Vehicle seat temperature adjustment method and apparatus, electronic device, and vehicle

Abstract

A vehicle seat temperature adjustment method and apparatus, an electronic device, and a vehicle. The method comprises: recognizing a plurality of influential factors for affecting the seat temperature change of a vehicle; respectively acquiring influential factor data corresponding to the plurality of influential factors; inputting the influential factor data into a vehicle seat temperature control prediction model for prediction, so as to obtain seat temperature prediction values corresponding to the influential factors, wherein the vehicle seat temperature control prediction model is configured to predict seat temperatures corresponding to different influential factors; on the basis of the plurality of seat temperature prediction values corresponding to the plurality of influential factors, and weights respectively corresponding to the plurality of influential factors, determining a target seat temperature prediction value of the vehicle; and on the basis of the target seat temperature prediction value, adjusting the seat temperature of the vehicle.

Description

Method and device for adjusting temperature of vehicle seat, electronic equipment and vehicle

[0001] Cross-reference to Related Applications

[0002] The present disclosure claims priority to the Chinese patent publication with publication number 2024106419173 and publication name "Method and device for adjusting temperature of vehicle seat, electronic equipment and vehicle" filed on May 22, 2024 with the China Patent Office, the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0003] The present disclosure relates to the technical field of vehicles, and in particular, to a method and device for adjusting temperature of a vehicle seat, an electronic equipment and a vehicle. BACKGROUND

[0004] Currently, when adjusting the temperature of a vehicle seat, the temperature of the seat is usually adjusted by modifying the temperature level. However, this adjustment method cannot accurately determine the seat temperature that makes the user feel comfortable, and most of the time, the provided seat temperature of the vehicle is too hot or too cold. When the user's demand changes, for example, when the user needs a lower seat temperature for a long time, the seat temperature cannot be automatically adjusted according to the change in user demand, resulting in a poor user experience.

[0005] Currently, there is no effective solution to the above technical problem of low intelligence level of vehicle seat temperature adjustment.

[0006] SUMMARY

[0007] The present disclosure provides a method and device for adjusting temperature of a vehicle seat, an electronic equipment and a vehicle to at least solve the technical problem of low intelligence level of vehicle seat temperature adjustment.

[0008] According to an aspect of an embodiment of the present disclosure, a method for adjusting temperature of a vehicle seat is provided. The method comprises: identifying a plurality of influencing factors for affecting the change of the seat temperature of the vehicle; respectively acquiring influencing factor data corresponding to the plurality of influencing factors, wherein the influencing factor data is used to represent data related to the influencing factors; inputting the influencing factor data into a vehicle seat temperature control prediction model for prediction to obtain a seat temperature prediction value corresponding to the influencing factors, wherein the vehicle seat temperature control prediction model is set to predict the seat temperature corresponding to different influencing factors; determining a seat temperature target prediction value of the vehicle based on a plurality of seat temperature prediction values corresponding to the plurality of influencing factors and weights corresponding to the plurality of influencing factors, respectively; and adjusting the seat temperature of the vehicle based on the seat temperature target prediction value.

[0009] Optionally, the method further comprises: establishing an initial vehicle seat temperature control prediction model based on a random forest algorithm, wherein the initial vehicle seat temperature control prediction model comprises a plurality of decision sub-models corresponding to a plurality of influencing factors; obtaining influencing factor sample data corresponding to the plurality of influencing factors; and training the initial vehicle seat temperature control prediction model based on the plurality of influencing factor sample data to obtain a vehicle seat temperature control prediction model.

[0010] Optionally, obtaining the influencing factor sample data corresponding to the plurality of influencing factors comprises: obtaining historical data corresponding to the plurality of influencing factors in a historical time period; performing standardization processing on the historical data to obtain processed historical data; and obtaining the influencing factor sample data corresponding to the plurality of influencing factors from the processed historical data.

[0011] Optionally, training the initial vehicle seat temperature control prediction model based on the plurality of influencing factor sample data to obtain a vehicle seat temperature control prediction model comprises: dividing the plurality of influencing factor sample data into a training set and a test set, wherein the data amount of the training set and the data amount of the test set satisfy a preset ratio; training the plurality of decision sub-models in the initial vehicle seat temperature control prediction model using data in the training set corresponding to the plurality of influencing factors; in response to completion of the training of the plurality of decision sub-models, verifying the plurality of decision sub-models that have been trained using the test set corresponding to the plurality of influencing factors to obtain a training accuracy of the initial vehicle seat temperature control prediction model comprising the plurality of decision sub-models that have been trained; and in response to the training accuracy being less than an accuracy threshold, adjusting model parameters of the initial vehicle seat temperature control prediction model comprising the plurality of decision sub-models that have been trained to obtain a vehicle seat temperature control prediction model.

[0012] Optionally, verifying the plurality of decision sub-models that have been trained using the test set corresponding to the plurality of influencing factors to obtain a training accuracy of the initial vehicle seat temperature control prediction model comprising the plurality of decision sub-models that have been trained comprises: inputting data in the test set corresponding to the plurality of influencing factors into the plurality of decision sub-models; obtaining seat temperature prediction sample values corresponding to the plurality of influencing factors output by the plurality of decision sub-models; determining a seat temperature target prediction sample value based on the seat temperature prediction sample values corresponding to the plurality of influencing factors and weights corresponding to the plurality of influencing factors, wherein the seat temperature target prediction sample value is used to indicate a seat temperature predicted by the initial vehicle seat temperature control prediction model, and the seat temperature satisfies the comfort of a vehicle occupant; and comparing the seat temperature target prediction sample value with an actual seat temperature value to determine the training accuracy of the initial vehicle seat temperature control prediction model, wherein the actual seat temperature value is used to indicate a measured seat temperature value that satisfies the comfort of the vehicle occupant under the plurality of influencing factors.

[0013] Optionally, the model parameters of the initial vehicle seat temperature control prediction model including the plurality of trained decision sub-models are adjusted to obtain a vehicle seat temperature control prediction model, including: adjusting the model parameters of the plurality of trained decision sub-models included in the initial vehicle seat temperature control prediction model respectively to obtain a plurality of adjusted decision sub-models; determining the initial vehicle seat temperature control prediction model containing the plurality of adjusted decision sub-models as an adjusted initial vehicle seat temperature control prediction model; verifying the adjusted initial vehicle seat temperature control prediction model based on the test set to obtain a training accuracy of the adjusted initial vehicle seat temperature control prediction model; and in response to the training accuracy of the adjusted initial vehicle seat temperature control prediction model being greater than or equal to an accuracy threshold, determining the adjusted initial vehicle seat temperature control prediction model as the vehicle seat temperature control prediction model.

[0014] Optionally, the method for adjusting the temperature of the vehicle seat further includes: standardizing the plurality of influencing factors to obtain a plurality of standardized coefficients corresponding to the plurality of influencing factors; determining the influence degrees of the plurality of influencing factors on the change of the temperature of the vehicle seat based on the standardized coefficients; and determining the weights corresponding to the plurality of influencing factors based on the influence degrees.

[0015] Optionally, the plurality of influencing factors include at least one of the following: a physical index of a vehicle occupant, a behavior action of the vehicle occupant on the vehicle seat, an environmental temperature of the vehicle, an environmental humidity of the vehicle, a vehicle type, a sealing degree of the vehicle, a vehicle power, a material of the vehicle seat, and a contact area between the vehicle occupant and the vehicle seat.

[0016] According to another aspect of the embodiments of the present disclosure, a device for adjusting the temperature of a vehicle seat is also provided. The device includes: an identification unit configured to identify a plurality of influencing factors for affecting the change of the temperature of the seat of the vehicle; an acquisition unit configured to acquire influence factor data corresponding to the plurality of influencing factors respectively, wherein the influence factor data is used to represent data related to the influencing factors; a prediction unit configured to input the influence factor data into a vehicle seat temperature control prediction model to perform prediction to obtain seat temperature prediction values corresponding to the plurality of influencing factors, wherein the vehicle seat temperature control prediction model is used to predict the seat temperature corresponding to different influencing factors; a determination unit configured to determine a target seat temperature prediction value of the vehicle based on the plurality of seat temperature prediction values corresponding to the plurality of influencing factors and the weights corresponding to the plurality of influencing factors respectively; and an adjustment unit configured to adjust the temperature of the seat of the vehicle based on the target seat temperature prediction value.

[0017] According to another aspect of the embodiments of the present disclosure, an electronic device is also provided, including: a memory storing an executable program; and a processor configured to run the program, wherein the program performs the method for adjusting the temperature of the vehicle seat in various embodiments of the present disclosure when running.

[0018] According to another aspect of the embodiments of the present disclosure, a computer readable storage medium is also provided, which includes a stored executable program, wherein the executable program controls the device where the computer readable storage medium is located to perform the method for adjusting the temperature of the seat of the vehicle in various embodiments of the present disclosure when the executable program is running.

[0019] According to another aspect of the embodiments of the present disclosure, a computer program product is also provided, which includes a computer program, and the computer program implements the method for adjusting the temperature of the seat of the vehicle in various embodiments of the present disclosure when executed by a processor.

[0020] According to another aspect of the embodiments of the present disclosure, a computer program product is also provided, which includes a non-volatile computer readable storage medium, and the non-volatile computer readable storage medium stores a computer program, and the computer program implements the method for adjusting the temperature of the seat of the vehicle in various embodiments of the present disclosure when executed by a processor.

[0021] According to another aspect of the embodiments of the present disclosure, a computer program is also provided, and the computer program implements the method for adjusting the temperature of the seat of the vehicle in various embodiments of the present disclosure when executed by a processor.

[0022] According to another aspect of the embodiments of the present disclosure, a vehicle is also provided. The vehicle is configured to perform the method for adjusting the temperature of the seat of the vehicle.

[0023] In the embodiments of the present disclosure, a plurality of influencing factors for affecting the change of the temperature of the seat of the vehicle are identified; influencing factor data corresponding to the plurality of influencing factors is respectively acquired, wherein the influencing factor data is used to represent data related to the influencing factors; the influencing factor data is input into a vehicle seat temperature control prediction model for prediction to obtain a seat temperature prediction value corresponding to the influencing factors, wherein the vehicle seat temperature control prediction model is configured to predict the seat temperature corresponding to different influencing factors; a target seat temperature prediction value of the vehicle is determined based on a plurality of seat temperature prediction values corresponding to the plurality of influencing factors and weights respectively corresponding to the plurality of influencing factors; and the temperature of the seat of the vehicle is adjusted based on the target seat temperature prediction value. That is, in the present disclosure, the influencing factor data corresponding to the plurality of influencing factors affecting the change of the temperature of the seat of the vehicle can be input into the vehicle seat temperature control prediction model, the seat temperature prediction value corresponding to each influencing factor can be predicted, and the target seat temperature prediction value of the vehicle can be determined based on the seat temperature prediction value corresponding to each influencing factor, and then the temperature of the seat of the vehicle is adjusted to the target seat temperature prediction value. The temperature of the seat of the vehicle predicted by considering the plurality of influencing factors can more accurately match the user's demand, greatly improving the comfort of the user, and through the automatic adjustment, the technical effect of improving the intelligent level of the adjustment of the temperature of the seat of the vehicle is realized, thereby solving the technical problem of low intelligent level of the adjustment of the temperature of the seat of the vehicle. Attached Figure Description

[0024] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this disclosure, illustrate exemplary embodiments of the present disclosure and are used to explain the disclosure, but do not constitute an undue limitation of the disclosure. In the drawings:

[0025] Figure 1 is a flowchart of a method for adjusting the temperature of a vehicle seat according to an embodiment of the present disclosure;

[0026] Figure 2 is a schematic diagram of a random forest algorithm model according to an embodiment of the present disclosure;

[0027] Figure 3 is a flowchart of a vehicle seat temperature prediction method according to an embodiment of the present disclosure;

[0028] Figure 4 is a schematic diagram of a vehicle seat temperature regulating device according to an embodiment of the present disclosure;

[0029] Figure 5 is a schematic diagram of the structure of a non-volatile storage medium according to an embodiment of the present disclosure;

[0030] Figure 6 is a schematic diagram of the structure of a processor according to an embodiment of the present disclosure. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present disclosure, the technical solutions of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present disclosure, and not all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present disclosure.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] According to an embodiment of the present disclosure, a method for adjusting the temperature of a vehicle seat is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] FIG. 1 is a flowchart of a method for adjusting the temperature of a vehicle seat according to an embodiment of the present disclosure. As shown in FIG. 1, the method includes the following steps:

[0035] Step S101, identifying a plurality of influencing factors for affecting the change of the seat temperature of the vehicle.

[0036] In the technical solution provided by step S101 of the present disclosure, the plurality of influencing factors for affecting the change of the seat temperature of the vehicle at least include: the height and weight of the vehicle occupant on the vehicle seat, the ambient temperature of the vehicle, the ambient humidity of the vehicle, the type of the vehicle, the degree of closure of the vehicle, the behavior of the vehicle occupant, the power of the vehicle, the seat material of the vehicle, and the contact area between the vehicle occupant and the seat. Here, only exemplary examples are given, and the influencing factors for affecting the change of the seat temperature of the vehicle are not limited.

[0037] In this embodiment, the plurality of influencing factors for affecting the change of the seat temperature of the vehicle can be identified.

[0038] Step S102, obtaining influencing factor data corresponding to each of the plurality of influencing factors.

[0039] In the technical solution provided by step S102 of the present disclosure, after the plurality of influencing factors for affecting the change of the seat temperature of the vehicle are identified by step S101, the influencing factor data corresponding to each of the plurality of influencing factors can be further obtained. The influencing factor data is used to indicate data related to the influencing factor.

[0040] In this embodiment, after the plurality of influencing factors for affecting the change of the seat temperature of the vehicle are identified, the specific data of the plurality of influencing factors corresponding to the current seat temperature of the vehicle can be obtained.

[0041] For example, taking the ambient temperature of the vehicle as an example of the plurality of influencing factors, obtaining the ambient temperature of the vehicle can be obtaining the specific value of the ambient temperature corresponding to the current vehicle, for example, it can be 36°C. The ambient temperature can be obtained by a temperature sensor, and this is only an exemplary example and does not limit the specific way of obtaining the ambient temperature of the vehicle.

[0042] Step S103, inputting the influencing factor data into a vehicle seat temperature control prediction model for prediction to obtain a seat temperature prediction value corresponding to the influencing factor.

[0043] In the technical solution provided in step S103 of the present disclosure, the vehicle seat temperature control prediction model is configured to predict the seat temperature corresponding to different influencing factors. Based on this, after obtaining the influencing factor data corresponding to each of the multiple influencing factors in step S102, the influencing factor data corresponding to each of the multiple influencing factors can be input into the vehicle seat temperature control prediction model for prediction, and then the seat temperature prediction value corresponding to each influencing factor can be obtained.

[0044] In this embodiment, the vehicle seat temperature control prediction model is a model that is established in advance by a random forest algorithm and trained by influencing factor sample data. Since the random forest algorithm includes multiple decision trees, the vehicle seat temperature control prediction model established by the random forest algorithm can include multiple decision sub-models corresponding to the decision trees. Each decision sub-model is configured to predict a seat temperature prediction value corresponding to an influencing factor.

[0045] For example, when the influencing factor data corresponding to the multiple influencing factors is input into the vehicle seat temperature control prediction model, the influencing factor corresponding to each decision sub-model in the vehicle seat temperature control prediction model can be determined first, and then the influencing factor data corresponding to each influencing factor can be input into the decision sub-model corresponding thereto, so that each decision sub-model predicts a seat temperature prediction value corresponding to each influencing factor, and then the seat temperature prediction values corresponding to the multiple influencing factors predicted by the multiple decision sub-models in the vehicle seat temperature control prediction model are obtained.

[0046] In step S104, the seat temperature target prediction value of the vehicle is determined based on the multiple seat temperature prediction values corresponding to the multiple influencing factors and the weights corresponding to the multiple influencing factors, respectively.

[0047] In the technical solution provided in step S104 of the present disclosure, after determining the seat temperature prediction values corresponding to the multiple influencing factors respectively in step S103, the seat temperature target prediction value of the vehicle can be determined based on the seat temperature prediction values corresponding to the multiple influencing factors respectively and the weights corresponding to the multiple influencing factors respectively.

[0048] In this embodiment, each influencing factor corresponds to a different weight according to the degree of influence of the influencing factor on the seat temperature value of the vehicle, and each influencing factor corresponds to a decision sub-model. Based on this, the weight corresponding to each influencing factor can be determined as the weight of the decision sub-model corresponding to the influencing factor. After predicting the seat temperature prediction value corresponding to the influencing factor corresponding to each decision sub-model, the seat temperature prediction value predicted by each decision sub-model and the weight corresponding to each decision sub-model can be weighted and averaged to obtain the seat temperature target prediction value of the vehicle under the multiple influencing factors.

[0049] For example, the seat temperature target prediction value of the vehicle under various influencing factors can be determined by the following formula.

[0050] Wherein, Y can be used to indicate the seat temperature target prediction value of the vehicle under various influencing factors, n can be used to indicate the number of influencing factors, y i The i-th influencing factor can be used to indicate the seat temperature prediction value corresponding to the i-th influencing factor.

[0051] Step S105, automatically adjusting the seat temperature of the vehicle based on the seat temperature target prediction value.

[0052] In the technical solution provided by the above step S105 of the present disclosure, after determining the seat temperature target prediction value of the vehicle, the seat temperature of the vehicle can be automatically adjusted according to the seat temperature target prediction value, thereby providing a comfortable seat temperature for the vehicle object.

[0053] In the above steps S101 to S105 of the present disclosure, the influencing factor data corresponding to the various influencing factors affecting the change of the seat temperature of the vehicle can be input into the vehicle seat temperature control prediction model, the seat temperature prediction value corresponding to each influencing factor can be predicted, and the seat temperature target prediction value of the vehicle can be determined based on the seat temperature prediction value corresponding to each influencing factor, and then the seat temperature of the vehicle is adjusted to the seat temperature target prediction value. The vehicle seat temperature predicted by considering various influencing factors can more accurately match the user's demand, greatly improving the user's comfort, and through the automatic adjustment mode, the intelligent level of the vehicle seat temperature adjustment is realized, thereby solving the technical problem of low intelligent level of the vehicle seat temperature adjustment.

[0054] The above method of the embodiment will be further introduced below.

[0055] As an optional implementation, the method for adjusting the seat temperature of the vehicle further includes: establishing an initial vehicle seat temperature control prediction model based on a random forest algorithm, wherein the initial vehicle seat temperature control prediction model includes a plurality of decision sub-models, and the plurality of decision sub-models correspond to a plurality of influencing factors; obtaining influencing factor sample data corresponding to the plurality of influencing factors; training the initial vehicle seat temperature control prediction model based on the plurality of influencing factor sample data to obtain the vehicle seat temperature control prediction model.

[0056] In this embodiment, the initial vehicle seat temperature control prediction model is constructed by a random forest algorithm. The random forest algorithm is used for classification or regression by constructing multiple decision trees. When constructing each decision tree, the random forest algorithm randomly selects a sample subset and a feature subset, and then uses these subsets to establish a tree model. The final prediction result is obtained by averaging or voting the prediction results of all decision trees. Based on this, the initial vehicle seat temperature control prediction model is established according to the random forest algorithm. Alternatively, other algorithms can also be used to construct the initial temperature control prediction model. Here, only an example is given, and the specific algorithm for constructing the initial vehicle seat temperature control prediction model is not limited.

[0057] Alternatively, since the random forest algorithm includes multiple decision trees, the initial vehicle seat temperature control prediction model constructed by the random forest algorithm includes multiple decision sub-models, wherein the multiple decision sub-models correspond to the multiple decision trees, and one decision sub-model is set to predict the seat temperature prediction value corresponding to one influencing factor.

[0058] Alternatively, after establishing the initial vehicle seat temperature control prediction model, the influence factor sample data corresponding to the multiple influencing factors can be obtained, and then each decision sub-model in the initial vehicle seat temperature control prediction model is trained based on the influence factor sample data to obtain the vehicle seat temperature control prediction model.

[0059] As an optional implementation, obtaining the influence factor sample data corresponding to the multiple influencing factors includes: obtaining historical data corresponding to the multiple influencing factors in a historical time period; at least performing standardization processing on the historical data to obtain processed historical data; and obtaining the influence factor sample data corresponding to the multiple influencing factors, respectively, from the processed historical data.

[0060] In this embodiment, when obtaining the influence factor sample data for training the initial vehicle seat temperature control prediction model, the historical data corresponding to the multiple influencing factors in a historical time period can be obtained first, wherein the historical time period can be the past month, the past week, the past day, or the past hour, and the specific limitation is not given here.

[0061] For example, taking the past month's environment temperature as an example, the specific value of the environment temperature in which the vehicle travels in the past month can be obtained, wherein the corresponding environment temperature of the vehicle in the past month can be obtained by a vehicle-mounted temperature sensor. Alternatively, the corresponding environment temperature of the vehicle in the past month can be obtained by a vehicle data recording system. Here, only an example is given, and the specific way of obtaining the environment temperature of the vehicle in the past month is not limited.

[0062] Optionally, after obtaining the historical data corresponding to the plurality of influence factors respectively in the historical time period, since there may be missing data or data anomalies in the obtained data, based on this, the obtained historical data can be standardized. For example, the historical data is processed for missing value, outlier and data standardization, etc. to improve the data quality.

[0063] Optionally, after the historical data is standardized to obtain the standardized historical data, the influence factor sample data corresponding to the plurality of influence factors respectively can be randomly obtained from the standardized historical data.

[0064] As an optional implementation, the initial vehicle seat temperature control prediction model is trained based on the plurality of influence factor sample data to obtain the vehicle seat temperature control prediction model, including: dividing the plurality of influence factor sample data into a training set and a test set, wherein the data amount of the training set and the data amount of the test set satisfy a preset ratio; using the data in the training set corresponding to the plurality of influence factors respectively to train the plurality of decision sub-models in the initial vehicle seat temperature control prediction model; in response to the plurality of decision sub-models being trained, using the test set corresponding to the plurality of influence factors respectively to verify the plurality of decision sub-models that have been trained, to obtain the training accuracy of the initial vehicle seat temperature control prediction model including the plurality of decision sub-models that have been trained; in response to the training accuracy being less than an accuracy threshold, adjusting the model parameters of the initial vehicle seat temperature control prediction model including the plurality of decision sub-models that have been trained, to obtain the vehicle seat temperature control prediction model.

[0065] In this embodiment, after obtaining the influence factor sample data corresponding to the plurality of influence factors, the plurality of influence factor sample data can be divided into a training set and a test set according to a preset ratio. The preset ratio can be set in advance. For example, the preset ratio can be that the training set accounts for 70%, and the test set accounts for 30%, or the training set accounts for 80%, and the test set accounts for 20%. Here, only exemplary examples are given, and the specific value of the preset ratio is not limited.

[0066] For example, taking the influence factor sample data corresponding to the environmental temperature in the plurality of influence factor sample data as an example, the influence factor data corresponding to the environmental temperature can be divided into a training set and a test set according to the preset ratio.

[0067] Optionally, after the plurality of influence factor sample data is divided into the training set and the test set, the data in the training set corresponding to each influence factor can be used to train the decision sub-model corresponding to the influence factor in the initial vehicle seat temperature control prediction model. After training each decision sub-model corresponding to each influence factor in the initial vehicle seat temperature control prediction model according to the method, the data in the test set corresponding to each influence factor can be used to verify the trained decision sub-model to verify the performance and training accuracy of the trained decision sub-model. Then, according to the training accuracy of each decision sub-model, the training accuracy of the initial vehicle seat temperature control prediction model is determined, and when the training accuracy is less than the accuracy threshold, the model parameters of the initial vehicle seat temperature control prediction model are adjusted to obtain the vehicle seat temperature control prediction model. The training accuracy can be reflected by the prediction accuracy of the predicted value of the vehicle seat temperature.

[0068] As an optional implementation, the plurality of trained decision sub-models are verified by using the test set corresponding to each influence factor, respectively, to obtain the training accuracy of the initial vehicle seat temperature control prediction model including the plurality of trained decision sub-models, including: inputting the data in the test set corresponding to each influence factor into the plurality of decision sub-models, respectively; obtaining the seat temperature prediction sample values corresponding to each influence factor output by the plurality of decision sub-models; determining a target seat temperature prediction sample value based on the seat temperature prediction sample values corresponding to each influence factor and the weights corresponding to each influence factor, respectively, wherein the target seat temperature prediction sample value is used to indicate the seat temperature predicted by the initial vehicle seat temperature control prediction model, and the seat temperature satisfies the comfort of the vehicle occupant; comparing the target seat temperature prediction sample value with an actual seat temperature value to determine the training accuracy of the initial vehicle seat temperature control prediction model, wherein the actual seat temperature value is used to indicate the measured seat temperature value that satisfies the comfort of the vehicle occupant under the plurality of influence factors.

[0069] In this embodiment, when the plurality of decision sub-models in the initial vehicle seat temperature control prediction model are verified by using the test set corresponding to each influence factor, the data in the test set corresponding to each influence factor can be input into the plurality of trained decision sub-models, and the seat temperature prediction sample values corresponding to each influence factor output by the plurality of decision sub-models can be obtained.

[0070] Optionally, after obtaining the seat temperature prediction sample values corresponding to each influence factor, respectively, a weighted average operation can be performed according to the seat temperature prediction sample values corresponding to each influence factor, respectively, and the weights corresponding to each influence factor, respectively, to obtain a target seat temperature prediction sample value of the vehicle.

[0071] Optionally, since the seat temperature target prediction sample value is used to indicate the seat temperature satisfying the comfort of the vehicle occupant predicted by the initial vehicle seat temperature control prediction model, and the seat temperature actual value is used to indicate the seat temperature satisfying the comfort of the vehicle occupant actually measured by the vehicle occupant, based on this, the seat temperature target prediction sample value and the seat temperature actual value can be compared, and then the training accuracy of the initial vehicle seat temperature control prediction model can be determined.

[0072] For example, the training accuracy of the initial vehicle seat temperature control prediction model can be determined by taking the difference between the seat temperature target prediction sample value and the seat temperature actual value as the dividend, and taking the product of the sample quantity and the sample mean square error as the divisor.

[0073] Optionally, the test set can be used as outsourcing data to test the training accuracy of the initial vehicle seat temperature control prediction model.

[0074] Optionally, after the training accuracy of the initial vehicle seat temperature control prediction model is determined, if the training accuracy is less than the accuracy threshold, the model parameters of the initial vehicle seat temperature control prediction model can be adjusted until the training accuracy of the initial vehicle seat temperature control prediction model is not less than the accuracy threshold.

[0075] As an optional implementation, adjusting the model parameters of the initial vehicle seat temperature control prediction model including the plurality of trained decision sub-models to obtain the vehicle seat temperature control prediction model includes: adjusting the model parameters of the plurality of trained decision sub-models included in the initial vehicle seat temperature control prediction model respectively to obtain the plurality of adjusted decision sub-models; determining the initial vehicle seat temperature control prediction model containing the plurality of adjusted decision sub-models as the adjusted initial vehicle seat temperature control prediction model; verifying the adjusted initial vehicle seat temperature control prediction model based on the test set to obtain the training accuracy of the adjusted initial vehicle seat temperature control prediction model; and in response to the training accuracy of the adjusted initial vehicle seat temperature control prediction model being greater than or equal to the accuracy threshold, determining the adjusted initial vehicle seat temperature control prediction model as the vehicle seat temperature control prediction model.

[0076] In this embodiment, since the initial vehicle seat temperature control prediction model includes the plurality of trained decision sub-models, based on this, when the model parameters of the initial vehicle seat temperature control prediction model are adjusted, the model parameters of the plurality of decision sub-models can be adjusted respectively to obtain the plurality of adjusted decision sub-models, and then the plurality of adjusted decision sub-models are determined as the adjusted initial vehicle seat temperature control prediction model.

[0077] Optionally, after obtaining the adjusted initial vehicle seat temperature control prediction model, the training accuracy of the adjusted initial vehicle seat temperature control prediction model can be predicted by referring to the verification method of the initial vehicle seat temperature control prediction model described above, to determine whether the training accuracy of the adjusted initial vehicle seat temperature control prediction model meets the standard, i.e., whether the training accuracy of the trained initial vehicle seat temperature control prediction model is greater than or equal to the accuracy threshold. If the training accuracy of the adjusted initial vehicle seat temperature control prediction model is greater than or equal to the accuracy threshold, the adjusted initial vehicle seat temperature control prediction model is determined as the vehicle seat temperature control prediction model.

[0078] As an optional implementation, the method for adjusting the temperature of the vehicle seat further includes: performing standardization processing on the plurality of influencing factors to obtain a plurality of standardized coefficients corresponding to the plurality of influencing factors; determining the influence degree of the plurality of influencing factors on the change of the temperature of the vehicle seat based on the standardized coefficients; and determining the weight corresponding to each of the plurality of influencing factors based on the influence degree.

[0079] In this embodiment, since the plurality of influencing factors that affect the temperature of the vehicle seat are influencing factors in different scales, for example, the environmental temperature is in units of degrees Celsius, and the environmental humidity is in units of percentage, and thus cannot be directly compared. In this case, the plurality of influencing factors need to be standardized to obtain a plurality of standardized coefficients corresponding to the plurality of influencing factors, and then the influence degree of the plurality of influencing factors on the change of the temperature of the vehicle seat is determined based on the standardized coefficients, and then the weight corresponding to each of the plurality of influencing factors is determined based on the influence degree of the plurality of influencing factors on the change of the temperature of the vehicle seat.

[0080] For example, the standardized coefficients are used to compare the influence of independent variables (e.g., influencing factors) in different scales on the target variable (e.g., the temperature of the seat), and then different weights are assigned to the plurality of influencing factors. Since the plurality of influencing factors correspond to a plurality of decision sub-models respectively, based on this, the prediction importance of each decision sub-model can be defined according to the weight corresponding to the plurality of influencing factors, and then a more accurate seat temperature prediction value is obtained by weighting the prediction results of each decision sub-model.

[0081] In the above steps, the influence factor data corresponding to various influence factors affecting the change of the seat temperature of the vehicle can be input into the vehicle seat temperature control prediction model, the seat temperature prediction value corresponding to each influence factor is predicted, and the seat temperature target prediction value of the vehicle is determined based on the seat temperature prediction value corresponding to each influence factor, and then the seat temperature of the vehicle is adjusted to the seat temperature target prediction value. The vehicle seat temperature predicted by considering various influence factors can more accurately match the user's demand, greatly improving the user's comfort, and through the automatic adjustment mode, the intelligent level of the vehicle seat temperature adjustment is improved, thereby solving the technical problem of low intelligent level of the vehicle seat temperature adjustment.

[0082] The technical solutions of the embodiments of the present disclosure will be illustrated below in combination with preferred embodiments.

[0083] At present, when adjusting the temperature of the vehicle seat, the temperature of the vehicle seat is usually adjusted by modifying the temperature adjustment gear of the vehicle, but this temperature adjustment method cannot accurately obtain the comfortable seat temperature of the user, and most of the time, the provided vehicle seat temperature has the problems of overheating or overcooling, which cannot satisfy the user. Moreover, when the user's demand changes, for example, the user needs a lower vehicle seat temperature for a long time, the seat temperature cannot be automatically adjusted according to the change of the user's demand, resulting in poor user experience.

[0084] In addition, part of the vehicle seat temperature control system keeps consistent with the temperature of the air conditioner in the vehicle, when the temperature of the air conditioner in the vehicle rises, the temperature of the vehicle seat also rises, but the combined action of the ambient temperature and the vehicle seat temperature may cause the user to feel hot. Similarly, when the ambient temperature and the vehicle seat temperature jointly decrease, the user may feel cold, the temperature control precision is poor, and the vehicle seat temperature control system and the temperature of the air conditioner in the vehicle work, so that the temperature of the vehicle seat cannot reach the comfortable temperature of the user, and there is a technical problem that the vehicle seat temperature cannot be intelligently adjusted.

[0085] However, the present disclosure provides a vehicle seat temperature adjustment method. By obtaining multiple influencing factors that affect the temperature of the vehicle seat, the weight corresponding to each influencing factor is determined according to the influence effect of each influencing factor on the temperature of the vehicle seat. Then, the data corresponding to each influencing factor is input into the vehicle seat temperature control prediction model pre-trained and optimized by the random forest algorithm for prediction to obtain the temperature of the vehicle seat. The random forest algorithm includes multiple decision trees, each of which is set to predict the temperature of the vehicle seat under one influencing factor. The final temperature of the vehicle seat is determined by the temperature of the vehicle seat predicted by each decision tree and the weight corresponding to each influencing factor. The vehicle seat temperature determined in this way takes into account multiple influencing factors, which can maximize the matching between the final determined vehicle seat temperature and the user's demand, improve the user experience, and because it is based on real-time prediction of multiple influencing factors and real-time adjustment of the temperature of the vehicle seat, even if the user's demand changes, the temperature of the vehicle seat can be adjusted in a timely manner according to the user's demand changes, realizing intelligent control of the temperature of the vehicle seat and solving the technical problem of being unable to intelligently control the temperature of the vehicle seat.

[0086] Next, the random forest algorithm model is further introduced.

[0087] FIG. 2 is a schematic diagram of a random forest algorithm model according to an embodiment of the present disclosure. As shown in FIG. 2, the random algorithm is evolved from the decision tree, and the core idea of the random forest algorithm is an "ensemble model" that integrates different features and a certain number of decision trees. The multiple decision trees can include decision tree a, decision tree b, decision tree x, etc., each of which is set to predict the temperature of the vehicle seat under one influencing factor. For example, decision tree a is set to predict the temperature of the vehicle seat under one influencing factor, which can be represented by result 1. Since each influencing factor corresponds to a weight, based on this, after predicting the temperature of the vehicle seat under one influencing factor by each decision tree, the vehicle seat temperature results corresponding to the multiple decision trees can be weighted and averaged to obtain an average result, which is the final result and can be used to indicate the temperature of the vehicle seat under multiple influencing factors.

[0088] Optionally, the principle of the random forest algorithm is "random customization", that is, the decision subset used by the random forest algorithm is random. The data set samples can be selected from the original data set by using the sampling method with replacement, each sample can be selected multiple times and can be included in different subsets, and the randomness of the decision variable subset is realized by using the sampling method with replacement to randomly select the decision variable.

[0089] Optionally, a sample subset containing n samples is randomly selected; a feature subset containing k features is randomly selected, where k << m < mk < m, where m is the number of all features in the original data. A decision tree is constructed using the randomly selected samples and features, and at each node, a best feature is selected for splitting to maximize their information gain. This continues until each leaf node contains only one sample.

[0090] For example, the sample subset is used as training data for constructing the decision tree, and the feature subset is used for constructing node splitting of the decision tree, and a decision tree is constructed using the randomly selected samples and features.

[0091] Optionally, the data set for training the random forest algorithm model is constructed according to time variation. For example, data under different influencing factors in a historical time period can be obtained. The historical time period can be one month in the past, one week in the past, one day in the past, one hour in the past, etc.

[0092] For example, taking the environmental temperature in the influencing factors as an example, the environmental temperature corresponding to the vehicle in the past one month or the environmental temperature corresponding to the vehicle in the past one week, etc. can be obtained. According to this method, the influencing factor data corresponding to various influencing factors can be obtained, and then the data set for training the model is formed.

[0093] Optionally, after obtaining the data set for training the model, the data set can be divided into a training set and a test set, and the training set is used to train the model. After the model training is completed, the test set is used to test the trained model to determine whether the model training is up to standard.

[0094] Optionally, in the regression problem of the random forest, the predicted result is the average value of multiple decision trees, that is, Assuming that the multiple decision trees are subject to independent identical distribution, and the variance is a 2 , then the final variance is Based on this, the random forest can reduce the prediction variance to a certain extent.

[0095] Optionally, there is out-of-bag data in the random forest, which can be used as a test set of the model to test the error of the model, and this error is also called out-of-bag error. The out-of-bag error is the number of misclassified divided by the total number of out-of-bag data, for example, the regression error of the out-of-bag data divided by the total number of out-of-bag data. The out-of-bag data error can be used to adjust the parameters during the model training process.

[0096] Optionally, due to different degrees of influence of various factors, different influencing factors have different scales. For example, temperature is in units of degrees Celsius, humidity is in units of percentage, and the two cannot be directly compared. Therefore, a standardization coefficient is needed to compare the influence of independent variables (influencing factors) on the target variable (vehicle seat temperature) in different scales. Further, different weights are assigned to all models to define the prediction importance of each model, and a more accurate result is obtained by weighting the results of each model.

[0097] FIG. 3 is a flowchart of a vehicle seat temperature prediction method according to an embodiment of the present disclosure. As shown in FIG. 3, the method comprises the following steps:

[0098] Step S301: Analyze the influencing factors of the vehicle seat temperature.

[0099] In this embodiment, the influencing factors that affect the vehicle seat temperature can be analyzed, wherein the influencing factors can include but are not limited to the height and weight of the user, the ambient temperature, the ambient humidity, the type of vehicle, the degree of closure of the vehicle (opening the window or door, etc.), the behavior of the user (sitting posture, etc.), the division of the power module of the vehicle (the maximum use of the power of the temperature control module), the material of the seat, and the contact area of the user, etc.

[0100] Step S302: Obtain data according to the influencing factors.

[0101] In this embodiment, after determining the influencing factors that affect the vehicle seat temperature through step S301, the data corresponding to the influencing factors is obtained from the data source. For example, when the influencing factor is the ambient temperature, the specific ambient temperature value can be obtained as the data corresponding to the influencing factor.

[0102] Step S303: Preprocess the data.

[0103] In this embodiment, after obtaining the data corresponding to the influencing factors through step S302, the data is preprocessed. For example, missing values and abnormal values in the data are processed, the data is standardized, etc. This is only an exemplary example, and the data preprocessing method is not limited.

[0104] Step S304: Select an algorithm for constructing a vehicle seat temperature control prediction model.

[0105] In this embodiment, after preprocessing the data, a machine learning algorithm for constructing a vehicle seat temperature control prediction model can be selected, for example, a random forest algorithm.

[0106] Step S305: Convert the data and extract features in the data.

[0107] In this embodiment, after the vehicle seat temperature control prediction model is constructed through step S304, data conversion can be performed on the data obtained in step S303, and data features can be extracted.

[0108] Step S306, constructing a training set and a test set.

[0109] In this embodiment, the data processed in step S305 can be divided into a training set and a test set.

[0110] Step S307, constructing a vehicle seat temperature control prediction model using an algorithm.

[0111] In this embodiment, the random forest algorithm determined in step S305 can be used to construct a vehicle seat temperature control prediction model.

[0112] Step S308, obtaining different vehicle seat temperature ranges based on different models.

[0113] In this embodiment, since the random forest algorithm includes multiple decision trees, each decision tree can be regarded as a model, and the vehicle seat temperature range under different influencing factors can be predicted through multiple decision trees.

[0114] Step S309, calculating the final vehicle seat temperature range according to the weights of the influencing factors.

[0115] In this embodiment, each influencing factor corresponds to a weight, and based on this, after the vehicle seat temperature range under different influencing factors is predicted in step S308, the vehicle seat temperature range under each influencing factor can be weighted to obtain the final vehicle seat temperature range.

[0116] In steps S301 to S309 described above, the seat temperature control prediction model based on ensemble learning combines multiple data sources such as real-time data of the seat temperature sensor, passenger behavior recognition, environmental condition monitoring, and passenger preference settings, and is trained and optimized through multiple machine learning algorithms. According to multiple factors, the proportion of the influence of different factors on the user comfort temperature is determined, an accurate seat temperature control prediction model is constructed, and the seat temperature suitable for the user is predicted through the seat temperature control prediction model, thereby providing a more comfortable ride environment for the user. Moreover, the model can be trained by temperature control data of different vehicles to obtain a comfortable temperature suitable for different vehicles, that is, the model has good portability.

[0117] According to the embodiments of the present disclosure, a vehicle seat temperature adjustment device is also provided. It should be noted that the vehicle seat temperature adjustment device can be configured to execute the vehicle seat temperature adjustment method in the embodiments.

[0118] FIG. 4 is a schematic diagram of a vehicle seat temperature adjustment device according to an embodiment of the present disclosure. As shown in FIG. 4, the vehicle seat temperature adjustment device 400 can include an identification unit 401, an acquisition unit 402, a prediction unit 403, a determination unit 404, and an adjustment unit 405.

[0119] The identification unit 401 is configured to identify a plurality of influencing factors for affecting a change in a seat temperature of a vehicle.

[0120] The acquisition unit 402 is configured to acquire influencing factor data corresponding to the plurality of influencing factors, respectively, wherein the influencing factor data is used to represent data related to the influencing factors.

[0121] The prediction unit 403 is configured to input the influencing factor data into a vehicle seat temperature control prediction model to perform prediction, to obtain a seat temperature prediction value corresponding to the influencing factors, wherein the vehicle seat temperature control prediction model is configured to predict a seat temperature corresponding to different influencing factors.

[0122] The determination unit 404 is configured to determine a seat temperature target prediction value of the vehicle based on a plurality of seat temperature prediction values corresponding to the plurality of influencing factors, and weights corresponding to the plurality of influencing factors, respectively.

[0123] The adjustment unit 405 is configured to automatically adjust the seat temperature of the vehicle based on the seat temperature target prediction value.

[0124] Optionally, the vehicle seat temperature adjustment device 400 further includes an establishment unit configured to establish an initial vehicle seat temperature control prediction model based on a random forest algorithm, wherein the initial vehicle seat temperature control prediction model includes a plurality of decision sub-models, and the plurality of decision sub-models correspond to the plurality of influencing factors; a first acquisition unit configured to acquire influencing factor sample data corresponding to the plurality of influencing factors; and a training unit configured to train the initial vehicle seat temperature control prediction model based on the plurality of influencing factor sample data, to obtain the vehicle seat temperature control prediction model.

[0125] Optionally, the first acquisition unit includes a first acquisition module configured to acquire historical data corresponding to the plurality of influencing factors in a historical time period; a standardization processing module configured to perform standardization processing on at least the historical data to obtain processed historical data; and a second acquisition module configured to acquire influencing factor sample data corresponding to the plurality of influencing factors, respectively, from the processed historical data.

[0126] Optionally, the training unit comprises: a division module configured to divide the plurality of influence factor sample data into a training set and a test set, wherein a data amount of the training set and a data amount of the test set satisfy a preset ratio; an input module configured to train the plurality of decision sub-models in the initial vehicle seat temperature control prediction model by using data in the training set corresponding to the plurality of influence factors respectively; a verification module configured to, in response to completion of training of the plurality of decision sub-models, verify the plurality of decision sub-models trained by using the test set corresponding to the plurality of influence factors respectively, to obtain a training accuracy of the initial vehicle seat temperature control prediction model including the plurality of decision sub-models trained; and an adjustment module configured to, in response to the training accuracy being less than an accuracy threshold, adjust model parameters of the initial vehicle seat temperature control prediction model including the plurality of decision sub-models trained, to obtain the vehicle seat temperature control prediction model.

[0127] Optionally, the verification module comprises: an input submodule configured to input data in the test set corresponding to the plurality of influence factors into the plurality of decision sub-models respectively; an acquisition submodule configured to acquire seat temperature prediction sample values corresponding to the plurality of influence factors output by the plurality of decision sub-models respectively; a first determination submodule configured to determine a seat temperature target prediction sample value based on the seat temperature prediction sample values corresponding to the plurality of influence factors and weights corresponding to the plurality of influence factors respectively, wherein the seat temperature target prediction sample value is used to indicate that the initial vehicle seat temperature control prediction model predicts a seat temperature satisfying the comfort of the vehicle-riding object; and a second determination submodule configured to compare the seat temperature target prediction sample value with an actual seat temperature value to determine a training accuracy of the initial vehicle seat temperature control prediction model, wherein the actual seat temperature value is used to indicate a measured seat temperature value satisfying the comfort of the vehicle-riding object under the plurality of influence factors.

[0128] Optionally, the adjustment module comprises: an adjustment submodule configured to adjust model parameters of the plurality of decision sub-models included in the initial vehicle seat temperature control prediction model trained respectively, to obtain adjusted plurality of decision sub-models; a third determination submodule configured to determine the initial vehicle seat temperature control prediction model including the adjusted plurality of decision sub-models as an adjusted initial vehicle seat temperature control prediction model; a verification submodule configured to verify the adjusted initial vehicle seat temperature control prediction model based on the test set, to obtain a training accuracy of the adjusted initial vehicle seat temperature control prediction model; and a fourth determination submodule configured to, in response to the training accuracy of the adjusted initial vehicle seat temperature control prediction model being greater than or equal to an accuracy threshold, determine the adjusted initial vehicle seat temperature control prediction model as the vehicle seat temperature control prediction model.

[0129] Optionally, the vehicle seat temperature adjustment device 400 further comprises a standardization unit configured to standardize the plurality of influence factors to obtain a plurality of standardized coefficients corresponding to the plurality of influence factors, wherein the standardization is used to indicate that the plurality of influence factors of different scales are converted into a unified measurement; a first determination unit configured to determine the influence degree of the plurality of influence factors on the change of the vehicle seat temperature based on the standardized coefficients; and a second determination unit configured to determine the weight corresponding to each of the plurality of influence factors based on the influence degree.

[0130] In this embodiment, the influence factor data corresponding to the plurality of influence factors affecting the change of the seat temperature of the vehicle can be input into the vehicle seat temperature control prediction model, the seat temperature prediction value corresponding to each influence factor is predicted, and the seat temperature target prediction value of the vehicle is determined based on the seat temperature prediction value corresponding to each influence factor, and then the seat temperature of the vehicle is adjusted to the seat temperature target prediction value. The vehicle seat temperature predicted by considering the plurality of influence factors can more accurately match the user demand, greatly improve the user comfort, and through the automatic adjustment, the intelligent level of the vehicle seat temperature adjustment is improved, thereby solving the technical problem of low intelligent level of the vehicle seat temperature adjustment.

[0131] Embodiments of the present disclosure also provide an electronic device, comprising a memory storing an executable program, and a processor configured to run the program, wherein the program performs the vehicle seat temperature adjustment method in various embodiments of the present disclosure when running.

[0132] Embodiments of the present disclosure also provide a computer-readable storage medium comprising a stored executable program, wherein the computer-readable storage medium controls the device where the computer-readable storage medium is located to perform the vehicle seat temperature adjustment method in various embodiments of the present disclosure when the executable program runs.

[0133] Embodiments of the present disclosure also provide a computer program product comprising a computer program, which, when executed by a processor, implements the vehicle seat temperature adjustment method in various embodiments of the present disclosure.

[0134] Embodiments of the present disclosure also provide a computer program, which, when executed by a processor, implements the vehicle seat temperature adjustment method in various embodiments of the present disclosure.

[0135] Embodiments of the present disclosure also provide a vehicle for performing the vehicle seat temperature adjustment method in various embodiments of the present disclosure.

[0136] According to the embodiments of the present disclosure, a non-volatile storage medium is also provided, wherein the non-volatile storage medium comprises a stored program, and when the program is executed, the device in which the non-volatile storage medium is located is controlled to perform the method for adjusting the temperature of the seat of the vehicle according to any one of the embodiments of the present disclosure.

[0137] FIG. 5 is a structural schematic diagram of a non-volatile storage medium according to an embodiment of the present disclosure. As shown in FIG. 5, a program product 50 according to the embodiments of the present disclosure is described, which stores a computer program, and the computer program realizes program codes of the following steps when executed by a processor: identifying a plurality of influencing factors for affecting the change of the seat temperature of the vehicle; respectively acquiring influencing factor data corresponding to the plurality of influencing factors, wherein the influencing factor data is used to represent data related to the influencing factors; inputting the influencing factor data into a vehicle seat temperature control prediction model for prediction to obtain a seat temperature prediction value corresponding to the influencing factors, wherein the vehicle seat temperature control prediction model is set to predict the seat temperature corresponding to different influencing factors; determining a seat temperature target prediction value of the vehicle based on the plurality of seat temperature prediction values corresponding to the plurality of influencing factors and the weights respectively corresponding to the plurality of influencing factors; and adjusting the seat temperature of the vehicle based on the seat temperature target prediction value.

[0138] The non-volatile storage medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries readable program codes. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The non-volatile storage medium can send, propagate or transmit programs for use by or in connection with an instruction execution system, apparatus or device.

[0139] The program codes included in the non-volatile storage medium can be transmitted by any suitable medium, including but not limited to wireless, wired, optical cable, radio frequency, etc., or any suitable combination of the above.

[0140] According to the embodiments of the present disclosure, a processor is also provided, which is configured to execute a program. FIG. 6 is a structural schematic diagram of a processor according to an embodiment of the present disclosure. As shown in FIG. 6, the processor 60 is configured to execute a program, and when the program is executed, the above-mentioned method for adjusting the temperature of the seat of the vehicle is performed.

[0141] Optionally, in the embodiment, the processor 60 can be configured to perform the following steps: identifying a plurality of influencing factors for affecting the seat temperature change of the vehicle; acquiring influencing factor data corresponding to each of the plurality of influencing factors, wherein the influencing factor data is used to represent data related to the influencing factor; inputting the influencing factor data into a vehicle seat temperature control prediction model to obtain a seat temperature prediction value corresponding to each of the influencing factors, wherein the vehicle seat temperature control prediction model is configured to predict the seat temperature corresponding to different influencing factors; determining a seat temperature target prediction value of the vehicle based on the plurality of seat temperature prediction values corresponding to the plurality of influencing factors and the weight corresponding to each of the plurality of influencing factors; and adjusting the seat temperature of the vehicle based on the seat temperature target prediction value.

[0142] The processor 60 described above can perform various functional applications and data processing by running software programs and components stored in the memory, that is, implement the above-mentioned method for adjusting the seat temperature of the vehicle.

[0143] The above-mentioned sequence numbers of the embodiments of the present disclosure are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0144] In the above-mentioned embodiments of the present disclosure, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0145] In the several embodiments of the present disclosure, it should be understood that the disclosed technology can be implemented in other ways. Of course, the embodiment described above is only a schematic and illustrative, for example, the division of the units can be a logical function division, and in actual implementation, another division mode can be adopted, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, unit or module, and can be electrical or other forms.

[0146] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment.

[0147] In addition, each functional unit in each embodiment of the present disclosure can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above integrated unit can be realized in the form of hardware, or in the form of software functional unit.

[0148] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present disclosure essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present disclosure. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0149] The above only describes the preferred embodiments of the present disclosure, and it should be noted that, for those skilled in the art, without departing from the principles of the present disclosure, a number of improvements and refinements can be made, and these improvements and refinements should also be considered as the protection scope of the present disclosure. Industrial applicability

[0150] The scheme provided by the embodiments of the present disclosure can be applied to the seat temperature adjustment process of a vehicle. Influence factor data corresponding to a plurality of influence factors affecting the change of the seat temperature of the vehicle are input into a vehicle seat temperature control prediction model, a seat temperature prediction value corresponding to each influence factor is predicted, and a seat temperature target prediction value of the vehicle is determined based on the seat temperature prediction value corresponding to each influence factor, and then the seat temperature of the vehicle is adjusted to the seat temperature target prediction value. The seat temperature of the vehicle predicted by considering a plurality of influence factors can more accurately match the user demand, greatly improving the comfort of the user, and through the automatic adjustment mode, the technical effect of improving the intelligent level of the seat temperature adjustment of the vehicle is realized.

Claims

1. A method for adjusting a temperature of a seat of a vehicle, comprising: identifying a plurality of influencing factors for affecting a temperature change of the seat of the vehicle; obtaining influencing factor data corresponding to each of the plurality of influencing factors, wherein the influencing factor data is used to represent data related to the influencing factor; inputting the influencing factor data into a vehicle seat temperature control prediction model to obtain a seat temperature prediction value corresponding to each of the plurality of influencing factors, wherein the vehicle seat temperature control prediction model is configured to predict a seat temperature corresponding to each of the plurality of influencing factors; determining a target seat temperature prediction value of the vehicle based on the plurality of seat temperature prediction values corresponding to the plurality of influencing factors and weights corresponding to the plurality of influencing factors, respectively; and automatically adjusting the temperature of the seat of the vehicle based on the target seat temperature prediction value.

2. The conditioning method of claim 1, wherein, The method further comprises: establishing an initial vehicle seat temperature control prediction model based on a random forest algorithm, wherein the initial vehicle seat temperature control prediction model comprises a plurality of decision sub-models corresponding to a plurality of influencing factors; obtaining influencing factor sample data corresponding to the plurality of influencing factors; training the initial vehicle seat temperature control prediction model based on the plurality of influencing factor sample data to obtain the vehicle seat temperature control prediction model.

3. The conditioning method of claim 2, wherein, Obtaining influencing factor sample data corresponding to a plurality of influencing factors comprises: obtaining historical data corresponding to the plurality of influencing factors in a historical time period; performing standardization processing on the historical data to obtain processed historical data; obtaining influencing factor sample data corresponding to the plurality of influencing factors from the processed historical data, respectively.

4. The conditioning method of claim 2, wherein, Training the initial vehicle seat temperature control prediction model based on the plurality of influencing factor sample data to obtain the vehicle seat temperature control prediction model comprises: dividing the plurality of influencing factor sample data into a training set and a test set, wherein a data amount of the training set and a data amount of the test set satisfy a preset ratio; training the plurality of decision sub-models in the initial vehicle seat temperature control prediction model using data in the training set corresponding to the plurality of influencing factors, respectively; in response to completion of training of the plurality of decision sub-models, verifying the plurality of decision sub-models that have been trained using the test set corresponding to the plurality of influencing factors to obtain a training accuracy of the initial vehicle seat temperature control prediction model comprising the plurality of decision sub-models that have been trained; in response to the training accuracy being less than an accuracy threshold, adjusting model parameters of the initial vehicle seat temperature control prediction model comprising the plurality of decision sub-models that have been trained to obtain the vehicle seat temperature control prediction model. Verifying the plurality of decision sub-models that have been trained using the test set corresponding to the plurality of influencing factors to obtain a training accuracy of the initial vehicle seat temperature control prediction model comprising the plurality of decision sub-models that have been trained comprises:

5. The conditioning method of claim 4, wherein, inputting data in the test set corresponding to the plurality of influencing factors into the plurality of decision sub-models, respectively; ​ obtaining a plurality of decision sub-models corresponding to the plurality of influence factors, respectively; determining a seat temperature target prediction sample value based on the plurality of influence factors corresponding to the seat temperature prediction sample value, and the weight corresponding to the plurality of influence factors, respectively, wherein the seat temperature target prediction sample value is used to indicate the seat temperature predicted by the initial vehicle seat temperature control prediction model, and the seat temperature satisfies the comfort of the vehicle occupant; comparing the seat temperature target prediction sample value with the actual seat temperature value to determine the training accuracy of the initial vehicle seat temperature control prediction model, wherein the actual seat temperature value is used to indicate the measured seat temperature value that satisfies the comfort of the vehicle occupant under the plurality of influence factors.

6. The conditioning method of claim 4, wherein, adjusting the model parameters of the initial vehicle seat temperature control prediction model including the plurality of decision sub-models trained to obtain the vehicle seat temperature control prediction model, comprising: adjusting the model parameters of the plurality of decision sub-models included in the initial vehicle seat temperature control prediction model to obtain the plurality of decision sub-models after adjustment; determining the initial vehicle seat temperature control prediction model containing the plurality of decision sub-models after adjustment as the initial vehicle seat temperature control prediction model after adjustment; verifying the initial vehicle seat temperature control prediction model after adjustment based on the test set to obtain the training accuracy of the initial vehicle seat temperature control prediction model after adjustment; in response to the training accuracy of the initial vehicle seat temperature control prediction model after adjustment being greater than or equal to the accuracy threshold, determining the initial vehicle seat temperature control prediction model after adjustment as the vehicle seat temperature control prediction model. The method further comprises:

7. The conditioning method of claim 1, wherein, standardizing the plurality of influence factors to obtain a plurality of standardized coefficients corresponding to the plurality of influence factors; determining the influence degree of the plurality of influence factors on the change of the vehicle seat temperature based on the standardized coefficients; determining the weight corresponding to the plurality of influence factors based on the influence degree, respectively. The plurality of influence factors include at least one of the following: a body index of the vehicle occupant, a behavior action of the vehicle occupant on the vehicle seat, an environmental temperature of the vehicle, an environmental humidity of the vehicle, a type of the vehicle, a degree of closure of the vehicle, a power of the vehicle, a material of the seat of the vehicle, and a contact area between the vehicle occupant and the vehicle seat.

8. The conditioning method of any one of claims 1 to 7, wherein, 9. A vehicle seat temperature adjustment device, comprising: an identification unit configured to identify a plurality of influence factors affecting the change of the seat temperature of the vehicle; an obtaining unit configured to obtain influence factor data corresponding to the plurality of influence factors, respectively, wherein the influence factor data is used to represent data related to the influence factors. ​ A prediction unit is configured to input the influence factor data into a vehicle seat temperature control prediction model to obtain a seat temperature prediction value corresponding to each of the influence factors, wherein the vehicle seat temperature control prediction model is configured to predict seat temperatures corresponding to different influence factors; A determination unit is configured to determine a seat temperature target prediction value of the vehicle based on the seat temperature prediction values corresponding to the plurality of influence factors and weights corresponding to the plurality of influence factors, respectively; An adjustment unit is configured to automatically adjust the seat temperature of the vehicle based on the seat temperature target prediction value.

10. An electronic device, comprising: The method comprises: a memory storing an executable program; a processor configured to run the program, wherein the program performs the method of any one of claims 1 to 8 when executed.

11. A computer readable storage medium, wherein, The computer-readable storage medium comprises a stored executable program, wherein the executable program controls the device where the storage medium is located to perform the method of any one of claims 1 to 8 when executed.

12. A computer program product, wherein, The computer program comprises a computer program that, when executed by a processor, implements the method of any one of claims 1 to 8.

13. A vehicle, wherein, The vehicle is configured to perform the method of any one of claims 1 to 8.

Images