Vehicle self-adaptive sleep inducing method, system and device and medium

Abstract

The invention provides a vehicle adaptive sleep inducing method, system and device and a medium, and belongs to the technical field of vehicles. The method comprises the steps that current state data of a pacifying target in a whole vehicle is obtained through a sleep inducing request, the whole process does not need complex operation of a user, intelligent and humanized service can be achieved through one-key starting or condition triggering, target state features are extracted from the current state data, the target state features are input into a set pacifying model, and the pacifying target in the whole vehicle can be pacified according to the target state features. An optimal pacifying strategy combination is determined, and a unique pacifying model is established for each infant through machine learning, so that the most effective pacifying scheme can be quickly started, and the sleep inducing success rate and speed are remarkably improved; and according to the optimal pacifying strategy combination, an active suspension system and a sound system of the current whole vehicle are driven, and the current vehicle body posture and the current playing audio are switched to pacify the pacifying target. The pacifying efficiency and the success rate are improved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a vehicle adaptive sleep-inducing method, system, device, and medium. Background Technology

[0002] In car travel scenarios, families with infants or young children often encounter a troubling phenomenon: while the vehicle is in motion, the bumps in the road, the slight vibrations of the engine, and the white noise generated by the vehicle moving at a constant speed create a cradle-like rocking environment, which easily helps infants fall asleep. However, once the vehicle reaches its destination and stops, the original vibration and white noise environment suddenly disappears. This abrupt change in environment can easily wake up a lightly sleeping infant, causing them to cry.

[0003] In existing technologies, in order to solve the problem of crying in strollers, in-vehicle entertainment systems or props are used for soothing. However, these existing technological solutions cannot adapt to the unique habits and preferences of different infants. The process is cumbersome and the effect is uncertain. It is especially inconvenient in driving scenarios, resulting in low soothing efficiency and success rate. Summary of the Invention

[0004] The main objective of this application is to propose a vehicle-adaptive soothing method, system, device, and medium to improve soothing efficiency and success rate.

[0005] To achieve the above objectives, one aspect of this application proposes a vehicle-adaptive sleep-inducing method, the method comprising: Obtain a soothing request, and based on the soothing request, obtain the current status data of the target being soothed within the vehicle. Extract target state features from the current state data, input the target state features into the current appeasement model of the appeasement target, and determine the optimal combination of appeasement strategies; Based on the optimal combination of soothing strategies, a corresponding control command is generated. Based on the corresponding control command, the active suspension system and audio system of the current vehicle are driven to switch the current vehicle posture and the currently playing audio in order to soothe the target.

[0006] In some embodiments, the step of inputting the target state features into the current appeasement model of the appeasement target to determine the optimal combination of appeasement strategies includes: Iterate through all the established appeasement strategies to form multiple appeasement combinations; For each of the aforementioned soothing combinations, the target state features are input, and the soothing mapping function set in the soothing model is used to output the predicted soothing effect score for each of the aforementioned soothing combinations. From the predicted appeasement effect scores, the appeasement combination corresponding to the highest score is selected, and the corresponding appeasement combination is taken as the optimal appeasement strategy combination.

[0007] In some embodiments, driving the active suspension system and audio system of the current vehicle according to the corresponding control command includes: Based on the optimal combination of soothing strategies, a swaying mode waveform is determined. According to the swaying mode waveform, a suspension control command is generated. According to the suspension control command, the active suspension system is driven to run the swaying mode waveform to switch the current vehicle posture. Based on the optimal combination of soothing strategies, the set playback audio is determined, an audio control command is generated according to the set playback audio, and the audio system is driven to play the set playback audio according to the audio control command.

[0008] In some embodiments, the method further includes: After executing the optimal combination of soothing strategies, the current state data after execution is obtained, and the state change amount is determined based on the current state data and the current state data after execution. Based on the state change, determine whether the optimal combination of appeasement strategies was successfully executed; When the optimal combination of soothing strategies is considered to have been successfully executed, the state change is used as new training data and the new training data is fed back into the established soothing model.

[0009] In some embodiments, determining whether the optimal combination of soothing strategies was successfully executed includes: If the optimal combination of appeasement strategies is deemed to have failed, then the process switches to the suboptimal combination of appeasement strategies and determines again whether the suboptimal combination of appeasement strategies has been successfully executed. If the suboptimal combination of soothing strategies is considered to be successfully executed, the soothing effect score of the suboptimal combination of soothing strategies is enhanced, and the state change based on the suboptimal combination of soothing strategies is used as new training data, and the new training data is fed back into the soothing model.

[0010] In some embodiments, obtaining the sleep-inducing request includes: Obtain the current vehicle status and / or trigger commands from the vehicle terminal to identify whether there is a target to be appeased inside the vehicle. Once a target for comfort is identified, a soothing request is generated based on the vehicle status and / or the triggering command.

[0011] In some embodiments, generating a sleep-inducing request based on the vehicle status and / or the triggering command includes: Once a target for soothing is identified, the vehicle speed data in the vehicle status is obtained. When the vehicle speed drops to the set stopping speed, the environmental state is considered to have changed, and the soothing request is generated.

[0012] To achieve the above objectives, another aspect of this application proposes a vehicle-adaptive sleep-inducing system, characterized in that the system includes: The data acquisition module is used to obtain soothing requests and, based on the soothing requests, obtain the current status data of the target being soothed inside the vehicle. The decision module is used to extract target state features from the current state data, input the target state features into the set soothing model, and determine the optimal combination of soothing strategies. The execution module is used to generate corresponding control commands based on the optimal combination of soothing strategies, and drive the active suspension system and audio system of the vehicle to switch the current vehicle posture and the currently playing audio in order to soothe the soothing target.

[0013] To achieve the above objectives, another aspect of the present application provides a vehicle control device, including a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the above-described vehicle adaptive sleep-inducing method.

[0014] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described vehicle adaptive sleep-inducing method.

[0015] The embodiments of this application include at least the following beneficial effects: This application provides a vehicle-adaptive method, system, device, and medium for soothing to sleep. This solution obtains the current state data of the target being soothed within the vehicle through a soothing request. The entire process requires no complex user operation and can be initiated with a single click or triggered by conditions, achieving intelligent and user-friendly service. Target state features are extracted from the current state data and input into a pre-set soothing model to determine the optimal combination of soothing strategies. Through machine learning, a unique "comfort model" is established for each infant, enabling the rapid activation of the most effective soothing solution and significantly improving the success rate and speed of soothing to sleep. Based on the optimal combination of soothing strategies, the system drives the vehicle's active suspension and audio systems to switch the current vehicle posture and the currently playing audio to soothe the target. By simulating cradle-like rocking through active suspension and combining it with soothing music or white noise, the system creates a smooth transition sleep environment for the baby, significantly reducing the probability of waking up after parking. The precise and personalized solution creates the most comfortable sleep transition environment for the baby, greatly reducing the probability of waking up after parking, improving the convenience of using the vehicle, and avoiding driving safety hazards caused by the baby's crying. This overcomes the shortcomings of existing technologies that cannot meet the personalized needs of babies and have rigid soothing strategies. Attached Figure Description

[0016] Figure 1 This is a flowchart of the vehicle adaptive sleep-inducing method provided in the embodiments of this application; Figure 2 This is a schematic diagram of the framework of the vehicle adaptive sleep-inducing system provided in the embodiments of this application; Figure 3 This is a schematic diagram of the hardware structure framework of the vehicle control device provided in the embodiments of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0018] It is understood that the terms "first," "second," etc., used in this application may be used to describe various concepts herein, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of embodiments of this application, Ethernet signaling information may also be referred to as interface signaling information, and similarly, interface signaling information may also be referred to as Ethernet signaling information. Depending on the context, the words "if" or "when" as used herein may be interpreted as "when," "in response to a determination," or "in the event of a determination."

[0019] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0021] As described in the background section, in the prior art, families with infants or young children commonly encounter a troubling phenomenon in car travel scenarios: while the vehicle is in motion, the bumps in the road, the slight vibrations of the engine, and the white noise generated when the vehicle is moving at a constant speed create a cradle-like rocking environment, which easily helps the infant fall asleep. However, once the vehicle reaches its destination and stops, the original vibration and white noise environment suddenly disappears. This abrupt change in environment can easily wake a lightly sleeping infant, causing them to cry.

[0022] In existing technologies, common methods to address the problem of crying infants in strollers include playing cartoons or music through the in-vehicle terminal system. However, this can distract the driver, and the screen light is not conducive to the baby falling asleep. Using rattles or sound-making toys hung inside the stroller has limited effectiveness, as it cannot simulate the full-body rocking sensation of a moving vehicle. After parking, parents need to turn around or get out of the car to manually rock the baby in the back seat, making the effect difficult to sustain.

[0023] However, these existing technical solutions have significant drawbacks: It cannot adapt to the unique habits and preferences of different infants. Some infants are sensitive to specific shaking frequencies, while others respond better to certain types of sounds, resulting in low generalization rather than personalization. It cannot learn from each soothing experience and cannot develop increasingly effective soothing strategies tailored to specific infants, leading to low soothing efficiency and success rates. The process is cumbersome and its effectiveness is uncertain, especially inconvenient in driving situations.

[0024] In some embodiments of one aspect of the present invention Figure 1 This is an optional flowchart of the vehicle adaptive sleep-inducing method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S100 to S300.

[0025] Step S100: Obtain a soothing request. Based on the soothing request, obtain the current status data of the target being soothed in the vehicle.

[0026] Step S200: Extract target state features from the current state data, input the target state features into the established appeasement model, and determine the optimal combination of appeasement strategies.

[0027] In step S300, based on the optimal combination of soothing strategies, a corresponding control command is generated. Based on the corresponding control command, the active suspension system and audio system of the current vehicle are driven to switch the current vehicle posture and the currently playing audio in order to soothe the target.

[0028] Steps S100 to S300, as illustrated in this embodiment, involve obtaining the current state data of the target being soothed within the vehicle through a sleep-inducing request. The entire process requires no complex user operation and can be initiated with a single click or triggered by conditions, providing an intelligent and user-friendly service. Target state features are extracted from the current state data and input into the established soothing model to determine the optimal combination of soothing strategies. Machine learning is used to establish a unique "comfort model" for each infant, enabling the rapid activation of the most effective soothing plan and significantly improving the success rate and speed of sleep induction. Based on the optimal combination of soothing strategies... This system drives the vehicle's active suspension and audio systems, switching the current vehicle posture and audio playback to soothe the target infant. By simulating a cradle-like rocking motion through the active suspension, combined with soothing music or white noise, it creates a smooth transition sleep environment for the baby, significantly reducing the probability of waking up after parking. This precise, personalized solution creates the most comfortable sleep transition environment for the baby, greatly reducing the likelihood of waking up after parking, improving vehicle convenience, and avoiding driving safety hazards caused by the baby's crying. It overcomes the shortcomings of existing technologies that cannot meet the personalized needs of infants and whose soothing strategies are rigid. When the vehicle returns to a stationary state, it not only simulates a cradle environment but also learns and optimizes itself to provide personalized, adaptive soothing solutions for specific infants, thus efficiently and accurately maintaining infant sleep—an intelligent method.

[0029] In some embodiments of S100, a triggered soothing request is obtained. Through the soothing request, the current vehicle performs a self-check and obtains multimodal data reflecting the state of the soothing target, including obtaining the current state data of the soothing target located in the current vehicle. The process of acquiring multimodal data includes: capturing facial expressions, eye status (open / closed), and body movement amplitude of the target being comforted via an in-vehicle camera; collecting sounds emitted by the target being comforted (such as babbling or crying) via an in-vehicle microphone; and monitoring physiological signals such as heart rate and respiratory rate of the target being comforted via biosensors integrated into the child safety seat.

[0030] In some embodiments of S200, key features are extracted from the current state data to obtain target state features.

[0031] Target state characteristics may include: body swaying frequency, crying decibels and spectrum, and heart rate variability. Other characteristics may also be included, but are not limited in this embodiment.

[0032] The target state characteristics are input into the established appeasement model corresponding to the current appeasement target, and the optimal combination of appeasement strategies is output.

[0033] Each soothing target has a corresponding soothing model. If there are multiple soothing targets in the current vehicle record, different infants can be identified by facial recognition or seat ID, and the corresponding personalized model can be automatically called.

[0034] The proposed appeasement model is a data model that is independently created and stored for each appeasement target. The appeasement model contains a proposed mapping function that can output a predicted appeasement effect score. The model is trained and continuously optimized using historical data.

[0035] Based on the current target state characteristics and the corresponding appeasement model, the optimal combination of appeasement strategies is calculated and selected in real time.

[0036] In some embodiments of S300, once the soothing mode is activated, two control commands are generated based on the optimal combination of soothing strategies: a suspension control command and an audio control command, which are sent to the active suspension system and the audio system, respectively.

[0037] The active suspension system receives suspension control commands, runs the required sway mode waveform, switches the current vehicle posture, and precisely controls the vehicle to produce the required sway.

[0038] The audio system receives audio control commands, plays the selected audio, and switches the current audio to soothe the target.

[0039] By combining different modes of the active suspension system and different audio frequencies of the audio system, the target is soothed and prevented from being startled when the vehicle body changes. Furthermore, by combining different modes, it can adapt to the unique habits and preferences of different targets, providing a personalized and adaptive soothing solution for specific targets.

[0040] In some embodiments of this invention, in S100, the process of obtaining the sleep-inducing request specifically includes the following steps: S110: Obtain the current vehicle status and / or trigger command from the vehicle terminal, and identify whether there is a target for reassurance inside the vehicle.

[0041] S120, when a soothing target is determined, generates a soothing request based on the vehicle status and / or trigger command.

[0042] In this embodiment, the triggering of the vehicle terminal and the vehicle status are used as trigger signal sources to determine whether to start the sleep mode.

[0043] Obtain the current vehicle status and, based on that status, identify whether a target for soothing exists inside the vehicle. If a target is identified, generate a soothing request based on the vehicle status. Vehicle status includes vehicle speed and vehicle attitude. In this embodiment, other parameters can also be included in the vehicle status to generate sleep-inducing instructions.

[0044] In one embodiment, taking vehicle speed as an example, when the vehicle speed drops to the set stopping speed, the soothing mode is automatically triggered. The in-vehicle camera is activated to identify if a target for soothing is present. If so, it is confirmed that the vehicle speed has dropped to the set stopping speed, thus indicating a change in the environmental state, and a soothing request is generated.

[0045] The system obtains the trigger command from the vehicle's onboard terminal and identifies whether a target for soothing exists within the vehicle based on the trigger command. When a target for soothing is identified, a soothing request is generated based on the trigger command.

[0046] In one embodiment, a soothing mode is automatically triggered in response to a trigger command from the vehicle terminal. The in-vehicle camera is activated to identify the presence of a target for comfort. If so, a soothing request is generated based on the trigger command.

[0047] In one embodiment, when the vehicle speed drops to the set stopping speed, a sleep-inducing mode is automatically triggered in response to a trigger command from the onboard terminal. The in-vehicle camera is activated to identify the presence of a target to be soothed. If so, a sleep-inducing request is generated based on the trigger command and the vehicle speed data indicating the approaching stopping speed.

[0048] The set stopping speed is zero. In this embodiment, the set stopping speed can also be other data, and there is no restriction in this embodiment.

[0049] Through S110 to S120, the system is automatically triggered by the vehicle speed signal, activating immediately the moment the vehicle comes to a complete stop. This allows the vibrations and ambient sounds perceived by the infant to smoothly transition from one state (driving) to another (simulated rocking), avoiding abrupt environmental stimuli and effectively maintaining sleep. This achieves a seamless transition. It retains the fundamental advantages of automatic triggering via vehicle speed signal and utilizing active suspension to simulate realistic rocking, ensuring the immediacy and effectiveness of the function.

[0050] In some embodiments of this invention, in step S200, the process of determining the optimal combination of appeasement strategies specifically includes the following steps: S210, iterates through all the established appeasement strategies to form a variety of appeasement combinations.

[0051] S220: For each soothing combination, input the target state features and use the soothing mapping function set in the soothing model to output the predicted soothing effect score for each soothing combination.

[0052] S230: Select the highest-scoring soothing combination from the predicted soothing effect scores, and use the corresponding soothing combination as the optimal soothing strategy combination.

[0053] In one embodiment of S210, key features are extracted from the current state data to obtain target state features. These features include, for example, body swaying frequency, crying decibels and spectrum, and heart rate variability.

[0054] Obtain the set soothing model corresponding to the current soothing target. Based on the set soothing model, the model will quickly traverse all possible soothing combinations in its strategy library (such as the permutation of rocking patterns A / B / C and music types X / Y / Z) to obtain a variety of soothing combinations.

[0055] In one embodiment of S220, for each soothing combination, the target state features are input, and a predicted soothing effect score is output using the pre-trained soothing mapping function in the model.

[0056] In one embodiment of S230, after obtaining the predicted scores of all candidate strategies, they are sorted in descending order, and the soothing combination corresponding to the highest score is selected. The corresponding soothing combination is taken as the optimal soothing strategy combination (i.e., suspension control parameters + audio selection).

[0057] It should be noted that the combination with the highest reassurance effect score is the optimal reassurance strategy combination, and the combination with the second highest predicted reassurance effect score is the suboptimal reassurance strategy combination.

[0058] In one embodiment, the process of establishing and initially learning the soothing model includes: when serving the current soothing target for the first time, after the soothing mode is triggered, several typical combinations of soothing strategies are tried sequentially from the default strategy library.

[0059] Each attempt retrieves the current state data and calculates the time required from the start of execution until the target falls asleep, i.e., the effective time, which serves as the actual soothing effect.

[0060] These combinations of reassurance strategies and their corresponding effective times are continuously input into the established reassurance model. After a set number of trips, a preliminary personalized comfort model is established for the current reassurance goal, that is, the reassurance model corresponding to the current reassurance goal. This model can clearly show that strategy 1) has the highest predicted reassurance effect score, that is, it is the most effective for the current reassurance goal.

[0061] Through S210 to S230, machine learning is used to create a unique soothing model for each target, enabling the rapid activation of the most effective soothing solution and significantly improving the success rate and speed of putting the child to sleep. The precise, personalized solution creates the most comfortable sleep transition environment for the target, greatly reducing the probability of waking up during parking. No driver intervention or trial and error is required, greatly reducing the burden on parents and allowing drivers valuable time for rest or other tasks, significantly improving the convenience of using the car.

[0062] In some embodiments of this invention, S300, the driving process of the active suspension system and the audio system specifically includes the following steps: S310 determines the sway mode waveform based on the optimal combination of soothing strategies, generates suspension control commands based on the sway mode waveform, and drives the active suspension system to run the sway mode waveform to switch the current vehicle posture.

[0063] S320 determines the set playback audio based on the optimal combination of soothing strategies, generates audio control commands based on the set playback audio, and drives the audio system to play the set playback audio based on the audio control commands.

[0064] In one embodiment of S310, based on the optimal combination of soothing strategies, a pre-stored or real-time calculated cradle rocking pattern waveform is determined, and a suspension control command is generated according to the rocking pattern waveform, and the suspension control command is sent to the active suspension system in the current vehicle.

[0065] Based on the suspension control command, the active suspension system operates the pre-stored or real-time calculated cradle rocking mode waveform, adjusts the damping or height of the four shock absorbers, so that the entire vehicle body produces a gentle and regular forward and backward or left and right swaying, thereby switching the current vehicle body posture.

[0066] In other words, the active suspension system receives suspension control commands from the strategy optimizer and precisely controls the vehicle body to produce the required sway.

[0067] The waveform of the shaking mode can be a sine wave or an irregular wave simulating slight bumps, and there are no restrictions in this embodiment.

[0068] In one embodiment of S320, based on the optimal combination of soothing strategies, the desired playback audio is determined. Using this audio, an audio control command is generated and sent to the vehicle's audio system. Based on the audio control command, the audio system plays the selected playback audio and switches the current playback audio, thereby soothing the target.

[0069] In other words, it controls the car audio system (especially the rear audio system) to receive commands and play selected soothing audio.

[0070] The audio to be played may include: preset lullabies, white noise (such as simulated wind noise or engine idling sound), or natural sounds (such as ocean waves or rain sounds). No limitations are imposed in this embodiment.

[0071] From S310 to S320, the active suspension simulates a cradle-like rocking motion, combined with soothing music or white noise, creating a smooth transitional sleep environment for the target, significantly reducing the probability of waking up after parking. This precise, personalized solution creates the most comfortable sleep transition environment, greatly minimizing the likelihood of waking up after parking. The active suspension system precisely controls the vehicle's posture, generating continuous and regular multi-dimensional swaying that is difficult to simulate manually. This holistic swaying sensation far surpasses traditional soothing methods, mimicking the most effective way to lull someone to sleep—a gentle rocking motion. It retains the fundamental advantages of automatic triggering via vehicle speed signals and realistic swaying simulation using active suspension, ensuring the immediacy and effectiveness of the function.

[0072] In some embodiments of this invention, the method for lulling someone to sleep further includes: S400: After executing the optimal combination of appeasement strategies, obtain the current state data after execution, and determine the state change based on the current state data and the current state data after execution.

[0073] S410: Based on the state change, determine whether the optimal combination of appeasement strategies has been successfully executed.

[0074] S420: When the optimal combination of soothing strategies is considered to have been successfully executed, the state change is used as new training data and the new training data is fed back into the soothing model.

[0075] In one embodiment of S400, after executing an optimal combination of appeasement strategies, the state of the appeasement target is continuously monitored to obtain the current state data after execution. Based on the state data before and after execution, the data changes before and after appeasement are calculated to obtain the state change amount. The state change amount is quantified as the actual appeasement effect.

[0076] For example, the time required from the start of the soothing process until the target falls asleep is calculated, i.e., the effective time. The target's heart rate steadily decreases, transitioning from crying to calm and entering deep sleep. The effective time and the change in heart rate are taken as the actual soothing effect.

[0077] In one embodiment of S410, the optimal combination of appeasement strategies is determined based on the state change amount.

[0078] Specifically, an in-car camera can be used to monitor whether the target is calming down or asleep. Alternatively, changes in heart rate can be used to determine if the target is calm. If so, the optimal combination of calming strategies is considered to have been successfully executed.

[0079] Alternatively, a set data change threshold can be used for judgment; if the data changes within the set threshold, the execution is considered successful. If the data changes outside the set threshold, the execution is considered unsuccessful.

[0080] In one embodiment of S420, when the optimal combination of appeasement strategies is considered to have been successfully executed, the state change is fed back as new training data to the machine learning and decision center to update and optimize the appeasement model set for the current appeasement target.

[0081] By continuously collecting data on the actual effects of new strategies through the S400 to S420, the model can be retrained and iteratively optimized, making its predictions increasingly accurate and its recommended soothing strategies increasingly effective, ultimately achieving personalized and intelligent precision soothing. The strategy is dynamically adjusted based on real-time feedback from the soothing target, and successful experiences are recorded. With increased usage, its performance is continuously optimized. Feedback from in-vehicle cameras or microphones can be introduced, transforming "open-loop" control into "closed-loop" adaptive control. This enables personalized soothing based on the preferences of different soothing targets, enhancing the system's effectiveness and technological sophistication.

[0082] In some embodiments of the present invention, the successful determination process of S410 further includes: S421, when the optimal appeasement strategy combination is deemed to have failed, the process switches to the suboptimal appeasement strategy combination and checks again whether the suboptimal appeasement strategy combination has been successfully executed.

[0083] S422, when the suboptimal combination of soothing strategies is considered to be successfully executed, the soothing effect score of the suboptimal combination of soothing strategies is enhanced, and the state change based on the suboptimal combination of soothing strategies is used as new training data, and the new training data is fed back into the soothing model.

[0084] In one embodiment of S421, if it is confirmed in S410 that the optimal soothing strategy combination has failed to be executed, then the combination corresponding to the second highest score is selected based on the predicted soothing effect score, and it is used as the second-best soothing strategy combination. S400 is run again for a second judgment.

[0085] After implementing the suboptimal combination of appeasement strategies, the status of the appeasement target is continuously monitored to obtain the current status data after implementation. Based on the status data before and after implementation, the data changes before and after appeasement are calculated to obtain the state change quantity. The state change quantity is quantified as the actual appeasement effect.

[0086] Based on the change in state, determine whether the suboptimal combination of appeasement strategies was successfully executed.

[0087] In this embodiment, the method for determining whether the suboptimal combination of soothing strategies has been successfully executed is the same as that in the embodiment of S410, and will not be described in detail in this embodiment.

[0088] In one embodiment of S422, when the suboptimal combination of soothing strategies is considered to be successfully executed, the association between the suboptimal combination of soothing strategies and success is strengthened, that is, the soothing effect score of the combination of strategies is improved.

[0089] The state changes based on the suboptimal combination of appeasement strategies are used as new training data and fed back to the machine learning and decision center to update and optimize the appeasement model for the current appeasement target.

[0090] Through S421 and S422, during a single soothing session, if the initial optimal combination of soothing strategies is ineffective (the infant is still restless), other high-probability success strategies are switched in real time, forming an intelligent closed loop of "perception-decision-execution-re-perception" until the soothing goal is achieved. Data is continuously accumulated through the feedback learning loop. For example, the system tried "sine wave shaking + ocean wave sound," and the infant fell asleep within 30 seconds; while "irregular wave shaking + lullaby" was less effective. The machine learning module reinforces the association between the former and "success," prioritizing that strategy in similar situations in the future, thereby achieving personalized, accurate recommendations and continuous optimization.

[0091] The following is a detailed description and explanation of the solutions in the embodiments of the present invention, in conjunction with specific scenarios: The new system is designed for baby Xiaoming for the first time. When the soothing mode is triggered, it tries several typical soothing strategy combinations from the default strategy library in turn (e.g., strategy 1 - gentle rocking back and forth + white noise; strategy 2 - gentle rocking left and right + classical music).

[0092] Obtain the current state data for each attempt and calculate the time required from the start of execution until Xiaoming falls asleep (i.e., the "effective time") as the actual soothing effect.

[0093] These soothing strategy combinations and their corresponding effective times were continuously input into the established soothing model. After 3-5 trips, a preliminary personalized comfort model, i.e., the established soothing model, was established for Xiaoming. The model clearly shows that strategy 1 (gentle back-and-forth rocking + white noise) had the highest prediction score, meaning it was the most effective for Xiaoming.

[0094] During subsequent journeys, once the vehicle comes to a complete stop and the speed drops to the preset stopping speed, the soothing mode is automatically triggered. The in-car camera is activated to identify the presence of a target for soothing. If so, a soothing request is generated. Based on the request, the current state data is obtained, and using Xiaoming's set soothing model, the optimal soothing strategy combination is determined, invoking the optimal soothing strategy combination customized for Xiaoming: "gentle back-and-forth rocking + white noise".

[0095] Meanwhile, the biosensors integrated into the car seat detected that Xiaoming's heart rate was decreasing slowly (indicating he was not yet fully relaxed). The system immediately made fine adjustments based on the model, determining the suboptimal combination of soothing strategies. While maintaining "white noise," the rocking frequency was slightly adjusted from 50 times / minute to 55 times / minute. Soon, Xiaoming's heart rate stabilized and he entered a deep sleep.

[0096] This successful fine-tuning experience was recorded as a new success story and used to further optimize Xiaoming's reassurance model, making it more accurate in the future.

[0097] In one scenario, the "baby soothing" icon on the in-vehicle terminal automatically triggers the soothing mode. This activates the in-vehicle camera to identify the target being soothed. If so, a soothing request is generated based on the trigger command.

[0098] Based on the request to soothe the baby to sleep, the system acquires current state data, uses the established soothing model to determine the optimal combination of soothing strategies, and invokes this optimal combination to control the speaker to start playing a gentle lullaby. The active suspension system sends commands to make it reciprocate back and forth at a frequency of 60 times per minute with a small amplitude (e.g., ±2mm) to simulate the rocking of a cradle.

[0099] After the preset 15 minutes of operation, or after receiving a manual shutdown command from the user, the system slowly stops shaking and playing music, and enters standby mode.

[0100] In another scenario, while the vehicle is in motion, an in-car camera continuously monitors the condition of an infant in the back seat.

[0101] When the vehicle speed drops to the set stopping speed, the vehicle reaches its destination and comes to a complete stop, automatically triggering the soothing mode. The in-car camera activates, recognizing the baby as asleep. A soothing request is generated. Based on the request, the system acquires current status data and uses the pre-set soothing model to determine the optimal combination of soothing strategies. This optimal strategy is then invoked, first playing white noise similar to the previous driving noise. Simultaneously, the active suspension begins to gently and irregularly sway the vehicle, mimicking the previous road conditions. During this process, the in-car microphone monitors ambient sound. If slight agitation of the baby is detected based on the current status data, the strategy is deemed unsuccessful, and a suboptimal strategy combination is switched to increase the swaying amplitude. If crying is detected, the system switches to more rhythmic music and a side-to-side rocking mode until the baby calms down.

[0102] Reference Figure 2 Another embodiment of this application also provides a vehicle adaptive sleep-inducing system, the system comprising: The data acquisition module is used to obtain soothing requests and, based on the soothing requests, obtain the current status data of the target being soothed inside the vehicle. The decision-making module is used to extract target state features from the current state data, input the target state features into the set appeasement model, and determine the optimal combination of appeasement strategies. The execution module is used to generate corresponding control commands based on the optimal combination of soothing strategies. Based on the corresponding control commands, it drives the active suspension system and audio system of the vehicle to switch the current vehicle posture and the currently playing audio in order to soothe the target.

[0103] It is understood that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0104] Another embodiment of this application provides a vehicle control device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned vehicle adaptive sleep-inducing method. This vehicle control device can be any smart terminal, including a tablet computer, an in-vehicle computer, or similar device.

[0105] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0106] Please see Figure 3 , Figure 3 The hardware structure of a vehicle control device according to another embodiment is illustrated. The vehicle control device includes: The processor can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to achieve the technical solutions provided in the embodiments of this application. The memory can be implemented in the form of read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory and called by the processor to execute the vehicle adaptive sleep-inducing method of the embodiments of this application. Input / output interfaces are used to implement information input and output; The communication interface is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). A bus is used to transfer information between various components of a device, such as processors, memory, input / output interfaces, and communication interfaces. The processor, memory, input / output interfaces, and communication interfaces communicate with each other within the device via a bus.

[0107] This invention also provides a vehicle, including the vehicle-adaptive sleep-inducing method described above.

[0108] The vehicle can be a private car, such as a sedan, SUV, MPV, or pickup truck. It can also be a commercial vehicle, such as a van, bus, small truck, or large semi-trailer. The vehicle must have an electric motor capable of outputting power or acting as a generator to store mechanical energy. When the vehicle is a new energy vehicle, it can be a hybrid or a pure electric vehicle.

[0109] Since the vehicle applies all the technical solutions of the above-described vehicle control device, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, which will not be repeated here.

[0110] Another embodiment of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described vehicle adaptive sleep-inducing method.

[0111] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0112] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0113] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0114] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0115] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0116] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0117] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0118] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0119] The units described above as separate components may or may not be physically separate. 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 units can be selected to achieve the purpose of this embodiment according to actual needs.

[0120] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0121] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A vehicle-adaptive sleep-inducing method, characterized in that, The method includes: Obtain a soothing request, and based on the soothing request, obtain the current status data of the target being soothed within the vehicle. Extract target state features from the current state data, input the target state features into the current appeasement model of the appeasement target, and determine the optimal combination of appeasement strategies; Based on the optimal combination of soothing strategies, a corresponding control command is generated. Based on the corresponding control command, the active suspension system and audio system of the current vehicle are driven to switch the current vehicle posture and the currently playing audio in order to soothe the target.

2. The vehicle adaptive sleep-inducing method according to claim 1, characterized in that, The step of inputting the target state features into the established soothing model for the current soothing target to determine the optimal soothing strategy combination includes: Iterate through all the established appeasement strategies to form multiple appeasement combinations; For each of the aforementioned soothing combinations, the target state features are input, and the soothing mapping function set in the soothing model is used to output the predicted soothing effect score for each of the aforementioned soothing combinations. From the predicted appeasement effect scores, the appeasement combination corresponding to the highest score is selected, and the corresponding appeasement combination is taken as the optimal appeasement strategy combination.

3. The vehicle adaptive sleep-inducing method according to claim 1, characterized in that, The step of driving the active suspension system and audio system of the vehicle according to the corresponding control command includes: Based on the optimal combination of soothing strategies, a swaying mode waveform is determined. According to the swaying mode waveform, a suspension control command is generated. According to the suspension control command, the active suspension system is driven to run the swaying mode waveform to switch the current vehicle posture. Based on the optimal combination of soothing strategies, the set playback audio is determined, an audio control command is generated according to the set playback audio, and the audio system is driven to play the set playback audio according to the audio control command.

4. The vehicle adaptive sleep-inducing method according to claim 1, characterized in that, The method further includes: After executing the optimal combination of soothing strategies, the current state data after execution is obtained, and the state change amount is determined based on the current state data and the current state data after execution. Based on the state change, determine whether the optimal combination of appeasement strategies was successfully executed; When the optimal combination of soothing strategies is considered to have been successfully executed, the state change is used as new training data and the new training data is fed back into the established soothing model.

5. The vehicle adaptive sleep-inducing method according to claim 4, characterized in that, The determination of whether the optimal combination of appeasement strategies was successfully executed includes: If the optimal combination of appeasement strategies is deemed to have failed, then the process switches to the suboptimal combination of appeasement strategies and determines again whether the suboptimal combination of appeasement strategies has been successfully executed. If the suboptimal combination of soothing strategies is considered to be successfully executed, the soothing effect score of the suboptimal combination of soothing strategies is enhanced, and the state change based on the suboptimal combination of soothing strategies is used as new training data, and the new training data is fed back into the soothing model.

6. The vehicle adaptive sleep-inducing method according to claim 1, characterized in that, The process of obtaining a sleep-inducing request includes: Obtain the current vehicle status and / or trigger commands from the vehicle terminal to identify whether there is a target to be appeased inside the vehicle. Once a target for comfort is identified, a soothing request is generated based on the vehicle status and / or the triggering command.

7. The vehicle adaptive sleep-inducing method according to claim 6, characterized in that, The step of generating a sleep-inducing request based on the vehicle status and / or the triggering command includes: Once a target for soothing is identified, the vehicle speed data in the vehicle status is obtained. When the vehicle speed drops to the set stopping speed, the environmental state is considered to have changed, and the soothing request is generated.

8. A vehicle-adaptive sleep-inducing system, characterized in that, The system includes: The data acquisition module is used to obtain soothing requests and, based on the soothing requests, obtain the current status data of the target being soothed inside the vehicle. The decision module is used to extract target state features from the current state data, input the target state features into the set soothing model, and determine the optimal combination of soothing strategies. The execution module is used to generate corresponding control commands based on the optimal combination of soothing strategies, and drive the active suspension system and audio system of the vehicle to switch the current vehicle posture and the currently playing audio in order to soothe the soothing target.

9. A vehicle control device, characterized in that, It includes a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the vehicle adaptive soothing method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the vehicle adaptive sleep-inducing method according to any one of claims 1 to 7.

Images