Anti-motion sickness strategy generation method and device, electronic equipment and storage medium

Abstract

The invention provides an anti-motion sickness strategy generation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the driving state information corresponding to a target vehicle when a target user sits on the target vehicle; based on the driving state information and recommendation weights corresponding to intervention strategies in a personalized motion sickness prevention intervention strategy library corresponding to the target user, selecting a plurality of intervention strategy combinations to obtain candidate strategies, and applying the candidate strategies; determining a total reward value corresponding to the candidate strategy based on the anti-motion sickness effect parameter corresponding to the candidate strategy in the candidate strategy application process; and adjusting recommendation weights corresponding to a plurality of intervention strategies included in the candidate strategies based on the total reward value, and updating the recommendation weights to a personalized anti-motion sickness intervention strategy library corresponding to the target user. According to the method, the individual characteristics of the user and the real-time scene requirement can be precisely met, the pertinence and the adaptability of anti-motion sickness intervention are effectively improved, the method is continuously improved along with use, and the anti-motion sickness effect can be continuously optimized after long-term use.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a method, device, electronic device, and storage medium for generating an anti-motion sickness strategy. Background Art

[0002] With the advancement of vehicle intelligence, various driver-assistance features are increasingly being installed, such as automatic emergency braking, adaptive cruise control, and automated parking. However, in the development of these systems, the increasing number of features comes at the expense of passenger comfort. The vehicle's lateral and longitudinal acceleration can easily cause disharmony between the body's balance and visual systems, leading to motion sickness symptoms such as dizziness, nausea, and palpitations.

[0003] Currently, existing products and methods all monitor the motion sickness condition of passengers and take corresponding measures to alleviate motion sickness, which is a post-event motion sickness relief strategy. Summary of the Invention

[0004] The embodiments of the present application provide a method, device, electronic device, and storage medium for generating an anti-motion sickness strategy, aiming to solve the technical problem of how to pre-generate an anti-motion sickness strategy.

[0005] In a first aspect, an embodiment of the present application provides a method for generating an anti-motion sickness strategy, the method comprising:

[0006] When the target user is riding in the target vehicle, obtaining driving status information corresponding to the target vehicle;

[0007] Based on the driving state information and the recommendation weights of the intervention strategies in the personalized anti-motion sickness intervention strategy library corresponding to the target user, selecting multiple intervention strategies from the personalized anti-motion sickness intervention strategy library, combining them to obtain candidate strategies, and applying the candidate strategies;

[0008] During the application of the candidate strategy, determining a total reward value corresponding to the candidate strategy based on an anti-motion sickness effect parameter corresponding to the candidate strategy;

[0009] The recommendation weights corresponding to the plurality of intervention strategies included in the candidate strategies are adjusted based on the total reward value, and the weights are updated into a personalized anti-motion sickness intervention strategy library corresponding to the target user.

[0010] In a second aspect, an embodiment of the present application further provides an anti-motion sickness strategy generating device, the device comprising:

[0011] A first acquisition module is used to acquire driving status information corresponding to the target vehicle when the target user is riding in the target vehicle;

[0012] The policy generation module is configured to select a plurality of intervention strategies from the personalized anti-motion sickness intervention strategy library based on the driving state information and the recommendation weight corresponding to each intervention strategy in the personalized anti-motion sickness intervention strategy library, combine the plurality of intervention strategies to obtain a candidate strategy, and apply the candidate strategy.

[0013] The determination module is configured to determine a total reward value corresponding to the candidate strategy based on the anti-motion sickness effect parameter corresponding to the candidate strategy during application of the candidate strategy.

[0014] The first processing module is configured to adjust the recommendation weight corresponding to each intervention strategy included in the candidate strategy based on the total reward value, and update the recommendation weight to the personalized anti-motion sickness intervention strategy library corresponding to the target user.

[0015] In a third aspect, an electronic device is provided, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and the computer program, when executed by the processor, implements the anti-motion sickness strategy generation method described above.

[0016] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program, when executed by a processor, implements the anti-motion sickness strategy generation method described above.

[0017] The embodiments of the present application at least have the following technical effects:

[0018] The technical scheme of the embodiments of the present application forms a complete closed loop by real-time acquisition of vehicle driving state, generation of adaptive candidate strategies in combination with a user personalized anti-motion sickness intervention strategy library, and dynamic optimization of the recommendation weight of the candidate strategy library in the personalized anti-motion sickness intervention strategy library according to the actual effect feedback of the candidate strategy. Thus, the user individual characteristics and real-time scene requirements can be accurately matched, the pertinence and adaptability of anti-motion sickness intervention can be effectively improved, and the anti-motion sickness effect can be continuously optimized in the long term with continuous improvement in use. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical schemes in the embodiments of the present application or the prior art, the drawings needed in the embodiment or prior art description will be briefly introduced as follows.

[0020] Figure 1 is a flowchart of the anti-motion sickness strategy generation method provided by the embodiments of the present application

[0021] Figure 2 is a structural schematic diagram of the anti-motion sickness strategy generation device provided by the embodiments of the present application

[0022] Figure 3A block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the technical problems, technical solutions and beneficial effects solved by this application more clearly understood, this application is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0024] In related technologies, with the advancement of vehicle intelligence, various assisted driving features are increasingly being installed, such as automatic emergency braking, adaptive cruise control, and automatic parking. However, during the development of assisted driving systems, the increasing number of features has come at the expense of passenger comfort. The vehicle's lateral and longitudinal acceleration can easily cause disharmony between the passenger's balance and visual systems, leading to motion sickness symptoms such as dizziness, nausea, and palpitations.

[0025] Currently, existing products and methods all monitor the motion sickness condition of passengers and take corresponding measures to alleviate motion sickness, which is a post-event motion sickness relief strategy.

[0026] Based on this, to solve the problem of how to pre-generate anti-motion sickness strategies, the present application provides an anti-motion sickness strategy generation method, apparatus, electronic device, and storage medium. The method involves obtaining driving status information corresponding to a target vehicle while a target user is riding in the target vehicle. Based on the driving status information and the recommendation weights corresponding to each intervention strategy in a personalized anti-motion sickness intervention strategy library corresponding to the target user, multiple intervention strategies are selected from the personalized anti-motion sickness intervention strategy library, combined to obtain a candidate strategy, and then applied. During the application of the candidate strategy, a total reward value corresponding to the candidate strategy is determined based on the anti-motion sickness effect parameters corresponding to the candidate strategy. Based on the total reward value, the recommendation weights corresponding to each of the multiple intervention strategies included in the candidate strategy are adjusted and updated to the personalized anti-motion sickness intervention strategy library corresponding to the target user. The present application generates an adapted candidate strategy by acquiring the vehicle's driving status in real time, combining it with the user's personalized anti-motion sickness intervention strategy library, and then dynamically optimizes the recommendation weights of the candidate strategy library in the personalized anti-motion sickness intervention strategy library based on actual effect feedback from the candidate strategy, forming a complete closed loop. This can accurately fit the user's individual characteristics and real-time scenario requirements, effectively improving the pertinence and adaptability of anti-motion sickness intervention. It will continue to improve with use, and long-term use can continuously optimize the anti-motion sickness effect.

[0027] Example 1

[0028] This application embodiment provides a method for generating an anti-motion sickness strategy. Figure 1 ,include:

[0029] Step 101: When a target user is riding in a target vehicle, the driving state information corresponding to the target vehicle is obtained.

[0030] The anti-motion sickness strategy generation method provided in the embodiments of the present application can be applied to the anti-motion sickness control system in the target vehicle. The anti-motion sickness control system can provide users with anti-motion sickness intervention solutions that adapt to their needs.

[0031] Specifically, the anti-motion sickness control system can obtain the target vehicle's driving status information while the target user is riding in the target vehicle. The driving status information can include vehicle motion status information and in-vehicle environmental status information. Vehicle motion status information includes driving speed (sudden acceleration, sudden deceleration, high speed driving), steering angle (continuous curves, sharp turns), road bumps (gravel roads, speed bumps), etc. In-vehicle environmental status information can include in-vehicle temperature (stuffy heat can easily aggravate discomfort), humidity, air quality (odor, airtightness), light intensity (strong direct light or dim light can easily cause visual discomfort), etc.

[0032] It should be noted that the acquisition of driving status information depends on vehicle sensors (such as speed sensors and gyroscopes) and in-vehicle environment sensors (such as temperature and humidity sensors and air quality sensors). Some information can be directly called through the vehicle control system (such as vehicle speed and steering data) to ensure real-time data (usually updated every 1 to 3 seconds) and provide accurate environmental basis for subsequent strategy generation.

[0033] Step 102 : Based on the driving state information and the recommendation weights corresponding to the respective intervention strategies in the personalized anti-motion sickness intervention strategy library corresponding to the target user, multiple intervention strategies are selected from the personalized anti-motion sickness intervention strategy library, combined to obtain candidate strategies, and the candidate strategies are applied.

[0034] The personalized anti-motion sickness intervention strategy library is a collection of pre-built strategies for target users. Its strategy types must cover dimensions such as "environmental adjustment" (such as adjusting temperature and ventilation), "behavioral guidance" (such as prompting to look forward, reduce looking down, and wear VR glasses), and "vehicle control" (such as suggesting deceleration and optimizing steering). Different intervention strategies correspond to different recommendation weights. The higher the recommendation weight, the better the historical effect of the strategy on the user. Specifically, the recommendation weight can be generated based on the user's historical data. For example, if the user's previous anti-motion sickness feedback for "adjusting the temperature in the car to 2°C" was better than "opening the windows for ventilation", then the weight of the intervention strategy "adjusting the temperature in the car to 23°C" would be higher than the intervention strategy "opening the windows for ventilation".

[0035] It's important to note that before building a personalized anti-motion sickness intervention strategy library, a basic anti-motion sickness intervention strategy library must be established. First, the causes of motion sickness in passengers must be assessed and identified. The assessment dimensions include motion sickness causes and scenario segmentation. Motion sickness risk factors related to motion sickness causes include: motion perception conflict, special road sections, and complex environments. Scenario segmentation includes: short-distance commuting, children in a car, long-distance highway driving, and mountain driving. Control factors are identified for each motion sickness risk factor. For example, control factors for motion perception conflict include rapid vehicle acceleration and deceleration, head acceleration, and angular velocity; for special road sections, centrifugal force around curves and vertical vibration; for complex environments, interior vehicle temperature, odor, and sound; for short-distance commuting, frequent starts and sudden acceleration and deceleration; for children in a car, immature vestibular development and easily distracted attention; for long-distance highway driving, constant speed, rapid lane changes, and overtaking; and for mountain driving, turns and grade changes.

[0036] Then, based on the above analysis results, a basic anti-motion sickness intervention strategy library is established. This library can include multiple intervention types, such as physical, psychological, and environmental. For each intervention type, there are multiple corresponding main intervention strategies. Furthermore, for each main intervention strategy, there are multiple corresponding sub-strategies. For example, main intervention strategies for physical interventions include: adjusting seat angle, wearing VR glasses, turning curvature, lane changing, vehicle suspension, vehicle acceleration and deceleration, vertical vibration, etc.; corresponding sub-strategies include: seat massage, seat ventilation and heating, VR display scene, lane change frequency, speed, number of vehicle starts, etc. Main intervention strategies for psychological interventions include: adjusting breathing and distraction; corresponding sub-strategies include: breathing rate, attention content and method. Main intervention strategies for environmental interventions include: air conditioning temperature adjustment, audio, and vehicle display compensation; corresponding sub-strategies include: air conditioning temperature value, fragrance type, sound type, volume, vehicle display brightness and color.

[0037] This embodiment of the application matches driving status information with possible motion sickness risk points, then combines the recommended weights of each strategy in a personalized anti-motion sickness intervention strategy library to select multiple high-weighted strategies as candidate strategies. Once a candidate strategy is determined, it can be automatically executed by the vehicle control system and the user can be prompted on the vehicle's central control screen.

[0038] This application combines real-time driving status with user personalized data to screen out intervention strategies that are suitable for the current scenario.

[0039] Step 103 : During the application of the candidate strategy, a total reward value corresponding to the candidate strategy is determined based on the anti-motion sickness effect parameter corresponding to the candidate strategy.

[0040] During the application of the candidate strategy, the anti-motion sickness control system will monitor the actual effect of the strategy, that is, obtain the anti-motion effect parameters and convert them into total reward values ​​to provide a basis for subsequent weight optimization.

[0041] Specifically, anti-motion sickness effect parameters can include objective physiological parameters and subjective feedback parameters. Objective parameters include the user's heart rate (heart rate drops from 90 beats / minute to 75 beats / minute after motion sickness relief) and eye movement stability (the frequency of eye movement drops from 10 times / minute to 3 times / minute); subjective parameters include the user's discomfort score submitted through the in-vehicle system and their acceptance of the strategy (such as "whether they are willing to execute this strategy again"). The total reward value can be the weighted sum of various effect parameters.

[0042] Step 104: Adjust the recommendation weights corresponding to the plurality of intervention strategies included in the candidate strategies based on the total reward value, and update the weights to the personalized anti-motion sickness intervention strategy library corresponding to the target user.

[0043] After obtaining the total reward value from the candidate strategy application process, the recommendation weights corresponding to the multiple intervention strategies included in the candidate strategy are adjusted based on the total reward value, and the recommendation weights are updated in the personalized anti-motion sickness intervention strategy library corresponding to the target user, ensuring that subsequent strategy generation is more tailored to the user's actual needs. Through the closed-loop operation of generation, application, feedback, and optimization, the embodiment of the present application allows the personalized anti-motion sickness intervention strategy library to be continuously improved as user data accumulates.

[0044] This embodiment of the application generates adaptive candidate strategies by acquiring real-time vehicle driving status and combining it with a user's personalized anti-motion sickness intervention strategy library. The recommended weights of the candidate strategies in the personalized anti-motion sickness intervention strategy library are then dynamically optimized based on feedback from the candidate strategies' actual effectiveness, forming a complete closed loop. This precisely tailors the system to the user's individual characteristics and real-time scenario requirements, effectively improving the targetedness and adaptability of anti-motion sickness intervention. Furthermore, the system continuously improves anti-motion sickness effectiveness with continued use.

[0045] The following describes how to determine the total reward value of a candidate strategy. In an optional embodiment of the present application, based on the anti-motion sickness effect parameter corresponding to the candidate strategy, determining the total reward value corresponding to the candidate strategy includes:

[0046] Determining whether a state space corresponding to the target vehicle has been transformed based on the driving state information;

[0047] Each time the state space of the target vehicle is transformed, obtaining an anti-motion sickness effect parameter corresponding to the candidate strategy;

[0048] Calculating a reward value corresponding to the candidate strategy according to the anti-motion sickness effect parameter;

[0049] The sum of the reward values ​​corresponding to each state space transition during the application of the candidate strategy is calculated to obtain a total reward value corresponding to the candidate strategy.

[0050] During the application of a candidate policy, the vehicle's state space transforms as it drives. For example, a vehicle may switch from a constant speed on a straight road to a series of curves, from smooth driving to a bumpy ride, or from a well-ventilated interior environment to a confined, stuffy, and hot interior. These driving state changes caused by significant differences in the driving route, road conditions, or interior environment are all considered state space transformations. Specifically, when determining whether the state space corresponding to the target vehicle has transformed, the state boundary can be defined based on significant changes in key indicators in the real-time driving state information. During the application of a candidate policy, the state space can undergo multiple transformations. Completing a state space transformation is equivalent to performing a training session. Each training session can determine whether a positive or negative reward will be given based on the policy's anti-motion sickness effect parameters. If the anti-motion sickness effect is poor, it is equivalent to completing a trial and error, and a negative reward will be given.

[0051] Each time the target vehicle's state space transitions, the anti-motion sickness effect parameters corresponding to the candidate strategy are obtained. These anti-motion sickness effect parameters can include both objective physiological data and subjective feedback. Objectively, sensors can be used to collect information such as changes in the user's heart rate, eye movement stability, and head shaking amplitude. For example, during continuous curve driving, if the user's heart rate is more stable and their eye movement trajectory is more stable than before, it indicates that the strategy is having a certain effect in that phase. Subjectively, the in-car interactive system can be used to obtain the user's discomfort level score and acceptance of the strategy, such as user feedback of "reduced dizziness." These parameters can intuitively reflect the anti-motion sickness effect of the strategy in the current state from different dimensions.

[0052] When calculating the reward value for this state-space transition based on the anti-motion sickness effect parameters, a corresponding score can be assigned based on the parameter performance. If physiological parameters indicate a stable state and the subjective feedback is positive, the strategy is effective in this state and the reward value is high. If physiological parameters show no significant improvement or even deteriorate, and the subjective feedback is poor, the reward value is low. For example, when driving on a bumpy road, if the user's heart rate does not fluctuate significantly and indicates that "discomfort has been alleviated," the reward value for this stage will be high.

[0053] Finally, the reward values ​​corresponding to each state space transition are summed to obtain the candidate strategy's total reward value. This total reward value is not a general evaluation of the strategy throughout the entire driving process, but rather integrates the strategy's effectiveness at each specific state stage, comprehensively reflecting the candidate strategy's overall performance in different scenarios.

[0054] This implementation of the present application evaluates and aggregates reward values ​​segmented by state-space transitions, allowing the total reward value to more realistically and meticulously reflect the actual effectiveness of the strategy, avoiding the problem of overlooking the strategy's effectiveness in specific scenarios due to a single, general evaluation. Subsequent weight adjustments based on this total reward value allow the recommended weights of the strategies to be more tailored to the needs of different driving conditions, enabling the subsequently generated anti-motion sickness strategies to be more effective in various scenarios, thereby improving the accuracy and applicability of the overall anti-motion sickness intervention.

[0055] In an optional embodiment of the present application, the anti-motion sickness effect parameter includes at least one of a physiological indicator change parameter of the target user, a motion sickness improvement degree parameter fed back by the target user, and a matching parameter between the candidate strategy and the state space;

[0056] Calculating a reward value corresponding to the candidate strategy according to the anti-motion sickness effect parameter includes:

[0057] Based on a preset reward function, a reward value corresponding to the candidate strategy is determined according to the physiological indicator change parameter, the motion sickness improvement degree parameter, and the matching parameter.

[0058] In the embodiment of the present application, the anti-motion sickness effect parameters can construct an evaluation system for the effectiveness of the strategy from different dimensions. Among them, the physiological indicator change parameters are objective data based on the physiological response of the human body, which can directly reflect the actual changes in the body's perception of motion sickness, such as heart rate variability, eye movement speed, etc. These parameters are collected in real time by the on-board physiological sensors, avoiding the deviation of subjective evaluation. The motion sickness improvement degree parameter comes from the user's subjective feedback and is obtained through the in-vehicle interactive system (such as voice inquiry and touch scoring). For example, the user's 1-5 point rating of the "current dizziness level" and feedback on "whether it feels comfortable" can capture individual perception details that physiological indicators cannot cover. The matching parameters between the strategy and the state space are used to determine whether the strategy is suitable for the current driving scenario. The matching degree is usually pre-set based on the strategy's targeted response to the core risks of the state space, and then fine-tuned based on the adaptability in actual implementation.

[0059] When calculating the reward value based on the preset reward function, the three types of parameters are converted into a unified score according to reasonable logic and integrated. Specifically, a reward calculation model can be established. This model can adopt the reward calculation idea of ​​the Q-learning algorithm, that is, defining the state space (including physiological, behavioral, and environmental data characteristics), the action space (candidate strategies), and the reward function R(s, a). The calculation formula is as follows:

[0060] R(s, a) = w1*HR+w2*Ad+w3*Env, where w1, w2, and w3 are weight coefficients corresponding to the indicators. These weight coefficients can be dynamically adjusted based on user preferences or machine learning algorithms. HR is a physiological indicator, Ad is a motion sickness improvement indicator, and Env is an indicator of the match between the strategy and the environment. Ad and Env can take values ​​between 0 and 1.

[0061] The pre-defined reward function requires pre-defined weights and scoring rules for each parameter. For example, weights can be assigned based on importance. For example, physiological indicators can be weighted 0.4 due to their objectivity, subjective feedback can be weighted 0.4 due to its direct correlation with feelings, and matching can be weighted 0.2 due to its impact on the effectiveness of the strategy foundation. A 50% improvement in physiological indicators is equivalent to 40 points, and a 30% improvement is equivalent to 25 points.

[0062] For example, in the "bumpy road" state, a candidate strategy is "reducing driving speed." If physiological indicators show a decrease in the user's heart rate from 90 beats / min to 80 beats / min (a 30% improvement, corresponding to 25 points), a positive reward is given. If the user reports a "significant improvement" in motion sickness (35 points), a positive reward is also given. Conversely, if motion sickness worsens, a negative reward can be given. This strategy is highly compatible with the "bumpy road" scenario (since deceleration reduces the impact of bumps, corresponding to 18 points). After weighted calculation, the reward value = 25 × 0.4 + 35 × 0.4 + 18 × 0.2 = 10 + 14 + 3.6 = 27.6 points, which intuitively reflects the overall effectiveness of the strategy in the current state.

[0063] The above implementation plan of this application obtains the reward value by quantitatively integrating three types of parameters: changes in physiological indicators, degree of motion sickness improvement, and degree of matching between strategy and state space, combined with a preset reward function. This not only avoids the limitations of single indicator evaluation, making the reward value closer to the real effect, but also ensures the consistency and comparability of the results. It can also provide a clear direction for subsequent strategy and weight adjustments, and promote the continuous improvement of the anti-motion sickness intervention effect.

[0064] In an optional embodiment of the present application, after determining the total reward value corresponding to the candidate strategy, the method further includes:

[0065] Determining whether the total reward value is less than a preset threshold;

[0066] When the total reward value is less than a preset threshold, at least one intervention strategy included in the candidate strategies is deleted from the personalized anti-motion sickness intervention strategy library.

[0067] After determining the total reward value, the embodiment of the present application compares the total reward value with a preset threshold. If the total reward value is less than the preset threshold, it indicates that the anti-motion sickness effect of the candidate strategy is poor. In this case, at least one intervention strategy included in the candidate strategy can be deleted from the personalized anti-motion sickness intervention strategy library to prevent invalid strategies from continuously occupying resources or interfering with subsequent strategy generation, thereby maintaining the efficiency and accuracy of the strategy library.

[0068] Specifically, when setting the preset threshold, the optimization goals and historical data of the personalized anti-motion sickness intervention strategy library can be combined. It cannot be too high, otherwise potential strategies may be mistakenly deleted, and it cannot be too low, otherwise invalid strategies cannot be eliminated. It is usually determined based on the distribution of a large number of historical total reward values. For example, the preset threshold is set to the "lower limit of the total reward value of most effective strategies" to ensure that obviously invalid strategies can be filtered out. For example, if historical data shows that the total reward value of effective strategies is generally above 60 points, then the preset threshold can be set to 60 points. When the total reward value of a candidate strategy is 50 points, it is judged to be below the threshold.

[0069] It's important to note that deleting an intervention strategy when its total reward falls below a preset threshold doesn't simply delete the entire candidate strategy; rather, it targets each intervention strategy within the candidate strategy. A candidate strategy is a combination of multiple intervention strategies, and a low total reward may indicate the ineffectiveness of some or all intervention strategies. Deletion is determined based on the contribution of each intervention strategy to the candidate strategy. If a strategy consistently leads to low total rewards in multiple combinations, it is considered invalid and deleted. If a strategy performs poorly in only one combination, it can be retained for future observation.

[0070] The above implementation plan of this application, by screening the total reward value through a preset threshold and deleting invalid intervention strategies below the threshold, can optimize the quality of the strategy library, reduce screening costs, improve strategy generation efficiency, shorten decision-making time, and enhance strategy targeting, so that subsequent strategies are more in line with user needs, and provide a dynamic purification mechanism for the strategy library.

[0071] The following describes how to obtain candidate strategies. In an optional embodiment of the present application, based on the driving state information and the recommendation weights corresponding to the respective intervention strategies in the personalized anti-motion sickness intervention strategy library corresponding to the target user, multiple intervention strategies are selected from the personalized anti-motion sickness intervention strategy library to obtain candidate strategies by combining them, including:

[0072] determining a driving scene according to the driving state information;

[0073] Selecting an intervention strategy that matches the driving scenario and has a recommendation weight greater than a preset weight from the personalized anti-motion sickness intervention strategy library to obtain an effective intervention strategy set;

[0074] selecting, from the personalized anti-motion sickness intervention strategy library, an intervention strategy that matches the driving scenario and has a recommendation weight less than the preset weight, to obtain a random intervention strategy set;

[0075] According to a preset exploration ratio, the multiple intervention strategies are selected from the effective intervention strategy set and the random intervention strategy set, and the candidate strategies are obtained by combining them, wherein the preset exploration ratio is determined based on the proportion of effective intervention strategies in the personalized anti-motion sickness intervention strategy library.

[0076] When determining candidate strategies, the driving scenario can be determined based on the real-time driving status information. The driving scenario here can be comprehensively divided into multiple dimensions such as driving speed, road conditions, steering frequency, and in-vehicle environment. For example, when the driving status information shows "vehicle speed 60km / h, continuous steering (once every 30 seconds), and closed interior", it can be determined as a "high-speed curve closed scenario"; when the information shows "vehicle speed 30km / h, bumpy road surface (amplitude of more than 5cm), and good ventilation in the vehicle", it can be determined as a "low-speed bumpy ventilation scenario". After clarifying the driving scenario, the high-risk inducements in the scenario can be identified to provide direction for subsequent strategy screening.

[0077] After determining the driving scenario, intervention strategies matching the scenario are selected from the personalized anti-motion sickness intervention strategy library and divided into sets. The effective intervention strategy set consists of strategies that "match the driving scenario and have a recommended weight greater than a preset weight." A recommended weight greater than the preset weight indicates that these strategies have been historically validated for the user's motion sickness prevention in similar scenarios. For example, the "look ahead" strategy, which had a weight greater than 0.6 in multiple "high-speed curve" scenarios, was included in the effective set. The random intervention strategy set consists of strategies that "match the scenario but have a recommended weight less than the preset weight." These strategies may have lower weights due to limited historical application, unclear effectiveness, or only being effective in specific combinations. For example, "play soothing music" may have a weight of 0.3 in the "low-speed bumpy" scenario, but it has the potential to alleviate anxiety. It should be noted that the preset weights can be set based on the overall distribution of weights in the personalized anti-motion sickness intervention strategy library to ensure that the effective set retains a sufficient number of highly effective strategies and the random set retains a certain number of strategies to be verified.

[0078] After determining the effective intervention strategy set and the random intervention strategy set, candidate strategy combinations are selected from the two sets according to a preset exploration ratio. The preset exploration ratio can be dynamically adjusted based on the maturity of the strategy library. When the strategy library is new, the exploration ratio can be increased, with 60% selected from the effective set and 40% selected from the random set, to increase testing of new strategies. As the strategy library matures, the exploration ratio can be reduced, such as 80% selected from the effective set and 20% selected from the random set, to prioritize strategy effectiveness. For example, in a "high-speed curve closed scenario," the effective set includes "look ahead" and "reduce speed to 40 km / h," and the random set includes "adjust seat angle" and "play white noise." If the exploration ratio is 7:3, two strategies are selected from the effective set and one strategy is selected from the random set, resulting in a candidate strategy of "look ahead + reduce speed + adjust seat angle" combined.

[0079] The above implementation plan of this application, by combining driving scenario determination, hierarchical screening strategies and proportional combinations, allows the candidate strategies to include verified high-weight strategies to ensure basic anti-motion sickness effects, while incorporating low-weight strategies to explore new possibilities for strategy library optimization, which not only accurately adapts to current driving scenario requirements, but also promotes continuous iteration and upgrading of the strategy library.

[0080] The following describes how to adjust the recommendation weights. In an optional embodiment of the present application, adjusting the recommendation weights corresponding to the multiple target intervention strategies included in the candidate strategy based on the total reward value includes:

[0081] Based on a predetermined correspondence between a total reward value and a weight adjustment coefficient, determining a target weight adjustment coefficient corresponding to the total reward value according to the total reward value;

[0082] The recommendation weights corresponding to the multiple target intervention strategies included in the candidate strategies are adjusted according to the target weight adjustment coefficient.

[0083] After determining the total reward value, the target weight adjustment coefficient is determined based on a predetermined correspondence. The correspondence between the total reward value and the weight adjustment coefficient must be set in advance based on the expected anti-motion sickness effect. A high total reward value indicates that the strategy performs well in the current scenario, corresponding to an adjustment coefficient that can increase the weight; a low total reward value indicates that the strategy is not effective, corresponding to an adjustment coefficient that decreases the weight. For example, an "excellent" total reward value corresponds to an adjustment coefficient of 1.3 (significantly increasing the weight), "good" corresponds to 1.1 (small increase), "average" corresponds to 1.0 (no change in weight), "poor" corresponds to 0.8 (reducing the weight), and "extremely poor" corresponds to 0.6 (significantly reducing the weight). Optionally, this correspondence can be fine-tuned in conjunction with the optimization objective of the strategy library. For example, when the optimization objective is to encourage exploration of new strategies, the adjustment coefficient can be appropriately increased for strategies with medium total reward values ​​in the random intervention strategy set.

[0084] After the target weight adjustment coefficient is obtained, the recommendation weights corresponding to the multiple target intervention strategies included in the candidate strategies are adjusted according to the target weight adjustment coefficient.

[0085] The above implementation plan of this application determines the target weight adjustment coefficient through the total reward value, and then adjusts the recommendation weight based on the actual contribution of each strategy, so that the weight can dynamically reflect the latest effect of the strategy, accurately optimize the strategy priority, and promote it to concentrate on high-effect strategies. Long-term use can sustainably improve the anti-motion sickness effect of the candidate strategy.

[0086] In an optional embodiment of the present application, after combining to obtain candidate strategies, the method further includes:

[0087] Obtaining tag information corresponding to the target user;

[0088] An exclusive intervention strategy matching the tag information is acquired, and the exclusive intervention strategy is added to the candidate strategies.

[0089] By obtaining the tag information corresponding to the target user, the embodiment of the present application can further obtain an exclusive intervention strategy that matches the tag information and add it to the candidate strategy, so that the strategy generation is based on the driving status and historical weight, further fitting the individual characteristics of the user, making up for the insufficient coverage of the general strategy for segmented needs, and improving the personalized accuracy of anti-motion sickness intervention.

[0090] Specifically, the label information needs to cover the key features related to motion sickness, which can be divided into basic attribute labels and behavioral preference labels. Among them, children's inner ear development is not yet mature, the risk of motion sickness is higher, people with motion sickness and low blood pressure are more sensitive to bumps, wearing glasses may affect visual adjustment, and adaptive strategies are needed. Basic attribute labels may include age, health status, physical characteristics, etc.; based on the fact that looking at the phone while riding in a car will inevitably cause dizziness, discomfort in confined spaces, refusal of automatic vehicle deceleration, preference for soothing music, etc., behavioral preference labels may include previous motion sickness triggers, acceptance of strategies, etc. Optionally, these labels can be obtained through user registration information, historical travel feedback, or actively filled out questionnaires. For example, if the user marks "prone to motion sickness + need ventilation when riding" when registering, the corresponding label will be generated.

[0091] Obtain a dedicated intervention strategy that matches the label information and add it to the candidate strategies. Dedicated strategies should be designed to meet the individual needs of the label and complement the general strategy. For example, for the "children" label, dedicated strategies could include "playing animations to distract attention" or "finding signposts." At the same time, the reward mechanism could be adjusted to include stickers, virtual medals, and other forms of interest to children.

[0092] The above implementation scheme of this application, by obtaining user tags and matching exclusive intervention strategies to add them to candidate strategies, can fill the gaps in general strategies in personalized needs, improve user acceptance of strategies, enhance the synergy between exclusive strategies and original strategies, make anti-motion sickness strategies more suitable for individuals, and further improve intervention accuracy and user experience.

[0093] In an optional embodiment of the present application, after updating the personalized anti-motion sickness intervention strategy library corresponding to the target user, the method further includes:

[0094] Uploading the personalized anti-motion intervention strategy library corresponding to the target user to the anti-motion sickness cloud server;

[0095] Wherein, when the target user takes a vehicle other than the target vehicle, the other vehicle obtains the personalized anti-motion intervention strategy library corresponding to the target user from the anti-motion sickness cloud server.

[0096] After updating the personalized anti-motion sickness intervention policy library corresponding to the target user, the embodiment of the present application also uploads the personalized anti-motion sickness intervention policy library corresponding to the target user to the anti-motion sickness cloud server to realize cross-vehicle policy sharing. When the target user takes other vehicles other than the target vehicle, the other vehicles obtain the personalized anti-motion sickness intervention policy library corresponding to the user from the anti-motion sickness cloud server.

[0097] It should be noted that when obtaining the personalized anti-motion sickness intervention policy library corresponding to the user, user identity authentication and policy library adaptation are required. User identity authentication can be achieved through face recognition, account login, etc., to ensure that other vehicles obtain the policy library of the corresponding user to avoid information confusion; policy library adaptation means that after other vehicles obtain the policy library, they will adapt the policy according to their own hardware conditions. For policies that are not supported by the vehicle, they will be automatically replaced with policies with similar functions and supported by the vehicle. For example, when a user rides in a friend's car, the friend's car obtains its personalized policy library from the cloud through the user's logged-in account. If the vehicle does not have the function of automatically adjusting the seat angle, the "adjust the seat angle to semi-reclining" policy will be replaced with "prompt to manually adjust the seat angle."

[0098] The above implementation scheme of this application realizes the cross-vehicle sharing of the user's personalized anti-motion sickness intervention policy library through a cloud server, allowing users to obtain and use their own policy library when riding in any vehicle, realizing cross-scenario policy reuse. The real-time update of the policy library ensures policy continuity. Other vehicles will also adapt their own hardware to provide corresponding intervention, improve the consistency of user experience, and greatly enhance the practicality and user experience of personalized anti-motion sickness services.

[0099] In an optional embodiment of the present application, before obtaining the driving status information corresponding to the target vehicle, the method further includes:

[0100] receiving an anti-motion sickness request for the target user;

[0101] In response to the anti-motion sickness request, a step of acquiring driving state information corresponding to the target vehicle is executed.

[0102] In the embodiments of the present application, the generation and application of candidate strategies can be triggered by a user's proactive motion sickness prevention request. In other words, a user can quickly initiate the generation of a motion sickness prevention strategy upon sensing motion sickness risk or discomfort. Upon receiving a motion sickness prevention request from a target user, the motion sickness prevention control system can acquire physiological indicator information corresponding to the target user and driving status information corresponding to the target vehicle to generate and apply the candidate strategies.

[0103] Specifically, anti-motion sickness request methods can be divided into two categories: active operation and preset trigger. Active operation includes users clicking the "anti-motion sickness mode" button through the touch screen in the car, voice command "turn on anti-motion sickness", and remote sending of requests through the mobile phone APP. For example, if the user knows in advance that he or she will take a car, he or she can initiate it on the APP before departure; preset trigger is when the user sets the trigger conditions in advance, such as "automatically request when the vehicle starts and detects that the user is seated" and "automatically initiate when the user's heart rate exceeds 90 beats / minute", without the need for manual operation.

[0104] The above-mentioned implementation scheme of the present application, by receiving the user's anti-motion sickness request and responding to obtain relevant information, can initiate intervention in time when the user has a need to avoid worsening of symptoms; the user can not initiate a request when it is not necessary, thereby reducing the consumption of resources such as sensors; at the same time, the user is given the right to initiate intervention, thereby improving the acceptance of the service.

[0105] Example 2

[0106] The present application also provides an anti-motion sickness strategy generating device 20, please refer to Figure 2 ,include:

[0107] The first acquisition module 210 is used to obtain the driving state information corresponding to the target vehicle when the target user is riding in the target vehicle;

[0108] a strategy generation module 220 for selecting, based on the driving state information and the recommendation weights of the intervention strategies in the personalized anti-motion sickness intervention strategy library corresponding to the target user, a plurality of intervention strategies from the personalized anti-motion sickness intervention strategy library, combining them to obtain candidate strategies, and applying the candidate strategies;

[0109] A determination module 230 is configured to determine, during the application of the candidate strategy, a total reward value corresponding to the candidate strategy based on the anti-motion sickness effect parameter corresponding to the candidate strategy;

[0110] The first processing module 240 is configured to adjust the recommendation weights corresponding to the plurality of intervention strategies included in the candidate strategies based on the total reward value, and update the weights to the personalized anti-motion sickness intervention strategy library corresponding to the target user.

[0111] Optionally, the determination module includes:

[0112] A judgment submodule, configured to judge whether a state space corresponding to the target vehicle has been transformed according to the driving state information;

[0113] an acquisition submodule, configured to acquire the anti-motion sickness effect parameter corresponding to the candidate strategy each time the state space of the target vehicle is transformed;

[0114] A first calculation submodule, configured to calculate a reward value corresponding to the candidate strategy according to the anti-motion sickness effect parameter;

[0115] The second calculation submodule is used to calculate the sum of the reward values ​​corresponding to the previous state space transitions during the application of the candidate strategy to obtain the total reward value corresponding to the candidate strategy;

[0116] Optionally, the anti-motion sickness effect parameter includes at least one of a physiological indicator change parameter of the target user, a motion sickness improvement degree parameter fed back by the target user, and a matching parameter between the candidate strategy and the state space;

[0117] The first calculation submodule is further configured to:

[0118] Based on a preset reward function, a reward value corresponding to the candidate strategy is determined according to the physiological indicator change parameter, the motion sickness improvement degree parameter, and the matching parameter.

[0119] Optionally, after determining the total reward value corresponding to the candidate strategy, the apparatus further includes:

[0120] A judgment module, used to judge whether the total reward value is less than a preset threshold;

[0121] The second processing module is configured to delete at least one intervention strategy included in the candidate strategies from the personalized anti-motion sickness intervention strategy library when the total reward value is less than a preset threshold.

[0122] Optionally, the policy generation module includes:

[0123] A first determining submodule, configured to determine a driving scene according to the driving state information;

[0124] A second determination submodule is configured to select an intervention strategy that matches the driving scenario and has a recommendation weight greater than a preset weight from the personalized anti-motion sickness intervention strategy library to obtain a valid intervention strategy set;

[0125] a third determination submodule, configured to select, from the personalized anti-motion sickness intervention strategy library, an intervention strategy that matches the driving scenario and has a recommendation weight less than the preset weight, to obtain a random intervention strategy set;

[0126] A selection submodule is used to select the multiple intervention strategies from the effective intervention strategy set and the random intervention strategy set according to a preset exploration ratio, and combine them to obtain the candidate strategy, wherein the preset exploration ratio is determined based on the proportion of effective intervention strategies in the personalized anti-motion sickness intervention strategy library.

[0127] Optionally, the first processing module includes:

[0128] a fourth determination submodule, configured to determine, based on a predetermined correspondence between the total reward value and the weight adjustment coefficient, a target weight adjustment coefficient corresponding to the total reward value according to the total reward value;

[0129] The adjustment submodule is configured to adjust the recommendation weights corresponding to the plurality of target intervention strategies included in the candidate strategies according to the target weight adjustment coefficient.

[0130] Optionally, after combining and obtaining candidate strategies, the method further includes:

[0131] A second acquisition module is used to obtain tag information corresponding to the target user;

[0132] The third processing module is configured to obtain an exclusive intervention strategy that matches the tag information and add the exclusive intervention strategy to the candidate strategies.

[0133] Optionally, after updating the personalized anti-motion sickness intervention strategy library corresponding to the target user, the device further includes:

[0134] An uploading module, configured to upload the personalized anti-motion intervention strategy library corresponding to the target user to the anti-motion sickness cloud server;

[0135] Wherein, when the target user takes a vehicle other than the target vehicle, the other vehicle obtains the personalized anti-motion intervention strategy library corresponding to the target user from the anti-motion sickness cloud server.

[0136] Optionally, before obtaining the driving state information corresponding to the target vehicle, the device further includes:

[0137] A receiving module, configured to receive an anti-motion sickness request for the target user;

[0138] An execution module is used to execute the step of obtaining the driving state information corresponding to the target vehicle in response to the anti-motion sickness request.

[0139] The anti-motion sickness strategy generation device provided in the embodiments of this application achieves the following technical effects: by acquiring real-time vehicle driving status and combining it with a user's personalized anti-motion sickness intervention strategy library, it generates adaptive candidate strategies. Then, based on feedback from the actual effectiveness of the candidate strategies, it dynamically optimizes the recommendation weights of the candidate strategies in the personalized anti-motion sickness intervention strategy library, forming a complete closed loop. This allows the device to precisely tailor the strategy to the user's individual characteristics and real-time scenario requirements, effectively improving the targetedness and adaptability of anti-motion sickness intervention. Furthermore, the device continuously improves with use, ensuring continuous optimization of the anti-motion sickness effect over time.

[0140] It should be noted that the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0141] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0142] Example 3

[0143] An embodiment of the present application also provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the various processes of the above-mentioned anti-motion sickness strategy generation method embodiment are implemented, and the same technical effects can be achieved. To avoid repetition, they will not be described here.

[0144] For example, Figure 3 FIG. 1 shows a schematic diagram of the physical structure of an electronic device. Figure 3 As shown, the electronic device 340 may include: a processor 310, a communications interface 320, a memory 330, and a communications bus 340. The processor 310, the communications interface 320, and the memory 330 communicate with each other via the communications bus 340. The processor 310 may invoke logic instructions stored in the memory 330 to perform the following steps: when a target user is riding in a target vehicle, obtaining driving state information corresponding to the target vehicle; based on the driving state information and the recommendation weights corresponding to the respective intervention strategies in a personalized anti-motion sickness intervention strategy library corresponding to the target user, selecting multiple intervention strategies from the personalized anti-motion sickness intervention strategy library, combining them to obtain candidate strategies, and applying the candidate strategies; during the application of the candidate strategies, determining a total reward value corresponding to the candidate strategies based on the anti-motion sickness effect parameters corresponding to the candidate strategies; and adjusting the recommendation weights corresponding to the respective intervention strategies included in the candidate strategies based on the total reward value, and updating the recommendation weights corresponding to the respective intervention strategies in the personalized anti-motion sickness intervention strategy library corresponding to the target user. The processor 310 may also execute other solutions in the embodiments of the present application, which will not be further elaborated here.

[0145] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application.

[0146] Example 4

[0147] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned anti-motion sickness strategy generation method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0148] In this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0149] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0150] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0151] In this application, a plurality refers to two or more.

[0152] In this application, unless otherwise expressly defined, the terms "mounted," "connected," and "connected" should be interpreted broadly. For example, they can refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediary; and internal communication between two components. A person of ordinary skill in the art will understand the specific meanings of these terms in this application.

[0153] The terms "first," "second," "third," "fourth," etc. in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0154] The term "and / or" in this application simply describes an association between related objects, indicating that three possible relationships exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this application generally indicates that the related objects are in an "or" relationship.

[0155] Unless otherwise specified, all steps of the present application may be performed sequentially or randomly. For example, a statement that the method includes steps A and B indicates that the method may include steps A and B performed sequentially, or steps B and A performed sequentially. For example, a statement that the method may also include step C indicates that step C may be added to the method in any order, for example, the method may include steps A, B, and C, or steps A, C, and B, or steps C, A, and B, etc.

[0156] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method for generating an anti-motion sickness strategy, characterized in that: include: When the target user is riding in the target vehicle, obtaining driving status information corresponding to the target vehicle; Based on the driving state information and the recommendation weights of the intervention strategies in the personalized anti-motion sickness intervention strategy library corresponding to the target user, selecting multiple intervention strategies from the personalized anti-motion sickness intervention strategy library, combining them to obtain candidate strategies, and applying the candidate strategies; During the application of the candidate strategy, determining a total reward value corresponding to the candidate strategy based on an anti-motion sickness effect parameter corresponding to the candidate strategy; The recommendation weights corresponding to the plurality of intervention strategies included in the candidate strategies are adjusted based on the total reward value, and the weights are updated into a personalized anti-motion sickness intervention strategy library corresponding to the target user.

2. The anti-motion sickness strategy generation method according to claim 1, characterized in that: Determining a total reward value corresponding to the candidate strategy based on the anti-motion sickness effect parameter corresponding to the candidate strategy includes: Determining whether a state space corresponding to the target vehicle has been transformed based on the driving state information; Each time the state space of the target vehicle is transformed, obtaining an anti-motion sickness effect parameter corresponding to the candidate strategy; Calculating a reward value corresponding to the candidate strategy according to the anti-motion sickness effect parameter; The sum of the reward values ​​corresponding to each state space transition during the application of the candidate strategy is calculated to obtain a total reward value corresponding to the candidate strategy.

3. The anti-motion sickness strategy generation method according to claim 2, characterized in that: The anti-motion sickness effect parameter includes at least one of a physiological indicator change parameter of the target user, a motion sickness improvement degree parameter fed back by the target user, and a matching parameter between the candidate strategy and the state space; Calculating a reward value corresponding to the candidate strategy according to the anti-motion sickness effect parameter includes: Based on a preset reward function, a reward value corresponding to the candidate strategy is determined according to the physiological indicator change parameter, the motion sickness improvement degree parameter, and the matching parameter.

4. The anti-motion sickness strategy generation method according to claim 1, characterized in that: After determining the total reward value corresponding to the candidate strategy, the method further includes: Determining whether the total reward value is less than a preset threshold; When the total reward value is less than a preset threshold, at least one intervention strategy included in the candidate strategies is deleted from the personalized anti-motion sickness intervention strategy library.

5. The anti-motion sickness strategy generation method according to claim 1, characterized in that: Based on the driving state information and the recommendation weights of the intervention strategies in the personalized anti-motion sickness intervention strategy library corresponding to the target user, multiple intervention strategies are selected from the personalized anti-motion sickness intervention strategy library to obtain candidate strategies by combining them, including: determining a driving scene according to the driving state information; Selecting an intervention strategy that matches the driving scenario and has a recommendation weight greater than a preset weight from the personalized anti-motion sickness intervention strategy library to obtain an effective intervention strategy set; selecting, from the personalized anti-motion sickness intervention strategy library, an intervention strategy that matches the driving scenario and has a recommendation weight less than the preset weight, to obtain a random intervention strategy set; According to a preset exploration ratio, the multiple intervention strategies are selected from the effective intervention strategy set and the random intervention strategy set, and the candidate strategies are obtained by combining them, wherein the preset exploration ratio is determined based on the proportion of effective intervention strategies in the personalized anti-motion sickness intervention strategy library.

6. The anti-motion sickness strategy generation method according to claim 1, characterized in that: Adjusting the recommendation weights corresponding to the plurality of target intervention strategies included in the candidate strategies based on the total reward value includes: Based on a predetermined correspondence between a total reward value and a weight adjustment coefficient, determining a target weight adjustment coefficient corresponding to the total reward value according to the total reward value; The recommendation weights corresponding to the multiple target intervention strategies included in the candidate strategies are adjusted according to the target weight adjustment coefficient.

7. The anti-motion sickness strategy generation method according to claim 1, characterized in that: After combining and obtaining the candidate strategies, the method further includes: Obtaining tag information corresponding to the target user; An exclusive intervention strategy matching the tag information is acquired, and the exclusive intervention strategy is added to the candidate strategies.

8. The anti-motion sickness strategy generation method according to claim 1, characterized in that: After updating the personalized anti-motion sickness intervention strategy library corresponding to the target user, the method further includes: Uploading the personalized anti-motion intervention strategy library corresponding to the target user to the anti-motion sickness cloud server; Wherein, when the target user takes a vehicle other than the target vehicle, the other vehicle obtains the personalized anti-motion intervention strategy library corresponding to the target user from the anti-motion sickness cloud server.

9. The anti-motion sickness strategy generation method according to claim 1, characterized in that: Before obtaining the driving state information corresponding to the target vehicle, the method further includes: receiving an anti-motion sickness request for the target user; In response to the anti-motion sickness request, a step of acquiring driving state information corresponding to the target vehicle is executed.

10. An anti-motion sickness strategy generating device, characterized in that: include: A first acquisition module is used to acquire driving status information corresponding to the target vehicle when the target user is riding in the target vehicle; a strategy generation module, configured to select a plurality of intervention strategies from the personalized anti-motion sickness intervention strategy library based on the driving state information and the recommendation weights of the intervention strategies in the personalized anti-motion sickness intervention strategy library corresponding to the target user, combine the plurality of intervention strategies to obtain candidate strategies, and apply the candidate strategies; a determination module, configured to determine, during the application of the candidate strategy, a total reward value corresponding to the candidate strategy based on the anti-motion sickness effect parameter corresponding to the candidate strategy; The first processing module is configured to adjust the recommendation weights corresponding to the plurality of intervention strategies included in the candidate strategies based on the total reward value, and update the weights to a personalized anti-motion sickness intervention strategy library corresponding to the target user.

11. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the method for generating an anti-motion sickness strategy according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the anti-motion sickness strategy generation method according to any one of claims 1 to 9 is implemented.

Images