Method and system for learning temperature adjustment habits of automobile air-conditioning users

Abstract

The present invention discloses a method and system for learning the temperature adjustment habits of automobile air conditioner users, including the following steps: S1. Establishing a historical temperature data table S2. Each time the user changes the set temperature in the automatic mode, recording the average values ​​of all historical indoor temperature values ​​and outdoor temperature values ​​set at the temperature value, and setting the temperature count value plus 1; S3. Constructing a loss function J according to the data in the historical temperature data table; S4. When the user turns on the automatic mode of the air conditioner next time, calculating the J of the set temperature points in the historical temperature data table one by one, and selecting the set temperature point with the smallest J as the user's preferred temperature point for target temperature setting. The present invention aims to improve the intelligence of the automatic air conditioner system. The present invention memorizes the user's historical operation records in the automatic mode, so that the temperature is automatically set to the user's preferred temperature point when the user turns on the automatic mode of the air conditioner next time.

Description

Technical Field

[0001] The invention relates to the field of automatic temperature control of automobile air conditioners, and in particular to a method and system for learning the temperature adjustment habits of automobile air conditioner users. Background Art

[0002] As a traditional standard product for automobiles, automobile air conditioning products are widely used in various models. The task of automobile air conditioning is to make the temperature in the car comfortable and the air fresh, which is also the high comfort requirement of passengers for the air in the car. Due to the difference in temperature between winter and summer, passengers hope that the temperature in the car will quickly reach a comfortable temperature after getting in the car.

[0003] In the Chinese invention patent with application number CN201310667545.3, a method for automatically controlling automobile air conditioning is proposed, wherein a controller is used to automatically control the automobile air conditioning system, a sunlight sensor is set at a place where the automobile is easily exposed to sunlight, an evaporator temperature sensor is set at the outlet of the evaporator of the automobile, an outdoor temperature sensor is set at the front of the outside of the automobile, an indoor temperature sensor is set in the interior of the automobile, and a water temperature sensor is installed in the heating device of the automobile. However, as a traditional automobile standard accessory, the above-mentioned automobile air conditioning product only realizes basic automatic control and does not realize intelligence. After pressing the AUTO button, the user still needs to manually adjust the set temperature fixed on the air conditioning panel to the set temperature of his or her preference, which is poor in terms of user experience. Summary of the invention

[0004] In view of the above problems, the present invention provides a method and system for learning the temperature adjustment habits of automobile air-conditioning users, which are used to solve the above problems.

[0005] The present invention is achieved through the following technical solutions:

[0006] The method for learning the temperature adjustment habits of automobile air-conditioning users includes the following steps:

[0007] S1. Establish a historical temperature data table, which is composed of a*b two-dimensional data, wherein the first dimension a of the two-dimensional data represents a set temperature points, and the second dimension b of the two-dimensional data represents the average indoor temperature, the average outdoor temperature and the count value of the number of times set to this temperature;

[0008] S2. Each time the user changes the set temperature in automatic mode, the average indoor temperature value and the average outdoor temperature value of all historical values ​​set at the temperature value are recorded, and the temperature count value is set plus 1;

[0009] S3. Construct loss function J based on the historical temperature data table data;

[0010] S4. When the user turns on the air conditioner automatic mode next time, the J of the set temperature points in the historical temperature data table is calculated one by one, and the set temperature point with the smallest J is selected as the user's preferred temperature point for target temperature setting.

[0011] Furthermore, the step S3 is specifically: according to the naive Bayesian machine learning method, the probability of the set temperature point is calculated, and the calculation formula is as follows:

[0012]

[0013] Among them, μ1 represents the mean indoor temperature at the set temperature point, σ1 represents the indoor temperature variance at the set temperature point, μ2 represents the mean outdoor temperature at the set temperature point, σ2 represents the outdoor temperature variance at the set temperature point, Represents the prior probability of the set temperature point.

[0014] Furthermore, the step S303 is specifically: according to the naive Bayesian machine learning method, the probability of the set temperature point is calculated, and the calculation formula is as follows:

[0015] J=(T in -T in_rec ) 2 +(T out -T out_rec ) 2 -K rec N rec Minimum;

[0016] Among them, T in Indicates the current indoor temperature, T out represents the front outdoor temperature, T in_rec Indicates the average value of the historical indoor temperature when the user sets the temperature point, T out_rec Indicates the average value of the historical outdoor temperature when the user sets the temperature point, N rec Indicates the number of times the temperature is set to this point, K rec Indicates the weight of the number of records.

[0017] Furthermore, the step S303 is specifically: according to the naive Bayesian machine learning method, the probability of the set temperature point is calculated, and the calculation formula is as follows:

[0018] J=(T in -T in_rec ) 2 +(T out -T out_rec ) 2 -K rec N rec ;

[0019] Among them, Tin Indicates the current indoor temperature, T out represents the front outdoor temperature, T in _ rec Indicates the average value of the historical indoor temperature when the user sets the temperature point, T out_rec Indicates the average value of the historical outdoor temperature when the user sets the temperature point, N rec Indicates the number of times the temperature is set to this point, K rec Indicates the weight of the number of records.

[0020] Furthermore, step S4 is specifically as follows: when the user turns off the power and then turns on the automatic mode, the current indoor and outdoor temperatures are matched with the indoor and outdoor temperatures in the historical records, and the one with the smallest variance with the historical records is found, and then the set temperature corresponding to the smallest variance is used as the user preferred temperature. When the variance values ​​are the same, the temperature point with the most settings is selected as the user preferred temperature.

[0021] The car air conditioning user temperature adjustment habit learning system includes:

[0022] A historical temperature data table module is used to establish a historical temperature data table, wherein the historical temperature data table is composed of a*b two-dimensional data, the first dimension a of the two-dimensional data represents a set temperature points, and the second dimension b of the two-dimensional data represents the indoor temperature average, the outdoor temperature average and the count value of the number of times set to this temperature;

[0023] The data extraction module is used to record the average indoor temperature value and the average outdoor temperature value of all historical values ​​set at the temperature value each time the user changes the set temperature in the automatic mode, and set the temperature count value to increase by 1;

[0024] Function construction module, used to construct loss function J according to the data in the historical temperature data table;

[0025] The preferred temperature point setting module is used to calculate the J of the set temperature points in the historical temperature data table one by one when the user turns on the air conditioning automatic mode next time, and select the set temperature point with the smallest J as the user's preferred temperature point for target temperature setting.

[0026] Furthermore, the function construction module specifically calculates the probability of the set temperature point according to the naive Bayes machine learning method, and the calculation formula is as follows:

[0027]

[0028] Among them, μ1 represents the mean indoor temperature at the set temperature point, σ1 represents the indoor temperature variance at the set temperature point, μ2 represents the mean outdoor temperature at the set temperature point, σ2 represents the outdoor temperature variance at the set temperature point, Represents the prior probability of the set temperature point.

[0029] Furthermore, the function building module is specifically: according to the naive Bayesian machine learning method, the probability of the set temperature point is calculated, and the calculation formula is as follows:

[0030] J=(T in -T in_rec ) 2 +(T out -T out_rec ) 2 -K rec N rec Minimum;

[0031] Among them, T in Indicates the current indoor temperature, T out represents the front outdoor temperature, T in_rec Indicates the average value of the historical indoor temperature when the user sets the temperature point, T out_rec Indicates the average value of the historical outdoor temperature when the user sets the temperature point, N rec Indicates the number of times the temperature is set to this point, K rec Indicates the weight of the number of records.

[0032] Furthermore, the function building module is specifically: according to the naive Bayesian machine learning method, the probability of the set temperature point is calculated, and the calculation formula is as follows:

[0033] J=(T in -T in_rec ) 2 +(T out -T out_rec ) 2 -K rec N rec ;

[0034] Among them, T in Indicates the current indoor temperature, T out represents the front outdoor temperature, T in_rec Indicates the average value of the historical indoor temperature when the user sets the temperature point, T out_rec Indicates the average value of the historical outdoor temperature when the user sets the temperature point, N rec Indicates the number of times the temperature is set to this point, K rec Indicates the weight of the number of records.

[0035] Furthermore, the preferred temperature point setting module specifically matches the current indoor and outdoor temperatures with the indoor and outdoor temperatures in the historical records when the user turns off the computer and then turns on the automatic mode, finds the one with the smallest variance with the historical records, and then uses the set temperature corresponding to the smallest variance as the user preferred temperature. When the variance values ​​are the same, the temperature point with the most settings is selected as the user preferred temperature.

[0036] Beneficial effects of the present invention: The present invention aims to improve the intelligence level of the automatic air-conditioning system. The present invention memorizes the user's historical operation records in the automatic mode, so that the temperature is automatically set to the user's preferred temperature point when the user turns on the automatic mode of the air-conditioning next time. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0038] Figure 1 A method flow chart of a method for learning the temperature adjustment habits of automobile air-conditioning users proposed in an embodiment of the present invention;

[0039] Figure 2 A schematic diagram of the structure of a terminal device for a method for learning the temperature adjustment habits of a vehicle air-conditioning user proposed in an embodiment of the present invention;

[0040] Figure 3 A schematic diagram of the structure of a computer-readable storage medium for learning the temperature setting habits of a vehicle air-conditioning user proposed in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0042] Example 1

[0043] like Figure 1 This embodiment proposes a method for learning the temperature adjustment habits of automobile air-conditioning users, comprising the following steps:

[0044] S1. Establish a historical temperature data table, which is composed of a*b two-dimensional data, wherein the first dimension a of the two-dimensional data represents a set temperature points, and the second dimension b of the two-dimensional data represents the average indoor temperature, the average outdoor temperature and the count value of the number of times set to this temperature;

[0045] S2. Each time the user changes the set temperature in automatic mode, the average indoor temperature value and the average outdoor temperature value of all historical values ​​set at the temperature value are recorded, and the temperature count value is set plus 1;

[0046] S3. Construct loss function J based on the historical temperature data table data;

[0047] S4. When the user turns on the air conditioner automatic mode next time, the J of the set temperature points in the historical temperature data table is calculated one by one, and the set temperature point with the smallest J is selected as the user's preferred temperature point for target temperature setting.

[0048] Furthermore, the step S3 is specifically: according to the naive Bayesian machine learning method, the probability of the set temperature point is calculated, and the calculation formula is as follows:

[0049]

[0050] Among them, μ1 represents the mean indoor temperature at the set temperature point, σ1 represents the indoor temperature variance at the set temperature point, μ2 represents the mean outdoor temperature at the set temperature point, σ2 represents the outdoor temperature variance at the set temperature point, Represents the prior probability of the set temperature point.

[0051] Furthermore, the step S303 is specifically: according to the naive Bayesian machine learning method, the probability of the set temperature point is calculated, and the calculation formula is as follows:

[0052] J=(T in -T in_rec ) 2 +(T out -T out_rec ) 2 -K rec N rec Minimum;

[0053] Among them, T in Indicates the current indoor temperature, T out represents the front outdoor temperature, T in_rec Indicates the average value of the historical indoor temperature when the user sets the temperature point, T out_rec Indicates the average value of the historical outdoor temperature when the user sets the temperature point, N rec Indicates the number of times the temperature is set to this point, K rec Indicates the weight of the number of records.

[0054] Furthermore, the step S303 is specifically: according to the naive Bayesian machine learning method, the probability of the set temperature point is calculated, and the calculation formula is as follows:

[0055] J=(Tin -T in_rec ) 2 +(T out -T out_rec ) 2 -K rec N rec ;

[0056] Among them, T in Indicates the current indoor temperature, T out represents the front outdoor temperature, T in_rec Indicates the average value of the historical indoor temperature when the user sets the temperature point, T out_rec Indicates the average value of the historical outdoor temperature when the user sets the temperature point, N rec Indicates the number of times the temperature is set to this point, K rec Indicates the weight of the number of records.

[0057] Furthermore, step S4 is specifically as follows: when the user turns off the power and then turns on the automatic mode, the current indoor and outdoor temperatures are matched with the indoor and outdoor temperatures in the historical records, and the one with the smallest variance with the historical records is found, and then the set temperature corresponding to the smallest variance is used as the user preferred temperature. When the variance values ​​are the same, the temperature point with the most settings is selected as the user preferred temperature.

[0058] The specific implementation principle process of this embodiment is as follows:

[0059] This embodiment uses a statistical learning method to set the set temperature after the user presses the AUTO button. The algorithm mainly consists of two parts: training and decision-making.

[0060] (1) Training process: Create a historical temperature data table consisting of 14*3 two-dimensional data. The first dimension 14 represents the set temperature of 17℃~30℃, and the second dimension 3 represents the average indoor temperature, the average outdoor temperature, and the count value of the number of times this temperature is set. Every time the user changes the set temperature in automatic mode, the average indoor temperature value and the average outdoor temperature value of all historical values ​​set at this temperature are recorded, and the temperature count value is set to increase by 1.

[0061] (2) Decision-making process: constructing loss function:

[0062] J=(T in -T in_rec ) 2 +(T out -T out_rec ) 2 -K rec N rec ;

[0063] Among them, T inis the current indoor temperature, T out is the current outdoor temperature, T in_rec The average value of the historical indoor temperature at the temperature point set by the user, T out_rec The average value of the historical outdoor temperature at the temperature point set by the user, N rec is the number of times the temperature is set to this point, K rec is the weight of the number of records.

[0064] When the user turns on the air conditioning automatic mode next time, the J of the 14 possible set temperature points in the historical temperature data table is calculated one by one, and the set temperature point with the smallest J is selected as the user's preferred temperature point for target temperature setting.

[0065] (3) Principle of the method: The user temperature adjustment habit learning method borrows the idea of ​​statistical learning theory. Assuming that when the user sets a certain temperature, the indoor and outdoor temperature values ​​satisfy the Gaussian distribution, the parameter μ of the Gaussian distribution is estimated through statistical data. Due to the existence of the law of large numbers, when the number of user settings increases under the condition of satisfying the Gaussian distribution, it will converge to the mean μ according to probability. Therefore, during training, the mean of the Gaussian distribution of each set temperature point can be found by finding the historical average value. According to the naive Bayes machine learning method, the probability of setting at this temperature point is:

[0066]

[0067] Among them, μ1 is the mean indoor temperature at the set temperature point, σ1 is the indoor temperature variance at the set temperature point, μ2 is the mean outdoor temperature at the set temperature point, σ2 is the outdoor temperature variance at the set temperature point, The prior probability for this set temperature point.

[0068] The above original formula involves the calculation of the decimal power of the natural base, which requires the use of the math library, and the probability of the 14 set temperature points from 17℃ to 30℃ is calculated one by one, and then the point with the largest probability is output. This is a relatively large amount of calculation for the microcontroller. Considering that the variance of the temperature setting points of the same driver will not differ too much, and for each set temperature point N total are the same, we will total Simplifying it, we can get the equivalent formula to the original equation: J = (T in -μ1) 2 +(T out -μ2) 2 -4*ln(N rec ) is the smallest. To further reduce the amount of computation, based on the idea of ​​Taylor expansion and retaining the first-order term, K rec N rec Instead of 4*ln(Nrec ).

[0069] Each time the user turns off the product and then turns on the automatic mode again, the product will match the current indoor and outdoor temperatures with the indoor and outdoor temperatures in the historical records, find the one with the smallest variance with the historical records, and then use the set temperature corresponding to the smallest variance as the user's preferred temperature. If the variance values ​​are the same, the temperature point with the most settings will be selected as the user's preferred temperature.

[0070] The method can improve the intelligence of the automatic air-conditioning controller, and automatically set the user's preferred set temperature according to the user's historical usage when the AUTO button is pressed.

[0071] Example 2

[0072] On the basis of Example 1, this embodiment further proposes a system for learning the temperature adjustment habits of automobile air conditioner users, including: a historical temperature data table module, used to establish a historical temperature data table, wherein the historical temperature data table is composed of a*b two-dimensional data, the first dimension a of the two-dimensional data represents a set temperature points, and the second dimension b of the two-dimensional data represents the indoor temperature average, the outdoor temperature average and the count value of the number of times set to this temperature;

[0073] The data extraction module is used to record the average indoor temperature value and the average outdoor temperature value of all historical values ​​set at the temperature value each time the user changes the set temperature in the automatic mode, and set the temperature count value to increase by 1;

[0074] Function construction module, used to construct loss function J according to the data in the historical temperature data table;

[0075] The preferred temperature point setting module is used to calculate the J of the set temperature points in the historical temperature data table one by one when the user turns on the air conditioning automatic mode next time, and select the set temperature point with the smallest J as the user's preferred temperature point for target temperature setting.

[0076] Furthermore, the function building module specifically includes:

[0077] Gaussian distribution parameter calculation unit: when the user sets a certain temperature point, the indoor and outdoor temperature values ​​satisfy the Gaussian distribution, and the parameter μ of the Gaussian distribution is estimated through statistical data;

[0078] Mean extraction unit: extracts the mean of the Gaussian distribution of each set temperature point by calculating the historical average value;

[0079] The probability calculation unit calculates the probability of the set temperature point according to the naive Bayes machine learning method.

[0080] Furthermore, the probability calculation unit is specifically calculated by the formula:

[0081]

[0082] The probability is calculated, where μ1 represents the mean indoor temperature at the set temperature point, σ1 represents the indoor temperature variance at the set temperature point, μ2 represents the mean outdoor temperature at the set temperature point, and σ2 represents the outdoor temperature variance at the set temperature point. Represents the prior probability of the set temperature point.

[0083] Furthermore, the function building module also includes a calculation simplification module, which specifically simplifies P and calculates the probability of the set temperature point by substituting σ1, σ2 and N total Simplifying, we get:

[0084] J=(T in -T in_rec ) 2 +(T out -T out_rec ) 2 -K rec N rec ;

[0085] Further, by Taylor expansion and retaining the first-order term, through K rec N rec Instead of 4*ln(N rec ),get:

[0086] J=(T in -T in_rec ) 2 +(T out -T out_rec ) 2 -K rec N rec ;

[0087] Among them, T in Indicates the current indoor temperature, T out represents the front outdoor temperature, T in_rec Indicates the average value of the historical indoor temperature when the user sets the temperature point, T out_rec Indicates the average value of the historical outdoor temperature when the user sets the temperature point, N rec Indicates the number of times the temperature is set to this point, K rec Indicates the weight of the number of records.

[0088] Furthermore, the preferred temperature point setting module specifically matches the current indoor and outdoor temperatures with the indoor and outdoor temperatures in the historical records when the user turns off the computer and then turns on the automatic mode, finds the one with the smallest variance with the historical records, and then uses the set temperature corresponding to the smallest variance as the user's preferred temperature. In the case of the same variance value, the temperature point with the most settings is selected as the user's preferred temperature.

[0089] Example 3

[0090] like Figure 2 Based on Example 2, this example proposes a terminal device for learning the temperature adjustment habits of automobile air-conditioning users. The terminal device 200 includes at least one memory 210, at least one processor 220, and a bus 230 connecting different platform systems.

[0091] The memory 210 may include a readable medium in the form of a volatile memory, such as a random access memory (RAM) 211 and / or a cache memory 212 , and may further include a read-only memory (ROM) 213 .

[0092] The memory 210 also stores a computer program, which can be executed by the processor 220, so that the processor 220 executes any one of the above-mentioned methods for learning the temperature adjustment habits of automobile air conditioner users in the embodiments of the present application, and its specific implementation is consistent with the implementation method and the technical effect achieved in the embodiments of the above-mentioned method, and some contents are not repeated here. The memory 210 can also include a program / utility 214 having a group (at least one) of program modules 215, such program modules include but are not limited to: an operating system, one or more application programs, other program modules and program data, each of these examples or some combination may include the implementation of a network environment.

[0093] Accordingly, the processor 220 may execute the above-mentioned computer programs, and may execute the program / utility 214 .

[0094] The bus 230 may be a bus representing one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0095] The terminal device 200 may also communicate with one or more external devices 240 such as keyboards, pointing devices, Bluetooth devices, etc., and may also communicate with one or more devices that can interact with the terminal device 200, and / or communicate with any device (such as a router, a modem, etc.) that enables the terminal device 200 to communicate with one or more other computing devices. Such communication may be performed through an input / output (I / O) interface 250. In addition, the terminal device 200 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and / or a public network, such as the Internet) through a network adapter 260. The network adapter 260 may communicate with other modules of the terminal device 200 through a bus 230. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the terminal device 200, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, etc.

[0096] Example 4

[0097] Based on Example 1, this example proposes a computer-readable storage medium for learning the temperature adjustment habits of automobile air conditioner users, wherein the computer-readable storage medium stores instructions, and when the instructions are executed by a processor, any of the above-mentioned methods for learning the temperature adjustment habits of automobile air conditioner users is implemented. The specific implementation method is consistent with the implementation method and the technical effect achieved in the above-mentioned method embodiment, and some contents are not repeated here.

[0098] Figure 3 The program product 300 provided in this embodiment for implementing the above method is shown, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product 300 of the present invention is not limited to this. In this document, the readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it. The program product 300 can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0099] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, wherein readable program codes are carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium may also be any readable medium other than the readable storage medium, which may send, propagate, or transmit a program used by or in combination with an instruction execution system, an apparatus, or a device. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above. The program code for performing the operation of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code may be executed entirely on a user computing device, partially on a user device, as an independent software package, partially on a user computing device, partially on a remote computing device, or entirely on a remote computing device or server. Where a remote computing device is involved, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0100] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for learning the temperature adjustment habits of automobile air-conditioning users, characterized in that: The following steps are involved: S1. Establish a historical temperature data table, which is composed of a*b two-dimensional data, wherein the first dimension a of the two-dimensional data represents a set temperature points, and the second dimension b of the two-dimensional data represents the average indoor temperature, the average outdoor temperature and the count value of the number of times set to this temperature; S2. Each time the user changes the set temperature in automatic mode, the average indoor temperature value and the average outdoor temperature value of all historical values ​​set at the temperature value are recorded, and the temperature count value is set plus 1; S3. Calculate the probability of the set temperature point based on the historical temperature data table data ; S4. When the user turns on the air conditioner automatic mode next time, the set temperature points in the historical temperature data table are calculated one by one. , select The maximum set temperature point is used as the user's preferred temperature point for target temperature setting; The step S3 specifically comprises: calculating the probability of the set temperature point according to the naive Bayes machine learning method, and the calculation formula is as follows: ； in, Indicates the current indoor temperature. Indicates the current outdoor temperature. Indicates the average value of the historical indoor temperature when the user sets the temperature point. Indicates the average value of the historical outdoor temperature when the user sets the temperature point. Indicates the number of times this temperature point is set. Indicates the weight of the number of records.

2. The method for learning the temperature adjustment habits of automobile air conditioner users according to claim 1, characterized in that: The step S4 is specifically as follows: when the user turns off the computer and then turns on the automatic mode, the current indoor and outdoor temperatures are matched with the indoor and outdoor temperatures in the historical records, and the temperature with the smallest variance with the historical records is found. Then, the set temperature corresponding to the smallest variance is used as the user preferred temperature. When the variance values ​​are the same, the temperature point with the most settings is selected as the user preferred temperature.

3. Automobile air-conditioning user temperature adjustment habit learning system, characterized by: include: A historical temperature data table module is used to establish a historical temperature data table, wherein the historical temperature data table is composed of a*b two-dimensional data, the first dimension a of the two-dimensional data represents a set temperature points, and the second dimension b of the two-dimensional data represents the indoor temperature average, the outdoor temperature average and the count value of the number of times set to this temperature; The data extraction module is used to record the average indoor temperature value and the average outdoor temperature value of all historical values ​​set at the temperature value each time the user changes the set temperature in the automatic mode, and set the temperature count value to increase by 1; Function building module, used to calculate the probability of the set temperature point based on the historical temperature data table data ; The preferred temperature point setting module is used to calculate the preferred temperature points in the historical temperature data table one by one when the user turns on the air conditioning automatic mode next time. , select The maximum set temperature point is used as the user's preferred temperature point for target temperature setting; The function building module is specifically: according to the naive Bayesian machine learning method, the probability of the set temperature point is calculated, and the calculation formula is as follows: ； in, Indicates the current indoor temperature. Indicates the current outdoor temperature. Indicates the average value of the historical indoor temperature when the user sets the temperature point. Indicates the average value of the historical outdoor temperature when the user sets the temperature point. Indicates the number of times this temperature point is set. Indicates the weight of the number of records.

4. The automobile air-conditioning user temperature adjustment habit learning system according to claim 3 is characterized in that: The preferred temperature point setting module specifically matches the current indoor and outdoor temperatures with the indoor and outdoor temperatures in the historical records when the user turns off the computer and then turns on the automatic mode, finds the one with the smallest variance with the historical records, and then uses the set temperature corresponding to the smallest variance as the user's preferred temperature. When the variance values ​​are the same, the temperature point with the most settings is selected as the user's preferred temperature.

Images