GB2592215A

GB2592215A - Method of controlling air conditioner (AC) setting in a vehicle, and system thereof

Info

Publication number: GB2592215A
Application number: GB2002282.8A
Authority: GB
Inventors: Zahng Jiong; Smiroldo Rigel; Li Lichi
Original assignee: Daimler AG
Current assignee: Mercedes Benz Group AG
Priority date: 2020-02-19
Filing date: 2020-02-19
Publication date: 2021-08-25
Also published as: GB202002282D0

Abstract

Air conditioner settings in a vehicle are controlled by an electronic control unit (ECU). The ECU receives information comprising at least one of environmental data (e.g. wind speed, ambient temperature, humidity, snow, road topography, road signs) and vehicle data (e.g. open/close status of a window, throttle details, seating position). The ECU uses a first artificial intelligence model to determine an environment feature vector and provides the vector and a historical user preference (e.g. manual selection of an air conditioner flow speed and temperature) to a second artificial intelligence model to determine one or more values that are used to control the air conditioner settings. Ideally the first AI model is trained using information from a plurality of vehicles and the second AI model is trained using the environment feature vector and historical user preference.

Description

F ORM 2 THE PATENTS ACT, 1970 (39 of 1970) The patent Rule, 2003

COMPLETE SPECIFICATION

(See section 10 and rule 13)

TITLE OF THE INVENTION

METHOD OF CONTROLLING AIR CONDITIONER (AC) SETTINGS IN A VEHICLE, AND SYSTEM THEREOF Name and address of the applicant: a) Name: Daimler AG b) Nationality: Germany c) Address: 70372, Stutt2art, Germany.

[00011 PREAMBLE TO THE DESCRIPTION:

[0002] The following specification particularly describes the invention and the manner in which it is to be performed:

[0003] DESCRIPTION OF THE INVENTION:

[0004] Technical field

[0005] The present disclosure relates to air conditioning in automobiles. More particularly, but not specifically, the present disclosure relates to a method of automatically controlling air conditioner settings in automobiles.

1() [0006] Background of the disclosure

[0007] Generally, modern automobiles (referred to as vehicle herein) are equipped with climate control and air conditioning systems. The climate control and air conditioning systems allow the temperature of an interior of the vehicle to be accurately controlled. Occupants in the vehicle may provide an input to set the required temperature, and the climate control and air conditioning systems automatically adjusts a speed of a fan and an amount of cold/hot air introduced into the vehicle. For example, the user upon setting a temperature of 18 degree Celsius, the climate control and air conditioning system increases the amount of cold air flow and the speed of the air flow into the vehicle. Further, the user may set the temperature in the vehicle to a predefined value using one or more applications/ user interface associated with the vehicle. The climate control and air conditioning systems maintain the vehicle interior at the predefined value of the temperature.

[0008] EP1418476B1 discloses an adaptive control system for controlling an output of the air conditioning system in a vehicle. The air conditioning system is controlled based on the user preferences learnt by a neural network and a sensor data. However, the conventional art described is limited to controlling the output of the air conditioning system to a predeteimined control pattern or a base pattern learnt by the neural network. Further, the adaptive control system fails to provide an optimal air conditioning in a new vehicle due to a lack of predetermined base pattern.

[0009] The present disclosure is directed to overcome one or more limitations stated above or any other limitations related to this disclosure.

[0010] The information disclosed in this background of the disclosure section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.

[0011] SUMMARY OF THE DISCLOSURE

[0012] In an embodiment, the present. disclosure relates to a method of controlling Air Conditioner (AC) settings in a vehicle, the method includes the steps of: receiving information including at least one of an environment data and a vehicle data, determining an environment feature vector using a first Artificial Intelligence (AT) model, where the information is provided as an input to the first Al model. Furthermore, the method includes providing the environment feature vector and a historical user preference as inputs to a second Al model. Finally, the method includes determining one or more values of the AC based on an output generated by the second Al model, where the one or more values are used to control the AC settings.

[0013] The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.

[0014] BRIEF DESCRIPTION OF DRAWINGS

[0015] The novel features and characteristic of the current disclosure are set forth in the appended claims. The disclosure itself, however, as well as a preferred mode of use, further objectives and advantages thereof, will best be understood by reference to the following detailed description of an illustrative embodiment when read in conjunction with the accompanying figures. One or more embodiments are now described, by way of example only, with reference to the accompanying figures wherein like reference numerals represent like elements and in which: [0016] Figure 1 shows an exemplary environment for controlling Air Conditioner (AC) settings in a vehicle, in accordance with some embodiments of the present disclosure; [0017] Figure 2 shows an exemplary flow chart illustrating method steps for controlling Air Conditioner (AC) settings in a vehicle, in accordance with some

embodiments of the present disclosure;

[0018] Figure 3 shows an exemplary architecture of first Artificial Intelligence (AI) model for generation of an environment feature vector, in accordance with

some embodiments of the present disclosure; and

[0019] Figure 4 shows an exemplary determination of one or more values for controlling the Air Conditioner (AC) setting, in accordance with some embodiments of the present disclosure.

[0020] It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer readable medium and executed by a computer or processor, whether or not such computer or processor is explicitly shown.

[0021] DETAILED DESCRIPTION

[0022] In the present document, the word "exemplary" is used herein to mean 30 "serving as an example, instance, or illustration." Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

[0023] While die disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and will be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the scope of the disclosure.

[0024] The terms co mpri ses", "includes", "co mpri si ng", "i ncludi ng", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus proceeded by "comprises... a", "including.., a" does not, without more constraints, preclude the existence of other elements or additional elements in the system or apparatus.

[9925] Embodiments of the present disclosure relate to a method for controlling Air Conditioner (AC) settings in a vehicle. An Electronic Control Unit (ECU) of the vehicle receives information including environment data and vehicle data from one of one or more sensors or a database associated with the vehicle. The ECU, based on the received information, determines an environment feature vector indicating one or more parameters affecting an optimal AC setting in the vehicle. Further, the ECU determines one or more values used to control the AC settings using the environment feature vector and historical user preference.

[0026] Figure 1 is indicative of an exemplary environment for controlling Air Conditioner (AC) settings in a vehicle (101). The vehicle (101) may he an autonomous vehicle or a manually driven vehicle or a semi-autonomous vehicle navigating along a road (102). The vehicle (101) includes one or more sensors (106) to capture information including at least one of the vehicle data and the environment data. The one or more sensors (106) includes at least one of a Radio Detection and Ranging (RADAR) sensor, an ultrasonic sensor, an imaging sensor, an accelerometer, a temperature sensor, a humidity sensor, a rain sensor, and the like. For example, the vehicle data may include at least one of number of passengers in the vehicle, seating position of the passengers in the vehicle, status of a sunroof, type of sunshade applied on windows of the vehicle and the like. Further, for example, the environment data may include at least one of wind speed, temperature, humidity, snow, weather forecast, road topography, road signs, and the like. The vehicle (101) further includes an Electronic Control Unit (ECU) (105) for receiving the information captured by the one or more sensors (106). In an embodiment, the environment data may be received in real time from a database (107) associated with the vehicle (101). The database (107) is communicatively coupled to the vehicle (101) via a communication network (not shown in the Figure) including at least one of a wired or a wireless interface.

[0027] In an embodiment, the vehicle (101) includes a user interface (104) to control or select Air Conditioner (AC) settings. The user (103) may manually select or control the AC settings using the user interface (104). For example, the AC settings may include at least one of a temperature control, amount of air flow via the AC vent (108), amount of coolness/hotness of the air flow, direction of air flow and the like. Further, the user (103) may select a smart mode (109) option provided in the user interface (104) for automatic control of the AC settings in the vehicle (101). Upon the user (103) selecting the smart mode (109) option, the ECU (105) determines an environment feature vector using a first Artificial Intelligence (Al) model. For example, the environment feature vector (308) generated by the first Al model is shown below: 21, 85, 03, 10.45, 12, 2019] where values in the environment feature vector (308) may correspond to temperature outside the vehicle (101) in degree Celsius, humidity outside the vehicle (101) in percentage, a winter season, time in 24-hour format, month, and year respectively. The first AT model generates the environment feature vector as an output using the information received from at least one of, the one or more sensors (106) and the database (107), associated with the vehicle (101). For example, the first Al model may be a deep learning model including one or more batch normalization layers, one or more dense hidden layers, one or more pooling layers and the like.

[0028] Further, the ECU (105) provides the environment feature vector and historical user preference as inputs to a second Al model. For example, the second Al model may include at least one of a regression model, a deep learning model and the like. The historical user preference includes one or more AC settings manually selected or adapted by the user (103) at plurality of previous instances. For example, the historical user preference may include a manual selection of medium air flow and a temperature of 22 degree Celsius and the like. The ECU (105) determines the one or more values to control the AC settings based on an output generated by the second Al model. The second Al model combines environment conditions and the historical user preference to Luaive at an optimal AC settings for the user (103). For example, when the temperature outside the vehicle (101) is -2 degree Celsius with snow precipitation and if the historical user preference is 22 degree Celsius, the second AT model may generate the output including the temperature value of 25 degree Celsius and a low fan speed due to cool temperature outside the vehicle (101). As the temperature inside the vehicle (101) increases the temperature value may be decreased gradually from 25 degree to 22 degrees. The ECU (105) automatically selects or adapts the one or more values of the AC settings and provides the user (103) in the vehicle (101) with the optimal climate.

[0029] Figure 2 shows an exemplary flow chart illustrating method steps for controlling Air Conditioner (AC) settings in a vehicle (101), in accordance with some embodiments of the present disclosure.

[0030] As illustrated in Figure 2, the method 200 may comprise of one or more steps for controlling AC settings in the vehicle (101), in accordance with some embodiments of the present disclosure. The method 200 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions, which perform particular functions or implement particular abstract data types.

[0031] The order in which the method 200 is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method. Additionally, individual blocks may he deleted from the methods without departing from the scope of the suhject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof.

[0032] As shown in Figure 2, at the step 201, the ECU (105) receives the information including at least one of the environment data and the vehicle data. captured by at least one of the one or more sensors (106) and/or the database (107) associated with the vehicle (101). Further, the environment data includes at least one of weather details outside the vehicle, road conditions, road signs. For example, the environment data includes at least one of the wind speed, the temperature outside die vehicle (101), die humidity outside the vehicle (101), weather conditions (for example, amount o I rain, sun brightness, snow), road topography (for example, steepness of the road (102), curvature of the road (102) and the like), and the like The vehicle data may further includes at least one of window details (for example, status of the window including open or close), throttle details (for example, a pattern of application of the throttle by the driver), and a seating position.

[0033] In an embodiment, the one or more sensors (106) may include at least one of an imaging sensor, a temperature sensor, an ultrasonic sensor, an accelerometer, a radar a Light Detection and Ranging (LiDAR), a humidity sensor, a weight sensor, a Global Positioning System (GPS) and the like. The ECU (105) receives the vehicle data using the one or more sensors (106) associated with the vehicle (101). For example, the vehicle data includes at least one of the number of passengers in die vehicle (101). seating position of the passengers in the vehicle (101), status of a sun roof, type of sun shade applied on windows of the vehicle (101), a rolling state of the windows of the vehicle (101), seat massager mode, location information (for example, street name, city, state, country and the like), date and time, temperature inside the vehicle (101), humidity inside the vehicle (101), direction of the air flow from the AC vents (108) and the like.

[0034] In an embodiment, the database (107) associated with the vehicle (107) may store the real-time environment data using the one or more applications including a weather application, vehicle traffic application and the like. The ECU (105) receives the environment data from the database (107) using the one or more sensors (106) associated with the vehicle (101).

[0035] At the step 202, the ECU (105) determines the environment feature vector using the first Artificial Intelligence (Al) model, where the information is provided as an input to the first Al model. The environment feature vector is determined based on one or more parameters associated with the first Al model, where the one or more parameters are generated based on a training of the first Al model using the information from a plurality of vehicles.

[0036] In an embodiment, the first Al model is trained on a remote server by providing the information from the plurality of vehicles as an input and the AC settings selected by the user (103) as the expected output. The plurally of vehicles send the information and the AC settings to the remote server for training the first Al model. In another embodiment, the plurality of vehicles may also provide information regarding the second Al model trained in the vehicle to the remote server. The plurality of vehicles is connected to the remote server via a communication network using at least one of a wired or a wireless interface. Further, the ECU (105) receives the one or more parameters associated with the first Al model periodically (for example, every 24 hours) from the remote server. The ECU (105) implements the first Al model and determines the environment feature vector from the information using the one or parameters received from the remote server. The remote server trains the first AT model with the information from the plurality of vehicles by modifying the one or more parameters associated with the first Al model. The first Al model learns an association or a mapping between the input (i.e. information from the plurality of vehicles) and AC settings selected or adapted by the user (103) or passengers. For example, the first Al model may learn an association that due to high temperature at a particular geographical location, the users or passengers select a lower temperature of 20 degree Celsius throughout the year. Further, the first AT model encodes the information into lower dimension environment feature vector. For example, the information including environment data and the vehicle data may include one or more redundant details and one or more non-relevant details, and the first Al model removes the one or more redundant details and die one or more non-relevant details from the information (302) to generate the environment feature vector (308).

[90371 hi an embodiment, the one or more parameters associated with the first Al model may include one or more weights of the first Al model. As shown in Figure 3, architecture of the first Al model (301) includes a deep learning model with two batch normalization layers (303 and 306) and two dense hidden layers (304 and 305). The person skilled in the art may appreciate the use of different architectures of the deep learning model and the architecture shown in the Figure 3 should not be considered as a limitation for determining the environment feature vector (308).

The batch normalization layers (303 and 306) compute a mean and a variance of the one or more inputs provided to the batch normalization layers (303 and 306). Further, the one or more inputs to the batch normalization layers (303 and 306) are normalized by subtracting the mean with each of the one or more inputs and dividing by the standard deviation. Furthermore, the normalized one or more inputs of the batch normalization layers (303 and 306) are scaled and shifted by randomly initialized parameters (7, 13) to generate the one or more outputs of the batch normalization layers (303 and 306). The dense hidden layers (304 and 305) connect each input to each output via the one or more parameters (for example one or more weights) followed by a non-linear activation function. The dense hidden layers (304 and 305) are trained using a supervised learning model, for example a back-propagation model and the like. As shown in Figure 3, the information (302) except the temperature (307) inside and outside the vehicle (101) is provided as input to the batch normalization layer -1 (303) and die output of the batch normalization layer -1 (303) is passed throne' the two dense layers (304 and 305). The output of the dense hidden layer -2 (305) is concatenated with the temperature (307) measured inside and outside the vehicle (101) and provided as input to the batch normalization layer -2 (306). The output of the batch normalization layer -2 (306) is the environment feature vector (308) generated by the first Al model (301) using the information (302) as the input. For example, the environment feature vector (308) generated by the first AT model (301) is shown below: 21, 85, 03, 10.45, 12, 2019] where values in the environment feature vector (308) may correspond to temperature outside the vehicle (101) in degree Celsius, humidity outside the vehicle (101) in percentage, a winter season, time in 24 hour format, month, and year respectively.

[0038] Referring back to Figure 2, at the step 203, the ECU (105) provides the environment feature vector (308) and a historical user preference as inputs to the second Al model. In an embodiment, the historical user preference is stored in the ECU of the vehicle (101).

[0039] In an embodiment, the environment feature vector (308) and the historical user preference (402) are concatenated and provided as input to the second Al model (401) as shown in Figure 4. For example, the second Al model (401) may include a regression model, a deep learning model and the like. The historical user preference (402) includes one or more AC settings manually selected or adapted by the user (103) at previous instances in time. For example, the AC settings manually selected or adapted by the user (103) may include at least one of a temperature control, amount of air flow via the AC vent (108), amount of coolness/hotness of the air flow, direction of air flow, amount window rolling, adjusting the seating position, opening/closing of the sun roof and the like.

[0040] Referring back to Figure 2, at the step 203, the ECU (105) determines the one or more values (403) of the AC based on the output generated by the second AT model (401), where the one or more values (403) are used to control the AC settings.

The second Al model (401) is trained using the environment feature vector (308) and the historical user preference (402) as shown in Figure 4. In an embodiment, the trained second AT model (401) is periodically provided to the remote server for training the first Al model (301).

[0041] In an embodiment, upon, the user (103) selection of the smart mode (109) option, the second AT model (401) learns to predict the optimal AC settings by correlating the environment feature vector (308) and the historical user preference (402). The second Al model (401) generates one or more values (403) as outputs indicative of the optimal AC settings of the user (103) or the passengers in the vehicle (101). The ECU (105) automatically adjusts or controls the AC settings based on the one or more values (403) generated by the second AT model (401). For example, the one or more values (403) of the AC may be given below: [21, high, close, mode -1] Where the one or more values (403) may correspond to the temperature of the AC inside the vehicle (101), amount of air flow of the AC, status of the sunroof of the vehicle (101), seat massager setting of the user (103) or passengers respectively.

[0042] In an embodiment, the ECU (105) may determine the one or more values (403) of the AC for each user (103) or passenger in the vehicle (101). Further, the ECU (105) automatically controls the AC settings for each user (103) or passenger in the vehicle (101). For example. the ECU (105) may set a temperature of 23 degree Celsius with high air flow to the passenger -1 and a temperature of 21 degree Celsius with low air flow and a seat massager to mode -2 for the passenger -2 and the like.

[0043] For example, consider the vehicle (101) navigating for first time at a geographical location -1 having -2 degree Celsius temperature outside the vehicle (101) and a snow precipitation. Based on the historical user preference (402), the passenger -1 generally prefers a temperature of 21 degree Celsius and passenger - 2 generally prefers a temperature of 24 degree Celsius. The first Al model (301) in the ECU (105) generates the environment feature vector (308) using the information (302). Further, based on output of the second Al model (401), the ECU (105) automatically controls the AC settings to a temperature of 23 degree Celsius for the passenger -1 and 26 degree Celsius with low air flow from the AC vent (108) for the passenger -2. Further, the temperature for the passenger -1 is gradually decreased from 23 degree Celsius to 21 degree Celsius and the temperature for the passenger -2 is gradually decreased from 26 degree Celsius to 24 degree Celsius. The environment feature vector (308) generated by the first Al model (301) has learnt the average temperature set by the user (103) or passengers at the geographical location -1 is higher than 23 degree Celsius due to cold weather conditions at the geographical location -1. Therefore, the environment feature vector (308) helps the second Al model (401) to set a higher temperature greater than the historical user preference (402) for the passenger -1 and passenger -2.

[90441 The method of controlling the AC settings in a vehicle (101) provides an optimal and comfortable climate to the user (103) or passengers in the vehicle (101).

The ECU (105) automatically controls the AC settings based on the weather conditions of the environment outside the vehicle (101) and the historical user preference (402) to provide better in-vehicle comfort to user (103) or passengers. The first Al model (301) trained in the remote server helps the vehicle (101) to provide optimal AC settings to the user (103) or passengers when the vehicle (101) navigates at new geographical locations for the first time.

[0045] The described operations may be implemented as a method, system or article of manufacture using standard programming and/or engineering models to produce software, firmware, hardware, or any combination thereof The described operations may be implemented as code maintained in a "non-transitory computer readable medium", where a processor may read and execute the code from the computer readable medium. The processor is at least one of a microprocessor and a processor capable of processing and executing the queries. A non-transitory computer readable medium may comprise media such as magnetic storage medium (e.g., hard disk drives, floppy disks, tape, etc.), optical storage (CD-ROMs, DVDs, optical disks, etc.), volatile and non-volatile memory devices (e.g., EEPROMs, ROMs, PROMs, RAMs, DRAMs, SRAMs, Flash Memory, fimaware, programmable logic, etc.), etc. Further, non-transitory computer-readable media comprise all computer-readable media except for a transitory. The code implementing the described operations may further be implemented in hardware logic (e.g., an integrated circuit chip, Programmable Gate Array (PGA), Application Specific integrated Circuit (AS1C), etc.).

[0046] Still further, the code implementing the described operations may be implemented in "transmission signals", where transmission signals may propagate through space or through a transmission media, such as an optical fiber, copper wire, etc. The transmission signals in which the code or logic is encoded may further comprise a wireless signal, satellite transmission, radio waves, infrared signals, Bluetooth, etc. The transmission signals in which the code or logic is encoded is capable of being transmitted by a transmitting station and received by a receiving station, where the code or logic encoded in the transmission signal may be decoded and stored in hardware or a non-transitory computer readable medium at the receiving and transmitting stations or devices. An "article of manufacture" comprises non-transitory computer readable medium, hardware logic, and/or transmission signals in which code may be implemented. A device in which the code implementing the described embodiments of operations is encoded may comprise a computer readable medium or hardware logic. Of course, those skilled in the art will recognize that many modifications may be made to this configuration without departing from the scope of the invention, and that the article of manufacture may comprise suitable information bearing medium known in the art.

[0047] The terms "an embodiment", "embodiment", "embodiments", "the 15 embodiment", "the embodiments", "one or more embodiments", "some embodiments", and "one embodiment" mean "one or more (but not all) embodiments of the invention(s)" unless expressly specified otherwise.

[0048] The terms "including", "comprising", "having" and variations thereof mean "including but not limited to", unless expressly specified otherwise.

[00491 The enumerated listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise.

[0050] The terms "a", "an' and "the" mean "one or more", unless expressly specified otherwise. A description of an embodiment with several components in communication with each other does not imply that all such components are required. On the contrary a variety of optional components are described to illustrate the wide variety of possible embodiments of the invention.

[0051] When a single device or article is described herein, it will be readily apparent that more than one device/article (whether or not they cooperate) may be used in place of a single device/article. Similarly, where more than one device or article is described herein (whether or not they cooperate), it will be readily apparent that a single device/article may be used in place of the more than one device or article or a different number of devices/articles may be used instead of the shown number of devices or programs. The functionality and/or the features of a device may be alternatively embodied by one or more other devices which are not explicitly described as having such functionality/features. Thus, other embodiments of the invention need not include the device itself.

[0052] The illustrated operations of Figure 2 show certain events occurring in a certain order. In alternative embodiments, certain operations may be performed in a different order, modified or removed. Moreover, steps may be added to the above described logic and still conform to the described embodiments. Further, operations described herein may occur sequentially or certain operations may be processed in parallel. Yet further, operations may be performed by a single processing unit or by distributed processing units.

[0053] Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected In delineate or circumscribe the inventive subject matter. It is therefore intended that the scope of the invention be limited not by this detailed description, but. rather by any claims that issue on an application based here on. Accordingly, the disclosure of the embodiments of the invention is intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims.

[0054] While various aspects and embodiments have been disclosed herein, other aspects and embodiments will be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope being indicated by the following claims.

REFERRAL NUMERALS:

Reference number Description

101 Vehicle 102 Road 103 User 104 User Interface Electronic Control Unit (ECU) 106 Sensors 107 Database 108 Air Condition vent 109 Smart Mode 301 First Al model 302 Information 303 and 306 Batch Normalization layers 304 and 305 Dense hidden layers 307 Temperature inside and outside the vehicle 308 Environment feature vector 401 Second Al model 402 Historical user preference 403 One or more values

Claims

[0055] Claims: We claim: 1. A method of controlling Air Conditioner (AC) settings in a vehicle (101), the method comprising: receiving, by an Electronic Control Unit (ECU) (105), information (302) comprising at least one of an environment data and a vehicle data; determining, by the ECU (105), an environment feature vector (308) using a first Artificial Intelligence (AI) model (301), wherein the information (302) is provided as input to the first Al model (301); providing, by the ECU (105), the environment feature vector (308) and historical user preference (402) as inputs to a second Al model (401); and determining, by the ECU (105), one or more values (403) of the AC based on an output generated by the second AT model (401), wherein the one or more values (403) are used to control the AC settings.
2. The method as claimed in claim 1, wherein the information (302) is received from at least one of one or more sensors (106) or a database (107) associated with the vehicle (101).
3. The method as claimed in claim 1, wherein the environment data comprises at least one of weather details outside the vehicle (101), weather details inside the vehicle (101), road conditions, and road signs, and the vehicle data comprises at least one of window details, throttle details, and a seating position.
4. The method as claimed in claim 1, wherein the environment feature vector (308) is determined based on one or more parameters associated with the first Al model (301), wherein the one or more parameters are generated based on a training of the first Al model (301) using the information (302) from a plurality of vehicles.
5. The method as claimed in claim 1, wherein the second Al model (401) is trained using the environment feature vector (308) and the historical user preference (402).
6. 6. An Electronic Control unit (ECU) (105), for controlling an Air Conditioner (AC) settings in a vehicle (101), the ECU (105) comprising: a processor; and a memory, communicatively coupled to the processor, storing processor executable instructions, which, on execution causes the processor to: receive information (302) comprising at least one of environment data and vehicle data; determine an environment feature vector (308) using a first Artificial Intelligence (AI) model (301), wherein the information (302) is provided as input to the first AT model (301); provide the environment feature vector (308) and historical user preference (402) as inputs to a second Al model (401); and determine one or more values (403) of the AC based on an output generated by the second Al model (401), wherein the one or more values (403) are used to control the AC settings.
7. The ECU (105) as claimed in 6, wherein the processor is configured to receive the information (302) from at least one of one or more sensors (106) and a database (107) associated with the vehicle (101).
8. The ECU (105) as claimed in 6, wherein the processor is configured determine the environment feature vector (308) based on one or more parameters associated with the first AT model (301), wherein the one or more parameters are generated based on a training of the first Al model (301) using the information (302) from a plurality of vehicles.
9. The ECU (105) as claimed in 6, wherein the processor is configured to train the second Al model (401) using the environment feature vector (308) and a historical user preference (402).
10. A method of controlling an Air Conditioner (AC) settings in a vehicle (101), the method comprising: receiving, by an Electronic Control Unit (ECU) (105), information (302) comprising at least one of environment data and vehicle data, wherein the information (302) is received from at least one of one or more sensors (106) and a database (107) associated with the vehicle (101); determining, by the ECU (105), an environment feature vector (308) using a first Artificial Intelligence (Al) model (301), wherein the information (302) is provided as input to the first AT model (301), wherein the environment feature vector (308) is determined based on one or more parameters associated with the first AT model (301), wherein the one or more parameters are generated based on a training of the first Al model (301) using the information (302) from a plurality of vehicles; providing, by the ECU (105). the environment feature vector (308) and historical user preference (402) as inputs to a second AT model (401), wherein the second AT model (401) is trained in the ECU (105) using the environment feature vector (308) and the historical user preference (402); and determining, by the ECU (105), one or more values (403) of the AC based on an output generated by the second AT model (401), wherein the one or more values (403) are used to control the AC settings.