Air conditioning temperature control method, related device and vehicle

Abstract

The application provides an air conditioner temperature control method, related equipment and a vehicle; the method comprises the following steps: obtaining historical data groups about temperature control of an air conditioner; dividing all the historical data groups into multiple categories by using multiple preset conditions; each historical data group in each category comprises corresponding feature data of multiple preset features and air conditioner temperature data corresponding to an air conditioner temperature; for each feature in each category, a feature mapping relationship between the feature and the air conditioner temperature is constructed by using corresponding feature data and corresponding air conditioner temperature data; for each category, a condition mapping relationship corresponding to the category is obtained by fusing feature mapping relationships between all the features and the air conditioner temperature; and the air conditioner is controlled by using the condition mapping relationship. It can be seen that the method linearizes the relationship between features and air conditioner temperatures, thereby improving the accuracy of temperature control of the air conditioner.

Description

Technical Field

[0001] The embodiments of this application relate to the technical field of equipment control, and in particular to an air conditioning temperature control method, related equipment, and vehicle. Background Technology

[0002] Among the relevant air conditioning temperature control methods, the temperature setting of the air conditioner is mainly based on the user's historical set temperature. However, this method recommends the air conditioner temperature based on too single criteria, so it does not have the ability to adjust the air conditioner temperature at any time, and the accuracy of the recommended air conditioner temperature is low, often not the temperature that the user most wants.

[0003] Therefore, a solution is needed that can take into account multiple influencing factors and accurately recommend air conditioning temperatures. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide an air conditioning temperature control method, related equipment and vehicle.

[0005] For the purposes described above, this application provides an air conditioning temperature control method, including:

[0006] Obtain historical data sets regarding temperature control by the air conditioner;

[0007] The historical data sets are divided into multiple categories using multiple preset conditions; each historical data set in each category includes: feature data corresponding to each of the multiple preset features and air conditioning temperature data corresponding to the air conditioning temperature.

[0008] For each feature in each category, a feature mapping relationship between the feature and the air conditioning temperature is constructed using the corresponding feature data and the corresponding air conditioning temperature data;

[0009] For each category, the feature mapping relationship between all the features and the air conditioning temperature is fused to obtain the conditional mapping relationship corresponding to the category, so as to control the air conditioning temperature using the conditional mapping relationship.

[0010] Furthermore, obtain historical data sets regarding temperature control by the air conditioner, including:

[0011] Obtain multiple initial data points regarding temperature control by the air conditioner; each initial data point includes a timestamp;

[0012] Based on the timestamp, the initial data of the same air conditioning device at the same time are grouped into a set of historical data.

[0013] Furthermore, using multiple preset conditions, all the historical data sets are divided into multiple categories, including:

[0014] Determine multiple sub-conditions for each of the stated conditions;

[0015] Select any sub-condition from each of the conditions;

[0016] Group all selected sub-conditions into one category;

[0017] In all the historical data sets, exhaust all the combinations of sub-conditions among the conditions to obtain multiple categories.

[0018] Furthermore, using the corresponding feature data and the corresponding air conditioning temperature data, a feature mapping relationship between the feature and the air conditioning temperature is constructed, including:

[0019] Construct a first fitting polynomial between the air conditioning temperature and the feature;

[0020] The first fitting polynomial is optimized using all the feature data corresponding to the feature and all the air conditioning temperature data;

[0021] The feature mapping relationship is represented by the optimized first fitting polynomial.

[0022] Furthermore, optimizing the first fitting polynomial using all the feature data corresponding to that feature and all the air conditioning temperature data includes:

[0023] Initialize the parameters in the first fitting polynomial;

[0024] Based on the initial first fitting polynomial, the corresponding air conditioning temperature estimate is determined using each of the feature data corresponding to that feature.

[0025] Determine the mean square error between the estimated air conditioning temperature and the corresponding air conditioning temperature data in the historical data group;

[0026] In response to the mean square error being greater than or equal to a preset mean square error threshold, the initialized parameters are optimized using a preset optimization algorithm based on the mean square error until the mean square error is less than the mean square error threshold, thus obtaining the optimized first fitting polynomial; or

[0027] In response to the mean square error being less than the mean square error threshold, the coverage of the air conditioner temperature estimate on the air conditioner temperature data is determined based on the numerical relationship between the air conditioner temperature estimate and the air conditioner temperature data.

[0028] In response to the coverage rate being less than or equal to a preset coverage threshold, the parameter is optimized using the optimization algorithm based on the coverage rate until the coverage rate is greater than the coverage threshold;

[0029] In response to the coverage rate being greater than the coverage rate threshold, the optimized first fitting polynomial is obtained.

[0030] Furthermore, by fusing the feature mapping relationship between all the aforementioned features and the air conditioning temperature, a conditional mapping relationship corresponding to this category is obtained, including:

[0031] Weights are assigned to the first fitting polynomial between each of the air conditioning temperatures and the features;

[0032] According to the set weights, the first fitting polynomials corresponding to each of the features are weighted to obtain the second fitting polynomial corresponding to the category.

[0033] The second fitting polynomial is used as a conditional mapping relationship between air conditioning temperature and this category;

[0034] Furthermore, using the aforementioned conditional mapping relationship to control the temperature of the air conditioner includes:

[0035] Using the aforementioned conditional mapping relationship, the value of the air conditioning temperature is determined;

[0036] The air conditioner is temperature controlled according to the specified temperature value.

[0037] Based on the same inventive concept, this application also provides an air conditioning temperature control device, including: a preprocessing module, a feature mapping relationship construction module, and a condition mapping relationship construction module;

[0038] The preprocessing module is configured to acquire historical data sets related to air conditioning temperature control; and divide all the historical data sets into multiple categories using multiple preset conditions. Each historical data set in each category includes feature data corresponding to multiple preset features and air conditioning temperature data corresponding to the air conditioning temperature.

[0039] The feature mapping relationship construction module is configured to construct a feature mapping relationship between the feature and the air conditioning temperature for each feature in each category, using the corresponding feature data and the corresponding air conditioning temperature data.

[0040] The module for constructing conditional mapping relationships is configured to, for each category, fuse all the feature mapping relationships between the features and the air conditioner temperature to obtain a conditional mapping relationship corresponding to that category, so as to use the conditional mapping relationship to control the temperature of the air conditioner.

[0041] In the same inventive concept, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the air conditioning temperature control method as described above.

[0042] Based on the same inventive concept, this application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions for causing the computer to perform the air conditioning temperature control method described above.

[0043] Based on the same inventive concept, this application also provides a vehicle, the vehicle including an air conditioning temperature control device or electronic device, the electronic device performing the air conditioning temperature control method as described in any of the above claims.

[0044] Based on the division of historical data groups, and taking into account the relationships between different conditions and features, feature mapping relationships and condition mapping relationships are constructed. This establishes a linear mapping relationship between air conditioning temperature and various features and conditions. Based on the established mapping relationship, the calculation relationship between each feature and air conditioning temperature can be accurately described. In other words, when the values ​​of each feature are determined, the corresponding air conditioning temperature value can be obtained. Furthermore, by setting the specific temperature of the air conditioner according to the value of the air conditioning temperature, more intelligent and accurate temperature control of the air conditioner can be achieved. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart of an air conditioning temperature control method according to an embodiment of this application;

[0047] Figure 2 This is a flowchart illustrating the construction of feature mapping relationships in an embodiment of this application;

[0048] Figure 3 This is a flowchart illustrating the optimization of the first fitting function according to an embodiment of this application;

[0049] Figure 4 This is a flowchart illustrating the construction condition mapping relationship in an embodiment of this application;

[0050] Figure 5 This is a schematic diagram of the structure of an air conditioning temperature control device according to an embodiment of this application;

[0051] Figure 6 This is a schematic diagram of the electronic device structure according to an embodiment of this application. Detailed Implementation

[0052] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0053] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0054] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the term "comprising" or any other variations thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0055] As described in the background section, the existing air conditioning temperature control methods are still insufficient to meet the needs of practical use.

[0056] In the process of implementing this application, the applicant discovered that the main problem with the relevant air conditioning temperature control method is that the relevant air conditioning temperature control method mainly sets the air conditioning temperature based on the user's historical default temperature. However, the basis for recommending the air conditioning temperature in this method is too singular. Therefore, it often lacks the ability to modify the temperature midway, or in other words, the ability to adjust the air conditioning temperature at any time is very weak.

[0057] On the other hand, relying on a single basis for recommending air conditioning temperatures also results in low accuracy of the recommended temperatures, which are often not the temperatures that users most desire.

[0058] The applicant found in the research that there are often multiple factors affecting the air conditioner temperature setting, and the relationship between some of these factors and the air conditioner temperature is non-linear. Therefore, transforming the non-linear problem into a linear problem is the key to integrating multiple influencing factors.

[0059] The embodiments of this application are described in detail below with reference to the accompanying drawings.

[0060] refer to Figure 1 An embodiment of the air conditioning temperature control method of this application includes the following steps:

[0061] Step S101: Obtain historical data sets on temperature control of the air conditioner.

[0062] In one embodiment of this application, controlling the temperature of a vehicle's air conditioning system is used as a specific example to describe the method.

[0063] In this embodiment, the operation of controlling the temperature of the vehicle's air conditioning is based on the analysis of big data. Therefore, it is necessary to obtain relevant historical data on the temperature control of the air conditioning of multiple vehicles.

[0064] Specifically, the relevant historical data may include vehicle history data about the vehicle being driven and environmental history data about the environment in which the vehicle is located.

[0065] The vehicle history data and environmental history data each include multiple initial data points, and each initial data point includes multiple conditional data points, multiple feature data points, and timestamps.

[0066] Specifically, conditional data in each initial data set can be determined based on multiple preset conditions, and feature data in each initial data set can be determined based on multiple preset features.

[0067] Furthermore, by clustering all the initial data, multiple historical data groups can be obtained. In each historical data group, all the initial data are the condition data, feature data, and air conditioning temperature data of the same vehicle at the same time. It can be seen that the initial data of the same vehicle can represent the initial data of the same air conditioning equipment.

[0068] In this embodiment, the preset conditions can be geographical conditions, seasonal conditions, vehicle type conditions, and time period conditions; the preset features can be ambient temperature features, ambient humidity features, ambient light intensity features, cabin temperature features, weather conditions features, and user age features.

[0069] Each preset condition represents a different operating condition of the vehicle's air conditioning, while each preset feature represents a factor that affects the vehicle's air conditioning system's temperature control.

[0070] Step S102: Divide all the historical data groups into multiple categories using multiple preset conditions. Each historical data group in each category includes feature data corresponding to multiple preset features and air conditioning temperature data corresponding to the air conditioning temperature.

[0071] In the embodiments of this application, all historical data groups are divided based on the aforementioned preset conditions.

[0072] In this embodiment, each preset condition is divisible, that is, each condition consists of multiple sub-conditions. According to the multiple sub-conditions of any condition, the entire historical data set can be divided into multiple different categories.

[0073] Furthermore, combining all the aforementioned preset conditions represents the overall operating condition of the vehicle's air conditioning system.

[0074] It can be seen that different overall operating conditions can be composed of different sub-conditions of each condition. Therefore, all possible combinations of sub-conditions between each condition can be exhausted, and all historical data sets can be divided into multiple different categories corresponding to different overall operating conditions.

[0075] It can be determined that each category has multiple historical data groups. As mentioned above, each historical data group has multiple feature data and condition data, and also has the corresponding air conditioning temperature data under the condition and feature.

[0076] Step S103: For each feature in each category, construct a feature mapping relationship between the feature and the air conditioning temperature using the corresponding feature data and the corresponding air conditioning temperature data.

[0077] In the embodiments of this application, based on the multiple categories determined above, the mapping relationship between air conditioning temperature and each feature can be determined by the feature data obtained in the aforementioned steps.

[0078] Specifically, based on the steps described above for constructing historical data groups, it can be seen that each historical data group in each category includes feature data corresponding to each feature.

[0079] Furthermore, within each category, for each feature, a feature mapping relationship is established between that feature and the air conditioning temperature to obtain multiple feature mapping relationships corresponding to that category.

[0080] Specifically, for each category, a feature mapping relationship is constructed between ambient temperature characteristics and air conditioning temperature; a feature mapping relationship is constructed between ambient humidity characteristics and air conditioning temperature; a feature mapping relationship is constructed between ambient light intensity characteristics and air conditioning temperature; a feature mapping relationship is constructed between cabin temperature characteristics and air conditioning temperature; a feature mapping relationship is constructed between weather condition characteristics and air conditioning temperature; and a feature mapping relationship is constructed between user age characteristics and air conditioning temperature.

[0081] As can be seen, this method can yield 6 feature mapping relationships in each category, each corresponding to one of the 6 different features preset in the aforementioned steps.

[0082] Step S104: For each category, fuse all the features and the feature mapping relationship between the air conditioner temperature to obtain the condition mapping relationship corresponding to the category, so as to use the condition mapping relationship to control the temperature of the air conditioner.

[0083] In the embodiments of this application, for each category, based on the multiple feature mapping relationships of the category determined by the above steps, the first fitting polynomials corresponding to each feature in the category can be fused by a fusion method, that is, all feature mapping relationships under the category are fused.

[0084] Furthermore, we obtain the mapping relationship between all features and air conditioning temperature, that is, the conditional mapping relationship between this category and air conditioning temperature.

[0085] Based on the definition of categories in the above steps, it can be seen that since each category is composed of multiple sub-conditions representing the overall operating condition, the condition mapping relationship specifically describes the mapping relationship between various influencing factors and air conditioning temperature when the overall operating condition is determined.

[0086] Furthermore, based on the above method, the conditional mapping relationship between all categories and air conditioning temperature is determined.

[0087] It can be determined that, through the above method, the mapping relationship between influencing factors and air conditioning temperature under various operating conditions has been obtained, that is, multiple conditional mapping relationships.

[0088] Furthermore, by utilizing the obtained multiple conditional mapping relationships, intelligent control of air conditioning temperature can be achieved.

[0089] Specifically, by collecting current condition data, the current operating condition of the air conditioner can be determined. In other words, the specific category can be determined through the current condition data, and the condition mapping relationship corresponding to that category can be selected.

[0090] Furthermore, the value of the air conditioner temperature is determined using the conditional mapping relationship; the air conditioner temperature is then controlled according to the value of the air conditioner temperature.

[0091] Specifically, the system collects current feature data, i.e., the factors currently affecting the air conditioning temperature. The collected feature data is then input into a conditional mapping relationship to map out the corresponding air conditioning temperature value for the current feature and category. Finally, the vehicle's air conditioning temperature is set to the mapped air conditioning temperature value to complete the temperature control of the vehicle's air conditioning.

[0092] As can be seen, the air conditioning temperature control method of the embodiments of this application, based on the division of historical data groups, comprehensively considers the relationship between different conditions and different features to construct feature mapping relationships and condition mapping relationships, so as to establish a linear mapping relationship between air conditioning temperature and various features and conditions. Based on the established linear mapping relationship, the calculation relationship between each feature and air conditioning temperature in terms of value can be accurately described. That is to say, when the value of each feature is determined, the corresponding air conditioning temperature value can be obtained. By setting the specific temperature of the air conditioner according to the value of the air conditioning temperature, the temperature control of the air conditioner can be achieved more intelligently and accurately.

[0093] In another embodiment of this application, obtaining a historical data set regarding temperature control by the air conditioner includes:

[0094] Obtain multiple initial data points regarding temperature control by the air conditioner, each of which includes a timestamp;

[0095] Furthermore, based on the timestamp, initial data about the same air conditioning device at the same time are grouped into a set of historical data.

[0096] Specifically, each initial data point in the vehicle's historical data may include: the temperature inside the vehicle's cockpit, the driver's age, the vehicle's model, the region where the vehicle is located, and a timestamp.

[0097] Furthermore, each initial data point in the environmental history data may include: the season in which the vehicle was used, the time period in which the vehicle was used, the ambient temperature of the environment in which the vehicle was located, the ambient humidity of the environment in which the vehicle was located, the ambient light intensity of the environment in which the vehicle was located, the weather conditions of the environment in which the vehicle was located, and a timestamp, etc.

[0098] It can be seen that, for the same vehicle, the vehicle's historical data at a certain moment and the environmental historical data at the same moment are factors that jointly affect the vehicle's air conditioning temperature control at that moment. Therefore, it is necessary to cluster the vehicle's historical data and environmental historical data at the same moment into a historical data group.

[0099] Specifically, the K-means algorithm can be used to cluster multiple initial data points by continuously optimizing the centroids of the classification categories during iteration, thereby obtaining multiple historical data groups.

[0100] In other embodiments, multiple historical data groups can be obtained by identifying the timestamps in each initial data set, clustering the initial data sets containing timestamps from the same vehicle at the same time, and grouping them into a single historical data group.

[0101] Furthermore, in each historical data group, the corresponding condition data and feature data can be determined according to the preset conditions and features in the aforementioned embodiments.

[0102] Specifically, vehicle type, region, season, and time of day are used as four conditional data points; cabin temperature, age, ambient temperature, ambient humidity, ambient light intensity, and weather conditions are used as six characteristic data points.

[0103] It should be noted that the conditional data and feature data in the historical data can be changed according to the preset conditions and features. For example, if the interior temperature of the driver's cabin, the interior temperature of the rear passenger cabin, and the vehicle space are preset features, then the corresponding interior temperature data of the driver's cabin, the interior temperature data of the rear passenger cabin, and the vehicle space data can be used as feature data. If whether the vehicle windows use solar film and the type of solar film are preset conditions, then the corresponding specific situation can be used as conditional data.

[0104] As can be seen, this embodiment quantifies the operating conditions and influencing factors through preset conditions and features, and effectively clusters the operating conditions and influencing factors of the same vehicle affecting the same air conditioning temperature at the same time into the same historical data group by using timestamps, thus determining the correspondence between condition data, feature data and air conditioning temperature data.

[0105] In another embodiment of this application, all the historical data sets are divided into multiple categories using multiple preset conditions, including:

[0106] Determine multiple sub-conditions for each of the stated conditions;

[0107] Select any sub-condition from each of the conditions;

[0108] Group all selected sub-conditions into one category;

[0109] In all the historical data sets, exhaust all the combinations of sub-conditions among the conditions to obtain multiple categories.

[0110] In this embodiment, based on the multiple conditions preset in the foregoing embodiments, sub-conditions of each condition are determined.

[0111] Specifically, for the geographical conditions, two first sub-conditions can be set: the northern region and the southern region.

[0112] For the seasonal condition, two second sub-conditions can be set: summer and winter.

[0113] For the vehicle type condition, two third sub-conditions can be set: compact vehicles and mid-to-large vehicles.

[0114] For the time period condition, two fourth sub-conditions can be set: daytime and nighttime.

[0115] Furthermore, in order to determine the combination of sub-conditions among various conditions, that is, to determine the different overall working conditions, any sub-condition can be selected from each of the above conditions and combined.

[0116] For example, you can select the northern region, summer, compact vehicle, and daytime, and treat this combination as a general operating condition.

[0117] It can be seen that, from all historical data sets, historical data sets that meet the above four sub-condition combinations are selected, and these historical data sets are grouped into one category.

[0118] Furthermore, following the above method of combining sub-conditions, all possible combinations are exhausted to obtain combinations of multiple sub-conditions, and the corresponding categories are determined from all historical data sets to divide all historical data sets into multiple categories.

[0119] It should be noted that the conditions and sub-conditions preset in any embodiment of this application are exemplary. Other conditions can also be set according to fine-grained requirements, or more sub-conditions can be subdivided into any condition in this embodiment. For example, the seasonal condition can be subdivided into four sub-conditions: spring, summer, autumn and winter, or the vehicle type condition can be subdivided into passenger cars, buses and engineering vehicles, etc.

[0120] As can be seen, in this embodiment, by utilizing multiple preset conditions and combining the sub-conditions between the conditions, various operating conditions of the vehicle air conditioner are effectively summarized.

[0121] In another embodiment of this application, such as Figure 2 As shown, using the corresponding feature data and the corresponding air conditioning temperature data, a feature mapping relationship between the feature and the air conditioning temperature is constructed, including:

[0122] Step S201: Construct a first fitting polynomial between the air conditioning temperature and the feature.

[0123] In this embodiment, based on the multiple categories defined in the preceding embodiments, for each feature within each category, a first fitting polynomial is constructed as shown below between the feature and the air conditioning temperature:

[0124] y = A × x 7 +B×x 6 +C×x 5 +D×x 4 +E×x 3 +F×x 2 +G×x1 +H×x 0

[0125] Where x represents the value of the feature; y represents the value of the air conditioning temperature; and A, B, C, D, E, F, G, and H are all parameters of the first fitting polynomial.

[0126] Furthermore, for each feature in each category, the aforementioned first fitting polynomial is constructed to obtain multiple first fitting polynomials for that category.

[0127] As can be seen, based on the features set in the aforementioned embodiments, six first fitting polynomials corresponding to each feature can be determined in each category.

[0128] Specifically, for the ambient temperature feature, a first fitting polynomial as shown above is constructed, with x1 representing the value of the ambient temperature and y1 representing the value of the air conditioning temperature corresponding to the ambient temperature feature in this category.

[0129] Furthermore, for the environmental humidity characteristics, a first fitting polynomial as shown above is constructed, with x2 representing the value of the environmental temperature and y2 representing the value of the air conditioning temperature corresponding to the environmental temperature characteristics in this category.

[0130] Furthermore, for the ambient light intensity characteristics, a first fitting polynomial as shown above is constructed, with x3 representing the ambient temperature value and y3 representing the air conditioning temperature value corresponding to the ambient temperature characteristics in this category.

[0131] Furthermore, for the cabin temperature characteristics, a first fitting polynomial as shown above is constructed, with x4 representing the ambient temperature value and y4 representing the air conditioning temperature value corresponding to the ambient temperature characteristics in this category.

[0132] Furthermore, for the weather condition features, a first fitting polynomial as shown above is constructed, with x5 representing the ambient temperature value and y5 representing the air conditioning temperature value corresponding to the ambient temperature feature in this category.

[0133] Furthermore, for the user age characteristic, a first fitting polynomial as shown above is constructed, with x6 representing the value of the ambient temperature and y6 representing the value of the air conditioning temperature corresponding to the ambient temperature characteristic in this category.

[0134] Step S202: Optimize the first fitting polynomial using all the feature data corresponding to the feature and all the air conditioning temperature data.

[0135] In this embodiment, based on the classification of all historical data groups in the foregoing embodiments, the specific historical data groups in each category can be determined.

[0136] Furthermore, the feature data corresponding to each feature in each category, as well as the air conditioning temperature data corresponding to that feature data, can be determined.

[0137] It can be seen that by using the feature data from multiple historical data sets and the air conditioning temperature data corresponding to each feature data, the first fitting polynomials constructed in step S201 above can be optimized to determine each parameter in each first fitting polynomial.

[0138] Step S203: Represent the feature mapping relationship using the optimized first fitting polynomial.

[0139] In this step, each optimized first fitting polynomial can be used as a feature mapping relationship between the corresponding feature and the air conditioning temperature.

[0140] Furthermore, for all features in each category, the corresponding first fitting polynomial is used as the feature mapping relationship between the feature and the air conditioning temperature.

[0141] As can be seen, in this embodiment, by constructing a first fitting polynomial, the mapping relationship between each feature and the air conditioning temperature is effectively reflected when the category is determined, that is, the overall operating conditions are determined, and each feature is considered individually. In other words, it expresses the individual influence of each influencing factor on the air conditioning temperature.

[0142] In another embodiment of this application, such as Figure 3 As shown, optimizing the first fitting polynomial using all the feature data corresponding to that feature and all the air conditioning temperature data includes:

[0143] Step S301: Initialize the parameters in the first fitting polynomial.

[0144] In this step, each of the first fitting polynomials constructed based on the aforementioned embodiments needs to first initialize its various parameters. Specifically, each parameter can be randomly assigned an initial random value, or an initial value can be set for each parameter according to the specific situation.

[0145] Step S302: Based on the initialized first fitting polynomial, determine the corresponding air conditioning temperature estimate using each of the feature data corresponding to that feature.

[0146] In this step, the initialization of the first fitting polynomial can be obtained by using the parameters initialized in step S301 above.

[0147] Furthermore, feature data of the same category concerning the same characteristic are input into the first fitting polynomial after initialization with specific parameter values ​​to calculate the estimated air conditioning temperature based on the feature data.

[0148] Among them, there should be multiple feature data for the same feature, and they should cover all reasonable value ranges.

[0149] Based on this, in the historical data group of this category, the values ​​of the air conditioning temperature data corresponding to this feature data can exhibit a normal distribution.

[0150] Furthermore, using the first fitting polynomial after initialization, the estimated value of the air conditioning temperature can be calculated when all feature data are input into it.

[0151] Step S303: Determine the mean square error between the estimated air conditioning temperature and the corresponding air conditioning temperature data in the historical data group.

[0152] In this step, based on the estimated air conditioning temperature obtained in step S302 above, the mean square error between the estimated air conditioning temperature and the air conditioning temperature data is calculated, where the air conditioning temperature data are the values ​​recorded in each historical data group, that is, the actual values ​​of the air conditioning temperature.

[0153] In this embodiment, the optimization direction of the first fitting polynomial is to minimize the mean square error, that is, it is necessary to determine the values ​​of each parameter when the mean square error is minimized.

[0154] In this embodiment, the minimum mean square error can also be transformed into the mean square error being within the mean square error threshold. Since the temperature of a car air conditioner is often set with a 0.5 degree Celsius interval between two adjacent settings, the mean square error threshold can be set to 0.5.

[0155] Step S304: In response to the mean square error being greater than or equal to a preset mean square error threshold, the initialized parameters are optimized using a preset optimization algorithm based on the mean square error until the mean square error is less than the mean square error threshold, thereby obtaining the optimized first fitting polynomial.

[0156] In this step, it is necessary to determine whether the mean square error calculated above is less than the mean square error threshold.

[0157] Furthermore, after the determination, if the mean square error is greater than or equal to the mean square error threshold, it indicates that the current parameter value is difficult to make the output of the first fitting polynomial close to the actual value of the estimated air conditioning temperature.

[0158] Furthermore, in this case, it is necessary to adjust the values ​​of the parameters and use the first fitting polynomial after parameter adjustment to calculate the feature data again to obtain a new estimated value of the air conditioning temperature.

[0159] Specifically, a preset optimization algorithm can be used to optimize the parameters of the fitted polynomial, that is, to redetermine the parameters and use the reduction of mean square error as the optimization objective. For example, a commonly used optimization algorithm can be set in Matlab or other software.

[0160] Furthermore, steps S302 and S303 are repeated again using the new air conditioning temperature estimate to calculate the mean square error and make a determination.

[0161] Even after determining that the mean square error is greater than or equal to the mean square error threshold, it is still necessary to continuously adjust the values ​​of the parameters until the mean square error is less than the mean square error threshold.

[0162] In another embodiment of this application, based on the calculation results of the mean square error in the foregoing embodiments, after determining the mean square error between the estimated air conditioning temperature and the corresponding air conditioning temperature data in the historical data group, the method further includes:

[0163] In response to the mean square error being less than the mean square error threshold, the coverage of the air conditioner temperature estimate on the air conditioner temperature data is determined based on the numerical relationship between the air conditioner temperature estimate and the air conditioner temperature data.

[0164] In response to the coverage rate being less than or equal to a preset coverage threshold, the parameter is optimized using the optimization algorithm based on the coverage rate until the coverage rate is greater than the coverage threshold;

[0165] In response to the coverage rate being greater than the coverage rate threshold, the optimized first fitting polynomial is obtained. In this step, based on the calculation result of the mean square error, when it is determined that the mean square error is less than the mean square error threshold, it indicates that the parameter values ​​at this time can make the output of the first fitting polynomial a temperature estimate that is close to the actual value.

[0166] Furthermore, the first fitting polynomial of all feature data is calculated at this time to obtain the values ​​of the air conditioning temperature data corresponding to each feature data.

[0167] Furthermore, determine the coverage of all estimated air conditioning temperatures on the air conditioning temperature data.

[0168] Specifically, the coverage of the estimated air conditioning temperature on the air conditioning temperature data can be obtained by calculating the ratio between the estimated air conditioning temperature and the actual air conditioning temperature.

[0169] In other embodiments, the characteristics of a normal distribution can also be used to determine the coverage.

[0170] Specifically, the estimated air conditioning temperature can be described as a first normal distribution in the form of a normal distribution, and the air conditioning temperature data can also be described as a second normal distribution in the form of a normal distribution. The coverage rate can be determined by comparing the ratio of the coverage areas of the first normal distribution and the second normal distribution.

[0171] It is understood that the coverage rate does not have to be a strict ratio between the estimated air conditioning temperature and the air conditioning temperature data. Other methods can be set to correct the ratio. Any calculation method that can reflect the coverage of the estimated air conditioning temperature on the air conditioning temperature data can be used to calculate the coverage rate.

[0172] Furthermore, if the coverage rate is greater than the coverage rate threshold, it can be further indicated that the estimated air conditioning temperature is close to the recorded air conditioning temperature in most cases. In other words, the first fitting polynomial at this time is very accurate in estimating the air conditioning temperature. 95% can be used as one of the specific examples of the coverage rate threshold.

[0173] In this embodiment, if the coverage rate is less than or equal to the coverage rate threshold of 95%, it indicates that there is a distance between the estimated air conditioning temperature and the recorded air conditioning temperature data. The first fitting polynomial still needs to be optimized, that is, the parameters need to be adjusted, and the coverage rate needs to be calculated and compared again until the coverage rate can be greater than the coverage rate threshold.

[0174] Similar to the parameter optimization in the previous embodiments, a preset optimization algorithm can be used to optimize the parameters of the fitting polynomial, that is, to redetermine the parameters and use increasing the coverage as the optimization goal. For example, a commonly used optimization algorithm can be set in Matlab or other software.

[0175] In this embodiment, when the coverage rate is greater than the coverage rate threshold of 95%, the first fitting polynomial at this time can be used as the optimized first fitting polynomial.

[0176] As can be seen, in this embodiment, by using a fitting polynomial to establish a linear mapping relationship between the features and the air conditioning temperature, and by simultaneously using the set mean square error and coverage threshold to determine the optimization of the first fitting polynomial, it is ensured that a first fitting polynomial with good fitting effect and accurate prediction can be obtained.

[0177] In another embodiment of this application, such as Figure 4 As shown, by fusing the feature mapping relationship between all the aforementioned features and the air conditioning temperature, a conditional mapping relationship corresponding to this category is obtained, including:

[0178] Step S401: Set weights for the first fitting polynomial corresponding to each feature.

[0179] In this step, different weights need to be set for multiple first-fit polynomial features in each category. It can be seen that the weights are essentially used to measure the degree of influence of each feature on the estimated air conditioning temperature.

[0180] Specifically, the first fitting polynomial can be determined by the rate of change between the corresponding features and the air conditioning temperature data.

[0181] First, determine the changes in the feature data at a certain interval, and then determine the corresponding changes in the air conditioning temperature data based on these changes in the feature data.

[0182] Then, the ratio between the change in feature data and the change in air conditioning temperature data is determined, and this ratio is used as the feature-air conditioning temperature change rate.

[0183] Furthermore, within this category, the characteristic-air conditioning temperature change rate is calculated for each feature.

[0184] Furthermore, since the units of measurement for each feature are different, it is necessary to normalize all features – the rate of change of air conditioning temperature.

[0185] Furthermore, the results obtained after normalization are used as the weights of each corresponding feature, that is, each first fitting polynomial.

[0186] Step S402: According to the set weights, the first fitting polynomials corresponding to each of the features are weighted to obtain the second fitting polynomial corresponding to the category.

[0187] In this step, based on the weights of each of the first fitting polynomials determined above, the second fitting polynomial is determined by weighted summation, as shown in the following formula:

[0188] Y1=a×y1+b×y2+c×y3+d×y4+e×y5+f×y6+w1

[0189] Where Y1 represents the estimated air conditioning temperature for this category, a, b, c, d, e, and f represent the respective weights of each first fitting polynomial, and w1 represents the mapping error compensation.

[0190] In this embodiment, the mapping error compensation can be set based on expert experience or calculated by statistical average deviation.

[0191] In some other embodiments, calibration compensation values ​​may be added to the second fitting polynomial obtained above.

[0192] Specifically, since there will always be an error between the estimated air conditioning temperature and the actual measurement result, the calibration compensation value can be added to the second fitting polynomial to correct the error, resulting in the formula shown below:

[0193] Y2=a×y1+b×y2+c×y3+d×y4+e×y5+f×y6+w1+w2

[0194] Where Y2 is the fitting polynomial with added calibration compensation value, and w1 is the added calibration compensation value.

[0195] Step S403: Use the second fitted polynomial as a conditional mapping relationship between the air conditioning temperature and the category.

[0196] As can be seen, in this embodiment, the weights of each first fitting polynomial are determined by the rate of change between the feature and the air conditioning temperature. The influence of the feature on the air conditioning temperature is described by the rate of change. A calibration compensation value is added to the weighted summation to obtain a second fitting polynomial that combines both empirical and statistical considerations.

[0197] It should be noted that the method of the embodiments of this application can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied in a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of the embodiments of this application, and the multiple devices will interact with each other to complete the method described.

[0198] It should be noted that the above description describes some embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0199] Based on the same inventive concept, and corresponding to the methods of any of the above embodiments, the embodiments of this application also provide an air conditioning temperature control device.

[0200] refer to Figure 5 The air conditioning temperature control device includes: a preprocessing module 501, a feature mapping relationship module 502, and a condition mapping relationship module 503;

[0201] The preprocessing module 501 is configured to acquire historical data sets related to air conditioning temperature control; and divide all the historical data sets into multiple categories using multiple preset conditions. Each historical data set in each category includes feature data corresponding to multiple preset features and air conditioning temperature data corresponding to the air conditioning temperature.

[0202] The feature mapping relationship construction module 502 is configured to construct a feature mapping relationship between the feature and the air conditioning temperature for each feature in each category using the corresponding feature data and the corresponding air conditioning temperature data.

[0203] The condition mapping relationship construction module 503 is configured to, for each category, fuse all the feature mapping relationships between the features and the air conditioner temperature to obtain a condition mapping relationship corresponding to the category, so as to use the condition mapping relationship to control the temperature of the air conditioner.

[0204] As an optional embodiment, the preprocessing module 501 is specifically configured as follows:

[0205] Obtain multiple initial data points regarding temperature control by the air conditioner; each initial data point includes a timestamp;

[0206] Based on the timestamp, the initial data of the same air conditioning device at the same time are grouped into a set of historical data.

[0207] Furthermore, multiple sub-conditions are determined for each of the stated conditions;

[0208] Select any sub-condition from each of the conditions;

[0209] Group all selected sub-conditions into one category;

[0210] In all the historical data sets, exhaust all the combinations of sub-conditions among the conditions to obtain multiple categories.

[0211] As an optional embodiment, the feature mapping relationship construction module 502 is specifically configured as follows:

[0212] Construct a first fitting polynomial between the air conditioning temperature and the feature;

[0213] The first fitting polynomial is optimized using all the feature data corresponding to the feature and all the air conditioning temperature data;

[0214] The feature mapping relationship is represented by the optimized first fitting polynomial.

[0215] The optimization of the first fitting polynomial using all the feature data corresponding to the feature and all the air conditioning temperature data includes:

[0216] Initialize the parameters in the first fitting polynomial;

[0217] Based on the initial first fitting polynomial, the corresponding air conditioning temperature estimate is determined using each of the feature data corresponding to that feature.

[0218] Determine the mean square error between the estimated air conditioning temperature and the corresponding air conditioning temperature data in the historical data group;

[0219] In response to the mean square error being greater than or equal to a preset mean square error threshold, the initialized parameters are optimized using a preset optimization algorithm based on the mean square error until the mean square error is less than the mean square error threshold.

[0220] In response to the mean square error being less than a preset mean square error threshold, the ratio between the estimated air conditioner temperature and the air conditioner temperature data is calculated and used as the coverage of the estimated air conditioner temperature on the air conditioner temperature data.

[0221] In response to the coverage rate being less than or equal to a preset coverage threshold, the initialized parameters are optimized using a preset optimization algorithm based on the coverage rate until the coverage rate is greater than the coverage threshold.

[0222] In response to the coverage rate being greater than the coverage rate threshold, the optimized first fitting polynomial is obtained.

[0223] As an optional embodiment, the module 503 for constructing condition mapping relationships is specifically configured as follows:

[0224] Weights are assigned to the first fitting polynomial between each of the air conditioning temperatures and the features;

[0225] According to the set weights, the first fitting polynomials corresponding to each of the features are weighted to obtain the second fitting polynomial corresponding to the category.

[0226] The second fitting polynomial is used as a conditional mapping relationship between air conditioning temperature and this category;

[0227] Using the aforementioned conditional mapping relationship, the value of the air conditioning temperature is determined;

[0228] The air conditioner is temperature controlled according to the specified temperature value.

[0229] For ease of description, the above apparatus is described in terms of its functions, divided into various modules. Of course, in implementing the embodiments of this application, the functions of each module can be implemented in one or more software and / or hardware.

[0230] The apparatus described above is used to implement the corresponding air conditioning temperature control method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0231] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, the embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the air conditioning temperature control method as described in any of the above embodiments.

[0232] Figure 6 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0233] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0234] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this application are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0235] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0236] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0237] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0238] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this application, and not necessarily all the components shown in the figures.

[0239] The apparatus described above is used to implement the corresponding air conditioning temperature control method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0240] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the air conditioning temperature control method as described in any of the above embodiments.

[0241] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0242] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the air conditioning temperature control method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0243] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides a vehicle, the vehicle including an air conditioning temperature control device and an electronic device, the electronic device performing the air conditioning temperature control method as described in any of the above embodiments.

[0244] The vehicle described in the above embodiments, by having the computer execute the air conditioning temperature control method as described in any of the above embodiments, has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0245] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application (including the claims) is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in detail for the sake of brevity.

[0246] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0247] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0248] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.

Claims

1. An air conditioning temperature control method, characterized by, include: Obtain historical data sets regarding temperature control by the air conditioner; The entire historical data set is divided into multiple categories using several preset conditions; Each of the historical data groups in each category includes: feature data corresponding to each of the multiple preset features and air conditioning temperature data corresponding to the air conditioning temperature; For each feature in each category, a feature mapping relationship between the feature and the air conditioning temperature is constructed using the corresponding feature data and the corresponding air conditioning temperature data; For each category, the feature mapping relationship between all the features and the air conditioner temperature is fused to obtain the condition mapping relationship corresponding to the category, so as to use the condition mapping relationship to control the temperature of the air conditioner; The method further includes: A first fitting polynomial is constructed to describe the rate of change between each feature and the corresponding air conditioning temperature; the weights of all the first fitting polynomials are determined; the influence of the feature on the air conditioning temperature is described by the rate of change; a calibration compensation value is added to the weighted summation of all the first fitting polynomials to obtain a second fitting polynomial; the second fitting polynomial is used to describe the conditional mapping relationship.

2. The method according to claim 1, characterized in that, The acquisition of historical data sets regarding air conditioner temperature control includes: Obtain multiple initial data points regarding temperature control by the air conditioner; each initial data point includes a timestamp; Based on the timestamp, the initial data of the same air conditioning device at the same time are grouped into a set of historical data.

3. The method according to claim 2, characterized in that, The process of dividing all historical data sets into multiple categories using preset conditions includes: Determine multiple sub-conditions for each of the stated conditions; Select any sub-condition from each of the conditions; Group all selected sub-conditions into one category; In all the historical data sets, exhaust all the combinations of sub-conditions among the conditions to obtain multiple categories.

4. The method according to claim 2, characterized in that, The step of constructing a feature mapping relationship between the feature and the air conditioning temperature using the corresponding feature data and the corresponding air conditioning temperature data includes: Construct a first fitting polynomial between the air conditioning temperature and the feature; The first fitting polynomial is optimized using all the feature data corresponding to the feature and all the air conditioning temperature data; The feature mapping relationship is represented by the optimized first fitting polynomial.

5. The method according to claim 4, characterized in that, The optimization of the first fitting polynomial using all the feature data corresponding to that feature and all the air conditioning temperature data includes: Initialize the parameters in the first fitting polynomial; Based on the initial first fitting polynomial, the corresponding air conditioning temperature estimate is determined using each of the feature data corresponding to that feature. Determine the mean square error between the estimated air conditioning temperature and the corresponding air conditioning temperature data in the historical data group; In response to the mean square error being greater than or equal to a preset mean square error threshold, the initialized parameters are optimized using a preset optimization algorithm based on the mean square error until the mean square error is less than the mean square error threshold, thereby obtaining the optimized first fitting polynomial.

6. The method according to claim 5, characterized in that, After determining the mean square error between the estimated air conditioning temperature and the corresponding air conditioning temperature data in the historical data set, the method further includes: In response to the mean square error being less than the mean square error threshold, the coverage of the air conditioner temperature estimate on the air conditioner temperature data is determined based on the numerical relationship between the air conditioner temperature estimate and the air conditioner temperature data. In response to the coverage rate being less than or equal to a preset coverage threshold, the parameter is optimized using the optimization algorithm based on the coverage rate until the coverage rate is greater than the coverage threshold; In response to the coverage rate being greater than the coverage rate threshold, the optimized first fitting polynomial is obtained.

7. The method according to claim 6, characterized in that, The feature mapping relationship between fusing all the features and the air conditioning temperature is used to obtain the conditional mapping relationship corresponding to this category, including: Weights are assigned to the first fitting polynomial between each of the air conditioning temperatures and the features; According to the set weights, the first fitting polynomials corresponding to each of the features are weighted to obtain the second fitting polynomial corresponding to the category. The second fitting polynomial is used as a conditional mapping relationship between air conditioning temperature and this category.

8. The method according to claim 1 or 7, characterized in that, The step of using the conditional mapping relationship to control the temperature of the air conditioner includes: Using the aforementioned conditional mapping relationship, the value of the air conditioning temperature is determined; The air conditioner is temperature controlled according to the specified temperature value.

9. An air conditioning temperature control device, comprising: The module consists of a preprocessing module, a feature mapping module, and a condition mapping module. The preprocessing module is configured to acquire historical data sets related to air conditioning temperature control; and divide all the historical data sets into multiple categories using multiple preset conditions. Each historical data set in each category includes feature data corresponding to multiple preset features and air conditioning temperature data corresponding to the air conditioning temperature. The feature mapping relationship construction module is configured to, for each feature in each category, construct a feature mapping relationship between the feature and the air conditioning temperature using the corresponding feature data and the corresponding air conditioning temperature data; wherein, a first fitting polynomial is constructed to describe the rate of change between each feature and the corresponding air conditioning temperature; the weights of all the first fitting polynomials are determined; and the influence of the feature on the air conditioning temperature is described by the rate of change. The condition mapping relationship construction module is configured to, for each category, fuse all the feature mapping relationships between the features and the air conditioner temperature to obtain a condition mapping relationship corresponding to the category, so as to use the condition mapping relationship to control the temperature of the air conditioner; wherein, a calibration compensation value is added to the weighted summation among all the first fitting polynomials to obtain a second fitting polynomial; the second fitting polynomial is used to describe the condition mapping relationship.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable by the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 8.

11. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions for causing the computer to perform the method according to any one of claims 1 to 8.

12. A vehicle, characterized in that, An air conditioner temperature control device as claimed in claim 9 or an electronic device as claimed in claim 10.

Images