A vehicle-mounted air conditioner defogging control method and system

Abstract

The application provides a vehicle-mounted air conditioner defogging control method and system, comprising predicting the ignition time and ignition probability value of a user based on a pre-trained ARMA model, obtaining the Gaussian distribution of the historical vehicle use time of the user through a probability density function based on the vehicle ignition time data, obtaining the ignition time probability model of the user within several time periods, correcting the prediction error of the ignition time and probability value based on the ignition time probability model, obtaining the ignition time correction value and probability correction value, and if the probability correction value is greater than a first threshold value and the current time is within a second preset time period before the ignition time correction value, a control instruction is sent to the vehicle-mounted system to control the vehicle-mounted air conditioner to start the defogging function. The application fully utilizes big data and time sequence prediction algorithms to provide intelligent defogging function for users, can realize starting intelligent defogging for users in advance, reduces the waiting time of users for the vehicle machine, and improves the user experience and driving safety.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle air conditioners, in particular to a vehicle air conditioner defogging control method and system. BACKGROUND

[0002] With the rapid development of intelligent networked vehicles, more and more vehicle functions can be turned on in advance when the vehicle is not started. The most typical one is that the user can remotely communicate with the vehicle TBOX through the mobile phone, and the TBOX controls the vehicle air conditioner to be turned on in advance, so that in some special scenarios, such as hot summer, the user does not need to start the vehicle and manually turn on the air conditioner, and then spend a few minutes waiting for the temperature in the vehicle to be suitable, thereby improving the vehicle experience to a certain extent.

[0003] Similarly, in terms of air conditioner defogging function of the vehicle, the user can turn on the air conditioner defogging function in advance through the mobile phone, or directly turn on the air conditioner defogging function at the vehicle end after getting on the vehicle. However, both of these two ways are user's active operation behavior, which is still not intelligent enough.

[0004] If the user's vehicle time can be predicted in advance, and whether defogging operation is needed is judged according to the monitored weather data, so as to actively turn on the air conditioner defogging function for the user a few minutes before the user uses the vehicle, it will save the user a certain defogging time and improve the driving safety, thereby greatly improving the user's vehicle experience.

[0005] Therefore, the present application is committed to providing an intelligent defogging method to make up for the deficiencies of the prior art in the air conditioner defogging of intelligent networked vehicles. SUMMARY

[0006] In order to solve the deficiencies in the prior art, the present application provides a vehicle air conditioner defogging control method and system, which obtains a user ignition vehicle time with higher confidence by comprehensively analyzing the statistical analysis and time series prediction analysis results of user historical vehicle data, analyzes the vehicle interior and exterior environment data close to the ignition vehicle time and the user's historical defogging operation habits, and quantitatively calculates the vehicle air conditioner defogging recommendation value, so as to provide intelligent defogging operation recommendation for the user and improve the user's vehicle experience.

[0007] To achieve the above purpose, the present application provides a vehicle air conditioner defogging control method, which comprises:

[0008] Based on a pre-trained ARMA model, the ignition time T0 of the user u and the probability value m(u) of starting the vehicle at the ignition time T0 are predicted, wherein the pre-trained ARMA model is trained based on the vehicle ignition time data in the historical vehicle data of the user u in the first preset time period;

[0009] Based on the vehicle ignition time data, a Gaussian distribution of the user's historical vehicle usage time is statistically analyzed using a probability density function to obtain an ignition time probability model for user u in several time periods. The ignition time probability model is used to characterize the probability distribution of user u igniting the vehicle in several time periods.

[0010] Based on the ignition time probability model, the prediction error correction is performed on the ignition time T0 and the probability value m(u) to obtain the ignition time correction value T1 and the probability correction value m'(u);

[0011] If the probability correction value m'(u) is greater than the first threshold and the current time is within the second preset time period before the ignition time correction value T1, a control instruction is sent to the vehicle system to control the vehicle air conditioner to start the defogger function.

[0012] Preferably, if the probability correction value m'(u) is greater than a first threshold and the current moment is within a second preset time period before the ignition timing correction value T1, sending a control instruction to the vehicle system to control the vehicle air conditioner to turn on the defogger function specifically includes:

[0013] If the current time is within a second preset time period before the ignition timing correction value T1, obtaining environmental data inside and outside the vehicle, including the environmental data used to calculate the temperature difference or humidity difference between the inside and outside of the vehicle, and the temperature difference or humidity difference is used to determine the environmental impact factor p(t) when user u turns on the air conditioning defogger operation;

[0014] If the user's recommended value F(u) for turning on the air conditioning defogger operation is greater than the second threshold, a control instruction is sent to the vehicle system to control the vehicle air conditioning to turn on the defogger function. The calculation formula of the recommended value F(u) is:

[0015] F(u)=m'(u)+p(t).

[0016] Preferably, the method further comprises:

[0017] The user's historical vehicle usage data also includes the vehicle's interior temperature, exterior temperature, interior humidity, exterior humidity, and air conditioning defogger activation information;

[0018] Based on the user's historical vehicle usage data, including the vehicle interior temperature, vehicle exterior temperature, vehicle interior humidity, vehicle exterior humidity, and air conditioning defogger activation information data, a probability density function is used to calculate the Gaussian distribution between the user's activation of the air conditioning defogger operation and the temperature or humidity difference between the inside and outside of the vehicle, thereby obtaining a user's historical defogger operation probability model. The historical defogger operation probability model is used to characterize the probability distribution of the user activating the air conditioning defogger under different temperature or humidity differences between the inside and outside of the vehicle.

[0019] After obtaining the environmental data inside and outside the vehicle, the probability value r(u) of the user turning on the air conditioning defogger is determined based on the environmental data and the historical defogger operation probability model, and the recommended value F(u) is calculated using the following formula:

[0020] F(u)=m'(u)+p(t)+r(u).

[0021] Preferably, based on the ignition time probability model, the prediction error correction is performed on the ignition time T0 and probability value m(u) of the user on the next day predicted by the ARMA model to obtain the ignition time correction value T1 and probability correction value m'(u) of the user on the next day, specifically including:

[0022] According to the ignition time T0, an ignition time probability model with the closest ignition time is selected, and a first Gaussian quantile interval of the ignition time probability model is determined;

[0023] If the ignition time T0 is earlier than the first Gaussian quantile interval, the ignition time correction value T1 is equal to the ignition time T0, and the probability correction value m'(u)=a*m(u);

[0024] If the ignition time T0 is in the first Gaussian quantile interval, the ignition time correction value T1 is equal to the starting time point of the first Gaussian quantile interval, and the second probability value m'(u)=m(u);

[0025] If the ignition time T0 is later than the first Gaussian quantile interval, the ignition time correction value T1 is equal to the end time point of the first Gaussian quantile interval, and the second probability value m'(u)=a*m(u);

[0026] The above parameter a represents the correction factor of the ignition time probability model to the ARMA model prediction.

[0027] Preferably, the ARMA model is constructed by training and fitting the ARMA model based on the vehicle ignition time data, specifically comprising:

[0028] Preprocessing the vehicle ignition time data, wherein the preprocessing specifically includes processing missing values ​​and outliers, data cleaning, attribute construction, and periodicity analysis;

[0029] Perform stationarity test and white noise test on the pre-processed vehicle ignition time data;

[0030] Construct an ARMA model, determine the autoregressive term order p and the moving average term order q of the ARMA model based on the autocorrelation function image and the partial autocorrelation function image, and use the preprocessed vehicle ignition time data to train and fit the ARMA model;

[0031] During the ARMA model training process, the mean square error between the ARMA model's prediction results and the vehicle's actual ignition time is calculated. If the mean square error is greater than the set threshold, the vehicle's actual ignition time is used as an indicator, and the weight of the vehicle's ignition time is higher when the ignition time is closer to the current time, and the weight of the vehicle's ignition time is lower when the ignition time is farther from the current time. By adjusting the corresponding weights, the data is input again to train and fit the ARMA model. If the mean square error is less than the set threshold, the training of the ARMA model is completed.

[0032] To achieve the above objectives, the present application also provides a vehicle air conditioning defogging control system, the control system comprising:

[0033] a time series prediction module, configured to predict the ignition time T0 of user u and a probability m(u) of igniting the vehicle at the ignition time T0 based on a pre-trained ARMA model, wherein the pre-trained ARMA model is trained based on vehicle ignition time data in historical vehicle usage data of user u during a first preset time period;

[0034] A historical ignition data statistics module is used to calculate the Gaussian distribution of the user's historical vehicle usage time based on the vehicle ignition time data using a probability density function to obtain an ignition time probability model for user u within several time periods. The ignition time probability model is used to characterize the probability distribution of user u igniting the vehicle within several time periods.

[0035] an ignition time correction module, configured to perform prediction error correction on the ignition time T0 and the probability value m(u) based on the ignition time probability model to obtain an ignition time correction value T1 and a probability correction value m'(u);

[0036] The first defogger control module is configured to send a control instruction to the vehicle system to control the vehicle air conditioner to activate the defogger function if the probability correction value m'(u) is greater than the first threshold and the current moment is within a second preset time period before the ignition timing correction value T1.

[0037] Preferably, the control system further comprises:

[0038] An environmental impact factor module, configured to obtain environmental data inside and outside the vehicle if the current moment is within a second preset time period before the ignition timing correction value T1, wherein the environmental data includes information for calculating a temperature difference or humidity difference between the inside and outside of the vehicle, and the temperature difference or humidity difference is used to determine an environmental impact factor p(t) for user u to activate the air conditioning defogger operation;

[0039] The second defogger control module is configured to send a control instruction to the vehicle system to control the vehicle air conditioner to turn on the defogger function if the user's recommended value F(u) for turning on the air conditioner defogger operation is greater than a second threshold. The recommended value F(u) is calculated as follows:

[0040] F(u)=m'(u)+p(t).

[0041] Preferably, the user's historical vehicle usage data also includes vehicle interior temperature, vehicle exterior temperature, vehicle interior humidity, vehicle exterior humidity, and air conditioning defogger activation information;

[0042] The control system further comprises:

[0043] A historical defogger statistics module is configured to calculate, based on the user's historical vehicle usage data, the interior temperature, exterior temperature, interior humidity, exterior humidity, and air conditioning defogger activation information data, and to obtain a user's historical defogger operation probability model by calculating the Gaussian distribution between the user's activation of the air conditioning defogger operation and the temperature or humidity difference between the interior and exterior of the vehicle. The historical defogger operation probability model is configured to characterize the probability distribution of the user activating the air conditioning defogger under different temperature or humidity differences between the interior and exterior of the vehicle.

[0044] The third demisting control module is used to obtain environmental data from both inside and outside the vehicle, determine the probability value r(u) of the user turning on the air conditioning demisting function based on the environmental data and the historical demisting operation probability model, and calculate the recommended value F(u) using the following formula:

[0045] F(u)=m'(u)+p(t)+r(u).

[0046] Compared with the prior art, the present invention has the following advantages:

[0047] Based on the pre-trained ARMA model, the user's ignition time and its probability value are predicted, and then the user's historical car ignition time data is statistically analyzed based on the probability density function to calculate the Gaussian distribution of the user's car use time, and the user's typical ignition time probability model is obtained. The prediction results of the ARMA model are error-corrected based on the ignition time probability model to obtain more accurate user ignition time and its probability value. Then, based on the indoor and outdoor environment data detected before the prediction result, the recommended value F(u) of the user's defogger requirement is finally calculated. According to the size of the recommended value F(u), it is judged whether it is necessary to control the air conditioner to turn on the defogger function in advance. This application makes full use of big data and time series prediction algorithms to provide users with intelligent defogger functions, which can realize the early activation of intelligent defogger for users, reduce the waiting time of users' car computers, and improve user experience and driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0049] Figure 1 It is a flow chart of a vehicle air conditioning defogger control method according to an embodiment of the present application.

[0050] Figure 2 It is a flow chart of a vehicle air conditioning defogger control method shown in yet another embodiment of the present application.

[0051] Figure 3 It is a flow chart of a vehicle air conditioning defogger control method according to another embodiment of the present application.

[0052] Figure 4 It is a schematic block diagram of a vehicle air-conditioning demisting control system according to an embodiment of the present application.

[0053] Figure 5 It is a schematic block diagram of a vehicle air-conditioning demisting control system according to another embodiment of the present application.

[0054] Figure 6 It is a schematic block diagram of a vehicle air-conditioning demisting control system according to another embodiment of the present application.

[0055] The above-mentioned drawings have shown clear embodiments of the present invention, which will be described in more detail later. These drawings and textual descriptions are not intended to limit the scope of the present invention in any way, but to illustrate the concept of the present invention to computer technicians in this field through specific embodiments. DETAILED DESCRIPTION

[0056] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0057] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0058] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner.In the following description, many specific details are provided so as to provide a full understanding of the embodiments of the present application. However, it will be appreciated by those skilled in the art that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, devices, steps etc. can be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0059] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices. The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily need to be executed in the order described. For example, some operations / steps may be further decomposed, while others may be combined or partially combined, so the actual execution order may vary depending on the actual situation.

[0060] Please see the attached Figure 1 , which shows a vehicle air conditioning defogging control method provided by an embodiment of the present application, the control method specifically includes the following steps:

[0061] Step S110: predicting the ignition time T0 of user u and the probability m(u) of igniting the vehicle at the ignition time T0 based on a pre-trained ARMA model, wherein the pre-trained ARMA model is trained based on the vehicle ignition time data in the historical vehicle usage data of user u during a first preset time period;

[0062] ARMA model, full name Autoregressive moving average model (ARMA), is a combination of autoregressive model (AR) and moving average model (MA). It is a classic time series forecasting and analysis method. The ARMA model expression can be:

[0063]

[0064] Among them, the parameter y t represents the predicted time point, the parameters p and q represent the order of autoregressive term and moving average term respectively, r i and θ i Represent the model parameters of the autoregressive model and the moving average model, respectively. The parameter x t-i represents the lag value of the previous i periods, ∈ t-i represents the disturbance term of the previous i periods, and u represents the sum of the mean of the p-period lagged value and the mean of the q-period disturbance value.

[0065] Optionally, before training and fitting the ARMA model, the vehicle ignition time data needs to be preprocessed. Generally, the preprocessing may include processing missing values ​​and outliers in the vehicle ignition time data, data cleaning, and periodicity analysis.

[0066] Specifically, the processing of missing values ​​and abnormal values ​​of vehicle ignition time data can include filling in data for individual dates where data is missing, that is, setting the vehicle ignition time data corresponding to these dates to 0; and setting the vehicle ignition time data corresponding to individual dates where data is abnormal, also setting the vehicle ignition time data corresponding to these dates to 0;

[0067] At the same time, the above data cleaning of vehicle ignition time data, that is, filtering out invalid data in historical usage data, retaining key ignition time data; and the periodic analysis can be based on a week as a cycle to analyze whether there is a periodic change in vehicle ignition time;

[0068] Preferably, in order to improve the prediction accuracy of the ARMA model, the pre-processed vehicle ignition time data can also be subjected to a stationarity test and a white noise test, wherein the stationarity test can adopt a time series stationarity test such as the ADF test method, that is, it can be required that the probability value corresponding to the statistic P>0.05 passes the test, otherwise the vehicle ignition time data is not stationary, and it is necessary to perform a differential operation first and then an ADF test until the vehicle ignition time data is a stationary random time series; and the white noise test can adopt a conventional Ljung-Box test, for example, requiring the probability value corresponding to the statistic P<0.05, then it is determined that the vehicle's historical ignition time data is non-white noise data.

[0069] Optionally, before training and fitting the ARMA model, it is necessary to first determine the values ​​of the autoregressive term order p and the moving average term order q of the ARMA model. For example, a stepwise heuristic method from low order to high order can be used to determine the autoregressive term order p and the moving average term order q of the ARMA model, and measure them using the Akaike Information Criterion (AIC criterion):

[0070] AIC=2k-2ln(L)

[0071] Among them, the parameter k is the number of model parameters, and L is the likelihood function.

[0072] When selecting the best model from a set of available models, the model with the smallest AIC(p,q) and the best fitting effect is usually selected as the final model, thereby determining the order of the ARMA model.

[0073] Preferably, in the process of training and fitting the ARMA model, it is necessary to calculate the mean square error between the prediction result of the ARMA model and the actual ignition time of the vehicle. If the mean square error is greater than a set threshold, the actual ignition time of the vehicle is used as an indicator, and the weight of the ignition time of the vehicle that is closer to the current time is higher, and the weight of the ignition time of the vehicle that is farther from the current time is lower. By adjusting the corresponding weights, the data is input again to train and fit the ARMA model. If the mean square error is less than the set threshold, the training of the ARMA model is completed.

[0074] At this point, the pre-processed user historical ignition time data is imported into the ARMA model of a certain order for fitting, and the remaining parameters of the ARMA model, namely the parameter r i ,θ i and u.

[0075] In addition, in the above step S110, the above first preset time period may be a time period in days or months, which is used to reflect the user's vehicle usage data in a recent period;

[0076] As a method, the above-mentioned user's historical vehicle usage data may include the vehicle's ignition time, and the ignition time may be obtained from the bus data on the vehicle side.

[0077] Thus, for example, the ignition time data of the user in the last month may be selected for use in subsequent analysis of the probability distribution of the user igniting the vehicle in various time periods of each day.

[0078] It should be noted that the accuracy of the ARMA model's prediction results is related to the historical vehicle usage data used for training and fitting, as well as the method for determining the ARMA model order. If the ARMA model's prediction results are not corrected, the reliability of the subsequent air conditioning defogger control cannot be guaranteed.

[0079] Step S120: Based on the vehicle ignition time data, a Gaussian distribution of the user's historical vehicle usage time is calculated using a probability density function to obtain an ignition time probability model for user u within a number of time periods. The ignition time probability model is used to represent the probability distribution of user u igniting the vehicle within a number of time periods.

[0080] Specifically, the vehicle ignition time data can represent the user's vehicle usage within the first preset time period. Mathematical statistical analysis using probability density functions for user historical behavior data within a certain time period is a classic mathematical method for analyzing user behavior. The obtained probability analysis results can usually be expressed in the form of a Gaussian distribution. Specifically, the probability density function can be expressed as follows:

[0081]

[0082] In the above formula, parameters a and b can represent two random time points within the first preset time period for analyzing the probability of a user using a car, and parameter x can represent the ratio of the user's historical ignition time data at the above two random time points to all the ignition time data within the first preset time period. By calculating the above integral formula, the Gaussian distribution of the user's ignition time probability within the first preset time period can be statistically calculated using the probability density function.

[0083] Optionally, after obtaining the Gaussian distribution of the user's ignition time probability within the first preset time period, a typical ignition time probability model of the user can be further obtained based on the Gaussian analysis result. For example, the Gaussian distribution of the user's ignition time probability can be used to obtain the probability distribution of the user igniting and starting the vehicle in several time periods such as 7:00-7:30, 11:30-12:00, and 17:30-18:00 every morning, which is above 95%. Based on this result, an ignition time probability model of the user in several time periods can be formed, and the ignition time probability model is used to characterize the probability distribution of the user igniting and starting the vehicle in different time periods.

[0084] Step S130 , based on the ignition time probability model, performing prediction error correction on the ignition time T0 and the probability value m(u) to obtain an ignition time correction value T1 and a probability correction value m'(u);

[0085] As a method, considering that any time series prediction model has a certain prediction error, if the prediction error is not corrected, the behavior processing ultimately performed based on the time series prediction model will also deviate from the user's actual needs with a high probability. Therefore, this embodiment uses a combination of statistical analysis and time series prediction to improve the prediction accuracy of the user's ignition time in the future, such as the next day's car ignition time. That is, based on the statistical analysis results of historical data, the time series prediction results based on historical data are corrected. For example, the user's ignition time probability model shows that the probability of the user igniting the car between 7:00 and 7:30 in the morning is in the 95% Gaussian quantile interval, while the result predicted by the ARMA time series prediction model is that the user will ignite the car at 6:30 the next morning with an 80% probability. At this time, considering that the statistical analysis results and the ARMA time series prediction results have discrepancies in the ignition start time, in order to improve the prediction accuracy of the ARMA model, this embodiment corrects the ARMA time series prediction results based on the statistical analysis results. Specifically, the prediction error correction of the ARMA time series prediction results can be performed as follows:

[0086] First, based on the ignition time T0 obtained by the ARMA model prediction, an ignition time probability model with the closest ignition time is selected, and the first Gaussian quantile interval of the above ignition time probability model is determined; for example, when the ARMA model prediction result is that the user's ignition time T0 on the next day is 6:30, 7:10 or 8:00, then based on the ignition time probability models of the user in several time periods obtained in step S140, an ignition time probability model with the closest ignition time is selected, for example, the ignition time probability model of the time period of 7:00 to 7:30 can be selected, and the first Gaussian quantile interval of the above ignition time probability model is determined. For example, the first Gaussian quantile interval can specifically be the 95% Gaussian quantile interval of the Gaussian distribution of the user behavior characteristics, which means that through the statistical analysis of the probability density function, it can be known that the probability confidence level of the user igniting and starting the car in the time period of 7:00 to 7:30 is 95%;

[0087] If the ignition time T0 is earlier than the first Gaussian quantile interval, the ignition time correction value T1 is equal to the ignition time T0, and the probability correction value m'(u)=a*m(u);

[0088] If the ignition time T0 is in the first Gaussian quantile interval, the ignition time correction value T1 is equal to the starting time point of the first Gaussian quantile interval, and the second probability value m'(u)=m(u).

[0089] If the ignition time T0 is later than the first Gaussian quantile interval, the ignition time correction value T1 is equal to the ending time point of the first Gaussian quantile interval, and the second probability value m'(u)=a*m(u).

[0090] The parameter a represents the correction weight value of the ignition time probability model to the prediction of the ARMA model.

[0091] Through the above processing, the prediction error correction can be performed on the prediction result of the ARMA model, including the ignition time of the user and the corresponding ignition probability value, so as to more accurately predict the ignition time behavior of the user on the next day.

[0092] In step S140, if the probability correction value m'(u) is greater than the first threshold value and the current time is within the second preset time period before the ignition time correction value T1, a control instruction is sent to the vehicle-mounted system to control the vehicle-mounted air conditioner to start the defogging function.

[0093] Optionally, after obtaining the user ignition time T1 with higher accuracy and the probability correction value m'(u) thereof, and the probability correction value m'(u) is greater than the first threshold value, a control instruction can be sent to the vehicle-mounted system to control the vehicle-mounted air conditioner to start the defogging function when the current time is within the second preset time period before the ignition time correction value T1.

[0094] The first threshold value can be a value defined by the user according to historical experience, for example, the first threshold value can be set to 0.8, that is, only when the probability value of the final user starting the vehicle at T1 is greater than 0.8, the user needs to be provided with the function of starting the air conditioner defogging function in advance.

[0095] Specifically, the second preset time period can be a shorter time period in minutes, for example, after the user vehicle ignition time is determined to be 7:00 in step S130, the user can start the air conditioner defogging function at a time period close to 7:00, such as 6:50.

[0096] Optionally, referring to FIG. 2, the second preset time period can be a time period before the ignition time correction value T1. Figure 2 When performing the above step S140, it can further include:

[0097] S1401, if the current time is within the second preset time period before the ignition time correction value T1, the environment data on both sides of the vehicle is obtained, the environment data includes the temperature difference or humidity difference between the inside and outside of the vehicle, and the temperature difference or humidity difference is used to determine the environmental influence factor p(t) of the user u starting the air conditioner defogging operation.

[0098] S1402: If the user's recommended value F(u) for turning on the air conditioner defogger function is greater than a second threshold, a control instruction is sent to the vehicle system to control the vehicle air conditioner to turn on the defogger function. The formula for calculating the recommended value F(u) is:

[0099] F(u)=m'(u)+p(t).

[0100] The above steps incorporate vehicle interior and exterior environmental data into the intelligent defogger control of the vehicle air conditioner. This environmental data includes information used to calculate the temperature or humidity difference between the interior and exterior of the vehicle. Specifically, fogging of the front window glass will affect the user's normal driving only when the temperature or humidity difference between the interior and exterior of the vehicle reaches a certain level. Therefore, within a second preset time period before the ignition time correction value T1, for example, if the user's vehicle ignition time is ultimately determined to be 7:00 in step S130, the temperature difference t between the interior and exterior of the vehicle can be obtained within a time period shorter than 7:00, such as 6:50. Since the temperature difference between the interior and exterior of the vehicle is one of the direct factors affecting window fogging, the environmental impact factor p(t) of the user's defogging demand can be determined based on this temperature difference t.

[0101] For example, when the temperature difference t between the inside and outside of the vehicle exists, indicating that the windows may be fogged when the user starts the car, in which case the windows need to be defogged in advance. Therefore, the environmental impact factor p(t) can be set to A+B*t, where the parameters A and B can be manually defined constants, for example, A=0.2 and B=0.5.

[0102] Similarly, when the humidity data inside and outside the vehicle is obtained, the environmental impact factor p(t) and the recommended value F(u) can also be determined in the same or similar manner as the above technical concept, which will not be elaborated here.

[0103] When the recommended value F(u) is higher than a preset value, it indicates that the windows will be fogged when the user starts the car. At this time, a control instruction needs to be sent to the vehicle system to control the air conditioner to turn on the defogger function, so that the air conditioner defogger operation is turned on when the user uses the car, thereby better ensuring the user's driving safety.

[0104] Optionally, in the above step S140, before sending the control instruction to the vehicle system, the user can be remotely asked and reminded through software such as a mobile phone APP whether to turn on the air conditioning defogger. If so, a control instruction is sent to the vehicle system to control the air conditioning to turn on the defogger function.

[0105] In the above technical solution, the user's future ignition time and its probability value are obtained by performing ARMA model prediction on the user's historical car ignition time data, and then the user's historical car ignition time data is statistically analyzed based on the probability density function to calculate the Gaussian distribution of the user's car usage time, and the user's typical ignition time probability model is obtained. Then, the prediction result of the ARMA model is error-corrected based on the ignition time probability model, so as to obtain the user's ignition time and its probability value on the next day with higher accuracy, and then, based on the indoor and outdoor environment data detected before the prediction result, the recommended value F(u) of the user's defogger requirement is finally calculated, and whether it is necessary to control the air conditioner to turn on the defogger function in advance is judged according to the size of the recommended value F(u). This embodiment makes full use of big data and time series prediction algorithm to provide users with intelligent defogger function, which can realize the early activation of intelligent defogger for users, reduce the waiting time of users' car computer, and improve user experience and driving safety.

[0106] Preferably, the above-mentioned user's historical car usage data also includes the temperature inside the car, the temperature outside the car, the humidity inside the car, the humidity outside the car, and the air conditioning defogger start information;

[0107] See attached Figure 3 , the above step S140 may further include:

[0108] S1401', based on the user's historical vehicle usage data, including the vehicle interior temperature, vehicle exterior temperature, vehicle interior humidity, vehicle exterior humidity, and air conditioning defogger activation information, a probability density function is used to calculate the Gaussian distribution between the user's activation of the air conditioning defogger operation and the temperature or humidity difference between the inside and outside of the vehicle, thereby obtaining a probability model for the user's historical defogger operation. The historical defogger operation probability model is used to characterize the probability distribution of the user activating the air conditioning defogger under different temperature or humidity differences between the inside and outside of the vehicle.

[0109] S1402': If the current time is within a second preset time period before the ignition timing correction value T1, obtain environmental data for both the interior and exterior of the vehicle. The environmental data includes information used to calculate a temperature difference or humidity difference between the interior and exterior of the vehicle. The temperature difference or humidity difference is used to determine an environmental impact factor p(t) for user u to activate the air conditioning defogger operation.

[0110] S1403', based on the above environmental data and the historical defog operation probability model, the probability value r(u) of the user turning on the air conditioner defogger is determined, and the recommended value F(u) is calculated using the following formula:

[0111] F(u)=m'(u)+p(t)+r(u).

[0112] Specifically, the above-mentioned in-vehicle temperature, outside-vehicle temperature, in-vehicle humidity, outside-vehicle humidity, air-conditioning defogger start information, etc. can be obtained through CAN bus data or buried point data.

[0113] Similar to the idea of ​​step S120, the above steps are further based on the user's historical defog operation data, including the temperature inside and outside the car, the humidity inside and outside the car, and the air-conditioning defogger start data. By adopting the statistical analysis method of the probability density function, the Gaussian distribution between the user's historical air-conditioning defogger operation and the temperature difference or humidity difference inside and outside the car and the user's historical defogger operation probability model are obtained. The user's historical defogger operation probability model can characterize the probability of the user turning on the air-conditioning defogger under different temperature differences or humidity differences inside and outside the car, that is, characterize the user's defogger operation habits.

[0114] In this way, after obtaining the temperature difference or humidity difference between the inside and outside of the car, the probability value r(u) of the user turning on the air conditioning defogger can be determined through the above-mentioned historical defogger operation probability model. After taking this probability value r(u) into account in the calculation expression of the recommended value F(u), the final vehicle air conditioning defogger control method will be more in line with the historical behavior habits of different users, thereby providing a better user experience.

[0115] See attached Figure 4 The present application further provides a vehicle air conditioning demisting control system 500 corresponding to the above-mentioned vehicle air conditioning demisting control method. The above-mentioned control system 500 includes:

[0116] A time series prediction module 510 is configured to predict the ignition time T0 of user u and the probability m(u) of igniting the vehicle at the ignition time T0 based on a pre-trained ARMA model, wherein the pre-trained ARMA model is trained based on the vehicle ignition time data in the historical vehicle usage data of user u during a first preset time period;

[0117] The historical ignition data statistics module 520 is used to calculate the Gaussian distribution of the user's historical vehicle usage time based on the vehicle ignition time data using a probability density function to obtain an ignition time probability model for user u within a certain time period. The ignition time probability model is used to represent the probability distribution of user u igniting the vehicle within a certain time period.

[0118] The ignition time correction module 530 is used to perform prediction error correction on the ignition time T0 and the probability value m(u) based on the ignition time probability model to obtain an ignition time correction value T1 and a probability correction value m'(u);

[0119] The first defogger control module 540 is configured to send a control instruction to the vehicle system to activate the defogger function of the vehicle air conditioner if the probability correction value m'(u) is greater than the first threshold and the current time is within a second preset time period before the ignition timing correction value T1.

[0120] In an alternative embodiment, see the attached Figure 5 , the control system 500 further includes:

[0121] Environmental impact factor module 550 is configured to obtain environmental data for both the interior and exterior of the vehicle if the current time is within a second preset time period before the ignition timing correction value T1. The environmental data includes information used to calculate a temperature difference or humidity difference between the interior and exterior of the vehicle. The temperature difference or humidity difference is used to determine an environmental impact factor p(t) for user u to activate the air conditioning defogger operation.

[0122] The second defogger control module 560 is configured to send a control instruction to the vehicle system to activate the defogger function of the vehicle air conditioner if the user's recommended value F(u) for activating the air conditioner defogger operation is greater than a second threshold. The formula for calculating the recommended value F(u) is:

[0123] F(u)=m'(u)+p(t).

[0124] In a preferred embodiment, the above user's historical vehicle usage data also includes the vehicle's interior temperature, exterior temperature, interior humidity, exterior humidity, and air conditioning defogger start information; see the attached Figure 6 , the control system 500 further includes:

[0125] Historical defogger statistics module 570 is configured to calculate, based on the user's historical vehicle usage data, the interior temperature, exterior temperature, interior humidity, exterior humidity, and air conditioning defogger activation information data, using a probability density function to calculate the Gaussian distribution between the user's activation of the air conditioning defogger operation and the temperature or humidity difference between the interior and exterior of the vehicle, thereby obtaining a user's historical defogger operation probability model. The historical defogger operation probability model is used to characterize the probability distribution of the user activating the air conditioning defogger under different temperature or humidity differences between the interior and exterior of the vehicle.

[0126] The third demisting control module 580 is configured to obtain environmental data from both the interior and exterior of the vehicle, determine the probability r(u) of the user turning on the air conditioning for demisting based on the environmental data and the historical demisting operation probability model, and calculate the recommended value F(u) using the following formula:

[0127] F(u)=m'(u)+p(t)+r(u).

[0128] Optionally, before the first defogger control module 540 or the second defogger control module 560 or the third defogger control module 580 sends a control instruction, it can remotely inquire and remind the user whether to turn on the air conditioning defogger. If so, a control instruction is sent to the vehicle system to control the air conditioning to turn on the defogger function.

[0129] As another way, the first defogger control module 540 or the second defogger control module 560 or the third defogger control module 580 may perform remote inquiry and reminder via an APP or text message.

[0130] Furthermore, the present application also provides a computer-readable medium, which stores a program or instruction, and the program or instruction enables the computer to execute the steps of the vehicle air-conditioning defogger control method described above.

[0131] At the same time, the present application also provides a terminal device, which includes at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program, and when the program is executed by the processing unit, the processing unit executes the steps of the vehicle air-conditioning defogger control method described above.

[0132] It should be noted that the computer-readable medium shown in the embodiments of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0133] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. In some cases, the names of these units do not constitute limitations on the units themselves.

[0134] The computer program product of the present application can be a computer program product, which is a machine-readable medium (media) having exact sequences of instructions, program, code segments, or routines, written in any of a variety of languages. Such a machine-readable medium (media) is a tangible, non-transitory, storage medium that is non-transitory and tangible, such as a floppy diskette, a hard disk, a CD-ROM, a DVD, a memory stick, a memory card, a memory, a tape, a cassette, or the like, which is further analogous to the media that store instructions for the execution of such instructions. The machine-readable medium (media) of the computer program product can also be a transitory medium, such as an electrical, optical, acoustical or other form of propagated signals, such as carrier waves, infrared signals, digital signals, etc. Accordingly, the present application should not be limited to any particular type of computer program product, machine-readable medium (media), or transitory medium.

[0135] Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. The specification and examples given herein are not intended to be exhaustive or limiting, and other alternatives not described herein will become apparent to the skilled practitioner in the art to which the present application pertains. The present application is intended to cover any and all adaptations or variations of various embodiments of the application including those adaptations or variations that are deemed to be within the scope of the present application.

[0136] It should be understood that the present application is not limited to the precise structures herein described and illustrated and that various modifications and changes can be made without departing from the scope of the present application. The scope of the present application is limited only by the claims appended hereto.

Claims

1. A vehicle air conditioning defogging control method, characterized in that: The steps are as follows: Predicting the ignition time T0 of user u and the probability m(u) of igniting the vehicle at the ignition time T0 based on a pre-trained ARMA model, wherein the pre-trained ARMA model is trained based on vehicle ignition time data in historical vehicle usage data of user u during a first preset time period; Based on the vehicle ignition time data, a Gaussian distribution of the user's historical vehicle usage time is statistically analyzed using a probability density function to obtain an ignition time probability model for user u in several time periods. The ignition time probability model is used to characterize the probability distribution of user u igniting the vehicle in several time periods. Based on the ignition time probability model, the prediction error correction is performed on the ignition time T0 and the probability value m(u) to obtain the ignition time correction value T1 and the probability correction value m'(u); If the current time is within a second preset time period before the ignition timing correction value T1, obtaining environmental data inside and outside the vehicle, including the environmental data used to calculate the temperature difference or humidity difference between the inside and outside of the vehicle, and the temperature difference or humidity difference is used to determine the environmental impact factor p(t) when user u turns on the air conditioning defogger operation; If the user's recommended value F(u) for turning on the air conditioning defogger operation is greater than the second threshold, a control instruction is sent to the vehicle system to control the vehicle air conditioning to turn on the defogger function. The calculation formula of the recommended value F(u) is: F(u)= m'(u) +p(t).

2. The control method according to claim 1, characterized in that: The method further comprises: The user's historical vehicle usage data also includes the vehicle's interior temperature, exterior temperature, interior humidity, exterior humidity, and air conditioning defogger activation information; Based on the user's historical vehicle usage data, including the interior temperature, exterior temperature, interior humidity, exterior humidity, and air conditioning defogger activation information data, a probability density function is used to calculate the Gaussian distribution between the user's activation of the air conditioning defogger operation and the temperature or humidity difference between the interior and exterior of the vehicle, thereby obtaining a user's historical defogger operation probability model. The historical defogger operation probability model is used to characterize the probability distribution of the user activating the air conditioning defogger under different temperature or humidity differences between the interior and exterior of the vehicle. After obtaining the environmental data inside and outside the vehicle, the probability value r(u) of the user turning on the air conditioning defogger is determined based on the environmental data and the historical defogger operation probability model, and the recommended value F(u) is calculated using the following formula: F(u)= m'(u) +p(t)+ r(u).

3. The control method according to claim 1 or 2, characterized in that: The method of performing prediction error correction on the ignition time T0 and the probability value m(u) based on the ignition time probability model to obtain the ignition time correction value T1 and the probability correction value m'(u) specifically includes: According to the ignition time T0, an ignition time probability model with the closest ignition time is selected, and a first Gaussian quantile interval of the ignition time probability model is determined; If the ignition time T0 is earlier than the first Gaussian quantile interval, the ignition time correction value T1 is equal to the ignition time T0, and the probability correction value m'(u)=a*m(u); If the ignition time T0 is in the first Gaussian quantile interval, the ignition time correction value T1 is equal to the starting time point of the first Gaussian quantile interval, and the second probability value m'(u)=m(u); If the ignition time T0 is later than the first Gaussian quantile interval, the ignition time correction value T1 is equal to the end time point of the first Gaussian quantile interval, and the second probability value m'(u)=a*m(u); The above parameter a represents the correction factor of the ignition time probability model to the ARMA model prediction.

4. The control method according to claim 1 or 2, characterized in that: The training and fitting process of the pre-trained ARMA model specifically includes: Preprocessing the vehicle ignition time data, wherein the preprocessing specifically includes processing missing values ​​and outliers, data cleaning, attribute construction, and periodicity analysis; Perform stationarity test and white noise test on the pre-processed vehicle ignition time data; Construct an ARMA model, determine the autoregressive term order p and the moving average term order q of the ARMA model based on the autocorrelation function image and the partial autocorrelation function image, and use the preprocessed vehicle ignition time data to train and fit the ARMA model; During the ARMA model training process, the mean square error between the ARMA model's prediction results and the vehicle's actual ignition time is calculated. If the mean square error is greater than the set threshold, the vehicle's actual ignition time is used as an indicator, and the weight of the vehicle's ignition time is higher when the ignition time is closer to the current time, and the weight of the vehicle's ignition time is lower when the ignition time is farther from the current time. By adjusting the corresponding weights, the data is input again to train and fit the ARMA model. If the mean square error is less than the set threshold, the training of the ARMA model is completed.

5. A vehicle air conditioning defogging control system, characterized in that: The control system includes: a time series prediction module, configured to predict the ignition time T0 of user u and a probability m(u) of igniting the vehicle at the ignition time T0 based on a pre-trained ARMA model, wherein the pre-trained ARMA model is trained based on vehicle ignition time data in historical vehicle usage data of user u during a first preset time period; A historical ignition data statistics module is used to calculate the Gaussian distribution of the user's historical vehicle usage time based on the vehicle ignition time data using a probability density function to obtain an ignition time probability model for user u within several time periods. The ignition time probability model is used to characterize the probability distribution of user u igniting the vehicle within several time periods. an ignition time correction module, configured to perform prediction error correction on the ignition time T0 and the probability value m(u) based on the ignition time probability model to obtain an ignition time correction value T1 and a probability correction value m'(u); An environmental impact factor module, configured to obtain environmental data inside and outside the vehicle if the current moment is within a second preset time period before the ignition timing correction value T1, wherein the environmental data includes information for calculating a temperature difference or humidity difference between the inside and outside of the vehicle, and the temperature difference or humidity difference is used to determine an environmental impact factor p(t) for user u to activate the air conditioning defogger operation; The second defogger control module is configured to send a control instruction to the vehicle system to control the vehicle air conditioner to turn on the defogger function if the user's recommended value F(u) for turning on the air conditioner defogger operation is greater than a second threshold. The recommended value F(u) is calculated as follows: F(u)= m'(u) +p(t).

6. The control system according to claim 5, characterized in that: The user's historical vehicle usage data also includes the vehicle's interior temperature, exterior temperature, interior humidity, exterior humidity, and air conditioning defogger activation information; The control system further comprises: A historical defogger statistics module is configured to calculate, based on the user's historical vehicle usage data, the interior temperature, exterior temperature, interior humidity, exterior humidity, and air conditioning defogger activation information data, and to obtain a user's historical defogger operation probability model by calculating the Gaussian distribution between the user's activation of the air conditioning defogger operation and the temperature or humidity difference between the interior and exterior of the vehicle. The historical defogger operation probability model is configured to characterize the probability distribution of the user activating the air conditioning defogger under different temperature or humidity differences between the interior and exterior of the vehicle. The third demisting control module is used to obtain environmental data from both inside and outside the vehicle, determine the probability value r(u) of the user turning on the air conditioning demisting function based on the environmental data and the historical demisting operation probability model, and calculate the recommended value F(u) using the following formula: F(u)= m'(u) +p(t)+ r(u).

7. A computer-readable medium, characterized in that It stores a computer program that can be executed by a terminal device. When the program is run on the terminal device, the terminal device executes the steps of any one of the methods according to claims 1-4.

8. A terminal device, characterized in that: The method comprises at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program, and when the program is executed by the processing unit, the processing unit executes the steps of the method according to any one of claims 1 to 4.

Images