Carsickness probability model training method and device, computer equipment and storage medium

Abstract

The invention discloses a carsickness probability model training method and device, computer equipment and a storage medium, and relates to the technical field of intelligent driving, and the method comprises the steps: obtaining historical feature data corresponding to a historical travel; determining an importance level corresponding to the historical feature data, and determining a target weight corresponding to the historical feature data based on the importance level; and performing model training based on the historical feature data and the target weight to obtain a carsickness probability model. Through the method, the information in the historical feature data can be effectively utilized, and the accuracy of predicting the carsickness probability by the carsickness probability model is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a motion sickness probability model training method, device, computer equipment and storage medium. Background Art

[0002] As passengers have higher and higher expectations for vehicles, in addition to the basic requirement of arriving at the destination safely, ride comfort has also become an important criterion. Motion sickness is one of the important factors affecting ride comfort. Motion sickness symptoms such as sweating, dizziness, nausea, and vomiting greatly affect the passenger's riding experience. Once motion sickness occurs during the driving process of the vehicle, the passenger either gets off the vehicle, resulting in failure to reach the destination, or insists on painfully, resulting in physical discomfort and extremely poor physical examination. Therefore, how to prevent passengers from motion sickness in a timely manner and improve the intelligence of the vehicle has become a technical problem that needs to be solved urgently.

[0003] At present, in order to prevent passengers from getting motion sickness in time, the current motion sickness probability of the target passenger is usually predicted based on the target passenger's historical motion sickness before the target passenger travels. However, since the causes of motion sickness of different passengers may be different, and the causes of motion sickness of the same passenger in different situations may also be different, the accuracy of predicting the current motion sickness probability based only on historical motion sickness is not high. Summary of the invention

[0004] Based on this, a motion sickness probability model training method, device, computer equipment and storage medium are provided to improve the problem in the prior art that the accuracy of predicting the current motion sickness probability based only on historical motion sickness situations is low.

[0005] In a first aspect, the present application provides a motion sickness probability model training method, the method comprising:

[0006] Acquire historical feature data corresponding to historical trips; wherein the historical feature data includes historical driving behavior data, historical passenger data, and historical vehicle data;

[0007] Determining an importance level corresponding to the historical feature data, and determining a target weight corresponding to the historical feature data based on the importance level;

[0008] Model training is performed based on the historical feature data and the target weight to obtain a motion sickness probability model.

[0009] In one embodiment, the acquiring of historical feature data corresponding to the historical trip includes:

[0010] Acquire historical driving behavior data corresponding to the historical trip; wherein the historical driving behavior data includes at least one of the number of sudden accelerations, the number of sudden decelerations, the number of sharp turns, and the number of sudden brakes;

[0011] Acquire historical passenger data corresponding to the historical trip; wherein the historical passenger data includes at least one of passenger information, passenger behavior, the number of passengers in the vehicle, and the position of passengers in the vehicle;

[0012] Obtain historical vehicle data corresponding to the historical trip; wherein the historical vehicle data includes at least one of vehicle type, vehicle energy recovery mode, congestion condition of the driving route, odor concentration in the vehicle, and vehicle suspension hardness.

[0013] In one embodiment, determining the target weight corresponding to the historical feature data based on the importance level includes:

[0014] The target weight corresponding to the historical feature data is determined based on the positive correlation between the importance level and the weight.

[0015] In one embodiment, the performing model training based on the historical feature data and the target weight to obtain a motion sickness probability model includes:

[0016] Performing weighted processing on the historical feature data based on the target weight to obtain training data;

[0017] The parameters of the preset model are initialized, and the initialized preset model is iteratively trained based on the training data to obtain the motion sickness probability model.

[0018] In a second aspect, the present application provides a motion sickness prompting method, which adopts the motion sickness probability model of the first aspect, and the method comprises:

[0019] Inputting the target feature data corresponding to the target passenger into the motion sickness probability model for prediction to obtain the target motion sickness probability corresponding to the target passenger; wherein the target feature data includes current driving behavior data, target passenger data and current vehicle data;

[0020] Prompt the target passenger for motion sickness according to the target motion sickness probability.

[0021] In one embodiment, providing the target passenger with a motion sickness reminder according to the target motion sickness probability includes:

[0022] Determining a probability range to which the target motion sickness probability belongs;

[0023] Execute a prompt operation corresponding to the probability range.

[0024] In one embodiment, the performing of the prompt operation corresponding to the probability range includes:

[0025] When the probability range is a first probability range, outputting the target motion sickness probability to a display screen of the current vehicle;

[0026] When the probability range is a second probability range, voice data corresponding to the target motion sickness probability is generated, the voice data is played, and the target motion sickness probability is output to the display screen; wherein the minimum value of the second probability range is greater than the maximum value of the first probability range;

[0027] When the probability range is a third probability range, the current vehicle is controlled to perform anti-motion sickness measures; wherein the minimum value of the third probability range is greater than the maximum value of the second probability range, and the anti-motion sickness measures include at least one of adjusting the vehicle driving state, adjusting the in-car audio state, adjusting the in-car lighting state, adjusting the in-car air state, and adjusting the seat state.

[0028] In a third aspect, the present application provides a motion sickness probability model training device, the device comprising:

[0029] An acquisition module, used to acquire historical feature data corresponding to historical trips; wherein the historical feature data includes historical driving behavior data, historical passenger data, and historical vehicle data;

[0030] A determination module, configured to determine an importance level corresponding to the historical feature data, and determine a target weight corresponding to the historical feature data based on the importance level;

[0031] A training module is used to perform model training based on the historical feature data and the target weight to obtain a motion sickness probability model.

[0032] In one embodiment, the acquisition module is specifically used for:

[0033] Acquire historical driving behavior data corresponding to the historical trip; wherein the historical driving behavior data includes at least one of the number of sudden accelerations, the number of sudden decelerations, the number of sharp turns, and the number of sudden brakes;

[0034] Acquire historical passenger data corresponding to the historical trip; wherein the historical passenger data includes at least one of passenger information, passenger behavior, the number of passengers in the vehicle, and the position of passengers in the vehicle;

[0035] Obtain historical vehicle data corresponding to the historical trip; wherein the historical vehicle data includes at least one of vehicle type, vehicle energy recovery mode, congestion condition of the driving route, odor concentration in the vehicle, and vehicle suspension hardness.

[0036] In one embodiment, the determining module is specifically used to:

[0037] The target weight corresponding to the historical feature data is determined based on the positive correlation between the importance level and the weight.

[0038] In one embodiment, the training module is specifically used for:

[0039] Performing weighted processing on the historical feature data based on the target weight to obtain training data;

[0040] The parameters of the preset model are initialized, and the initialized preset model is iteratively trained based on the training data to obtain the motion sickness probability model.

[0041] In a fourth aspect, the present application provides a motion sickness reminder device, the motion sickness reminder device comprising:

[0042] A prediction module, used for inputting target feature data corresponding to a target passenger into a motion sickness probability model for prediction, and obtaining a target motion sickness probability corresponding to the target passenger; wherein the target feature data includes current driving behavior data, target passenger data, and current vehicle data;

[0043] The motion sickness prompting module is used to provide motion sickness prompting to the target passenger according to the target motion sickness probability.

[0044] In one embodiment, the motion sickness prompt module is specifically used for:

[0045] Determining a probability range to which the target motion sickness probability belongs;

[0046] Execute a prompt operation corresponding to the probability range.

[0047] In one embodiment, the motion sickness prompt module is further used for:

[0048] When the probability range is a first probability range, outputting the target motion sickness probability to a display screen of the current vehicle;

[0049] When the probability range is a second probability range, voice data corresponding to the target motion sickness probability is generated, the voice data is played, and the target motion sickness probability is output to the display screen; wherein the minimum value of the second probability range is greater than the maximum value of the first probability range;

[0050] When the probability range is a third probability range, the current vehicle is controlled to perform anti-motion sickness measures; wherein the minimum value of the third probability range is greater than the maximum value of the second probability range, and the anti-motion sickness measures include at least one of adjusting the vehicle driving state, adjusting the in-car audio state, adjusting the in-car lighting state, adjusting the in-car air state, and adjusting the seat state.

[0051] In a fifth aspect, the present application provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the motion sickness probability model training method of the first aspect and the motion sickness prompt method of the second aspect when executing the computer program.

[0052] In a sixth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the motion sickness probability model training method of the first aspect and the motion sickness prompt method of the second aspect are implemented.

[0053] The above-mentioned motion sickness probability model training method, device, computer equipment and storage medium determine the target weight corresponding to the historical feature data based on the importance level corresponding to the historical feature data, and perform model training based on the historical feature data and the target weight corresponding to the historical feature data to obtain a motion sickness probability model. The information in the historical feature data can be effectively utilized to improve the accuracy of the motion sickness probability model in predicting the probability of motion sickness. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic diagram of a flow chart of a motion sickness probability model training method in one embodiment;

[0055] Figure 2 A schematic diagram of a process of a motion sickness prompting method in one embodiment;

[0056] Figure 3 is a structural block diagram of a motion sickness probability model training device in one embodiment;

[0057] Figure 4 is a structural block diagram of a motion sickness prompting device in one embodiment;

[0058] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The specific operating methods in the method embodiments can also be applied to device embodiments or system embodiments. It should be noted that in the description of the present application, "multiple" is understood as "at least two". "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, and A and B exist, and B exists alone. A is connected to B, which can represent: A is directly connected to B and A is connected to B through C. In addition, in the description of the present application, words such as "first" and "second" are only used to distinguish the purpose of description, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order.

[0060] The following is a brief introduction to the background technology of the embodiments of the present application.

[0061] At present, in order to prevent passengers from getting motion sickness in time, the current motion sickness probability of the target passenger is usually predicted based on the target passenger's historical motion sickness before the target passenger travels. However, since the causes of motion sickness of different passengers may be different, and the causes of motion sickness of the same passenger in different situations may also be different, the accuracy of predicting the current motion sickness probability based only on historical motion sickness is not high.

[0062] In order to solve the above problems, the embodiment of the present application provides a method for training a motion sickness probability model, which determines the target weight of the historical feature data based on the importance level corresponding to the historical feature data, and performs model training based on the historical feature data and the target weight corresponding to the historical feature data to obtain a motion sickness probability model, which can effectively utilize the information in the historical feature data and improve the accuracy of the motion sickness probability model in predicting the motion sickness probability. Among them, the method and device described in the embodiment of the present application are based on the same technical concept. Since the principles of the problems solved by the method and the device are similar, the embodiments of the device and the method can refer to each other, and the repeated parts will not be repeated.

[0063] To further illustrate the technical solution provided by the embodiments of the present application, a detailed description is given below in conjunction with the accompanying drawings and specific implementation methods.

[0064] Embodiment 1

[0065] Figure 1 A flowchart of a motion sickness probability model training method provided in an embodiment of the present application, the process includes the following steps:

[0066] Step 102, obtaining historical feature data corresponding to the historical trip.

[0067] Among them, historical feature data includes historical driving behavior data, historical passenger data and historical vehicle data.

[0068] Specifically, historical driving behavior data corresponding to the historical trips is obtained; wherein the historical driving behavior data includes at least one of the number of sudden accelerations, the number of sudden decelerations, the number of sharp turns, and the number of sudden brakes.

[0069] Exemplarily, the driving speeds at several moments recorded at a certain frequency by the speed sensor corresponding to the historical trip are obtained. Whenever the change between the driving speed at the next moment and the driving speed at the previous moment is greater than 20 km / h, the number of sudden accelerations is increased by 1, and whenever the change between the driving speed at the next moment and the driving speed at the previous moment is less than -20 km / h, the number of sudden decelerations is increased by 1. The steering wheel steering angles at several moments recorded at a certain frequency by the steering wheel angle sensor corresponding to the historical trip are obtained. Whenever the absolute change between the steering wheel steering angle at the next moment and the steering wheel steering angle at the previous moment is greater than 90 degrees, the number of sharp turns is increased by 1. The brake pedal depths at several moments recorded at a certain frequency by the pedal position sensor corresponding to the historical trip are obtained. Whenever the change between the brake pedal depth at the next moment and the brake pedal depth at the previous moment is greater than 15 mm, the number of sudden brakes is increased by 1.

[0070] It should be noted that the number of sudden accelerations and decelerations can also be determined based on the accelerator pedal depth and the brake pedal depth, and the number of sudden brakes can be determined based on the change in driving speed. The judgment conditions for the change in driving speed, the change in brake pedal depth, and the absolute change in steering wheel angle depend on the circumstances and are not limited here.

[0071] Obtain historical passenger data corresponding to historical trips; wherein the historical passenger data includes at least one of passenger information, passenger behavior, the number of passengers in the vehicle, and the position of passengers in the vehicle.

[0072] Exemplarily, passenger information is obtained, such as name, ID, number, age, gender, health status, etc.; the number of passengers in the car and the position of the passengers in the car are obtained through the in-car seat detection module; and passenger behavior is obtained through the in-car camera, such as playing with mobile phones, reading, etc.

[0073] Obtain historical vehicle data corresponding to historical trips; wherein the historical vehicle data includes at least one of: vehicle type, vehicle energy recovery mode, congestion condition of the driving route, concentration of odor in the vehicle, and hardness of the vehicle suspension.

[0074] Exemplarily, the vehicle type is obtained, such as an off-road vehicle, a bus, etc.; the vehicle energy recovery mode is obtained based on user settings, wherein the vehicle energy recovery mode includes strong and weak; the route is planned by the destination input by the passenger in the navigation app after getting on the vehicle, and the driving route is obtained, and the congestion situation of the driving route is obtained based on the navigation app (for example, the average speed of traffic is used as an evaluation criterion to identify congested sections, determine the mileage percentage of congested sections, the number of congested sections, the duration of congestion, etc.); the odor concentration in the vehicle is obtained through the odor signal input by the odor sensor; the hardness of the vehicle suspension is obtained based on the user setting signal.

[0075] Furthermore, the data obtained above can also be preprocessed, and at least one of the preprocessed sudden acceleration times, preprocessed sudden deceleration times, preprocessed sharp turns, and preprocessed sudden braking times can be used as historical driving behavior data; at least one of the preprocessed passenger information, preprocessed passenger behavior, preprocessed number of passengers in the car, and preprocessed passenger positions in the car can be used as historical passenger data; at least one of the preprocessed vehicle type, preprocessed vehicle energy recovery mode, preprocessed congestion of the driving route, preprocessed odor concentration in the car, and preprocessed vehicle suspension hardness can be used as historical vehicle data; wherein, preprocessing includes: cleaning the data, processing missing values, outliers, etc., and standardizing or normalizing the data to ensure that different feature dimensions are consistent.

[0076] Through the above method, historical feature data of multiple dimensions are obtained, so that when model training is performed based on the historical feature data of multiple dimensions to obtain a motion sickness probability model, the generalization and accuracy of the motion sickness probability model can be improved.

[0077] Step 104: Determine the importance level corresponding to the historical feature data, and determine the target weight corresponding to the historical feature data based on the importance level.

[0078] Specifically, the importance level corresponding to the historical feature data can be evaluated by a variety of methods, such as statistical methods (card room verification, mutual information), model-based methods (random forest, gradient boosting) or expert knowledge, or it can be manually set by the passenger. The importance level can be represented by 1, 2, 3,..., or by I, II, III,..., or by a, b, c..., depending on the specific situation and is not limited here.

[0079] Furthermore, the target weight corresponding to the historical feature data is determined based on the positive correlation between the importance level and the weight.

[0080] For example, historical feature data includes historical driving behavior data corresponding to historical trips, passenger positions in the car, number of passengers in the car, vehicle energy recovery mode, odor concentration in the car, congestion on the driving route, and vehicle suspension hardness, and the corresponding importance levels are: vehicle energy recovery mode (7) > historical driving behavior data (6) > odor concentration in the car (5) > congestion on the driving route (4) > passenger positions in the car (3) > number of passengers in the car (2) > vehicle suspension hardness (1). The positive correlation between importance level and weight is shown in Table 1:

[0081] Importance level 1 2 3 4 5 6 7 …… Weight 0.1 0.2 0.3 0.4 0.5 0.6 0.7 ……

[0082] Table 1 A positive correlation between importance level and weight

[0083] It can be seen from Table 1 that the target weight corresponding to the vehicle energy recovery mode is 0.7, the target weight corresponding to the historical driving behavior data is 0.6, the target weight corresponding to the odor concentration in the car is 0.5, the target weight corresponding to the congestion of the driving route is 0.4, the target weight corresponding to the passenger position in the car is 0.3, the target weight corresponding to the number of passengers in the car is 0.2, and the target weight corresponding to the hardness of the vehicle suspension is 0.1.

[0084] It should be noted that, those skilled in the art can set a positive correlation between the importance level and the weight according to different requirements based on the above, and this is not limited here.

[0085] Through the above method, the target weight corresponding to the historical feature data is determined based on the positive correlation between the importance level of the historical feature data and the weight, which can retain the different degrees of influence of different historical feature data on the motion sickness probability, thereby improving the accuracy and efficiency of the motion sickness probability model.

[0086] Step 106: Perform model training based on the historical feature data and the target weight to obtain a motion sickness probability model.

[0087] First, a motion sickness probability label corresponding to the historical feature data (eg, the historical motion sickness probability corresponding to the historical feature data) is obtained, wherein the motion sickness probability label can be obtained from passenger feedback and / or expert experience.

[0088] Specifically, the motion sickness probability model is obtained by performing model training based on the motion sickness probability label corresponding to the historical feature data, the historical feature data, and the target weight, including:

[0089] First, a suitable model is selected as a preset model, such as logistic regression, decision tree, random forest, gradient boosting tree, neural network, etc., and the parameters of the preset model are initialized to obtain an initialized preset model, wherein the initialization can be random.

[0090] Then, the historical feature data corresponding to the historical trips are divided into training set, validation set and test set. The training set is used to train the model, the validation set is used to adjust the model parameters and avoid overfitting, and the test set is used to evaluate the performance of the model.

[0091] In one embodiment, the training data in the training set can be obtained by weighting the historical feature data based on the target weight. For example, the historical feature data includes the vehicle energy recovery mode, historical driving behavior data and the odor concentration in the vehicle corresponding to the historical trip. The target weight corresponding to the vehicle energy recovery mode is 0.7, the target weight corresponding to the historical driving behavior data is 0.6, and the target weight corresponding to the odor concentration in the vehicle is 0.5. Then the weighted feature data is: vehicle energy recovery mode*0.7, historical driving behavior data*0.6, odor concentration in the vehicle*0.5, and it is used as training data.

[0092] Furthermore, the initialized preset model is iteratively trained based on the training data and the corresponding motion sickness probability labels to learn the mapping relationship between the motion sickness probability and the historical feature data, and obtain the motion sickness probability model.

[0093] During the training process, the difference between the model prediction results and the actual results is measured based on the loss function, and the model parameters are optimized by minimizing the loss function, such as adjusting the model's learning rate, number of iterations, regularization terms, etc. The specific optimization algorithm depends on the situation and is not limited here. At the same time, the test set or validation set is used to evaluate the model performance, and the structure or parameters of the model are adjusted according to the evaluation results to improve the accuracy and generalization ability of the model until the model performance meets the requirements (for example, the accuracy rate is greater than 90%, the recall rate is greater than 92%, etc.), and the motion sickness probability model is obtained. Common evaluation indicators include accuracy rate, recall rate, etc.

[0094] In the above-mentioned motion sickness probability model training method, the target weight corresponding to the historical feature data is determined based on the importance level corresponding to the historical feature data, and the model is trained based on the historical feature data and the target weight corresponding to the historical feature data to obtain the motion sickness probability model. This can effectively utilize the information in the historical feature data and improve the accuracy of the motion sickness probability model in predicting the probability of motion sickness.

[0095] Embodiment 2

[0096] Figure 2 A flow chart of a motion sickness prompting method provided in an embodiment of the present application, the flow includes the following steps:

[0097] Step 202: input the target feature data corresponding to the target passenger into the motion sickness probability model for prediction to obtain the target motion sickness probability corresponding to the target passenger.

[0098] The target feature data includes current driving behavior data, target passenger data and current vehicle data.

[0099] Specifically, the target feature data is preprocessed (consistent with the preprocessing in Example 1, and will not be repeated here), and the preprocessed target feature data is input into the motion sickness probability model in Example 1 to obtain the target motion sickness probability corresponding to the target passenger, and store it in the database.

[0100] Step 204: Prompt the target passenger for motion sickness based on the target motion sickness probability.

[0101] Specifically, the probability range to which the target motion sickness probability belongs is determined, and a prompt operation corresponding to the probability range is performed, thereby timely and efficiently avoiding motion sickness of passengers.

[0102] Exemplarily, when the probability range is the first probability range, the target motion sickness probability is output to the display screen of the current vehicle; when the probability range is the second probability range, voice data corresponding to the target motion sickness probability is generated, the voice data is played, and the target motion sickness probability is output to the display screen of the current vehicle; wherein the minimum value of the second probability range is greater than the maximum value of the first probability range; when the probability range is the third probability range, the current vehicle is controlled to perform anti-motion sickness measures; wherein the minimum value of the third probability range is greater than the maximum value of the second probability range, and the anti-motion sickness measures include at least one of adjusting the vehicle driving state, adjusting the in-car audio state, adjusting the in-car lighting state, adjusting the in-car air state, and adjusting the seat state. Thus, the efficiency of motion sickness prompts can be improved.

[0103] Among them, the above-mentioned first probability range, second probability range, and third probability range can be (0, 50%), [50%, 80%), and [80%, 100%], respectively, depending on the specific situation and are not limited here.

[0104] In the above-mentioned motion sickness prompt method, the target motion sickness probability corresponding to the target passenger is predicted based on the motion sickness probability model, and the target passenger is prompted with motion sickness according to the target motion sickness probability, which can timely prevent the passenger from getting motion sickness and improve the intelligence of the vehicle.

[0105] It should be understood that although Figure 1-2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1-2At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0106] In one embodiment, Figure 3 As shown, a motion sickness probability model training device is provided, comprising: an acquisition module 301, a determination module 302 and a training module 303, wherein:

[0107] The acquisition module 301 is used to acquire historical feature data corresponding to historical trips; wherein the historical feature data includes historical driving behavior data, historical passenger data and historical vehicle data;

[0108] A determination module 302 is used to determine the importance level corresponding to the historical feature data, and determine the target weight corresponding to the historical feature data based on the importance level;

[0109] The training module 303 is used to perform model training based on historical feature data and target weights to obtain a motion sickness probability model.

[0110] In one embodiment, the acquisition module 301 is specifically used for:

[0111] Obtaining historical driving behavior data corresponding to the historical trip; wherein the historical driving behavior data includes at least one of the number of sudden accelerations, the number of sudden decelerations, the number of sharp turns, and the number of sudden brakes;

[0112] Obtain historical passenger data corresponding to the historical trips; wherein the historical passenger data includes at least one of passenger information, passenger behavior, the number of passengers in the vehicle, and the position of passengers in the vehicle;

[0113] Obtain historical vehicle data corresponding to historical trips; wherein the historical vehicle data includes at least one of vehicle type, vehicle energy recovery mode, congestion condition of the driving route, odor concentration in the vehicle, and vehicle suspension hardness.

[0114] In one embodiment, the determination module 302 is specifically configured to:

[0115] The target weight corresponding to the historical feature data is determined based on the positive correlation between the importance level and the weight.

[0116] In one embodiment, the training module 303 is specifically used to:

[0117] Perform weighted processing on historical feature data based on target weights to obtain training data;

[0118] The parameters of the preset model are initialized, and the initialized preset model is iteratively trained based on the training data to obtain a motion sickness probability model.

[0119] In one embodiment, Figure 4 As shown, a motion sickness prompting device is provided, comprising: an acquisition module 301, a determination module 302, a training module 303, a prediction module 401 and a motion sickness prompting module 402, wherein:

[0120] The prediction module 401 is used to input the target feature data corresponding to the target passenger into the motion sickness probability model for prediction, and obtain the target motion sickness probability corresponding to the target passenger; wherein the target feature data includes current driving behavior data, target passenger data and current vehicle data;

[0121] The motion sickness prompting module 402 is used to provide motion sickness prompting to the target passenger according to the target motion sickness probability.

[0122] In one embodiment, the motion sickness prompt module 402 is specifically used for:

[0123] Determine the probability range to which the target motion sickness probability belongs;

[0124] Execute the prompt operation corresponding to the probability range.

[0125] In one embodiment, the motion sickness prompt module 402 is further used for:

[0126] When the probability range is the first probability range, outputting the target motion sickness probability to a display screen of the current vehicle;

[0127] When the probability range is the second probability range, voice data corresponding to the target motion sickness probability is generated, the voice data is played, and the target motion sickness probability is output to the display screen; wherein the minimum value of the second probability range is greater than the maximum value of the first probability range;

[0128] When the probability range is the third probability range, the current vehicle is controlled to perform anti-motion sickness measures; wherein the minimum value of the third probability range is greater than the maximum value of the second probability range, and the anti-motion sickness measures include at least one of adjusting the vehicle driving state, adjusting the in-car audio state, adjusting the in-car lighting state, adjusting the in-car air state, and adjusting the seat state.

[0129] For the specific limitations of the motion sickness probability model training device and the motion sickness prompt device, please refer to the limitations of the motion sickness probability model training method and the motion sickness prompt method in the above text, which will not be repeated here. Each module in the above-mentioned motion sickness probability model training device and motion sickness prompt device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0130] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store motion sickness probability model training and motion sickness prompt data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a motion sickness probability model training method and a motion sickness prompt method are implemented.

[0131] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0132] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0133] Obtaining historical feature data corresponding to historical trips; wherein the historical feature data includes historical driving behavior data, historical passenger data, and historical vehicle data;

[0134] Determine the importance level corresponding to the historical feature data, and determine the target weight corresponding to the historical feature data based on the importance level;

[0135] Model training is performed based on historical feature data and target weights to obtain a motion sickness probability model.

[0136] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0137] Obtaining historical driving behavior data corresponding to the historical trip; wherein the historical driving behavior data includes at least one of the number of sudden accelerations, the number of sudden decelerations, the number of sharp turns, and the number of sudden brakes;

[0138] Obtain historical passenger data corresponding to the historical trips; wherein the historical passenger data includes at least one of passenger information, passenger behavior, the number of passengers in the vehicle, and the position of passengers in the vehicle;

[0139] Obtain historical vehicle data corresponding to historical trips; wherein the historical vehicle data includes at least one of vehicle type, vehicle energy recovery mode, congestion condition of the driving route, odor concentration in the vehicle, and vehicle suspension hardness.

[0140] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0141] The target weight corresponding to the historical feature data is determined based on the positive correlation between the importance level and the weight.

[0142] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0143] Perform weighted processing on historical feature data based on target weights to obtain training data;

[0144] The parameters of the preset model are initialized, and the initialized preset model is iteratively trained based on the training data to obtain a motion sickness probability model.

[0145] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0146] Inputting the target feature data corresponding to the target passenger into the motion sickness probability model for prediction, and obtaining the target motion sickness probability corresponding to the target passenger; wherein the target feature data includes current driving behavior data, target passenger data, and current vehicle data;

[0147] According to the target motion sickness probability, the target passengers are given motion sickness prompts.

[0148] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0149] Determine the probability range to which the target motion sickness probability belongs;

[0150] Execute the prompt operation corresponding to the probability range.

[0151] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0152] When the probability range is the first probability range, outputting the target motion sickness probability to a display screen of the current vehicle;

[0153] When the probability range is the second probability range, voice data corresponding to the target motion sickness probability is generated, the voice data is played, and the target motion sickness probability is output to the display screen; wherein the minimum value of the second probability range is greater than the maximum value of the first probability range;

[0154] When the probability range is the third probability range, the current vehicle is controlled to perform anti-motion sickness measures; wherein the minimum value of the third probability range is greater than the maximum value of the second probability range, and the anti-motion sickness measures include at least one of adjusting the vehicle driving state, adjusting the in-car audio state, adjusting the in-car lighting state, adjusting the in-car air state, and adjusting the seat state.

[0155] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0156] Obtaining historical feature data corresponding to historical trips; wherein the historical feature data includes historical driving behavior data, historical passenger data, and historical vehicle data;

[0157] Determine the importance level corresponding to the historical feature data, and determine the target weight corresponding to the historical feature data based on the importance level;

[0158] Model training is performed based on historical feature data and target weights to obtain a motion sickness probability model.

[0159] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0160] Obtaining historical driving behavior data corresponding to the historical trip; wherein the historical driving behavior data includes at least one of the number of sudden accelerations, the number of sudden decelerations, the number of sharp turns, and the number of sudden brakes;

[0161] Obtain historical passenger data corresponding to the historical trips; wherein the historical passenger data includes at least one of passenger information, passenger behavior, the number of passengers in the vehicle, and the position of passengers in the vehicle;

[0162] Obtain historical vehicle data corresponding to historical trips; wherein the historical vehicle data includes at least one of vehicle type, vehicle energy recovery mode, congestion condition of the driving route, odor concentration in the vehicle, and vehicle suspension hardness.

[0163] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0164] The target weight corresponding to the historical feature data is determined based on the positive correlation between the importance level and the weight.

[0165] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0166] Perform weighted processing on historical feature data based on target weights to obtain training data;

[0167] The parameters of the preset model are initialized, and the initialized preset model is iteratively trained based on the training data to obtain a motion sickness probability model.

[0168] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0169] Inputting the target feature data corresponding to the target passenger into the motion sickness probability model for prediction, and obtaining the target motion sickness probability corresponding to the target passenger; wherein the target feature data includes current driving behavior data, target passenger data, and current vehicle data;

[0170] According to the target motion sickness probability, the target passengers are given motion sickness prompts.

[0171] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0172] Determine the probability range to which the target motion sickness probability belongs;

[0173] Execute the prompt operation corresponding to the probability range.

[0174] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0175] When the probability range is the first probability range, outputting the target motion sickness probability to a display screen of the current vehicle;

[0176] When the probability range is the second probability range, voice data corresponding to the target motion sickness probability is generated, the voice data is played, and the target motion sickness probability is output to the display screen; wherein the minimum value of the second probability range is greater than the maximum value of the first probability range;

[0177] When the probability range is the third probability range, the current vehicle is controlled to perform anti-motion sickness measures; wherein the minimum value of the third probability range is greater than the maximum value of the second probability range, and the anti-motion sickness measures include at least one of adjusting the vehicle driving state, adjusting the in-car audio state, adjusting the in-car lighting state, adjusting the in-car air state, and adjusting the seat state.

[0178] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0179] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0180] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A motion sickness probability model training method, characterized in that: include: Acquire historical feature data corresponding to historical trips; wherein the historical feature data includes historical driving behavior data, historical passenger data, and historical vehicle data; Determining an importance level corresponding to the historical feature data, and determining a target weight corresponding to the historical feature data based on the importance level; Model training is performed based on the historical feature data and the target weight to obtain a motion sickness probability model.

2. The method according to claim 1, characterized in that The obtaining of historical feature data corresponding to the historical trip includes: Acquire historical driving behavior data corresponding to the historical trip; wherein the historical driving behavior data includes at least one of the number of sudden accelerations, the number of sudden decelerations, the number of sharp turns, and the number of sudden brakes; Acquire historical passenger data corresponding to the historical trip; wherein the historical passenger data includes at least one of passenger information, passenger behavior, the number of passengers in the vehicle, and the position of passengers in the vehicle; Obtain historical vehicle data corresponding to the historical trip; wherein the historical vehicle data includes at least one of vehicle type, vehicle energy recovery mode, congestion condition of the driving route, odor concentration in the vehicle, and vehicle suspension hardness.

3. The method according to claim 1, characterized in that The determining the target weight corresponding to the historical feature data based on the importance level includes: The target weight corresponding to the historical feature data is determined based on the positive correlation between the importance level and the weight.

4. The method according to claim 1, characterized in that: The performing model training based on the historical feature data and the target weight to obtain a motion sickness probability model includes: Performing weighted processing on the historical feature data based on the target weight to obtain training data; The parameters of the preset model are initialized, and the initialized preset model is iteratively trained based on the training data to obtain the motion sickness probability model.

5. A motion sickness prompting method, using the motion sickness probability model according to any one of claims 1 to 4, characterized in that: The method comprises: Inputting the target feature data corresponding to the target passenger into the motion sickness probability model for prediction to obtain the target motion sickness probability corresponding to the target passenger; wherein the target feature data includes current driving behavior data, target passenger data and current vehicle data; Prompt the target passenger for motion sickness according to the target motion sickness probability.

6. The method according to claim 5, characterized in that Prompting the target passenger for motion sickness according to the target motion sickness probability includes: Determining a probability range to which the target motion sickness probability belongs; Execute a prompt operation corresponding to the probability range.

7. The method according to claim 6, characterized in that The performing of the prompt operation corresponding to the probability range includes: When the probability range is a first probability range, outputting the target motion sickness probability to a display screen of the current vehicle; When the probability range is a second probability range, voice data corresponding to the target motion sickness probability is generated, the voice data is played, and the target motion sickness probability is output to the display screen; wherein the minimum value of the second probability range is greater than the maximum value of the first probability range; When the probability range is a third probability range, the current vehicle is controlled to perform anti-motion sickness measures; wherein the minimum value of the third probability range is greater than the maximum value of the second probability range, and the anti-motion sickness measures include at least one of adjusting the vehicle driving state, adjusting the in-car audio state, adjusting the in-car lighting state, adjusting the in-car air state, and adjusting the seat state.

8. A motion sickness probability model training device, characterized in that: The device comprises: An acquisition module, used to acquire historical feature data corresponding to historical trips; wherein the historical feature data includes historical driving behavior data, historical passenger data, and historical vehicle data; A determination module, configured to determine an importance level corresponding to the historical feature data, and determine a target weight corresponding to the historical feature data based on the importance level; A training module is used to perform model training based on the historical feature data and the target weight to obtain a motion sickness probability model.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images