Child forgetting reminding method and device in vehicle, vehicle and storage medium

Abstract

The application relates to the technical field of vehicles, in particular to a child forgetting reminding method and device in a vehicle, a vehicle and a storage medium, wherein the method comprises the following steps: acquiring vital sign data, visual image data, pressure distribution data and vehicle state data of the vehicle; respectively calculating corresponding confidence degrees based on the vital sign data, the visual image data and the pressure distribution data; determining a monitoring mode of the vehicle based on the vehicle state data, and determining a fusion weight of the confidence degrees according to the monitoring mode and the temperature in the vehicle; calculating a comprehensive risk value based on the confidence degrees and the corresponding fusion weight; and executing corresponding grading response actions according to the comprehensive risk value. Thus, the problems of related technologies, such as high false alarm and missed alarm rates and lack of effective active intervention, are solved; the fusion weight of the multiple sensors and the monitoring mode are dynamically adjusted according to the vehicle state, so that a closed-loop child forgetting reminding from "passive alarm" to "active intervention" is realized.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, device, vehicle, and storage medium for reminding children to remember their whereabouts in a vehicle. Background Technology

[0002] With the increasing intelligence of automobiles, safety accidents caused by children being accidentally left in vehicles have become a major concern.

[0003] In related technologies, visual sensors or simple multi-sensor fusion solutions are mainly used to remind children to remember things they don't want to remember.

[0004] However, the above methods have the following technical defects: (1) When using ultrasonic or infrared sensors to detect the movement of objects or heat in the vehicle, the detection sensitivity drops sharply when the child is asleep or the ambient temperature is close to body temperature, which poses a serious risk of missed detection; the solution using visual sensors uses cameras to detect movement or human contour recognition, but its weakness is that it is greatly affected by lighting conditions and is prone to failure when the child is covered by blankets or other items; (2) The simple fusion of multiple sensors will result in rigid fusion logic, single intervention methods, and inability to accurately determine the starting moment of the key risk scenario of "the driver has left the vehicle and locked the vehicle", which urgently needs to be solved. Summary of the Invention

[0005] This application provides a method, device, vehicle, and storage medium for reminding children to stay in a vehicle, in order to solve the problems of related technologies such as reliance on a single sensor, high false alarm and false alarm rates, and lack of effective active intervention.

[0006] The first aspect of this application provides a method for reminding passengers to avoid forgetting their children in a vehicle, including the following steps: Acquire vehicle vital signs data, visual image data, pressure distribution data, and vehicle status data; Calculate the corresponding confidence levels based on the vital signs data, the visual image data, and the pressure distribution data, respectively. The monitoring mode of the vehicle is determined based on the vehicle status data, and the fusion weight of the confidence level is determined according to the monitoring mode and the vehicle interior temperature. A comprehensive risk value is calculated based on the confidence level and the corresponding fusion weight, and a corresponding graded response action is executed according to the comprehensive risk value.

[0007] According to one embodiment of this application, the step of calculating the corresponding confidence levels based on the vital sign data, the visual image data, and the stress distribution data includes: Extract quantitative indicators from the vital signs data, and obtain the confidence level of the vital signs data based on the quantitative indicators; Identify target features in the visual image data, and obtain the confidence level of the visual image data based on the target features; The spatial features of the pressure distribution data are extracted and matched with a preset child sitting posture pressure distribution template to obtain the confidence level of the pressure distribution data.

[0008] According to one embodiment of this application, determining the vehicle monitoring mode based on the vehicle status data includes: When the vehicle is powered off and all the vehicle doors are locked, the monitoring mode of the vehicle is determined to be the standard monitoring mode. When the vehicle interior temperature exceeds a preset temperature threshold under the standard monitoring mode, the monitoring mode is determined to be a high-risk enhanced mode. When the vehicle is powered off and at least one door is unlocked or at least one window is open, the monitoring mode is determined to be a low-power standby mode.

[0009] According to one embodiment of this application, the calculation of the comprehensive risk value based on the confidence level and the corresponding fusion weight includes: Calculate the first product of the confidence level of the vital signs data and the corresponding fusion weight, the second product of the confidence level of the visual image data and the corresponding fusion weight, and the third product of the confidence level of the stress distribution data and the corresponding fusion weight; The comprehensive risk value is calculated based on the first product, the second product, the third product, and a preset fusion function.

[0010] According to one embodiment of this application, the step of executing a corresponding graded response action based on the comprehensive risk value includes: If the comprehensive risk value is greater than the first threshold and less than or equal to the second threshold, the vehicle's graded response is determined to be a primary response, and a first-level early warning is issued based on the primary response. If the overall risk value is greater than the second threshold and less than or equal to the third threshold, and no response action of the user is detected within a preset time, then the vehicle's graded response is determined to be a medium response, and a second-level warning reminder is issued based on the medium response. If the overall risk value is greater than the third threshold and the vehicle interior temperature is greater than the preset temperature threshold, then the vehicle's graded response is determined to be a high-level response, and a level-three warning reminder is issued based on the high-level response, wherein the third threshold is greater than the second threshold, and the second threshold is greater than the first threshold.

[0011] The child forgetfulness reminder method in a vehicle according to embodiments of this application acquires vital sign data, visual image data, pressure distribution data, and vehicle status data of the vehicle; calculates corresponding confidence levels based on the vital sign data, visual image data, and pressure distribution data respectively; determines the vehicle's monitoring mode based on the vehicle status data, and determines the fusion weight of the confidence level according to the monitoring mode and the vehicle's interior temperature; calculates a comprehensive risk value based on the confidence level and the corresponding fusion weight, and executes corresponding graded response actions according to the comprehensive risk value. This solves the problems of related technologies relying on a single sensor, high false alarm and false negative rates, and lack of effective proactive intervention. By dynamically adjusting the fusion weight and monitoring mode of multiple sensors based on vehicle status perception, a closed-loop child forgetfulness reminder system is achieved, moving from "passive alarm" to "proactive intervention."

[0012] A second aspect of this application provides a child forgetfulness reminder device for use in a vehicle, comprising: The acquisition module is used to acquire vehicle vital signs data, visual image data, pressure distribution data, and vehicle status data; The calculation module is used to calculate the corresponding confidence levels based on the vital sign data, the visual image data, and the pressure distribution data, respectively. The execution module is used to determine the monitoring mode of the vehicle based on the vehicle status data, determine the fusion weight of the confidence level according to the monitoring mode and the vehicle interior temperature, calculate the comprehensive risk value based on the confidence level and the corresponding fusion weight, and execute the corresponding graded response action according to the comprehensive risk value.

[0013] According to one embodiment of this application, the computing module includes: Extract quantitative indicators from the vital signs data, and obtain the confidence level of the vital signs data based on the quantitative indicators; Identify target features in the visual image data, and obtain the confidence level of the visual image data based on the target features; The spatial features of the pressure distribution data are extracted and matched with a preset child sitting posture pressure distribution template to obtain the confidence level of the pressure distribution data.

[0014] According to one embodiment of this application, the execution module includes: When the vehicle is powered off and all the vehicle doors are locked, the monitoring mode of the vehicle is determined to be the standard monitoring mode. When the vehicle interior temperature exceeds a preset temperature threshold under the standard monitoring mode, the monitoring mode is determined to be a high-risk enhanced mode. When the vehicle is powered off and at least one door is unlocked or at least one window is open, the monitoring mode is determined to be a low-power standby mode.

[0015] According to one embodiment of this application, the execution module includes: Calculate the first product of the confidence level of the vital signs data and the corresponding fusion weight, the second product of the confidence level of the visual image data and the corresponding fusion weight, and the third product of the confidence level of the stress distribution data and the corresponding fusion weight; The comprehensive risk value is calculated based on the first product, the second product, the third product, and a preset fusion function.

[0016] According to one embodiment of this application, the execution module includes: If the comprehensive risk value is greater than the first threshold and less than or equal to the second threshold, the vehicle's graded response is determined to be a primary response, and a first-level early warning is issued based on the primary response. If the overall risk value is greater than the second threshold and less than or equal to the third threshold, and no response action of the user is detected within a preset time, then the vehicle's graded response is determined to be a medium response, and a second-level warning reminder is issued based on the medium response. If the overall risk value is greater than the third threshold and the vehicle interior temperature is greater than the preset temperature threshold, then the vehicle's graded response is determined to be a high-level response, and a level-three warning reminder is issued based on the high-level response, wherein the third threshold is greater than the second threshold, and the second threshold is greater than the first threshold.

[0017] According to the vehicle-mounted child forgetfulness reminder device of this application embodiment, it acquires vital sign data, visual image data, pressure distribution data, and vehicle status data of the vehicle; calculates the corresponding confidence levels based on the vital sign data, visual image data, and pressure distribution data respectively; determines the vehicle's monitoring mode based on the vehicle status data, and determines the fusion weight of the confidence level according to the monitoring mode and the vehicle's interior temperature; calculates a comprehensive risk value based on the confidence level and the corresponding fusion weight; and executes a corresponding graded response action according to the comprehensive risk value. This solves the problems of related technologies such as reliance on a single sensor, high false alarm and false negative rates, and lack of effective proactive intervention. By dynamically adjusting the fusion weights and monitoring modes of multiple sensors based on vehicle status perception, it achieves a closed-loop child forgetfulness reminder system, moving from "passive alarm" to "proactive intervention."

[0018] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the child forgetting reminder method in the vehicle as described in the above embodiments.

[0019] A fourth aspect of this application provides a computer-readable storage medium storing computer instructions for causing the computer to perform the child forgetting reminder method in a vehicle as described in the above embodiments.

[0020] A fifth aspect of this application provides a computer program product, including a computer program that is executed to implement the child forgetting reminder method in a vehicle described in the above embodiments.

[0021] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0022] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart illustrating a method for reminding children to stay in a vehicle according to an embodiment of this application; Figure 2 This is a block diagram of a child forgetfulness reminder device in a vehicle according to an embodiment of this application; Figure 3 This is a system architecture diagram according to an embodiment of the present application; Figure 4 This is an overall flowchart according to one embodiment of the present application; Figure 5 This is a structural schematic diagram of a vehicle according to an embodiment of this application. Detailed Implementation

[0023] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0024] The following description, with reference to the accompanying drawings, outlines a method, device, vehicle, and storage medium for reminding children to remember their place in a vehicle, representing embodiments of this application. Addressing the problems mentioned in the background art, such as reliance on a single sensor, high false alarm / missed alarm rates, and lack of effective proactive intervention, this application provides a method for reminding children to remember their place in a vehicle. This method acquires vital sign data, visual image data, pressure distribution data, and vehicle status data. It calculates corresponding confidence levels based on the vital sign data, visual image data, and pressure distribution data. It determines the vehicle's monitoring mode based on the vehicle status data, determines the fusion weight of the confidence level based on the monitoring mode and the vehicle's interior temperature, calculates a comprehensive risk value based on the confidence level and the corresponding fusion weight, and executes a corresponding tiered response action based on the comprehensive risk value. This solves the problems of reliance on a single sensor, high false alarm / missed alarm rates, and lack of effective proactive intervention in related technologies. By dynamically adjusting the fusion weights and monitoring modes of multiple sensors based on the perception of the vehicle status, a closed-loop child forgetfulness reminder system is achieved, moving from "passive alarm" to "proactive intervention."

[0025] Specifically, Figure 1 This is a flowchart illustrating a method for reminding children to stay in a vehicle, as provided in an embodiment of this application.

[0026] like Figure 1 As shown, the child forgetfulness reminder method in this vehicle includes the following steps: In step S101, the vehicle's vital signs data, visual image data, pressure distribution data, and vehicle status data are acquired.

[0027] Specifically, such as Figure 2As shown, when the vehicle is powered off, the multi-source sensing module is activated to collect data and acquire multi-dimensional sensor data of the vehicle. This multi-source sensing module includes a millimeter-wave radar unit, a visual camera unit, a seat pressure sensing unit, and a temperature sensor unit located within the vehicle cabin. The multi-dimensional sensor data mainly includes vital sign data, visual image data, pressure distribution data, and vehicle status data. Vital sign data is collected by the millimeter-wave radar unit located in the roof lining (facing the passenger area). Based on the frequency difference between the millimeter-wave radar's transmitted and echo signals, the distance to a living being (e.g., a child) and chest cavity micro-movement information are calculated. Time-frequency analysis of the echo signals is performed to extract the child's respiratory rate and heart rate. Features: Visual image data is collected by a visual camera unit (e.g., a camera) located near the rearview mirror in the vehicle cabin. This camera continuously collects visual image data inside the vehicle, mainly including the user's facial information, body posture, and image information of children-related items; Pressure distribution data is collected by a seat pressure sensing unit (e.g., a pressure sensor array) integrated under the seat foam, and the pressure value of each seat area is detected by the pressure sensor array to form a pressure distribution map, which reflects the user's sitting posture pattern; Vehicle status data is obtained by the body controller network, which includes, but is not limited to, door lock status, window status, vehicle power mode, in-vehicle ambient temperature, and vehicle GPS (Global Positioning System) location information.

[0028] In step S102, the confidence levels are calculated based on the vital signs data, visual image data, and pressure distribution data, respectively.

[0029] According to one embodiment of this application, the confidence scores are calculated based on vital sign data, visual image data, and pressure distribution data, respectively, including: extracting quantitative indicators of vital sign data and obtaining the confidence scores of vital sign data based on the quantitative indicators; identifying target features in visual image data and obtaining the confidence scores of visual image data based on the target features; extracting spatial features of pressure distribution data and matching the spatial features with a preset child sitting posture pressure distribution template to obtain the confidence scores of pressure distribution data.

[0030] Specifically, such as Figure 3As shown, this application extracts quantitative indicators for vital sign data. These quantitative indicators are the respiratory rate and heart rate features extracted after time-frequency analysis of the echo signals collected by millimeter-wave radar. Then, based on the periodicity, amplitude stability, and deviation of the respiratory rate and heart rate features from the normal physiological parameter range, the confidence level of the vital sign data, namely the confidence level of life C_life, is obtained. When the respiratory rate and heart rate features exhibit stable periodic fluctuations and the amplitude is within the preset physiological range, the confidence level of life C_life approaches 1. When the respiratory rate and heart rate features are weak or have no obvious periodicity, the confidence level of life C_life approaches 0.

[0031] Furthermore, this application identifies target features in visual image data using a camera, namely, identifying the user's facial information, body contours, and features of child-related items in the visual image data. Then, based on the recognition probability output by the target detection algorithm, and combined with the matching degree between the morphological features of the detected target and the preset child sample features, the confidence level of the visual image data is calculated, namely the visual recognition confidence level C_vision. When clear facial features are detected and the morphological parameters conform to the ergonomic size range of children, the visual recognition confidence level C_vision approaches 1. When there is insufficient light, the target is occluded, or no child features are detected, the visual recognition confidence level C_vision approaches 0.

[0032] Furthermore, this application extracts spatial features from the pressure distribution data using a pressure sensor array. These spatial features mainly include the pressure distribution profile, center of gravity position, pressure gradient, and pressure-bearing area. Then, the spatial features are matched with a preset child sitting posture pressure distribution template. The confidence level of the pressure distribution data, i.e., the pressure pattern confidence level C_pressure, is calculated based on the matching degree. When the geometric similarity between the pressure distribution profile and the preset child sitting posture pressure distribution template exceeds a preset threshold, the pressure pattern confidence level C_pressure approaches 1. When the pressure distribution presents a large area of ​​discrete points or is closer to the adult sitting posture template, the pressure pattern confidence level C_pressure approaches 0.

[0033] In step S103, the vehicle monitoring mode is determined based on the vehicle status data, and the fusion weight of the confidence level is determined according to the monitoring mode and the vehicle interior temperature. The comprehensive risk value is calculated based on the confidence level and the corresponding fusion weight, and the corresponding graded response action is executed according to the comprehensive risk value.

[0034] According to one embodiment of this application, determining the vehicle monitoring mode based on vehicle status data includes: determining the vehicle monitoring mode as a standard monitoring mode when the vehicle is powered off and all vehicle doors are locked; determining the monitoring mode as a high-risk enhanced mode when the vehicle interior temperature is greater than a preset temperature threshold under the standard monitoring mode; and determining the monitoring mode as a low-power standby mode when the vehicle is powered off and at least one door is unlocked or at least one window is open.

[0035] The preset temperature threshold can be set based on the critical point of life safety of the living organism, the physiological characteristics of children, the comfort of the living organism, and the rate of deterioration of the thermal environment, without specific limitations.

[0036] Specifically, the monitoring modes of this application include at least a low-power standby mode, a standard monitoring mode, and a high-risk enhanced mode, with the switching between modes driven by vehicle status data and vehicle interior temperature.

[0037] Specifically, when the system detects that the vehicle is powered off and at least one door is unlocked or at least one window is open, it indicates that the user may only be leaving the vehicle briefly, such as to retrieve an item or refuel, and there is no risk of a child being locked in a closed vehicle. At this time, the system enters a low-power standby mode, which operates by reducing the sensor sampling frequency and calculation frequency, maintaining only basic vital signs monitoring capabilities, reducing battery power consumption and avoiding frequent alarms to the vehicle owner.

[0038] Furthermore, when the system detects that the vehicle is powered off and all doors are locked, it indicates that the driver has left the vehicle and locked it, and a risk scenario has been formed where a child has been forgotten in the enclosed vehicle. At this time, the system enters the standard monitoring mode and activates the complete multi-sensor fusion algorithm at the normal sampling and calculation frequency to begin continuous and comprehensive monitoring of vital signs and risk assessment inside the vehicle.

[0039] Furthermore, when the system detects the ambient temperature inside the vehicle using the temperature sensor unit in standard monitoring mode, if the ambient temperature exceeds the preset temperature threshold, it indicates that the thermal environment inside the vehicle is rapidly deteriorating, and children face an imminent risk of heatstroke. At this point, the system automatically switches the monitoring mode from standard monitoring mode to high-risk enhanced mode to increase the sensor sampling frequency and confidence calculation frequency, reduce the alarm threshold of the comprehensive risk value, and enhance the monitoring of vital signs inside the vehicle with a more sensitive detection approach, ensuring that early warning and intervention are triggered in the early stages of environmental deterioration.

[0040] According to one embodiment of this application, the comprehensive risk value is calculated based on the confidence level and the corresponding fusion weight, including: calculating the first product of the confidence level of vital sign data and the corresponding fusion weight, the second product of the confidence level of visual image data and the corresponding fusion weight, and the third product of the confidence level of stress distribution data and the corresponding fusion weight; and calculating the comprehensive risk value based on the first product, the second product, the third product, and a preset fusion function.

[0041] The purpose of the preset fusion function is to map the three-dimensional confidence scores C_life, C_vision, and C_pressure with the dynamic weights W1, W2, and W3 into a comprehensive risk value R. This R value should be able to objectively, accurately, and in real time reflect the degree of risk of a child being forgotten in the car.

[0042] Specifically, based on the monitoring mode and the vehicle interior temperature, the fusion weights W1, W2, and W3 are determined for the confidence level of life presence C_life, the confidence level of visual recognition C_vision, and the confidence level of pressure mode C_pressure. That is, the fusion weight of the confidence level of life presence C_life is W1, the fusion weight of the confidence level of visual recognition C_vision is W2, and the fusion weight of the confidence level of pressure mode C_pressure is W3. The basic allocation ratio of each fusion weight is determined based on the current monitoring mode, and then dynamically adjusted according to the vehicle interior temperature. Each weight satisfies the normalization constraint W1+W2+W3=1.

[0043] Specifically, when the monitoring mode is the standard monitoring mode, its basic allocation ratio is the preset initial weight combination; when the monitoring mode is the high-risk enhanced mode, the fusion weight W1 of the confidence level of life presence C_life is increased, and the fusion weight W2 of the confidence level of visual recognition C_vision is decreased accordingly, so as to strengthen the dominant role of vital signs evidence in risk assessment; when the monitoring mode is the low-power standby mode, only the fusion weight W1 corresponding to the confidence level of life presence C_life is kept to be non-zero, while the fusion weight W2 of the confidence level of visual recognition C_vision and the fusion weight W3 of the confidence level of pressure mode C_pressure are both zero, so as to achieve low-power operation.

[0044] It should be noted that, under any monitoring mode, when the temperature inside the vehicle rises, the fusion weight W1 of the confidence level of life C_life is dynamically increased to enhance the sensitivity to vital signs signals under high temperature conditions.

[0045] Furthermore, the comprehensive risk value is calculated based on the confidence level and the corresponding fusion weights. That is, the comprehensive risk value R is calculated by weighted summation of the normalized fusion weights W1, W2, W3 and the corresponding confidence levels C_life, C_vision, C_pressure, and the expression is as follows: R=F(W1·C_life,W2·C_vision,W3·C_pressure)=W1·C_life+W2·C_vision+W3·C_pressure; Wherein F is a fusion function, and the comprehensive risk value R is a continuous value in the range of 0 to 1, which characterizes the comprehensive risk level faced by the child in the vehicle. A higher R value indicates a higher risk, and is used for comparison with a plurality of preset risk thresholds to trigger corresponding graded response actions.

[0046] According to an embodiment of the present application, executing the corresponding graded response action according to the comprehensive risk value includes: if the comprehensive risk value is greater than a first threshold and less than or equal to a second threshold, determining that the graded response of the vehicle is a primary response, and performing a first-level warning reminder based on the primary response; if the comprehensive risk value is greater than the second threshold and less than or equal to a third threshold, and no user response action is detected within a preset time period, determining that the graded response of the vehicle is an intermediate response, and performing a second-level warning reminder based on the intermediate response; if the comprehensive risk value is greater than the third threshold and the temperature inside the vehicle is greater than a preset temperature threshold, determining that the graded response of the vehicle is an advanced response, and performing a third-level warning reminder based on the advanced response, wherein the third threshold is greater than the second threshold, and the second threshold is greater than the first threshold.

[0047] Wherein the preset time period, the first threshold, the second threshold, and the third threshold may all be set based on the life safety critical point of the living body, the physiological characteristics of children, the comfort level of the living body, and the deterioration speed of the thermal environment, which are not specifically limited herein.

[0048] Specifically, the present application further includes a graded execution module, which comprises a local warning unit, configured to control the vehicle horn, lights, and central control screen for display; a remote communication unit, configured to communicate with the mobile terminal and the cloud platform through the vehicle-mounted T-BOX (Telematics BOX, vehicle-mounted telematics terminal); and a vehicle body control interface unit, configured to control actuators such as an air conditioning system and vehicle windows under a decision instruction.

[0049] Specifically, in the embodiment of the present application, the comprehensive risk value R calculated above is compared with a first threshold T1, a second threshold T2 and a third threshold T3 respectively, where T1<T2<T3, and the comprehensive risk value R determines the corresponding response level according to the threshold interval it falls in. The response levels are a primary response, an intermediate response and an advanced response in ascending order, and each level of response constitutes a progressive safety closed loop of "on-site warning - active intervention - external rescue".

[0050] Specifically, when the comprehensive risk value is greater than the first threshold T1 and less than or equal to the second threshold T2, that is, T1<R≤T2, it is determined that there is a risk of a child being left unattended in the vehicle but the situation has not reached an emergency level, and a primary response is triggered. For example, the hazard warning lights of the vehicle are controlled to flash at a specific frequency and the horn is sounded briefly to attract the attention of pedestrians around the vehicle. Meanwhile, a first-level warning reminder is pushed to the bound vehicle owner's mobile terminal APP (Application, mobile application program) through the vehicle-mounted T-BOX. The content of the reminder may include information such as a risk prompt, the vehicle position and current in-vehicle environment parameters. If the user confirms receipt of the notification through the APP within a preset time, the system continues monitoring without escalating the response. If the user confirms that they will return to the vehicle, the system suspends subsequent escalation.

[0051] Further, when the comprehensive risk value is greater than the second threshold T2 and less than or equal to the third threshold T3, that is, T2<R≤T3, it is determined that the risk level has risen, and the system starts a user response monitoring timer to detect whether a user's response action is detected within a preset time. The user's response actions include but are not limited to: confirmation feedback or cancellation instruction on the mobile terminal APP side, door opening signal, and vehicle power-on signal. If no user response action is detected within the preset time, it can be determined that the user cannot respond in time. At this time, an intermediate response is automatically executed. For example, through the vehicle body control interface, under the safe condition that the vehicle transmission is confirmed to be in the parking gear and the power battery or engine state permits, the vehicle air conditioning system is started and switched to the fresh air ventilation mode to reduce the in-vehicle temperature and supplement fresh air, so as to delay the deterioration of the environment; meanwhile, a second-level warning reminder carrying an emergency identifier is sent to a preset emergency contact, wherein the second-level warning reminder at least includes information such as the risk level, vehicle position and in-vehicle ambient temperature.

[0052] Further, when the comprehensive risk value is greater than the third threshold T3, that is, R>T3, it is determined that the child in the vehicle is facing an imminent threat to life safety. The system further determines whether the in-vehicle ambient temperature is greater than a preset temperature threshold. If the in-vehicle ambient temperature is greater than the preset temperature threshold, there is no need to wait for the user's response, and an advanced response is immediately executed under the condition of the user's pre-authorization. For example, the vehicle-mounted T-BOX automatically sends a help request to a preset emergency rescue platform, wherein the help request at least includes information such as the vehicle VIN code, real-time GPS coordinates, risk level, in-vehicle ambient temperature and summary of key sensor data, and a voice call is automatically initiated to connect to an emergency rescue agent; after the advanced response is triggered, the system continuously monitors the in-vehicle state, and if a signal of door opening or the child being removed is detected, the advanced response is automatically terminated and the system is reset.

[0053] It should be noted that during the execution of responses at all levels, the system maintains a continuous monitoring state. If the risk level drops below the trigger threshold of the current response level, the current response action is automatically downgraded or terminated to avoid excessive intervention.

[0054] Specifically, to facilitate a better understanding of this application by those skilled in the art, a specific embodiment will be described below: Taking a parking scenario under direct sunlight in summer as an example, after the vehicle is turned off, the system confirms through the vehicle status gateway that all doors are locked, and then enters the standard monitoring mode to start continuous monitoring of the vehicle's interior environment.

[0055] First, data acquisition and confidence calculation are performed: The system activates the multi-source perception module to acquire data. The millimeter-wave radar unit detects weak breathing and heartbeat signals in the rear seats of the vehicle. The signals exhibit stable periodic characteristics. After time-frequency analysis, the confidence of life presence is calculated as C_life=0.7. At the same time, the camera simultaneously acquires visual image data from the rear seats. Due to the dim lighting in the rear seats and the fact that the child's body is partially covered by a blanket, the confidence of facial feature recognition is low. However, the image recognition algorithm identifies related items such as the child's water cup from the image. After comprehensive judgment, the confidence of visual recognition is calculated as C_vision=0.4. Meanwhile, the pressure sensor array built into the seat detects a typical child sitting posture pressure distribution pattern in the left rear seat area, i.e., the pressure concentration area is small, the overall weight distribution is uniform, and the center of gravity is low. After matching with the preset child sitting posture pressure distribution template, the confidence of the pressure pattern is calculated as C_pressure=0.9.

[0056] Secondly, context-aware fusion decision-making is performed: the system obtains the current vehicle interior temperature as 38℃ through the temperature sensor, and combines this with the outside temperature of 35℃ obtained from the vehicle status gateway. It determines that the vehicle interior temperature is in a rapid rising phase. In high-temperature environments, the reliability of vital signs evidence is highest. Therefore, the system increases the fusion weight W1 of the life presence confidence C_life to 0.6, sets the fusion weight W2 of the child visual recognition confidence C_vision to 0.2, and increases the fusion weight of the pressure mode confidence C_pressure... With weight W3 set to 0.2 and the sum of all weights normalized to 1, based on the above dynamic weight allocation, the system calculates the comprehensive risk value R = 0.6 × 0.7 + 0.2 × 0.4 + 0.2 × 0.9 = 0.42 + 0.08 + 0.18 = 0.74 using a weighted summation method. This comprehensive risk value R is in the range of 0 to 1, with a higher value indicating a greater risk. After comparison with the preset multi-level risk thresholds, R = 0.74 exceeds the first threshold of 0.5 and the second threshold of 0.7, and it is determined that the current risk level has reached the trigger condition for a medium-level response.

[0057] Finally, the tiered warning response: The system immediately triggers a primary response, such as controlling the vehicle's hazard lights to flash at a specific frequency and briefly sounding the horn once to attract the attention of pedestrians around the vehicle. Simultaneously, a Level 1 warning notification is pushed to the owner's linked mobile app via the in-vehicle T-BOX. The notification includes a risk warning "A child detected inside the vehicle" and the current interior temperature. The system then starts a user response monitoring timer, continuously monitoring for any user response actions within a preset 2-minute period. These actions include the user confirming receipt of the notification via the app, sending a command to cancel the alarm via the app, or a door opening signal. If no such response action is detected within 2 minutes, the system determines that the user has failed to respond in a timely manner. The system automatically upgrades to a medium response level. At this point, the interior temperature has further risen to 40°C. The system first confirms through the body controller that the vehicle's transmission is in park and that the battery charge / engine status allows the air conditioning to be started. Then, under safe conditions, the system automatically starts the air conditioning system and switches to external circulation ventilation mode (e.g., setting the temperature to 24°C) to lower the interior temperature and replenish fresh air, thus slowing down the deterioration of the environment. At the same time, the system sends a level-two alarm text message with an "emergency" icon to the preset emergency contact (such as the owner's spouse). The message may include "A child has been left in the car, the ambient temperature has reached 40°C, please handle immediately" and a link to the vehicle's real-time GPS location, so that the emergency contact can quickly locate and go to the rescue.

[0058] Once the intermediate response is triggered, the system continues to monitor vital signs and environmental parameters inside the vehicle. If a door opening signal or a child removal signal is subsequently detected, the system will automatically terminate the current response and reset to standby mode. If the temperature inside the vehicle continues to rise and the R value further exceeds the third threshold, the system will upgrade to an advanced response and automatically send a request for help containing the vehicle's location and risk level to the emergency rescue platform.

[0059] In summary, this application can achieve the following beneficial effects: (1) High reliability: By fusing heterogeneous sensors such as millimeter-wave radar (detecting vital signs), vision (identifying children’s characteristics), and pressure sensing (analyzing occupant distribution patterns), and combining them with confidence algorithms, the risk of false alarms (non-living entities) and false alarms (static children) is greatly reduced.

[0060] (2) High level of intelligence: The vehicle status (door lock, power supply, temperature) is introduced as context, enabling the system to understand different scenarios such as "parking", "leaving the car" and "locking the car", and dynamically adjust the monitoring strategy and decision weight to achieve accurate judgment and energy consumption balance.

[0061] (3) Forming a safety closed loop: It not only provides multi-level alarms (in-vehicle, mobile phone, emergency contact), but also innovatively activates the air conditioning ventilation as a physical intervention under specific conditions to buy precious rescue time for children, and can ultimately link with external rescue, forming a complete safety closed loop of "perception-decision-intervention-rescue".

[0062] (4) Privacy-friendly: The original visual data can be identified by the in-vehicle processing unit, and only the summary of the warning event is uploaded to the cloud, thus protecting user privacy.

[0063] The child forgetfulness reminder method in a vehicle according to embodiments of this application acquires vital sign data, visual image data, pressure distribution data, and vehicle status data of the vehicle; calculates corresponding confidence levels based on the vital sign data, visual image data, and pressure distribution data respectively; determines the vehicle's monitoring mode based on the vehicle status data, and determines the fusion weight of the confidence level according to the monitoring mode and the vehicle's interior temperature; calculates a comprehensive risk value based on the confidence level and the corresponding fusion weight, and executes corresponding graded response actions according to the comprehensive risk value. This solves the problems of related technologies relying on a single sensor, high false alarm and false negative rates, and lack of effective proactive intervention. By dynamically adjusting the fusion weight and monitoring mode of multiple sensors based on vehicle status perception, a closed-loop child forgetfulness reminder system is achieved, moving from "passive alarm" to "proactive intervention."

[0064] Next, referring to the accompanying drawings, a child forgetfulness reminder device for vehicles proposed according to an embodiment of this application is described.

[0065] Figure 4 This is a block diagram of a child forgetfulness reminder device in a vehicle according to an embodiment of this application.

[0066] like Figure 4 As shown, the child forgetting reminder device 10 in the vehicle includes: an acquisition module 100, a calculation module 200, and an execution module 300.

[0067] The acquisition module 100 is used to acquire vital sign data, visual image data, pressure distribution data and vehicle status data of the vehicle. The calculation module 200 is used to calculate the corresponding confidence levels based on vital sign data, visual image data, and stress distribution data, respectively. The execution module 300 is used to determine the vehicle's monitoring mode based on vehicle status data, determine the fusion weight of confidence level according to the monitoring mode and the temperature inside the vehicle, calculate the comprehensive risk value based on the confidence level and the corresponding fusion weight, and execute the corresponding graded response action according to the comprehensive risk value.

[0068] According to one embodiment of this application, the computing module 200 includes: Extract quantitative indicators from vital sign data, and obtain the confidence level of vital sign data based on the quantitative indicators; Identify target features in visual image data and obtain the confidence level of the visual image data based on the target features; Spatial features of the pressure distribution data are extracted and matched with a preset child sitting posture pressure distribution template to obtain the confidence level of the pressure distribution data.

[0069] According to one embodiment of this application, the execution module 300 includes: When the vehicle is powered off and all vehicle doors are locked, the vehicle's monitoring mode is determined to be the standard monitoring mode. When the temperature inside the vehicle exceeds the preset temperature threshold under the standard monitoring mode, the monitoring mode is determined to be a high-risk enhanced mode. When the vehicle is powered off and at least one door is unlocked or at least one window is open, the monitoring mode is determined to be low-power standby mode.

[0070] According to one embodiment of this application, the execution module 300 includes: Calculate the first product of the confidence level of vital sign data and the corresponding fusion weight, the second product of the confidence level of visual image data and the corresponding fusion weight, and the third product of the confidence level of stress distribution data and the corresponding fusion weight; The comprehensive risk value is calculated based on the first product, the second product, the third product, and the preset fusion function.

[0071] According to one embodiment of this application, the execution module 300 includes: If the overall risk value is greater than the first threshold and less than or equal to the second threshold, the vehicle's graded response is determined to be a primary response, and a first-level warning is issued based on the primary response. If the overall risk value is greater than the second threshold and less than or equal to the third threshold, and no user response is detected within the preset time, the vehicle's response level is determined to be a medium response, and a second-level warning reminder is issued based on the medium response. If the overall risk value is greater than the third threshold and the vehicle interior temperature is greater than the preset temperature threshold, the vehicle's graded response is determined to be a high-level response, and a three-level warning reminder is issued based on the high-level response, wherein the third threshold is greater than the second threshold, and the second threshold is greater than the first threshold.

[0072] According to the vehicle-mounted child forgetfulness reminder device of this application embodiment, it acquires vital sign data, visual image data, pressure distribution data, and vehicle status data of the vehicle; calculates the corresponding confidence levels based on the vital sign data, visual image data, and pressure distribution data respectively; determines the vehicle's monitoring mode based on the vehicle status data, and determines the fusion weight of the confidence level according to the monitoring mode and the vehicle's interior temperature; calculates a comprehensive risk value based on the confidence level and the corresponding fusion weight; and executes a corresponding graded response action according to the comprehensive risk value. This solves the problems of related technologies such as reliance on a single sensor, high false alarm and false negative rates, and lack of effective proactive intervention. By dynamically adjusting the fusion weights and monitoring modes of multiple sensors based on vehicle status perception, it achieves a closed-loop child forgetfulness reminder system, moving from "passive alarm" to "proactive intervention."

[0073] Figure 5 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include: The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0074] When the processor 502 executes the program, it implements the child forgetting reminder method provided in the above embodiments.

[0075] Furthermore, the vehicle also includes: Communication interface 503 is used for communication between memory 501 and processor 502.

[0076] The memory 501 is used to store computer programs that can run on the processor 502.

[0077] Memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0078] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 5The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0079] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0080] Processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0081] This embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method for reminding children to stay in a vehicle.

[0082] This application also provides a computer program product, including a computer program that is executed to implement the child forgetting reminder method in a vehicle described above.

[0083] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0084] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0085] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0086] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0087] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0088] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.

[0089] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0090] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for reminding passengers to avoid forgetting their children in a vehicle, characterized in that, Includes the following steps: Acquire vehicle vital signs data, visual image data, pressure distribution data, and vehicle status data; Calculate the corresponding confidence levels based on the vital signs data, the visual image data, and the pressure distribution data, respectively. The monitoring mode of the vehicle is determined based on the vehicle status data, and the fusion weight of the confidence level is determined according to the monitoring mode and the vehicle interior temperature. A comprehensive risk value is calculated based on the confidence level and the corresponding fusion weight, and a corresponding graded response action is executed according to the comprehensive risk value.

2. The method according to claim 1, characterized in that, The calculation of the corresponding confidence levels based on the vital sign data, the visual image data, and the stress distribution data includes: Extract quantitative indicators from the vital signs data, and obtain the confidence level of the vital signs data based on the quantitative indicators; Identify target features in the visual image data, and determine the confidence level of the visual image data based on the target features; The spatial features of the pressure distribution data are extracted and matched with a preset child sitting posture pressure distribution template to obtain the confidence level of the pressure distribution data.

3. The method according to claim 1, characterized in that, Determining the vehicle monitoring mode based on the vehicle status data includes: When the vehicle is powered off and all the vehicle doors are locked, the monitoring mode of the vehicle is determined to be the standard monitoring mode. When the vehicle interior temperature exceeds a preset temperature threshold under the standard monitoring mode, the monitoring mode is determined to be a high-risk enhanced mode. When the vehicle is powered off and at least one door is unlocked or at least one window is open, the monitoring mode is determined to be a low-power standby mode.

4. The method according to claim 1, characterized in that, The calculation of the comprehensive risk value based on the confidence level and the corresponding fusion weight includes: Calculate the first product of the confidence level of the vital signs data and the corresponding fusion weight, the second product of the confidence level of the visual image data and the corresponding fusion weight, and the third product of the confidence level of the stress distribution data and the corresponding fusion weight; The comprehensive risk value is calculated based on the first product, the second product, the third product, and a preset fusion function.

5. The method according to claim 1, characterized in that, The step of executing the corresponding tiered response action based on the comprehensive risk value includes: If the comprehensive risk value is greater than the first threshold and less than or equal to the second threshold, the vehicle's graded response is determined to be a primary response, and a first-level early warning is issued based on the primary response. If the overall risk value is greater than the second threshold and less than or equal to the third threshold, and no user response is detected within a preset time, then the vehicle's response level is determined to be a medium response, and a second-level warning reminder is issued based on the medium response. If the overall risk value is greater than the third threshold and the vehicle interior temperature is greater than the preset temperature threshold, then the vehicle's graded response is determined to be a high-level response, and a level-three warning reminder is issued based on the high-level response, wherein the third threshold is greater than the second threshold, and the second threshold is greater than the first threshold.

6. A child forgetfulness reminder device for use in a vehicle, characterized in that, include: The acquisition module is used to acquire vehicle vital signs data, visual image data, pressure distribution data, and vehicle status data; The calculation module is used to calculate the corresponding confidence levels based on the vital sign data, the visual image data, and the pressure distribution data, respectively. The execution module is used to determine the monitoring mode of the vehicle based on the vehicle status data, determine the fusion weight of the confidence level according to the monitoring mode and the vehicle interior temperature, calculate the comprehensive risk value based on the confidence level and the corresponding fusion weight, and execute the corresponding graded response action according to the comprehensive risk value.

7. The apparatus according to claim 6, characterized in that, The computing module includes: Extract quantitative indicators from the vital signs data, and obtain the confidence level of the vital signs data based on the quantitative indicators; Identify target features in the visual image data, and obtain the confidence level of the visual image data based on the target features; The spatial features of the pressure distribution data are extracted and matched with a preset child sitting posture pressure distribution template to obtain the confidence level of the pressure distribution data.

8. The apparatus according to claim 6, characterized in that, The execution module includes: When the vehicle is powered off and all the vehicle doors are locked, the monitoring mode of the vehicle is determined to be the standard monitoring mode. When the vehicle interior temperature exceeds a preset temperature threshold under the standard monitoring mode, the monitoring mode is determined to be a high-risk enhanced mode. When the vehicle is powered off and at least one door is unlocked or at least one window is open, the monitoring mode is determined to be a low-power standby mode.

9. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and capable of running on the processor, the processor executing the program to implement the child forgetting reminder method in a vehicle as described in any one of claims 1-5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the child forgetting reminder method in a vehicle as described in any one of claims 1-5.

Images