10. The touch intent recognition device according to claim 9, characterized in that, The processing module is also used for: Obtain the driving status of the driver of the vehicle; If the driving state is not any of the at least one calibrated driving state, a child touch permission request is sent to the vehicle's central control display device to obtain the driver's response to the child touch permission request; The at least one calibrated driving state is a driving state that requires maintaining attention; Based on the response result, the touch area is unlocked and access is controlled.

11. A method for recognizing touch intent, characterized in that, The touch intent recognition method, applied to any one of claims 1-10, comprises: The sensing information collected by the two-dimensional matrix capacitor near-field sensing electrode assembly during the object approach period is obtained; Determine the sensing characteristics corresponding to the sensing information; The presence of a child's touch intent in the touch area is determined based on the sensing characteristics; wherein, the sensing characteristics include: sensing speed, sensing area, sensing intensity, and sensing trajectory; the sensing speed is used to characterize the speed at which an object approaches the touch area; the sensing area is used to characterize the coverage area of ​​the sensing region of the two-dimensional matrix capacitor near-field sensing electrode assembly when the object approaches the touch area; the sensing region is a region composed of capacitor units whose capacitance changes; the sensing intensity is used to characterize the ratio between the target capacitance value and the coverage area; the target capacitance value is the difference between the maximum and minimum capacitance changes in the sensing region; the sensing trajectory is used to characterize the object movement trajectory sensed by the two-dimensional matrix capacitor near-field sensing electrode assembly when the object approaches the touch area.

12. A vehicle, characterized in that, The vehicle includes a touch intent recognition device as described in any one of claims 1-10.

Images