WO2023122678A1 - System and method for content segregation - Google Patents

Abstract

Methods and systems are provided for automatically adjusting cabin settings. In one example, a method comprises communicating with one or more mobile devices paired with a vehicle, learning, with a model, a plurality of comfort settings associated with the vehicle in the presence of one or more mobile devices and vehicle occupants, and automatically adjusting the plurality of comfort settings in response to a current set of sensed mobile devices and vehicle occupants correlating with a previous set of sensed mobile devices and vehicle occupants associated with the learned model.

Description

SYSTEM AND METHOD FOR CONTENT SEGREGATION

CROSS REFERENCE TO RELATED APPLICATIONS

[0001] The present application claims priority to U.S. Provisional Application No. 63/265,822, entitled “SYSTEM AND METHOD FOR CONTENT SEGREGATION”, and filed on December 21, 2021. The entire contents of the above-listed application are hereby incorporated by reference for all purposes.

FIELD

[0002] The disclosure relates to content segregation for personalizing vehicle settings automatically.

BACKGROUND/SUMMARY

[0003] Vehicles may include multiple adjustable comfort settings that are unrelated to driving parameters. The adjustable comfort settings may personalize a driving experience for a vehicle operator and other occupants. The adjustable comfort settings may include seat position, cabin temperature, a window position, cabin interior light settings, media source, media volume, media genre, and audio settings. The comfort settings may be adjusted by one or more of the vehicle occupants via physical controls, an interactive screen of an infotainment system, a mobile device, or the like.

[0004] Some vehicles may adjust comfort settings based on an identified vehicle operator. The vehicle operator may be identified based on a profile selection, biometrics, such as voice recognition, retinal scans, and/or fingerprints, and/or a personalized device such as a key fob or mobile device may be used. However, one issue with such systems may include that customization of the comfort settings may not account for an entire vehicle environment including all passengers, a seating arrangement of the passengers, vehicle cargo, time of day, weather, location, and/or the like.

SUMMARY

[0005] The disclosure provides support for a method including communicating with one or more mobile devices paired to a vehicle, learning, with a model, a plurality of comfort settings associated with the vehicle in the presence of the one or more mobile devices and vehicle occupants, and automatically adjusting the plurality of comfort settings in response to a current set of sensed mobile devices and vehicle occupants matching correlating with a previous set of sensed mobile devices and vehicle occupants associated with the learned model..

[0006] The disclosure further includes detecting mobile devices in communication with a communication system of the vehicle. A hybrid interface engine (HIE) may store and categorize adjustments to cabin settings. The adjustments may be modeled and learned such that subsequent conditions, identical to the previously learned conditions, may include where the HIE may signal to a controller of the vehicle to automatically adjust cabin settings without input from a vehicle operator or occupant. The HIE may store and hash settings of the vehicle based on non-identifying information of the occupants. The hash may be a unique key, and may be used to pair data and protocols to specific sets including one or more mobile devices. The specific sets may further include other data, including feedback from vehicle weight sensors and feedback from an imaging device positioned in a cabin.

[0007] It should be understood that the summary above is provided to introduce, in simplified form, a selection of concepts that are further described in the detailed description. It is not meant to identify key or essential features of the claimed subject matter, the scope of which is defined uniquely by the claims that follow the detailed description. Furthermore, the claimed subject matter is not limited to implementations that solve any disadvantages noted above or in any part of this disclosure.

BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The disclosure may be better understood from reading the following description of non-limiting embodiments, with reference to the attached drawings, wherein below:

[0009] FIG. 1 shows an example of components within a vehicle and a hybrid inference engine (HIE) according to an embodiment of the present disclosure;

[0010] FIG. 2 shows a communication diagram for example communications between a user device, a wireless system, a vehicle, a hash creator, a datalogger, a learning component, and an inferencing component according to an embodiment of the present disclosure;

[0011] FIG. 3 shows an example of logged data in a table based on vehicle occupants and conditions, according to an embodiment of the present disclosure; [0012] FIG. 4 shows an example method for determining if a current vehicle environment matches a previous vehicle environment with an associated learned model, according to an embodiment of the present disclosure; and

[0013] FIGS. 5 A -5D show changes to comfort settings based on an arrangement of vehicle occupants according to an embodiment of the present disclosure.

DETAILED DESCRIPTION

[0014] The present disclosure provides support for methods and systems for automatically adjusting cabin settings. The cabin settings may be automatically adjusted based on a previously learned model. In one example, a current vehicle environment may be matched to a previous vehicle environment, wherein both environments include identical mobile devices communicating with a communication system of the vehicle. The environments may further include identical weight sensor outputs and occupant arrangements. The environments may still further include vehicle location, weather, road grade, and other details independent of drivetrain conditions.

FIG. 1 shows an example of the components within a vehicle and the hybrid inference engine (HIE). FIG. 2 shows a communication diagram for example communications between a user device (e.g., a mobile device), a wireless system, a vehicle (e.g., the vehicle of FIG. 1), a hash creator, a datalogger, a learning component, and an inferencing component. FIG. 3 shows an example of logged data in a table based on vehicle occupants and conditions. FIG. 4 shows an example method for determining if a current vehicle environment matches a previous vehicle environment with an associated learned model. FIGS. 5A-5D show changes to comfort settings based on an arrangement of vehicle occupants according to an embodiment of the present disclosure.

[0015] A hybrid interface engine (HIE) may be used to receive data of the vehicle settings and the occupants, interpret data, and create actions based on models for specific vehicle environments. The HIE may also identify a vehicle environment and determine if a model is learned in association with a previous vehicle environment identical to the vehicle environment. If the environments match and the model is learned, then the HIE may automatically send actions to adjust the cabin settings of the vehicle without vehicle operator or occupant input. As such, the cabin setting may be adjusted without the vehicle operator or occupant adjusting a knob or dial, contacting a touchscreen, or providing any input related to the cabin setting. [0016] The HIE may atempt to identify the vehicle environment through communication with mobile devices. A controller of the vehicle may receive feedback from weight sensors and other sensors of the vehicle to determine if there are vehicle occupants free of a mobile device (e.g., vehicle occupants that do not have a mobile device or smart device). If there are vehicle occupants free of a mobile device, then data more specific to characteristics of the vehicle occupants may be gathered, such as weight, fingerprints, retinal scans, facial recognition of facial features, hair color, height, and the like. However, if each of a plurality of mobile devices is correlated to a vehicle occupant, then identifying features may not be gathered. As such, only a media access control (MAC) address, device name, or other device identifying feature may be retrieved and occupant-identifying features such as name, phone number, home address, IP address, fingerprints, facial features, and the like may not be retrieved.

[0017] The vehicle services adjusted by the HIE may include one or more of a seat position, a steering wheel position, a window position, a media volume, a media genre, a media type, a media source, an audio direction (e.g., activation/deactivation of one or more speakers), audio setings (e.g., bass, treble, voice, etc.), a cabin temperature, an air conditioning (AC)Zheater seting, a direction and a strength of cabin air flow, a cabin light brightness, a window position, and a heated seat seting. The HIE may signal to the controller to adjust setings for the heater/AC including temperature throughout the vehicle, strength of fans, temperature setings for particular zones of vehicle, and humidity setings. For the speakers, media players, and voice audio settings including surround sound, quiet zones, etc.

[0018] The disclosure also describes improving the experiences of an occupant or multiple occupants of a vehicle in response to detection of at least one mobile device using a MAC ID of each of the at least one mobile devices that a specific occupant may carry (e.g., paired to a communication system of the vehicle) and which is further paired to the communication system. A device that is paired to a vehicle may be within a distance to connect to a communication system of the vehicle. For example, improving an experience may include increasing occupant comfort by adjusting vehicle services. The disclosure also describes improving the experiences of an occupant or a plurality of occupants relative changes in the weight data of the occupant(s) recorded by sensors. The disclosure also describes improving an occupant or multiple occupant experiences relative to both non-identifying data from a single or plurality occupants and/or a single or plurality of mobile device associated with the occupant(s). For the example in the present disclosure, non-identifying information of the electronic mobile devices may include MAC IDs and non-identifying information of the occupant(s) may include changes in weight data of the occupant(s) recorded by sensors. The data of the MAC IDs, the weight data, other non-identifying information, or the combination thereof of the occupant or occupants may be referred to as metadata. Metadata in the present disclosure is defined as data specific to vehicle occupants used to create context that does not directly identify the occupants. The metadata may create context for the HIE to execute changes to the services in a vehicle

[0019] It is also to be understood that the specific assemblies and systems illustrated in the attached drawings, and described in the following specification are exemplary embodiments of the inventive concepts defined herein. For purposes of discussion, the drawings are described collectively. Thus, like elements may be commonly referred to herein with like reference numerals and may not be re-introduced.

[0020] Turning to FIG. 1, it shows a schematic 10 of a system 100 of a vehicle 24. The system 100 may be used to personalize a plurality of services 101 for a cabin 30 of vehicle 24. The cabin 30 may be herein referred to as a vehicle interior interchangeably. The cabin 30 may include lights, temperature control systems, audio systems, display devices, a steering wheel, adjustable seating, and windows.

[0021] The system 100 of the present application provides automatic adjustment of one or more vehicle components communicatively coupled to the system 100. The system 100 of vehicle 24 may receive, leam, and adjust settings of the services 101 based on data from vehicle sensors, metadata associated with a single or plurality of mobile devices. Herein, mobile devices may include portable devices configured to communicate with a communication system of the vehicle 24 via a wired or a wireless connection.

[0022] V ehicle 24 may be a passenger vehicle, a commercial vehicle, an off-highway vehicle, or other transportation system. In particular, vehicle 24 of FIG. 1 may be a motor vehicle including drive wheels (not shown) and a prime mover 26. In some examples, prime mover may be an internal combustion engine. In other examples, prime mover 26 may include both an engine and an electric machine and vehicle 24 may be a hybrid vehicle. For example, vehicle 24 may include a hybrid propulsion system including an energy conversion device, such as the electric machine, operable to absorb energy from vehicle motion and/or the engine and convert the absorbed energy to an energy form suitable for storage by an energy storage device. In another example, vehicle 24 may be a fully electric vehicle, with prime mover 26 configured as the electric machine, and, in some examples, may incorporate fuel cells, solar energy capturing elements, and/or other energy storage systems for powering the vehicle. Further, in some instances, vehicle 24 may be an autonomous vehicle. For example, vehicle 24 may be a fully autonomous vehicle (e.g., fully self-driving vehicle) configured to drive with reduced input from an operator.

[0023] Vehicle 24 may include a plurality of vehicle systems, including a braking system for decreasing vehicle speed, a propulsion system for providing motive power to wheels of the vehicle, a steering system for adjusting a direction of the vehicle, a transmission system for controlling a gear selection for the engine, an exhaust system for processing exhaust gases, and the like. Further, vehicle 24 may include a controller 28 configured as an in-vehicle computing system. An HIE 109 may be communicatively coupled to or part of the controller 28. The HIE 109 may be communicatively coupled to the services 101 of vehicle 24. Likewise, a user interface 40 may be communicatively coupled to the services 101 of vehicle 24.

[0024] In one example, the HIE 109 may represent a machine learning algorithm stored on memory of the controller 28 and configured to receive inputs from various sensors via the controller 28. The HIE 109 may track changes to the inputs in response to various changes to a vehicle environment and suggest actions based on subsequent vehicle environments correlating with a previously experienced vehicle environment. The HIE 109 and models generated thereby to learn and/or anticipate changes to inputs based on the vehicle environment is described in greater detail below.

[0025] The cabin 30 may be configured to receive a single or plurality of occupants. The single or plurality of occupants may be users, each of which may comprise one or more mobile devices, which may herein be interchangeably referred to as user devices.

[0026] The cabin 30 may comprise a plurality of seats 126. The occupants, mobile devices, and seats may be enclosed by the cabin 30 of the vehicle 24. The schematic 10 comprises an occupant 130 arranged on a seat of the plurality of seats 126. The plurality of seats 126 may be identical or different in size, shape, and capabilities. Capabilities of the plurality of seats 126 may include one or more of heating, cooling, actuation of a base of the seat, actuation of a head rest of the seat, and actuation of a back of the seat. The vehicle 24 may include one seat or a plurality of seats without departing from the scope of the present disclosure. For example, the vehicle 24 may include exactly 5 seats. Additionally or alternatively, the vehicle 24 may include fewer than or more than 5 seats. [0027] The occupant 130 may comprise a mobile device 102. In one example, the mobile device 102 may be one of a plurality of mobile devices. Each vehicle occupant may comprise one or more mobile devices. Additionally or alternatively, one or more vehicle occupants may not comprise a mobile device (e.g., are free of a mobile device).

[0028] Mobile device 102 may be an electronic mobile device, such as a mobile phone; however mobile device 102 may be other mobile devices, such as an MP3 player, a computer tablet, a PDA, a portable computer, such as a laptop, a calculator, a health monitoring device, a watch, or any portable device configured to communicate with a communication system of the vehicle 24 via a wired or a wireless connection, such as Bluetooth. Additionally or alternatively, the mobile device 102 may be configured to fit within the interior of the vehicle 24.

[0029] The HIE 109 may receive input data 106 corresponding to a vehicle environment. Input data 106 may be input into the HIE 109 from sensors of the vehicle 24, and components of the services 101 of the vehicle 24. Input data 106 may include operation data from services 101. Input data 106 may also include data from other systems and components of the vehicle 24. MAC ID(s) as well as settings data for at least one mobile device 102, such as media selection, voice settings, communication settings, applications being operated, or services 101 the mobile device 102 may be influencing or affecting, may be sent to the controller 28. Input data 106 may also include metadata, such as non-identifying information of occupant 130 and the mobile device 102. Input data 106 is sent and input into memory of the controller 28.

[0030] In one example, the input data 106 may include one or more comfort settings selected and/or adjusted by the vehicle occupants and/or connected mobile devices. The comfort settings may include one or more of the services 101. Herein, the comfort settings may be interchangeably referred to as cabin settings or occupant settings.

[0031] The HIE 109 may also send output data 107 to the services 101 of vehicle 24. Output data 107 may include signals to change the settings of services 101 created and interpreted by the HIE 109. The HIE 109 may receive input data 106 and may send output data 107 to alter a plurality of components and services part of services 101. Additionally, the components and services part of services 101 may be adjusted manually by an occupant or occupants of cabin 30 via the user interface 40. As an example of an embodiment in schematic 10, services 101 that may be adjusted by and communicatively coupled to the HIE 109 may include a heater/ AC 119, a voice 104, a media player 105, a speaker/audio system 103, light settings, seat positions, steering wheel positions, side mirror positions, rearview mirror positions, voice recognition, and display devices.

[0032] The voice 104 and speaker/audio system 103 may be used instead of the audio input and output components of the mobile device 102 for communication applications, such for phone calls, voice over internet protocol (voIP), or generating characters for phone text, email, and/or other text based communication. The voice 104 may also receive and relay audio commands from a single or plurality of occupants, such as the occupant 130, of the vehicle 24.

[0033] The controller 28, based on a determination of the HIE 109, may adjust a plurality of conditions for the heater/ AC 119 via service APIs, such as average internal temperature, humidity settings, temperature settings for particular zones, directions and velocities of air flow, seat heating and cooling elements, etc. within the cabin 30 of the vehicle 24. Additionally, the controller 28, via determination of the HIE 109, may adjust power and airflow provided by the heater/AC 119 to the cabin 30 of the vehicle 24.

[0034] The controller 28, via determination of the HIE 109, may adjust a plurality of conditions in the speaker/audio system 103, voice 104, and/or media player 105 such as volume throughout and volume for particular zones of the cabin 30 of the vehicle. For example, the controller 28 may adjust the speaker/audio system 103 to have quite zones in cabin 30. A quiet zone may include where an output of a speaker is reduced relative to outputs from other speakers. The output of speaker/audio system 103, voice 104, and the media player 105 for audio communication, such as phone calls, may also be adjusted by the controller 28 based on a suggestion of the HIE 109 or occupant input.

[0035] The controller 28, based on feedback of the HIE 109, may adjust the media player 105 to select a source of audio or audio visual media, such as from FM radio, AM radio, satellite radio, a cd player, a DVD player, cassette tape, a mobile device, such as mobile device 102, or a digital storage medium, such as a USB and/or thumb drive or a hard drive. Additionally, the HIE may adjust the media player 105 to select a genre of media, such as rock and roll, country, hip hop, rap, pop, podcast, etc., for certain sources of media, such as from mobile device 102.

[0036] It is to be appreciated that the scope of services 101 described herein may be non-limiting and other services may send input data 106 to or may be affected by the service APIs from the HIE 109. For example, lights enclosed by the cabin 30 referred to herein as interior light, headlights, seats, doors, windows, and door and compartment locks may be altered based on determinations of HIE 109. The brightness and color of interior lights, length of time interior lights are on, the status of headlights when the vehicle is turned on, the temperature and/or position of the seat, forecast information, door and compartment lock engagement, and/or window may be altered based on determinations of the HIE 109.

[0037] It is to be appreciated that the services 101 and conditions described may be adjusted manually via the user interface 40 by an occupant or occupants of the vehicle, such as occupant 130. The services 101 and conditions described may be used in various combinations to improve the experience of the occupant(s), such as occupant 130. These examples are in no way a comprehensive list of devices and conditions, and other vehicle services devices and conditions produced by the listed devices and other devices a part of services 101 may be used.

[0038] The system 100 uses the HIE 109 to log, interpret, suggest actions, and send actions to the services 101 based on the data described above. The metadata may be sent collectively together with data from the services 101 as input data, such as input data 106, to the HIE 109. The HIE 109 may then recommend adjustments to settings based on the preferences of the occupants. The occupants, such as occupant 130, of a vehicle 24 and conditions used in the services 101 may be assigned a first vehicle environment ID 146 and anticipated by the HIE 109 based on models generated for learning previously gathered metadata.

[0039] As an example, metadata may be received from mobile device 102. The mobile device 102 may be carried by occupant 130, and used as an identifier for a vehicle environment that includes occupant 130 without gathering personal identifying information. A communication system 108 may be used to gather metadata from mobile devices, such as mobile device 102, and communicate metadata to the controller 28. The mobile device 102 may communicatively couple to the communication system 108, such that the mobile device 102 may be communicatively coupled to the interface 40 and services 101 via the communication system 108. The coupling of the mobile device 102 to the communication system 108 may allow an operator to adjust conditions of the services 101 via the mobile device 102.

[0040] As one example, the communication system 108 may be wireless or include a wireless function, such as Bluetooth. The communication system 108 may communicatively couple to electronic mobile devices, such as the mobile device 102, via a wireless signal. The mobile device 102 or other electronic devices may be paired to the vehicle 24 if within a distance at which the communication system 108 may receive signals from and be connected to the mobile device. The mobile device 102 may connect to the communication system 108 when with a threshold range of the vehicle. The threshold range to the vehicle may be based on a communication type. For example, the mobile device 102 may communicate with the communication system 108 from a greater distance via Wi-Fi compared to a distance used to communicate via Bluetooth. As another example, the communication system 108 may be wired or include a wired component, such as a USB or USB C port. For this example, the communication system 108 may be communicatively coupled to electronic mobile devices, such as the mobile device 102, via a wired coupling.

[0041] For example, electronic mobile device, such as the mobile device 102, may digitally interface with the services 101 of the vehicle 24 through the communication system 108 such that services 101 may be adjusted based on inputs provided to the mobile device. For this example, voice settings on the mobile device 102 may be adjusted so voice 104 may receive and be used to respond to audio or text based communication. For this example, media on the mobile device 102 may also be selected as a source for the media player 105. Both the voice 104 and media player 105 may be selected as input for the mobile device 102 through the interface 40. The settings of the mobile device 102 when paired with the communication system 108 may be recorded, saved, and assigned a unique key by the HIE 109.

[0042] A mobile device, such as mobile device 102, may have a MAC ID specific to the mobile device. Each of a single or plurality of mobile devices 102 may have at least one MAC ID. MAC ID(s) of the mobile device(s) 102 may be recorded when connected to the communication system 108. For example, the MAC ID(s) of the mobile device 102 may be used as metadata and an anonymous condition identifier for occupant 130 by the HIE 109. The MAC ID(s) of other electronic mobile devices may be used as metadata. The MAC ID(s) may be passed with data from services 101 as input data 106 through a HIE interface 110 to the HIE 109. The input data 106 may be stored with a unique identifier.

[0043] The reading of the MAC ID(s) by the HIE interface 110 is optional, and an occupant, such as occupant 130, may opt out of having a MAC IDs, such as MAC ID(s), shared with the HIE interface 110. Additionally, if occupant 130 or other occupants do not possess, connect, or optionally refuse sharing the MAC ID(s) of an electronic device, such as MAC ID(s) of the mobile device 102, other data based on non- identifying information of occupant 130 or other occupants may be used as a substitute. [0044] For one example, weight data 127 of an occupant, such as occupant 130, may also be used by the HIE 109 as an additional anonymous condition identifier. The weight data 127 may be based on the weights of one or more occupants (occupant weight) in one or more seats. For example, the weight data 127 may be obtained from occupant 130 when seated in seat 126. For this example, the weight data 127 may be based on the weight of occupant 130. However, in other examples the weight data 127 may be obtained from a plurality of occupants that may include occupant 130. For this example, the weight data 127 may include the weights of each occupant, such as occupant 130, sitting and abutting a seat of vehicle 24, such as a seat 126. The weight data 127 may also include a total weight tabulated from all the occupants sitting in and abutting seats, such as occupant 130 sitting and abutting seat 126, of vehicle 24.

[0045] Seat 126 may possess weight sensors 128, such as a silicon-filled bladder and/or electronic control unit pressure sensor. The weight sensors 128 may be used to sense the position and estimate the weight of the occupants when planted in seats. The weight estimated on each seat, such as seat 126, by the sensors 128 may be sent to the HIE 109. Weight from each seat 126 may also be tabulated into a total weight. The weight data 127 may at least include the weights recorded in each seat of vehicle 24 and may include the total weight recorded. For one example, the occupant 130 may be sat in seat 126. The sensor 128 may record and/or estimate the weight of the occupant 130.

[0046] For another example, height data 134 of the height of occupants may be used as a substitute for or in conjunction with weight data 127. Height data 134 may be based on the height of an occupant, such as the height of occupant 130. Occupant height may be sensed and estimated from a single or plurality of height sensors 132. Height sensors 132 may an in-cabin imaging device, such as a camera. Additionally or alternatively, an imaging system including a plurality of imaging devices may be arranged in the cabin 30. The imaging devices may be configured to visualize the vehicle interior and provide feedback to the controller 28. The imaging devices may be further configured to scan facial features as part of a facial recognition routine or scan retinas as part of a retinal scan routine. The height sensors 132 may also use for eye gaze tracking, etc. The height sensor 132 may sense the position of an occupant relative to a seat, such as occupant 130 when in face sharing contact with the surface of seat 126. The position of an occupant relative to a seat, may be referred to herein as an occupant seating position.

[0047] However, it is to be appreciated that other sensors, besides the weight and height sensors 128, 132, may be used to gather non-identifying information about the occupants, such as occupant 130. Such systems may transmit other non-identifying information, besides weight and/or height data 127, 134. Other sensors may include fingerprint scanners, facial recognition sensors, retinal scanners, and other identifying features.

[0048] The height and/or weight data 127, 134 may be sensed continuously by weight and/or height sensors 128, 132, respectively. The height and/or weight data 127, 134 may be read by the HIE interface 110 continuously or in a repetitive and cyclical process. If height and/or weight data 127, 134 is not read after a cycle, the actions recommended by the HIE 109 may change. For example, the height and/or weight data 127, 134 may be read by HIE interface 110 every' five minutes. However, it is to be appreciated that reading of metadata by the HIE interface 110 may be adjustable. As another example, the height and/or weight data 127, 134 may be read by the HIE interface 1 10 every' minute. For these and other examples, the reading of and frequency at which metadata is read may be adjusted by the occupants of the vehicle such as via the user interface 40. Likewise, other non-identifying information may be read in a similar manner as described above.

[0049] A machine learning (ML) model 115 may be generated to leam conditions associated with mobile devices in communication with the communication system 108 of the vehicle 24. Additionally or alternatively, the conditions may be further associated with the other metadata, such as weight and height. The machine learning model 115 may leam the desired parameters of the services 101 and suggest automatic service adjustments to the controller 28 during a next vehicle operation where mobile are identical to a learned model.

[0050] In an example, the data gathering network configuration may be used to deliver personalized content to one or multiple occupants in a vehicle 24. These preferences may change based on the combination of non-identifying information associated with specific occupants. For example, the MAC ID(s) of the mobile devices 102 may be used as a proxy for occupant 130 being seated in the cabin 30. As another example, the weight data 127 estimated from the weight of occupant 130 by weight sensor 128 may be used as a proxy for occupant 130 being seated in the cabin 30. As another example, the height data 134 estimated from the height of occupant 130 by height sensors 132 may be used as a proxy for occupant 130 being seated in the cabin 30. For these and other examples, the MAC ID(s), weight data 127, and/or height data 134 of occupant 130 may be used as proxies for occupant 130 being seated in the cabin 30. For these and other examples the MAC ID(s), weight data 127, and/or height data 134 may be used to identify a specific combination of occupants, which may include occupant 130, without utilizing identifying information of each occupant. The MAC ID(s), the weight data 127, and the height data 134 may be referred to collectively as a metadata, 127, 128.

[0051] MAC ID(s), weight data 127 and/or height data 134 may be hashed by the HIE 109 to hide non-identify ing information, such as the MAC ID or an estimated weight or height of an occupant. Other metadata that may be obtained from the occupants may also be hashed to hide non-identifying information of the occupant. Both the use of metadata and the hashed metadata allows the parameters of the occupant or a plurality of occupants to be determined in an anonymous way. The hashing by the HIE 109 creates a string of characters as unique key represent a current vehicle environment. The unique key may identify and/or label a ML model corresponding to a current vehicle environment. In one example, the current vehicle environment includes at least data related to mobile devices communicating with the communication system 108. Additionally or alternatively, the current vehicle environment further includes one or more of weight sensor data, height sensor data, weather, vehicle location, road surface, estimated travel time, occupant arrangement, intended final destination, and the like. The machine learning model may learn adjustments to the services 101 for a given vehicle environment and suggest automatic adjustments to the services 101 in response to the given vehicle environment repeating during a future vehicle on event.

[0052] Before being hashed, input data 106 may be provided to the controller 28 and stored in a database 112. A hash creator 122 may generate a unique key (e.g., a hash) comprising a plurality of characters unique to the set of input data 106. A datalogger 121 may receive the data and unique key from the hash creator 122 and transfer hashed data 113 to the machine learning model 115. Models and suggested actions learned based on the hashed data 113 may be used only in future vehicle environments that correlate with the vehicle environment identical to hashed data 113. The machine learning model 115 may output to a processor of the controller 28 one or more suggested actions to execute automatically in response to a current vehicle environment correlating with a previous vehicle environment with an associated learned model.

[0053] In one example, hashing the data provides standardization. Further, the hashing alters the data into another form, such as a string of characters. The hash creator 122 generates hashes that are always the same number of characters. Variation in the size of data used to create the hashed data do not change the number of characters. Data is hashed in single direction, meaning data can be transformed into a hash but that data cannot be reverted back to its original data. When the hash creator 122 receives input data during a current vehicle environment, the hash creator 122 produces an exact same hash previously produced for a prior vehicle environment identical to the current vehicle environment. For these reasons, in some examples, data that may have more variation or error with each read, such as weight and height data 127, 134, may be rounded to an approximate value before being hashed by the hash creator 122. For these examples, if the weight data and/or height data 127, 134 is approximately the same as a weight and/or height data, respectively, from a previous vehicle environment ID, the hash creator 122 may generate a vehicle environment ID.

[0054] In some examples, additionally or alternatively, the hash is different if the input data with the current vehicle environment does not correlate with a previous vehicle environment. In some embodiments, additionally or alternatively, portions of the hash may correspond to different service settings. For example, one or more characters of the hash may correspond to a number of mobile devices, a different set of characters may correspond to temperature settings, a further set of characters may correspond to seat positions. By doing this, portions of previously learned models may be at least partially correlated to the current vehicle environment despite the two environments not exactly matching. In this way, matched sections of the hash may be identified and suggested actions learned based on the matched sections of the hash may be automatically executed. [0055] In one example, and as will be described in greater detail herein, the controller 28 may signal to actuators of the cabin 30 to automatically adjust various settings based on feedback from the machine learning model 115.

[0056] Turning now to FIG. 2, a routine 200 is shown illustrating a sequence of operations that may be performed by a user device 202, a wireless communication system 204 (e.g., “wireless comm”), the vehicle 24, the hash creator 122, the datalogger 121, the learning component 123, and the inferencing component 117. In one example, the wireless communication system 204 is identical to or a non-limiting example of the communication system 108. The user device 202 may include the mobile device 102 of FIG. 1 along with key fobs, laptops, tablets, watches, and other smart devices. In one example, the user device 202 may include at least one device with wireless communication capabilities.

[0057] The routine 200 begins at 212, which includes the user device 202 sending a signal to register and pair the user device to the wireless communication system 204. The user device 202 may send the message via Wi-Fi, Bluetooth, long-range radio, dedicated short-range communication (DSRC), radio frequency identification (RFID), and the like. [0058] The vehicle 24 may optionally determine if ignition is on at 213. Ignition may include an engine combusting or an electric motor receiving current. In some examples, the routine 200 may proceed without determining if ignition is on and instead may determine if a vehicle battery is discharging. For example, the vehicle may determine if a battery is on.

[0059] The wireless communication device 204 may power on at 214 and scan for devices at 216. As such, the wireless communication device may receive information from the user device 202. The user device 202 may provide a MAC ID in one example. Additionally or alternatively, the user device 202 may send a device number, serial number, make, model, device nickname, and the like.

[0060] The wireless communication device 204 may send device content to the hash creator 122 at 218. The hash creator 122 may create a hash based on the content received at 220. In one example, the hash is a unique key generated based on the content provided. [0061] In one example, the wireless communication device 204 may receive information from a plurality of user devices. The wireless communication device 204 and/or the controller 28 of the vehicle 24 may further receive data from various vehicle sensors such as weight sensors, to determine an arrangement of the vehicle occupants. Additionally or alternatively, a single occupant may include a plurality of user devices. The unique key generated by the hash creator may further include each of the user devices associated with each occupant within the vehicle.

[0062] At 222, the vehicle 24, via the controller (e.g., controller 28 of FIG. 1), may log data at the datalogger 121 at 220. The hash creator 122 may send the hash to the datalogger 121 at 224. The hash may be concentrated to datalogs, which may further account for a vehicle environment. The datalogger may periodically log data related to the vehicle environment, the data may be related to seat position, air conditioning status, air conditioning temperature, window position, light settings, media source, media volume, media genre, vent position, weather, road conditions, and the like. This data may be logged in combination with the specific user devices paired along with the arrangement of the vehicle occupants under the single hash.

[0063] Seat position may relate to one or more of an angle of the seat along with a position of the seat relative to other components of the vehicle. For example, a driver’s seat position relative to the steering wheel may be logged. Additionally or alternatively, an angle of the rear seats may be logged.

[0064] The air conditioning status may be based on an activation or a deactivation of the air conditioning system. The air conditioning temperature may relate to a cabin temperature and/or to a fan speed set for the air conditioning system.

[0065] The window position may relate to positions of any adjustable window of the vehicle. This may include an open position, a closed position, a partially open position, an angled position, and the like. Additionally or alternatively, if a window is arranged in a roof of the vehicle (e.g., a sun roof or a moon roof) and comprises an adjustable cover, then a position of the adjustable cover may be logged.

[0066] The light settings may include interior light settings such as door sill lights, steering well lights, rear seat lights, and the like. Additionally or alternatively, the light settings may further include a dash panel lighting and brightness thereof, an infotainment display screen brightness, head rest display screen brightness, and light settings of other lights included in the interior cabin of the vehicle. The light settings may further log data related to a desired setting of vehicle headlights and high beams, which may include logging manual or automatic control of the high beams and headlights.

[0067] The media source may include one of the user devices, a radio, an application stored within memory of the infotainment system, or the like. The media volume may relate to media volume requested through an entirety of the vehicle along with volume settings. Volume settings may include treble levels, bass levels, audio levels, speaker settings, media volume biasing, and the like. Media volume biasing may include an occupant requesting volume to be higher/lower in a first area of the vehicle relative to other areas. Media genre may be related to music, television, movies and the like. The media genre may further specify a music genre, a television genre, and a movie genre. Examples learning and adjusting media genre based on the paired user devices and the arrangement of the vehicle occupants is described in greater detail below.

[0068] The vent position may be related to a desired direction of air flow. The vent position may include directing air toward a windshield, side windows, toward an occupant head, toward an occupant torso, toward an occupant’s feet, or toward areas between or away from individual occupants.

[0069] Road conditions may include traffic congestion, road type (e.g., dirt, gravel, pavement, etc.), and vehicle location. The vehicle location may be categorized into city driving, highway driving, rural driving, and the like. The vehicle location may be further categorized based on a geofencing of various landmarks and/or locations. For example, schools, parks, stadiums, work offices, home, drive-thru’s, parking lots, and the like may include specific geofencing that may be logged with the hash.

[0070] The datalogger 121 may send the above combination of data to the learning component 123 at 226. The learning component 123 may create models 228 of the occupant behavior under various vehicle environments. The models may be machine learning models that may continuously update based on sensed occupant behaviors that deviate from a predicted occupant behavior.

[0071] The learning component 123 may transfer the models to the inferencing component 117 at 230. The inferencing component 117 may inference and/or predict desired vehicle conditions based on the models received along with a received current vehicle environment for future vehicle conditions.

[0072] The wireless communication device 204 may send a current vehicle environment to the inferencing component at 232. The inferencing component 117 may compare the current vehicle environment to environments of previously received models to determine if a correlation is present. If a correlation is present, then the inferencing component 117 may send actions to the wireless communication device 204, which may include a controller 28 of the vehicle 24, identical or closely similar to previously executed actions. If a correlation is not present, then the inferencing component 117 may send actions that are a modification of actions previously executed based on one or more at least partially similar previous vehicle environments.

[0073] In some examples, if the vehicle occupants modify one or more of the above described settings following the inferencing component 117 sending actions at 234, then the steps 218-230 may be repeated, thereby creating a new model for the new vehicle environment. In this way, the inferencing component may continuously leam changes to the vehicle settings based on sensed user devices of vehicle occupants in combination with vehicle occupant positioning and various other vehicle and environmental conditions.

[0074] In one example, the new model may be differentiated from prior models in that data associated with one or more vehicle environment conditions is independent of previously learned models. For example, if a new mobile device is paired and not present in any previously learned models then settings learned in association with the new mobile device may be unrelated to the previous models. Associating comfort settings to the new mobile device may be executed via the in-cabin imaging system, feedback from the new mobile device, and/or a comparison to the previous learned models. For example, if the new mobile device is paired along with previously paired mobile devices, then comfort settings associated with the previously paired mobile devices in the previously learned models may be filtered from the new model. As such, the unfiltered comfort settings may be associated with the new mobile device. Additionally or alternatively, comfort settings may be adjusted via a mobile device, wherein the comfort settings adjusted may be associated to the mobile device. The in-cabin imaging system may identify which vehicle occupant adjusted one or more comfort settings, wherein the comfort settings adjusted may be correlated to a mobile device of the vehicle occupant and/or a sensed weight. The comfort settings associated with the new mobile device may be automatically suggest actions during future vehicle on events if the new mobile device is present and one or more other vehicle environment parameters match the previous vehicle environment where the comfort settings of the new mobile device were learned.

[0075] FIG. 3 displays a chart 300 illustrating how the connected/paired mobile devices of vehicle occupants may change settings to the heater/air conditioner (AC) 119 and mediaplayer 105. This example in FIG. 3 is similar to how a HIE 109 datalogger 121 records hashed data based on connected mobile device 102 identifiers (e.g. MAC IDs) in 300B-E and vehicle 24 services 101 input data 106 in 300F-I. The chart 300 has been labeled alpha numerically. For this example and figure, chart 300 rows are labeled with numbers: 301, 302, 303, etc. For this example and figure, chart 300 columns are labeled with letters: 300A, 300B, 300C etc. For this example, when a specific cell in the chart 300 is read, the cell references the last numeral of the row combined with the Latin letter of the column. For example, a cell located in the first row 301 and the first column 300 A, may be referenced as 301 A. For example, a cell located in the second row 302, and the third column 300C, may be referenced as 302C.

[0076] In an example, chart 300 may display mobile device data used to specify conditions for occupants in the form of MAC IDs. Chart 300 demonstrates how the data is stored in the datalogger 121 that may be hashed into and concatenated with a vehicle environment ID. it is not the only possible method of specifying data to occupants. As mentioned in previous examples data on the weight data 127 of the occupants could be used in place of or in conjunction with MAC IDs of the occupants. Using weight data 127 of the occupants may be as effective as MAC IDs of mobile devices 102 for creating vehicle environment IDs to improve and personalize services 101 of vehicle 24 to different combinations of occupants, such as occupant 130. [0077] Other forms of metadata may be used besides MAC IDs. For example, weight data 127 of occupants recorded by seat 126 and weight sensors 128, may be used in place of MAC IDs in the chart 300. For example, weight data 127 of occupants recorded by seat 126 weight sensors 128, may be used to replace some of and in conjunction with other MAC IDs in the chart 300. For example, height data 134 of occupants recorded by height sensors 132, may be used in place of MAC IDs in the chart 300. For example, height data 134 of occupants recorded by height sensors 132, may be used to replace some of and in conjunction with other MAC IDs in the chart 300. For example, weight data 127 and/or height data 134, may be used to in place of MAC IDs in the chart 300. For example, weight data 127 and/or height data 134, may be used to replace some of and in conjunction with other MAC IDs in the chart 300.

[0078] FIG. 3 shows an example in chart 300 of the metadata. Metadata used in chart 300 is exclusively for MAC IDs from mobile devices 102. In an example, the chart 300 rows 301-306 reference different configurations occupants. Occupants are labeled with letters and/or numbers. For this example, there are three occupants labeled as Al, A2, and G. For this example, configurations in the chart 300 include a first occupant Al, a second occupant A2, and a third occupant G together in cell 301A, the first occupant Al and second occupant A2 in cell 302A, the second occupant A2 in cell 303 A, the first occupant Al in cell 304A, the second occupant A2 and third occupant G in cell 305 A, and first occupant Al and third occupant G in cell 306A.

[0079] Column 300A may be labeled as and labeled with occupants in, and may be referred to herein as the occupants column 300A. “MAC ID” may be the label for columns 300B-300E, wherein each column may have a MAC ID that is different from the others or may be empty. The column 300B referred to herein as a first MAC ID column 300B. The column 300C referred to herein as a second MAC ID column 300C. The column 300D referred to herein as a third MAC ID column 300D. The column 300E may be referred to herein as a fourth MAC ID column 300E. The temperature settings of heater/ AC 119 may be contained in column 300F. Column 300F may be referred to herein as temperature settings column 300F. For this example, the AC temperature of the heater/ AC 119 may be adjusted and have a corresponding column is the in column 300F. The media player 105 settings may be contained in columns 300G-300I. The varying settings and corresponding columns of the media player 105 shown in chart 300 are media volume in column 300G, media source in column 300H, and media genre in column 3001. Column 300G may contain the media volume settings, and may therein be referred to as the volume column 300G. Column 300H may contain the media source settings, and may therein be referred to as the source column 300H. Media sources in column 300H include categories, such as radio and CD. Column 3001 may contain the media genre settings, and may therein be referred to as the genre column 3001.

[0080] The chart 300 may contain a plurality of rows. A row 310 may be located at the top of the chart. Row 310 may contain the labels for columns 300A-I and may be referred to as the label row 310. For an example of one embodiment, chart 300 may contain a plurality of six rows below the label row 310. From the top to the bottom of chart 300 may contain first row: row 301; a second row: row 302; a third row: row 303; a fourth row: row 304; a fifth row: row 305; and a sixth row: row 306. The data in each of rows 301-306 may be associated with a different vehicle environment ID created by different arrangements of occupants in column 300A and non-identifying information in columns 300B-300E.

[0081] For this example, however, the chart 300 may have alternative configurations that have been considered. Alternative configurations for chart 300 may include additional columns for MAC IDs and/or services 101. Alternative configurations for chart 300 may include additional rows for more scenarios. The chart 300 describes conditions of columns 300F-G and the corresponding service devices they affect, such as media player 105 and heater/ AC 119, are comprehensive list of conditions or devices may be recorded in a chart similar to or with different configurations than the example chart 300. Alternative configuration of chart 300 may include other service conditions, applications, and devices part of the services 101 of vehicle 24 have been considered.

[0082] For this example, the arrangement of MAC IDs corresponds with different devices possessed by the occupants of vehicle 24. For this example, the MAC IDs do not correspond to a specific column 300B-300E. MAC IDs fill columns based on the size of their number. For example, if the MAC ID that is the lowest is “111 ”, then MAC ID “111” may fill the first MAC ID column, for this example column 300B of the chart 300. For this example, if the MAC ID that is the largest is “444”, MAC ID “444” may fill the last MAC ID column, for this example column 300E of the chart 300. However, for example if a single device connected or the electronic mobile device with MAC ID that is the lowest has a MAC ID of “444”, the MAC ID of “444” may be placed in the first MAC ID column, for this example column 300B. For this example, the first MAC ID column 300B may be filled by the device with the MAC ID with the lowest number. For this example, if occupant Al connects their mobile device, 304B may be filled by the MAC ID “111”: the MAC ID of the first mobile device they connected. However, for this example if occupant Al possess a second mobile device with the MAC ID of “222” and not the first device with the MAC ID of “111”, then the cell of column 300B may be filled by the MAC ID “222”. For this example, if occupant A2 connects a mobile device with a MAC ID of “333” after devices of occupant Al had been previously connected and hashed, then it may fill the cell to the right of the MAC IDs “111” and “222” belonging to of occupant Al. For this example, some cells formed in columns 300B-300E are blank, since not all of the mobile devices 102 of the occupants are connected.

[0083] For this example, there are 4 columns for MAC IDs that are different from one another in columns 300B-300E. For this example, components and features of the services 101 of vehicle 24 may include the heater/ AC 119, voice 104, the media player 105, and the speaker/audio system 103. For this example, the adjusted heater/ AC 119 setting is the AC temperature of column 300E. However, other settings, such as the heater temperature, the seat temperature, and the external temperature of the vehicle 24, may be recorded into a similar to 300 or chart of a different configuration conjunction with the mobile devices 102 of the occupants. For this example, the columns 300G-300I contain altered settings for media player 105. These media player 105 settings include settings are volume in column 300F, media source in 300H, and media genre in column 3001. For this example, media sources may include radio and CD.NA: not applicable may also be a media source when the media player 105 is off, or when volume on the media player 105 and/or the speaker/audio system 103 are reduced to zero. However, other media sources have been considered, such as but not limited to mp3 players and the mobile devices 102. [0084] For one example, in the chart 300, the occupants of the first row 301 in column 300A, include occupants Al, A2, and G. Four devices are detected from the occupants with MAC IDs of “111”, “222”, “333”, and “444” in cells 301B-E. In this example, the vehicle 24 is operating with the occupants in cell 301 A and the four devices recorded in cells 301B-E. The data of the heater/ AC 119 temp conditions in cell 301F, the media volume in cell 301G, the media source in cell 301H, and the media genre in cell 3011 are recorded in the first row 301. In this example, the data previously described is assigned and associated with four of the MAC IDs of the mobile devices 102 of row 301 in cells 301B-E. In this example, in first row 301, the heater/AC 119 temp in column 300F is at 19 arbitrary units and stored in the corresponding cell 301F. In first row 301, the media volume of column 300G is at 15 arbitrary units and stored in the corresponding cell 301G. In first row 301, the media source in column 300H is radio and stored in the corresponding cell 301H. In first row 301, the media genre in column 3001 is blank due to the media source being radio in the corresponding cell 301H. If the media source were on digital library of music, such as on a digital storage device, such as CDs or thumb drives, or a mobile device, such as an MP3 player or phone, a genre may have been chosen instead of cell 3011 remaining blank.

[0085] For this example, the data in row 301 may be hashed into and paired with a vehicle environment ID to form the hashed data 113. The hashed data 113 may be sent to the learning component 123 so the settings may be learned for this combination of MAC IDs and data in row 301.

[0086] For this example, the vehicle 24 may be restarted and the electronic devices sharing the MAC IDs in cells 301B-E may be detected by the communication system 108 at a later time. MAC IDs in cells 301 B-E are detected, the vehicle 24 may automatically adjust to the settings recorded in in cells 301F-I. For this example, the action recommender 117 may receive the context data and the first vehicle environment ID 118 from FIG. 1. For this example, the action recommender 117 may send a recommended action 120 based on the conditions of the services 101 recorded in cells 301F-I. For this example, the temperature of the heater/ AC 119 may be adjusted to 19 arbitrary units, such as in cell 301F. For example, the media volume may be adjusted to 15 arbitrary units, such as in cell 301G. For example, the media source may be adjusted to start the radio, such as in cell 301H. For example, the media genre may have no preference, such as in cell 3011.

[0087] For another example, in the chart 300, the occupants of the second row 302 in column 300A, include occupants Al and A2. In this example, three devices are detected from the occupants with MAC IDs of “111”, “222”, and “333” in cells 301B-E. In this example, the mobile device 102 of occupant G - with a MAC ID “444” - are not present. In this example, the vehicle 24 is operated with the occupants recorded in cell 302 A. Three MAC IDs: “111”, “222”, “333”, of devices are recognized and recorded in cells 301B-D. In this example, the AC temp in column 300F is increased to 20 arbitrary units and stored in the corresponding chart cell 302F. In this example, the media volume in column 300G remains the same as in the previous example in cell 301G at 15 arbitrary units. The media volume in column 300G is stored in the chart cell 302G. In this example, the media source in column 3 OOH has been changed to a CD and is stored in the corresponding chart cell 302H. In this example, the media genre in column 3001 may read as “Rock” from the CD and is stored in the corresponding cell 3021. [0088] For this example, the data in row 302 may be hashed into and paired with a vehicle environment ID to form the hashed data 113. The hashed data 113 may be sent to the learning component 123 so the settings may be learned for this combination of MAC IDs and data in row 302.

[0089] For this example, the vehicle 24 may be restarted and the electronic devices sharing the MAC IDs in cells 302B-E may be detected by the communication system 108 at a later time. Once the MAC IDs of the device in cells 302B-E are detected, the vehicle 24 may automatically adjust to the settings recorded in row 302. For this example, the action recommender 117 may receive the context data and the first vehicle environment ID 118 from FIG. 1. For this example, the action recommender 117 may send a recommended action 120 based on the conditions of the services 101 recorded in FIG. 3 cells 302F-I. For example, the heater/ AC 119 temperature may be automatically adjusted to 20 arbitrary units, such as in cell 302F. For example, the media volume may be automatically adjusted to 15 arbitrary units, such as in cell 302F. For example, the media source may be automatically adjusted to start play a CD currently in the media player 105, such as in column 3 OOH. For example, the media genre may have a preference to rock, such as in cell 3021. For this example, when mobile devices 102 with MAC IDs of “111”, 222”, and “333” are present, a library of music from a mobile device 102, such as an MP3 or a mobile phone, may show preference to rock with a rock playlist as selected by the action recommender 117, recommended action 120, and service APIs.

[0090] Turning now to FIG. 4, it shows a method 400 for generating a new model in response to an occupant modifying actions sent by the HIE. Instructions for the method 400 may be stored on memory of a controller (e.g., the controller 28 of the vehicle 24). The controller may execute the method based on the instructions and signal to various actuators to perform various actions based on the method.

[0091] At 402, the method 400 may include determining current parameters. Current parameters may include weather and road conditions. Weather and road conditions may be sense via vehicle sensors, a navigation device of the vehicle, and the like.

[0092] At 404, the method 400 may include identifying one or more user devices (e.g., mobile device 102). The one or more user devices may communicate via a wired or wireless connection to the controller of the vehicle. Additionally or alternatively, the vehicle may include a device communication system configured to broadcast a signal. User devices in range of the signal may respond and optionally pair with the vehicle. Once paired, the user device may provide data, including device identification, device type, MAC address, and the like. In some examples, additionally or alternatively, the user device may provide data related to an occupant, including name, address, and the like. In other examples, additionally or alternatively, only information related to the user device may be provided, and details related to the occupant associated with the device may be withheld. In one example, only devices paired via a Bluetooth connection or a wired connection may be considered and mobile devices connected via Wi-Fi or other long range wireless connections may be ignored. As such, mobile devices that may not be near the vehicle may be ignored and not included in a current vehicle environment. [0093] In some examples of the method 400, in the absence of a user device associated to one or more occupants in the vehicle, the vehicle may include biometric sensors for identifying vehicle occupants. Biometric sensors may include retinal scanners, finger print scanners, facial recognition, weight sensors, and the like. The biometric data may be stored in association with a specific occupant profile comprising various desired comfort settings associated with the occupant and their location/arrangement within the vehicle.

[0094] At 406, the method 400 may include determining if at least one user device is sensed and associated to each occupant. In some examples, an occupant may not have a user device (e.g., an infant or child). In one example, the imaging system in the cabin may be used If a user device is not sensed for an occupant, then at 408, the method 400 may include sensing biometric data of occupants with which a user device is not associated. The biometric data may include one or more of an occupant weight, an occupant fingerprint, an occupant retinal image, an occupant facial image, or similar. [0095] If at least one user device is sensed for each occupant and/or biometric data is sensed for one or more occupants such that each occupant of the vehicle is identified, then the method 400 may proceed to 410, which may include sending a current vehicle environment with user device and/or biometric data to the controller. The current vehicle environment may include a number of occupants, an arrangement of the occupants, and the like. The current vehicle environment may further include weather, road conditions, a current vehicle location, a desired final vehicle location, and traffic congestion conditions. The arrangement of the occupants may be determined via weight sensors and/or vehicle cameras. Additionally or alternatively, Bluetooth or other wireless receivers may be located in various positions of the vehicle, wherein an occupant location may be determined based on a received with which a user device is communicating. [0096] At 412, the method 400 may include determining if a learned model or learned models match a current vehicle environment. The current vehicle environment may include the current parameters, the sensed user devices, the arrangement of the vehicle occupants, and the like. Matching the current vehicle environment may include a plurality of current vehicle environment conditions being identical to a plurality of previous vehicle environment conditions associated with one or more learned models. Additionally or alternatively, each parameter/condition of the vehicle environment may include a corresponding value, wherein a match is determined based on a sum of the values. For example, a specific user device may receive a higher value than a road condition or a vehicle location. If user devices of a current vehicle condition match user devices of a previously learned vehicle condition and road conditions/vehicle location do not, then a matched learned model may be identified.

[0097] In some examples, additionally or alternatively, for a learned model to be matched to the current vehicle environment, a number and type of user devices are identical for each condition. If multiple learned models include the identical number and type of user devices, the learned models may be further filtered based on the other parameters, such as weather, vehicle location, road conditions, desired destination, and the like. Each of the parameters may receive a value and the values may be summed, such that a match may be determined via the summed values. Additionally or alternatively, the parameters of the learned models may be compared to the current vehicle environment, wherein the learned model with a greater number of matched parameters may be selected for automatically adjusting settings. In some embodiments, additionally or alternatively, multiple learned models may be selected, wherein settings learned therein may be associated to specific parameters. For example, heated seats may be associated with weather, media type and duration may be associated with an anticipated drive time, and the like.

[0098] In some examples, one or more portions of the current vehicle environment may be correlated to a portion of or all of a learned model such that partial matches may be used for suggesting automatic actions. For example, if a user device is paired and one or more models are learned with the user device included in the vehicle environment, then one or more comfort settings common to the learned models may be automatically sent. [0099] If a learned model is correlated with to the current vehicle environment, then at 414, the method 400 may include automatically sending actions based on the correlated learned model(s). Automatically sending actions may include prophylactically sending actions to adjust/maintain comfort settings without a vehicle occupant input. In this way, cabin, media, seat position, steering wheel position, drive modes, and other comfort settings may be automatically adjusted without the vehicle occupant adjusting knobs, depressing buttons, touching a touch screen, or modifying vehicle settings via another method.

[0100] If a learned model(s) is uncorrelated to the current vehicle environment, such that one or more of the mobile devices, weight sensor values, or other vehicle environment parameters do not comprise an identical value in a learned model(s) then at 416, the method 400 may include generating a new hash key in association with the current vehicle environment.

[0101] At 418, the method 400 may include learning parameters via a new model. The new model may include information regarding comfort settings selected by the vehicle occupants. In one example, the settings may be monitored within a threshold time of a vehicle start. In some examples, additionally or alternatively, settings may be monitored continuously during the vehicle on event. The settings may be recorded in the model in combination with the current vehicle environment. During the vehicle on event, the current vehicle environment may change. For example, the media settings, cabin temperature, and other comfort settings may change and be recorded. If a number of vehicle occupants and/or user devices present in the vehicle changes, then the model may be updated or a new model may be generated.

[0102] At 420, the method 400 may include not sending automatic actions. As such, one or more comfort settings may not be automatically adjusted.

[0103] In this way, user devices are identified and associated to vehicle occupants without identification features related to the vehicle occupant (e.g., name, address, fingerprint, retinal scan, etc.). The user device(s) may communicate with various receivers of the vehicle via wired or wireless communication, wherein a specific arrangement of the vehicle occupants may be determined. The arrangement along with the number of occupants and number of user devices may be stored in memory with an associated unique key code. Cabin settings may be automatically adjusted without input from an occupant based on an identical previous vehicle environment. In some examples, cabin setting may be automatically adjusted without input from an occupant based on a similar previous vehicle environment, wherein a similar previous vehicle environment may include a greater than threshold number (e.g., 90%) of identical vehicle environment conditions relative to the current vehicle environment. If an identical or similar vehicle environment is not learned, then settings may not be automatically adjusted for the current vehicle environment and a new model may be generated and learned.

[0104] Turning now to FIGS. 5A, 5B, 5C, and 5D, they show different vehicle environments and applications of learned models based on the different vehicle environments.

[0105] FIG. 5A shows a first vehicle environment 500 with three occupants including a first occupant 502, a second occupant 504, and a third occupant 506. The first occupant 502 may comprise a first user device 522 and the second occupant 504 may comprise a second user device 524. The third occupant 506 may not comprise a user device. The first and second user devices 522, 524 may be sensed via a communication system of a vehicle 501. A weight sensor may identify the presence of the third occupant 506 and the controller may determine that the third occupant 506 does not comprise a mobile device configured to communicate with the communication system of the vehicle 501.

[0106] A first hash key may be generated and associated with the first vehicle environment 500. A first model may learn the desired comfort settings associated with the first and second user devices 522, 524 and the weight value of the third occupant.

[0107] FIG. 5B shows a second vehicle environment 525 with five occupants including the first occupant 502, the second occupant 504, the third occupant 506, a fourth occupant 508, and a fifth occupant 510. The first occupant 502 comprises the first user device 522. The second occupant 504 comprises the second user device 524. The fourth occupant 508 comprises a fourth user device 526. The fifth occupant 510 comprises a fifth user device 528. The third occupant does not comprise a user device. In one example, the communication system may communicate with and pair with the plurality of user devices. A weight sensor may identify the presence of the third occupant 506 and a weight value may be associated therewith.

[0108] A second hash key may be generated and associated with the second vehicle environment 525. A second model may learn the desired comfort settings associated with the first, second, fourth and fifth user devices and the weight value of the third occupant. In one example, in response to sending the second vehicle environment 525, the controller may at least partially adjust comfort settings based on the comfort settings learned in the first model. For example, cabin front temperature settings associated with the first and second occupants may be automatically adjusted along with a desired seat position thereof. Additionally or alternatively, media settings may be automatically adjusted to match settings learned in the first model.

[0109] In one example, the second model may leam conditions that differentiate it from the first model. For example, an audio volume may be reduced in the second vehicle environment 525, which may be learned and suggest upon a next vehicle environment that exactly matches the second vehicle environment 525.

[0110] FIG. 5C shows a third vehicle environment 550 with only the first occupant 502. The first occupant comprises the first user device 522 and an additional user device 532. A third model may leam comfort settings associated with the first user device 522 and the additional user device 532 being present in the vehicle 501. In one example, upon starting the vehicle 501, one or more comfort settings may be automatically adjusted based on comfort settings learned in the previous models common to the presence of the first user device 522. As such, media settings, seat position, steering wheel position, and the like may be automatically adjusted despite a model including the first user device and the additional user device not being present. Additionally or alternatively, the additional user device may not be associated to an additional occupant via feedback from the vehicle weight sensors.

[0111] FIG. 5D shows a fourth vehicle environment 575 with only the first occupant 502 and the first user device 522. A fourth model may leam the comfort settings associated with only the first user device 522 being present. In one example, the comfort settings in the presence of only the first user device 522 may differ from comfort settings in the presence of the first user device 522 and the additional user device 532 of FIG. 5C. In one example, media settings, such as genre and volume may differ.

[0112] Automatic adjustment of the comfort settings in the fourth vehicle environment 575 may include one or more settings learned in the first through third models and associated with the first user device 522. The one or more settings may include seat position, steering wheel position, audio volume, media genre, and the like.

[0113] In this way, comfort settings and/or cabin settings may be automatically adjusted based on feedback from a machine learning model. The machine learning model may leam desired settings for a plurality of unique vehicle environments and suggest automatic adjustments in response to a current vehicle environment matching one of the previous vehicle environments. If settings are adjusted during the current vehicle environment, then the model may be updated or a new model may be generated. The technical effect of automatically adjusting comfort settings is to improve customer satisfaction.

[0114] The disclosure provides support for a method including communicating with one or more mobile devices paired to a vehicle, learning, with a model, a plurality of comfort settings associated with the vehicle in the presence of the one or more mobile devices and vehicle occupants, and automatically adjusting the plurality of comfort settings in response to a current set of sensed mobile devices and vehicle occupants correlating with a previous set of sensed mobile devices and vehicle occupants associated with the model. A first example of the method further includes where the plurality of comfort settings comprises one or more of a seat position, a steering wheel position, a window position, a media volume, a media genre, a media type, a media source, an audio direction, audio settings, a cabin temperature, an air/conditioning setting, a direction and a strength of cabin air flow, a cabin light brightness, and a heated seat setting. A second example of the method, optionally including the first example, further includes where the one or more mobile devices include devices configured to communicate with the vehicle via a wired or a wireless connection. A third example of the method, optionally including one or more of the previous examples, further includes determining a presence of a vehicle occupant free of a mobile device via one or more of a weight sensor and an incabin imaging device. A fourth example of the method, optionally including one or more of the previous examples, further includes learning with a new model the plurality of comfort settings associated with the vehicle in response to the current set of sensed mobile devices and vehicle occupants being uncorrelated with a previous set of sensed mobile devices and vehicle occupants. A fifth example of the method, optionally including one or more of the previous examples, further includes automatically adjusting only a portion of the plurality of comfort settings in response to the current set of identified mobile devices and vehicle occupants partially correlating with a previous set of identified mobile devices and vehicle occupants being associated with the learned model. A sixth example of the method, optionally including one or more of the previous examples, further includes where the portion of the plurality of comfort settings automatically adjusted are based on comfort settings learned and associated with mobile devices and sensed weight values currently present in the vehicle. A seventh example of the method, optionally including one or more of the previous examples, further includes where communicating comprises communicating via Bluetooth. [0115] The disclosure provides further support for a system including a vehicle comprising a wireless communication system, and a controller with instructions on memory that when executed cause the controller to identify a plurality of paired mobile devices via the wireless communication system, sense a plurality of occupant weights via a weight sensor, learn, with a first model, desired comfort settings of the vehicle associated with a first combination of the plurality of mobile devices and the plurality of occupant weights, and automatically apply the desired comfort settings in response to a current combination of mobile devices and occupant weights correlating with the first combination learned with the first model. A first example of the system further includes where the instructions further cause the controller to leam, with a second model, desired comfort settings of the vehicle associated with the current combination in response to the current combination being uncorrelated with the first combination. A second example of the system, optionally including the first example, further includes where the current combination comprises a number of mobile devices equal to a number of mobile devices of the first combination, and wherein each of the plurality of occupant weights of the current combination is equal to at least one of the plurality of occupant weights of the first combination. A third example of the system, optionally including one or more of the previous examples, further includes where the vehicle further comprises an imaging system arranged in a cabin interior. A fourth example of the system, optionally including one or more of the previous examples, further includes where the instructions further cause the controller to determine an arrangement of vehicle occupants within the cabin interior, and wherein the first model based on the first combination is further based on the arrangement. A fifth example of the system, optionally including one or more of the previous examples, further includes where the instructions further cause the controller to generate a second model in response to an arrangement of the vehicle occupants associated with the current combination uncorrelated with the arrangement of vehicle occupants associated with the first combination. A sixth example of the system, optionally including one or more of the previous examples, further includes where the instructions further cause the controller to sense a vehicle environment, the vehicle environment comprising one or more of weather, location, road condition, traffic congestion, and estimated travel time.

[0116] The disclosure provides additional support for a method for a vehicle including communicating with one or more mobile devices paired with the vehicle, learning, with a model, a plurality of comfort settings associated with the vehicle in the presence of one or more mobile devices and vehicle occupants, automatically adjusting the plurality of comfort settings in response to a current set of paired mobile devices and vehicle occupants correlating with a previous set of paired mobile devices and vehicle occupants associated with the learned model, and learning with a new model the plurality of comfort settings associated with the vehicle in response to the current set of paired mobile devices and vehicle occupants being uncorrelated to a previous set of sensed mobile devices and vehicle occupants. A first example of the method further includes where partially correlating the current set to one or more previous sets of sensed mobile devices and vehicle occupants, and automatically adjusting a portion of the plurality of comfort settings based on correlated mobile devices included in the current set with the one or more previous sets. A second example of the method, optionally including the first example, further includes where comfort settings learned with the new model during the partially correlated current set are independent of the learned model of the previous set. A third example of the method, optionally including one or more of the previous examples, further includes where the one or more mobile devices communicates a MAC address with a communication system of the vehicle. A fourth example of the method, optionally including one or more of the previous examples, further includes where automatically adjusting the plurality of comfort settings comprises automatically signaling actuators to adjust one or more of the plurality of comfort settings free of input from a vehicle occupant.

[0117] The description of embodiments has been presented for purposes of illustration and description. Suitable modifications and variations to the embodiments may be performed in light of the above description or may be acquired from practicing the methods. For example, unless otherwise noted, one or more of the described methods may be performed by a suitable device and/or combination of devices, such as the user interface described with reference to FIG. 1. The methods may be performed by executing stored instructions with one or more logic devices (e.g., processors) in combination with one or more additional hardware elements, such as storage devices, memory, hardware network interfaces/antennas, switches, actuators, clock circuits, etc. The described methods and associated actions may also be performed in various orders in addition to the order described in this application, in parallel, and/or simultaneously. The described systems are exemplary in nature, and may include additional elements and/or omit elements. The subject matter of the present disclosure includes all novel and non-obvious combinations and sub-combinations of the various systems and configurations, and other features, functions, and/or properties disclosed.

[0118] As used in this application, an element or step recited in the singular and preceded with the word “a” or “an” should be understood as not excluding plural of said elements or steps, unless such exclusion is stated. Furthermore, references to “one embodiment” or “one example” of the present disclosure are not intended to be interpreted as excluding the existence of additional embodiments that also incorporate the recited features. The terms “first,” “second,” and “third,” etc. are used merely as labels, and are not intended to impose numerical requirements or a particular positional order on their objects. The following claims particularly point out subject matter from the above disclosure that is regarded as novel and non-obvious.

[0119] It will be appreciated that the configurations and routines disclosed herein are exemplary in nature, and that these specific embodiments are not to be considered in a limiting sense, because numerous variations are possible. Moreover, unless explicitly stated to the contrary, the terms “first,” “second,” “third,” and the like are not intended to denote any order, position, quantity, or importance, but rather are used merely as labels to distinguish one element from another. The subject matter of the present disclosure includes all novel and non-obvious combinations and sub-combinations of the various systems and configurations, and other features, functions, and/or properties disclosed herein.

[0120] As used herein, the term “approximately” is construed to mean plus or minus five percent of the range unless otherwise specified.

[0121] The following claims particularly point out certain combinations and subcombinations regarded as novel and non-obvious. These claims may refer to “an” element or “a first” element or the equivalent thereof. Such claims should be understood to include incorporation of one or more such elements, neither requiring nor excluding two or more such elements. Other combinations and sub-combinations of the disclosed features, functions, elements, and/or properties may be claimed through amendment of the present claims or through presentation of new claims in this or a related application. Such claims, whether broader, narrower, equal, or different in scope to the original claims, also are regarded as included within the subject matter of the present disclosure.

Claims

CLAIMS:

1. A method, comprising: communicating with one or more mobile devices paired to a vehicle; learning, with a model, a plurality of comfort settings associated with the vehicle in the presence of the one or more mobile devices and vehicle occupants; and automatically adjusting the plurality of comfort settings in response to a current set of sensed mobile devices and vehicle occupants correlating with a previous set of sensed mobile devices and vehicle occupants associated with the model.

2. The method of claim 1, wherein the plurality of comfort settings comprises one or more of a seat position, a steering wheel position, a window position, a media volume, a media genre, a media type, a media source, an audio direction, audio settings, a cabin temperature, an air/conditioning setting, a direction and a strength of cabin air flow, a cabin light brightness, and a heated seat setting.

3. The method of claim 1, wherein the one or more mobile devices include devices configured to communicate with the vehicle via a wired or a wireless connection.

4. The method of claim 1, further comprising determining a presence of a vehicle occupant free of a mobile device via one or more of a weight sensor and an in-cabin imaging device.

5. The method of claim 1 , further comprising learning with a new model the plurality of comfort settings associated with the vehicle in response to the current set of sensed mobile devices and vehicle occupants being uncorrelated with a previous set of sensed mobile devices and vehicle occupants.

6. The method of claim 1, further comprising automatically adjusting only a portion of the plurality of comfort settings in response to the current set of identified mobile devices and vehicle occupants partially correlating with a previous set of identified mobile devices and vehicle occupants being associated with the learned model.

33

7. The method of claim 6, wherein the portion of the plurality of comfort settings automatically adjusted are based on comfort settings learned and associated with mobile devices and sensed weight values currently present in the vehicle.

8. The method of claim 1, wherein communicating comprises communicating via Bluetooth.

9. A system, comprising: a vehicle comprising a wireless communication system; and a controller with instructions on memory that when executed cause the controller to: identify a plurality of paired mobile devices via the wireless communication system; sense a plurality of occupant weights via a weight sensor; leam, with a first model, desired comfort settings of the vehicle associated with a first combination of the plurality of mobile devices and the plurality of occupant weights; and automatically apply the desired comfort settings in response to a current combination of mobile devices and occupant weights correlating with the first combination learned with the first model.

10. The system of claim 9, wherein the instructions further cause the controller to leam, with a second model, desired comfort settings of the vehicle associated with the current combination in response to the current combination being uncorrelated with the first combination.

11. The system of claim 9, wherein the current combination comprises a number of mobile devices equal to a number of mobile devices of the first combination, and wherein each of the plurality of occupant weights of the current combination is equal to at least one of the plurality of occupant weights of the first combination.

12. The system of claim 9, wherein the vehicle further comprises an imaging system arranged in a cabin interior.

34

13. The system of claim 12, wherein the instructions further cause the controller to determine an arrangement of vehicle occupants within the cabin interior, and wherein the first model based on the first combination is further based on the arrangement.

14. The system of claim 13, wherein the instructions further cause the controller to generate a second model in response to an arrangement of the vehicle occupants associated with the current combination uncorrelated with the arrangement of vehicle occupants associated with the first combination.

15. The system of claim 9, wherein the instructions further cause the controller to sense a vehicle environment, the vehicle environment comprising one or more of weather, location, road condition, traffic congestion, and estimated travel time.

16. A method for a vehicle, comprising: communicating with one or more mobile devices paired with the vehicle; learning, with a model, a plurality of comfort settings associated with the vehicle in the presence of one or more mobile devices and vehicle occupants; automatically adjusting the plurality of comfort settings in response to a current set of paired mobile devices and vehicle occupants correlating with a previous set of paired mobile devices and vehicle occupants associated with the learned model; and. learning with a new model the plurality of comfort settings associated with the vehicle in response to the current set of paired mobile devices and vehicle occupants being uncorrelated to a previous set of sensed mobile devices and vehicle occupants.

17. The method of claim 16, further comprising partially correlating the current set to one or more previous sets of sensed mobile devices and vehicle occupants, and automatically adjusting a portion of the plurality of comfort settings based on correlated mobile devices included in the current set with the one or more previous sets.

18. The method of claim 17, wherein comfort settings learned with the new model during the partially correlated current set are independent of the learned model of the previous set.

19. The method of claim 16, wherein the one or more mobile devices communicates a MAC address with a communication system of the vehicle.

20. The method of claim 16, wherein automatically adjusting the plurality of comfort settings comprises automatically signaling actuators to adjust one or more of the plurality of comfort settings free of input from a vehicle occupant.