In-vehicle passenger care method and device and storage medium

Abstract

The invention provides an in-vehicle passenger care method and device and a storage medium, and the method comprises the steps: obtaining the multi-source care information of a target passenger under the condition that the target passenger in a vehicle is recognized; based on the multi-source care information, generating a time sequence instruction sequence oriented to the target travel, wherein the time sequence instruction sequence comprises a control instruction corresponding to at least one target time point; and by executing the sequential instruction sequence, the control instructions corresponding to the target time points are distributed to the corresponding vehicle subsystem controllers at the target time points to be executed, so that care services are provided for target passengers through the vehicle subsystems. According to the technical scheme, the sequential instruction sequence is automatically generated and executed, manual step-by-step operation of a driver is replaced, the driving safety is expected to be improved, cross-subsystem cooperative control can be achieved, immersive experience is provided for target passengers in a vehicle, prospective active planning is carried out based on multi-source care information, and the driving safety is improved. And the care service is more intelligent and appropriate.

Description

Technical Field

[0001] This application relates to the field of intelligent vehicle control technology, and in particular to a method, device and storage medium for caring for in-vehicle occupants. Background Technology

[0002] With the increasing ownership of family cars, the frequency and duration of car rides for passengers with special needs, such as children, the elderly, and pregnant women, have increased significantly. During vehicle operation, to ensure a more comfortable ride for these passengers, drivers often need to manually adjust multiple vehicle subsystems, such as adjusting the air conditioning temperature, selecting age-appropriate entertainment content, and adjusting the status of windows or sunshades.

[0003] Currently, such operations are typically performed independently using a central touchscreen or physical buttons, requiring drivers to repeatedly switch and tap between different interfaces such as air conditioning, entertainment, and vehicle controls. This process is not only cumbersome but also continuously occupies the driver's vision and attention while driving, posing a potential risk to driving safety. Summary of the Invention

[0004] In view of this, this application provides a method, device, and storage medium for caring for in-vehicle occupants. Specifically, this application is achieved through the following technical solution: According to a first aspect of the embodiments of this specification, a method for caring for in-vehicle occupants is provided, comprising: upon identifying a target occupant in the vehicle, acquiring multi-source care information of the target occupant; based on the multi-source care information, generating a time-sequential instruction sequence oriented towards a target journey, the time-sequential instruction sequence including at least one control instruction corresponding to a target time point; and by executing the time-sequential instruction sequence, distributing the control instruction corresponding to each target time point to a corresponding vehicle subsystem controller for execution at each target time point, so as to provide care services to the target occupant through the vehicle subsystem.

[0005] According to a second aspect of the embodiments of this specification, an in-vehicle occupant care device is provided, comprising: an information acquisition unit, configured to acquire multi-source care information of a target occupant when a target occupant is identified in the vehicle; an instruction planning unit, configured to generate a time-sequential instruction sequence oriented towards a target journey based on the multi-source care information, the time-sequential instruction sequence including at least one control instruction corresponding to a target time point; and an instruction distribution unit, configured to distribute the control instruction corresponding to each target time point to a corresponding vehicle subsystem controller for execution at each target time point by executing the time-sequential instruction sequence, so as to provide care services to the target occupant through the vehicle subsystem.

[0006] According to a third aspect of the embodiments of this specification, an electronic device is provided, comprising: a processor; and a computer-readable storage medium storing computer program instructions that, when executed by the processor, cause the processor to perform the method described in the first aspect.

[0007] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0008] According to a fifth aspect of the embodiments of this specification, a computer program product is provided, including a computer program / instructions that, when executed by a processor, implement the method described in the first aspect.

[0009] As can be seen from the above technical solutions, the embodiments of this application automatically acquire multi-source care information after identifying the target occupant in the vehicle, and generate a time-series instruction sequence covering the target journey based on the multi-source care information, so as to automatically and accurately execute a series of complex care settings according to the timeline during the target journey, without requiring the driver to manually and step by step operate multiple vehicle subsystems, thereby freeing the driver from the burden of complicated operations, reducing the distraction of their attention, and aiming to improve driving safety.

[0010] Furthermore, the sequential command sequence can coordinately control multiple vehicle subsystems such as air conditioning, entertainment, lighting, and body, and accurately execute the corresponding control commands in the sequential command sequence according to the target time point. This breaks the information silo state of traditional vehicle subsystems being independent and unable to link, and realizes the dynamic scheduling and collaborative work of the whole vehicle resources. This allows multiple vehicle subsystems to cooperate like an organism around the service strategy of each target time point, providing a comfortable and immersive riding experience for the target passengers.

[0011] Furthermore, since the generated sequence of time-based instructions contains control instructions for future times within the target journey, it possesses the ability to proactively plan and dynamically adapt. For example, it can plan service content for different target time points in the future based on information such as journey time, destination, and changes in passenger status, making care services more intelligent, appropriate, and in line with the physiological and psychological laws of passengers. Attached Figure Description

[0012] Figure 1 This is a schematic diagram of the control flow of an on-board controller according to an exemplary embodiment of this application; Figure 2 This is a schematic flowchart illustrating an exemplary embodiment of a vehicle occupant care method. Figure 3This is a schematic diagram illustrating a sequential instruction sequence for a child in a vehicle, as shown in an exemplary embodiment of this application. Figure 4 This is a block diagram illustrating an electronic device according to an exemplary embodiment of this application; Figure 5 This is a block diagram illustrating a parking recommendation device according to an exemplary embodiment of this application. Detailed Implementation

[0013] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. 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.

[0014] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0015] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0016] During vehicle operation, in order to provide a more comfortable riding experience for special passengers, drivers often need to manually set multiple vehicle subsystems. However, the manual setting process is cumbersome, distracts the driver, and poses a potential risk to driving safety.

[0017] To address this issue, related technologies have also provided automation solutions based on preset scene modes. For example, by executing fixed device linkage scripts, parameters such as air conditioning and ambient lighting can be automatically adjusted when a care mode is triggered. However, this solution still has significant limitations. For instance, its scene settings are static and isolated, making it impossible to dynamically coordinate vehicle subsystems according to actual driving situations; the response mechanism is passive and lacks foresight, only able to adjust based on feedback from a single sensor signal, unable to combine trip information for planning; and the functional logic is simple and rigid, typically only able to execute a single rule of "if the condition is met, then perform the action," unable to handle complex, time-sequential tasks involving multiple time points.

[0018] Based on this, embodiments of this application provide a method for caring for vehicle occupants, such as... Figure 1 As shown, this embodiment constructs a central decision-making and planning engine as the intelligent hub of the vehicle cockpit. This engine integrates multi-dimensional data such as occupant information, trip information, and environmental information, and uses a built-in intelligent model to generate a time-series of instructions covering the entire trip with clearly defined steps. This instruction sequence is not a static script, but an adaptive plan that can dynamically adjust based on real-time situations, such as changes in occupant emotions and trip progress. After generating the time-series of instructions, the engine distributes the relevant control instructions in the sequence to the corresponding vehicle subsystem controllers at the appropriate time points within the trip, driving these originally independent subsystems to work collaboratively, automatically building and maintaining a safe, comfortable, and enjoyable immersive in-vehicle environment for the occupants. Furthermore, the intelligent model continuously learns and optimizes during the execution of in-vehicle care services for each target trip, providing increasingly intelligent and personalized care services over time.

[0019] The embodiments described in this specification will now be described in detail.

[0020] This application provides a method for caring for in-vehicle occupants. This method is implemented by a system or device that implements this application by executing computer program instructions. In a vehicle scenario, this system or device is typically embodied as an on-board central computing unit, a smart cockpit domain controller, or a combination thereof. Figure 2 This is a schematic flowchart illustrating an exemplary embodiment of a vehicle occupant care method, as shown in this application. Figure 2 As shown, the in-vehicle occupant care method 200 includes at least the following steps S210 to S230: Step S210: If a target occupant is identified inside the vehicle, obtain multi-source care information of the target occupant.

[0021] In some embodiments, the target occupant includes at least one of the following: a child, an infant, a pregnant woman, an elderly person, or a patient.

[0022] In some embodiments, the presence of the target occupant is identified by cabin sensors, such as by an in-cabin camera capturing an image of the target occupant or by an in-cabin microphone recognizing the target occupant's voice. In other embodiments, a target occupant's entry command can be received via a user terminal. Based on this command, the presence of the target occupant is confirmed for information collection. This integrates functions that previously required multiple operations, such as adjusting the air conditioning, selecting entertainment content, and controlling the duration, into a simpler one-button operation, eliminating safety hazards caused by the driver manually operating various vehicle subsystems.

[0023] In some embodiments, the multi-source care information includes at least two of occupant information, environmental information, and trip information, wherein: The occupant information refers to information related to the target occupant inside the vehicle, used to construct a user profile of the target occupant to achieve personalized services. The occupant information includes occupant characteristic information and occupant status information. Occupant characteristic information refers to the occupant's inherent attributes or recent preferences, such as age group, gender, and video preference type; occupant status information refers to the occupant's state inside the vehicle, such as emotional state (e.g., crying, happy), activity state (e.g., sleeping, dangerous actions), and vital signs (e.g., body temperature). Specifically, preset or learned occupant characteristic information associated with the target occupant can be obtained by accessing locally stored user profiles or synchronizing with a cloud account. Alternatively, the occupant's age group and gender can be identified based on the Occupant Monitoring System (OMS) camera. Occupant status information is obtained through non-contact collection and analysis using biometric sensors such as the OMS camera, microphone, and infrared temperature sensor.

[0024] The environmental information refers to information related to the physical environment inside and outside the vehicle, used to understand the physical environment of the target occupants and as a basis for adjusting cabin comfort. The environmental information includes in-vehicle temperature, in-vehicle humidity, in-vehicle air quality, and outside temperature, outside humidity, real-time road conditions, etc.; environmental information can be obtained through the environmental sensor array in the cabin and vehicle network data.

[0025] The trip information is related to vehicle driving planning and is used to provide a basis for planning in the time dimension. The trip information includes at least one of the navigation destination and estimated travel time. The above-mentioned trip information can be obtained through an in-vehicle navigation system and a telematics unit.

[0026] Step S220: Based on the multi-source care information, generate a timing instruction sequence for the target journey, wherein the timing instruction sequence includes at least one control instruction corresponding to a target time point.

[0027] In some embodiments, the multi-source care information is feature fused to obtain fused multi-source care information; the fused multi-source care information is input into a pre-trained decision model, and the decision model outputs the temporal instruction sequence. The decision model is a machine learning model, reinforcement learning model, rule-based reasoning model, etc.

[0028] The decision-making model performs multi-objective optimization reasoning based on built-in knowledge and learned patterns. Its goal is to generate a comprehensive service strategy that simultaneously satisfies the comfort, safety, and health (e.g., anti-addiction) of the target occupants and convert it into a temporal sequence of instructions. For example, for a 5-year-old child who has just finished school, is feeling down, and is in the heat outside, during a 45-minute journey home, the decision-making model, based on multi-source care information such as child information, environmental information, and journey information, generates a temporal sequence of instructions containing four target time points T1-T4 for the 45-minute journey, where: The target time point T1 indicates the start of the trip, and its specific time can be the trip start time T+0 minutes. The service strategy corresponding to the target time point T1 is to quickly cool down and soothe emotions. The corresponding control commands include temperature adjustment commands, seat adjustment commands, and announcement commands, so that at the target time point T1, the interior temperature is 22 degrees Celsius, the seat ventilation function is turned on, a welcome message is played through the voice assistant, and soothing light music is played.

[0029] The target time point T2 can be the 5th minute after the start of the trip, i.e., time T+5 minutes. The service strategy corresponding to the target time point T2 is to provide short-term entertainment. The corresponding control commands include commands such as ambient lighting adjustment, content playback, screen mode settings, and dimming of the sunshade on the child's side window. At the target time point T2, the ambient lighting in the car will switch to a soft blue, the child's preferred cartoon will play, the screen's eye protection mode will be activated, and the child's side window sunshade will be dimmed to the preset position.

[0030] The target time point T3 can be 25 minutes after the start of the trip, i.e., time T+25 minutes. The service strategy corresponding to the target time point T3 is to implement health management intervention. The corresponding control instructions include anti-addiction management instructions, broadcast instructions, temperature adjustment instructions, etc., so that the video content has been paused at the target time point T3, and the child is guided to look out the window to relax their eyes. At the same time, the air conditioning temperature in the car has been gradually increased from 22 degrees to 24 degrees.

[0031] The target time point T4 can be 35 minutes after the start of the trip, i.e., time T+35 minutes. The service strategy corresponding to the target time point T4 is to gradually reduce entertainment stimulation and announce the end of the trip. The corresponding control instructions include content playback instructions and broadcast instructions, so that by the target time point T4, the entertainment content has been switched from video to audio stories, and a reminder that we are about to arrive home is broadcast through the voice assistant to help children smoothly transition to getting off the vehicle.

[0032] It should be understood that the time points, service strategies, and control instructions listed in this embodiment are merely one possible planning scheme based on the exemplary scenario, intended to clearly illustrate the dynamic planning capability and execution logic of this step. In practical applications, the decision model will reason and adjust based on acquired multi-source care information (e.g., passenger category, real-time mood changes, trip destination type, weather conditions, and passenger preferences). Therefore, the actual generated sequence of time-series instructions may exhibit various variations in time points, control instruction content, and coordination methods of each subsystem, and is not limited to the specific details described in this example. This example is only used to explain this embodiment and does not constitute any limitation on the scope of protection of this embodiment.

[0033] The decision model also needs to determine the service planning timeline during the reasoning process. This timeline represents the target occupant's journey time within the vehicle. For example, starting with the moment the target occupant is identified, and ending with the estimated arrival time at the destination provided by the navigation system, target time points are allocated based on the journey length, intersection nodes, and experience data. These target time points are T1, T2, T3, and T4, as mentioned above. The service strategy corresponding to each time point is then converted into executable instructions. The decision model assembles all the control instructions arranged on the timeline into a structured, sequential instruction sequence. This sequence includes at least the planned execution timestamp for each control instruction, the target subsystem identifier, and the specific instruction parameters.

[0034] Step S230: By executing the sequential instruction sequence, the control instructions corresponding to each target time point are distributed to the corresponding vehicle subsystem controller for execution at each target time point, so as to provide care services to the target occupants through the vehicle subsystem.

[0035] In some embodiments, the central decision-making and planning engine maintains a timer synchronized with the start time of the target journey. It continuously monitors the time of the target journey and compares it with the target time points in the sequence of timed instructions. When the system time reaches or is about to reach the target time point of a control instruction, the central decision-making and planning engine immediately initiates the control instruction distribution process. For example, 55 seconds before T4 (with a preset lead time), the control instruction set for time T4 is distributed. Based on the target subsystem identifier of the control instruction, the central decision-making and planning engine packages the control instruction into a data frame recognizable by the corresponding vehicle subsystem via the vehicle's internal network, such as CAN, Ethernet, or inter-domain communication bus, and sends it point-to-point to the corresponding vehicle subsystem controller for execution.

[0036] In some embodiments, the vehicle subsystem includes at least one of an air conditioning system, an infotainment system, a body control system, a lighting system, a voice interaction system, and a fragrance system.

[0037] In some embodiments, the control instruction corresponding to each target time point in the sequential instruction sequence is at least one of the following: air conditioning adjustment instruction, media control instruction, body control instruction, lighting control instruction, voice control instruction, and fragrance control instruction.

[0038] The air conditioning adjustment commands correspond to the air conditioning system and may include adjustments such as temperature adjustment, airflow adjustment, and mode adjustment; the media control commands correspond to the infotainment system and may include adjustments such as content playback, anti-addiction management, and screen mode settings; the vehicle body control commands correspond to the vehicle body control system and may include adjustments such as window opening / closing, sunshade adjustment, and seat adjustment; the lighting control commands correspond to the lighting system and may include adjustments such as light color, brightness, and mode; the voice control commands correspond to the voice interaction system and may include adjustments such as specific content playback and voice dialogue interaction; the fragrance control commands correspond to the fragrance system and may include adjustments such as fragrance type selection, concentration adjustment, release mode, and fragrance on / off.

[0039] Each vehicle subsystem controller, such as the air conditioning controller, infotainment system, body control, lighting controller, and voice interaction controller, receives the control command corresponding to each target time point, parses and executes the control command at its control logic layer. For example, for the control command set at target time point T2, the body control controller drives the motor to adjust the sunshade to the specified position based on the received sunshade adjustment command; the infotainment system activates the child-locked eye protection mode interface based on the received screen mode setting command, and starts playing the specified cartoon based on the content playback command; the lighting controller adjusts the color and brightness of the ambient light to a soft blue based on the received ambient light adjustment command.

[0040] In some embodiments, the timing instruction sequences for different target journeys are different, and the target time point, vehicle subsystem, or instruction parameters corresponding to the control instructions contained in the different timing instruction sequences are different.

[0041] The number and intervals of target time points included in the sequential command sequence will be dynamically adjusted based on the trip duration, passenger status, and needs. For example, a 60-minute trip to the hospital for pregnant women may include 5 carefully planned target time points; while a 15-minute trip to pick up or drop off children may only include 2 target time points. Furthermore, because different passengers may have different needs, the types of vehicle subsystems invoked by the sequential command sequence will also differ. For instance, when the target passenger is a child, the infotainment system and air conditioning system are the primary targets; when the target passenger is a pregnant woman, the primary targets may be seat controls in the body control system, such as seat posture, massage adjustment, and more comfortable suspension modes; and if the target passenger is an elderly person, the primary targets may be the voice interaction system and body control system. In some scenarios, even when the same type of control command is issued to the same vehicle subsystem, the specific command parameters may vary depending on the occupant and the scenario. For example, the air conditioning temperature may be set to 22°C for children, while it may be set to 26°C for the elderly. For occupants prone to motion sickness, the system may be linked to the fragrance system to select a refreshing and invigorating fragrance parameter.

[0042] like Figure 2 As illustrated by the in-vehicle occupant care method, after identifying the target occupant, multi-source care information is automatically acquired. Based on this information, a temporal sequence of instructions covering the target journey is generated. This sequence automatically and precisely executes a series of complex care settings along a timeline during the journey, eliminating the need for the driver to manually operate multiple vehicle subsystems step-by-step. This frees the driver from cumbersome operations and reduces distractions, thereby improving driving safety. The temporal sequence of instructions can collaboratively control multiple vehicle subsystems such as air conditioning, entertainment, lighting, and bodywork. It precisely executes corresponding control commands within the temporal sequence based on the target time point, breaking down the traditional information silos where vehicle subsystems are independent and unable to coordinate. This enables dynamic scheduling and collaborative work of the entire vehicle's resources, allowing multiple vehicle subsystems to work together like an organic whole around the care target, providing a comfortable and immersive riding experience for the target occupant. Furthermore, since the generated sequence of time-based instructions contains control instructions for future times within the target journey, it possesses the ability to proactively plan and dynamically adapt. For example, it can plan service content for different target time points in the future based on information such as journey time, destination, and changes in passenger status, making care services more intelligent, appropriate, and in line with the physiological and psychological laws of passengers.

[0043] In some embodiments, during the execution of the sequential instruction sequence, the in-vehicle occupant care method 200 further includes: monitoring the status feedback data of the target occupant; and adjusting the control instructions that have not yet been executed in the sequential instruction sequence based on the status feedback data.

[0044] The state feedback data refers to the physiological and emotional state data of passengers continuously collected by the perception system during the execution of a sequential instruction sequence. This data reflects the immediate response of the target passenger in the vehicle to the current care service and is used to evaluate the effectiveness of the implemented service strategy. The state feedback data is obtained through real-time collection and analysis of in-vehicle OMS cameras and microphones. This data includes changes in emotional state, changes in activity state, and voice interaction feedback. Changes in emotional state refer to identifying emotional transitions such as a passenger changing from crying to calm, from calm to happy, or showing signs of agitation. For example, after playing soothing music, the camera captures the cessation of crying and a relaxed expression. Changes in activity state refer to monitoring behavioral changes such as a passenger changing from awake to asleep, or from sitting quietly to moving frequently. For example, after watching cartoons for a period of time, signs of fatigue such as rubbing eyes or turning away from the screen may appear. Voice interaction feedback refers to capturing children's self-talk, responses to the voice assistant, or questions through the microphone to analyze their interests or needs.

[0045] After obtaining the aforementioned status feedback data, the central decision-making and planning engine analyzes the status feedback data. For example, based on the status feedback data, it determines whether the effect of the executed control commands on improving the occupant status has met expectations. If so, it generates at least a sequence of alternative commands based on the status feedback data to replace the control commands that have not yet been executed in the sequential command sequence.

[0046] In one example, during the instruction generation phase, an expected effect indicator is also set. The expected effect refers to the occupant's emotional state as identified by the OMS camera within the evaluation time window after the instruction execution begins, such as the next 5 minutes. If the cumulative duration of the identified happy or calm state exceeds a preset threshold (e.g., 60%) in the latter half of the evaluation time window, such as the last minute, and no crying or distressing occurs again, then the improvement effect is considered to have met expectations.

[0047] If, during the latter half of the assessment window, the status feedback data shows that the emotional state remains characterized by crying or agitation, or that the percentage of calm states does not reach the threshold, then the improvement effect is deemed to have failed to meet expectations. In this case, at least the latest status feedback data should be used to generate an alternative instruction sequence.

[0048] In some embodiments, generating a sequence of alternative instructions based at least on the status feedback data further includes obtaining other multi-source care information at the decision time, and inputting the other multi-source care information based on the decision time and the status feedback data into the decision model to generate a sequence of alternative instructions from the decision time to the end of the trip through the decision model.

[0049] In some embodiments, the in-vehicle occupant care method 200 further includes optimizing the decision model by: responding to an intervention operation of a vehicle subsystem that executes a control command at the current target time point; determining intervention command data generated by the intervention operation and multi-source care information corresponding to the occurrence of the intervention operation; and optimizing and updating the decision model based on the intervention command data and its corresponding multi-source care information.

[0050] For the current target journey, if the target occupant or other vehicle occupants intervene in one or more vehicle subsystems corresponding to the current target time point within the time window between the current target time point and the next target time point, it indicates that the control commands generated at the current target time point may not meet the needs of the target occupant. Based on this, this embodiment utilizes the intervention command data generated by the intervention operation, along with multi-source environmental information at the time, to optimize the decision-making model. The aim is to generate control commands that meet the expected needs for the target occupant in similar subsequent scenarios, reducing the frequency of subsequent manual interventions. Thus, through continuous execution-monitoring-adjustment-learning, the central decision-making and planning engine can continuously optimize its decision-making model, thereby making its in-vehicle occupant care services increasingly precise and personalized.

[0051] The following is an example of daily care for children to illustrate the relevant content of the sequential instruction sequence in the technical solution of this application.

[0052] Assuming the target occupant is an 8-year-old primary school student, and the vehicle picks up the student after school, the target journey is a 60-minute drive from school to home. Through onboard sensors and user profiling, the vehicle's central decision-making and planning engine obtains multi-source care information, including that the target occupant is a child, has just finished a day of classes, appears slightly tired, and the outdoor weather is sunny and mild. Based on this, the decision model generates a temporal sequence of instructions containing five target time points T1-T5, such as... Figure 3 As shown, the timing instruction sequence is as follows: The target time point T1 (trip start time, T+0 minutes) aims to quickly establish a comfortable and reassuring environment to alleviate children's post-school fatigue and create a safe and comfortable initial riding experience. The generated control commands include air conditioning adjustment commands, vehicle control commands, voice control commands, and media control commands. Specifically, the air conditioning adjustment command parameters are automatic mode, 23℃, medium fan speed, and external circulation mode; the vehicle control command parameters are a 10-minute soothing massage for the rear right seat; the voice control command parameters are a pre-set message, such as "The comfortable seat and temperature have been adjusted; we're ready to go home!"; and the media control command parameters are a content ID and a volume of 25%, where the content ID is, for example, a specified playlist.

[0053] At the target time point T2 (T+15 minutes), the service strategy is to activate age-appropriate entertainment content to provide passengers with their preferred audiovisual content after their emotions have calmed down, maintaining a pleasant riding experience. The generated control commands include vehicle control commands and media control commands; the parameters for the vehicle control commands are: rear right-side screen, educational animated series, and eye protection mode; the parameters for the vehicle control commands also include: rear headlight color set to warm yellow, brightness set to 40%.

[0054] The target time point T3 (T+35 minutes) employs a rest-guided approach, enforcing anti-addiction rules and guiding children to relax their eyes and replenish fluids. The generated control instructions include media control instructions and voice control instructions. Media control instructions include pausing the video and triggering the anti-addiction rest interface. Voice control instructions play preset content, such as, "You've been watching for 20 minutes now, let your eyes rest. There's warm water next to your seat, have some."

[0055] The target time point T4 (T+50 minutes) employs a service strategy focused on reducing visual stimulation to help children transition from an entertaining state to a calm one. Based on this, the generated control commands include media control commands, vehicle control commands, and air conditioning adjustment commands. The media control commands include turning off audio and video; the vehicle control commands include raising the rear right-side window sunshade to full opening; and the air conditioning adjustment commands are set to 25°C.

[0056] The target time is T5 (55 minutes before the end of the trip). The service strategy is to announce the end of the trip in advance and prepare to disembark. Based on this, the generated control instructions include voice control instructions, the instruction parameters of which are to play specified content, such as "We'll be home in 5 minutes, you can start packing your bag now."

[0057] After the decision model generates the above-mentioned time-series instruction sequence, 30 seconds before the system time reaches each target time point, the control instruction for the corresponding target time point is sent to the corresponding vehicle subsystem to provide a coherent, proactive, and personalized care service throughout the entire journey.

[0058] Figure 4 This is a schematic diagram of a network device illustrated in this specification according to an exemplary embodiment. Please refer to... Figure 4 At the hardware level, the device includes a processor 402, an internal bus 404, a network interface 406, memory 408, a hardware acceleration device 410, and non-volatile memory 412, and may also include other hardware required for its functions. One or more embodiments of this application can be implemented in software, for example, the processor 402 reads the corresponding computer program from the non-volatile memory 412 into memory 408 and then runs it. Of course, in addition to software implementation, one or more embodiments of this application do not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the above processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0059] Figure 5 This is a block diagram illustrating an exemplary embodiment of an in-vehicle occupant care device, which can be applied to, for example... Figure 4 The electronic device shown implements the technical solution of this application. The in-vehicle occupant care device includes an information acquisition unit 510, an instruction planning unit 520, and an instruction distribution unit 530, wherein: The information acquisition unit 510 is used to acquire multi-source care information of the target occupant when the target occupant inside the vehicle is identified. The instruction planning unit 520 is used to generate a timing instruction sequence oriented towards the target process based on the multi-source care information, wherein the timing instruction sequence includes at least one control instruction corresponding to the target time point. The instruction distribution unit 530 is used to distribute the control instructions corresponding to each of the target time points to the corresponding vehicle subsystem controllers for execution at each of the target time points by executing the sequential instruction sequence, so as to provide care services to the target occupants through the vehicle subsystem.

[0060] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0061] Accordingly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the methods described in any of the above embodiments.

[0062] Accordingly, embodiments of this application also provide a computer program product configured to perform the methods described in any of the above embodiments.

[0063] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, which can take the form of a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email sending and receiving device, game console, tablet computer, wearable device, or any combination of these devices.

[0064] In a typical configuration, a computer includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0065] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0066] Computer-readable media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0067] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily intended to describe features of specific embodiments of a particular invention. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.

[0068] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0069] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0070] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0071] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. An in-vehicle occupant care method characterized by comprising: The method comprises: In the case of identifying a target occupant in the vehicle, acquiring multi-source care information of the target occupant; Based on the multi-source care information, a time sequence instruction sequence for the target trip is generated, which contains control instructions corresponding to at least one target time point; By executing the time sequence instruction sequence, the control instructions corresponding to each target time point are distributed to the corresponding vehicle subsystem controller for execution, so as to provide care services for the target occupant through the vehicle subsystem.

2. The method of claim 1, wherein, During the execution of the time sequence instruction sequence, the method further comprises: Monitoring the state feedback data of the target occupant; Based on the state feedback data, the control instructions in the time sequence instruction sequence that have not been executed are adjusted.

3. The method of claim 2, wherein, The adjustment of the control instructions in the time sequence instruction sequence that have not been executed based on the state feedback data comprises: Based on the state feedback data, it is determined whether the improvement effect of the target occupant state of the executed control instructions reaches the expectation; If yes, an alternative instruction sequence is generated based on at least the state feedback data to replace the control instructions in the time sequence instruction sequence that have not been executed.

4. The method of claim 1, wherein, The generation of the time sequence instruction sequence for the target trip based on the multi-source care information comprises: The multi-source care information is fused to obtain fused multi-source care information; The fused multi-source care information is input into a pre-trained decision model, and the time sequence instruction sequence is output by the decision model, which is a machine learning model.

5. The method of claim 4, wherein, The method further comprises optimizing the decision model by the following steps: In response to the intervention operation of the vehicle subsystem for executing the control instructions of the current target time point, intervention instruction data generated by the intervention operation and the corresponding multi-source care information when the intervention operation occurs are determined; Based on the intervention instruction data and its corresponding multi-source care information, the decision model is updated and optimized.

6. The method of claim 1, wherein, The multi-source care information comprises at least two of occupant information, environmental information and trip information; And / or The vehicle subsystem comprises at least one of an air conditioning system, an infotainment system, a body control system, a lighting system, a voice interaction system and a fragrance system; And / or The target occupant comprises at least one of a child, an infant, a pregnant woman, an old person and a patient.

7. The method of claim 1 wherein, The control instructions corresponding to each target time point of the time sequence instruction sequence are at least one of air conditioning adjustment instructions, media control instructions, body control instructions, lighting control instructions, voice control instructions and fragrance control instructions; And / or The time sequence instruction sequences of different target trips are different, and at least one of the target time points, the vehicle subsystems or the instruction parameters corresponding to the control instructions included in different time sequence instruction sequences is different.

8. An electronic device, comprising: It comprises: A processor; And A computer readable storage medium, in which computer program instructions are stored, which make the processor execute the method of any one of claims 1 to 7 when executed by the processor.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to execute the method of any one of claims 1 to 7.

10. A computer program product, characterised in that, A computer program comprising computer program elements which, when executed by a processor, implement the method according to any one of claims 1 to 7. A computer program comprising computer program elements which, when executed by a processor, implement the method according to any one of claims 1 to 7.

Images