Method for providing control command for controlling at least one occupant setting of seat position of vehicle

Abstract

The present disclosure relates to a method (100) for providing control instructions (CI) for controlling at least one occupant setting (OS) for a seat position (14) in a vehicle (10), a method (200) for generating an occupant setting profile (OSP1, OSP2) for an occupant (1, 2) in a vehicle (10), and a computer program product, a data processing device (20) and a vehicle (10) corresponding thereto.

Description

Technical Field

[0001] The present disclosure relates to a method for providing control instructions for controlling at least one occupant setting for a seat position in a vehicle, a method for generating an occupant setting profile for an occupant in a vehicle, corresponding computer program products and data processing devices, and a vehicle. Background Art

[0002] Occupants of a vehicle spend a great deal of time adjusting different settings (e.g., comfort settings) in the vehicle that are specific to their seating position. While some settings apply only to the driver (e.g., the position of the rearview mirrors), some other settings generally apply to more than one seat (e.g., the front seats or all seats in the vehicle). When an occupant moves from one seat in the vehicle to another in the vehicle, the occupant needs to adjust the settings based on the occupant's personal preferences each time if the occupant wants to experience the same settings. Such adjustments that require manual input from the occupant are time-consuming and cumbersome. Summary of the invention

[0003] This problem is at least partially addressed or alleviated by the subject matter of the present disclosure, further examples of which are included in the present disclosure.

[0004] According to a first aspect of the present disclosure, there is provided a method for providing control instructions for controlling at least one occupant setting for a seat position in a vehicle, comprising:

[0005] - receiving audio data based on speech of an occupant in the vehicle;

[0006] - identifying a seat position of an occupant in the vehicle based on the received audio data;

[0007] - identifying an occupant settings profile of the occupant, in particular indicating one or more occupant settings of the occupant, based on a comparison of the received audio data and stored audio data associated with different occupant settings profiles; and

[0008] - providing control instructions for controlling at least one occupant setting for the identified seat position of the occupant based on the identified occupant setting profile.

[0009] The method can be implemented at least in part by a computer, which means that one, more or all steps of the method can be performed by a computer, and the method can be implemented in software or in hardware, or in software and hardware. In addition, the method can be performed by a computer program instruction running on a component providing a data processing function. The data processing component or device can be a suitable computing component (such as an electronic control module, etc.), which can also be a distributed computer system. The data processing device or computer can include one or more processors, memories, data interfaces, etc., respectively.

[0010] Therefore, when using the method of the first aspect of the present disclosure, one or more occupant settings at the seat position can be conveniently controlled by using control instructions based on the identified occupant setting profile, without the need for the occupant to perform cumbersome and time-consuming manual adjustments. The control instructions can be executed by a corresponding control unit of the vehicle (e.g., a seat position control unit and one or more actuators for adjusting the seat position controlled thereby). For example, it is convenient when an occupant switches seats during a journey with the vehicle or between journeys with the vehicle (i.e., moves from one seat position (e.g., the driver's seat) to another seat position (e.g., the front occupant or in other words, the co-pilot seat). In this case, the occupant does not have to manually adjust the settings of the new seat position to the settings of its previous seat position. Instead, via the method of the first aspect of the present disclosure, adjustments can be made by controlling one or more occupant settings, particularly based on voice and / or automatically.

[0011] The received audio data is based on the speech of the occupant in the vehicle. For example, the occupant's speech may include a single word, multiple words or a complete sentence and / or a monologue or dialogue. The audio data may be recorded by one or more audio recording devices of the vehicle (e.g., such as one or more microphones or one or more microphone arrays). The microphone array may include two or more microphones, which may be arranged at different locations in the vehicle. Therefore, for example, audio data may be received from such one or more audio recording devices.

[0012] The received audio data can be used to identify the seat position of an occupant in the vehicle. This can be done by locating a speech source relative to a known arrangement of one or more audio recording devices and / or a known arrangement of seat positions. For example, when a microphone array is used to record the received audio data, or in other words, if the received audio data is based on recordings from one or more microphone arrays, the direction of sound and / or sound level recorded by the different microphones can be used to determine the seat position of the speaking occupant. For example, when the voice of the speaking occupant is recorded as the highest sound level, it can be determined that the speaking occupant is sitting near the microphone, however, depending on further factors that need to be considered, such as the acoustics of the vehicle interior.

[0013] For the recognition of the seat position, an artificial intelligence (AI) model, in particular a machine learning model (such as a deep learning model), can be used. The AI ​​model can receive audio data as input data and output the recognized seat position as output data. The AI ​​model has been trained with audio data of a specific vehicle, in particular the arrangement of one or more audio recording devices and / or the internal design that defines the acoustic behavior of the vehicle interior, and it can have been verified. For such training, audio data including human natural language with voice and / or language from an audio database can be used. The AI ​​model can be further trained to recognize the seat position by providing the audio data received in the method during use of the method. This can be advantageous because different occupants can say different things at different sound levels (e.g., in different directions), or occupants can speak at the same time, and the AI ​​model can further learn, in particular for the speech of the vehicle occupants, so as to more accurately locate the correct seat position of these occupants in each case.

[0014] The identification of the occupant's occupant setting profile is based on a comparison (particularly matching) of the received audio data and the stored audio data associated with different occupant setting profiles. Therefore, different predetermined occupant setting profiles may exist for different occupants. These different occupant setting profiles may correspond to different preferred or typical profiles of one or more occupant settings of each occupant before riding the vehicle at least once or several times. The occupant setting profile may indicate one or more occupant settings of each occupant before riding the vehicle at least once or several times. Based on the received audio data, the comparison may be used to identify who the occupant is in the identified seat position of the previous occupant. For each of these previous occupants, audio data has been stored and can be used for the method. The stored audio data has been recorded by at least one audio recording device of the vehicle mentioned above and is associated with the occupant setting profile of one or more current occupant settings, which will be explained in more detail below. Therefore, the received audio data (which may be the currently received audio data) can be compared (particularly matched) with the stored audio data (which may be previously received and / or recorded audio data, and may come from different occupants). The comparison can be done by comparing the received audio data with the stored audio data. When comparing the audio data, an attempt can be made to find the best match between the received audio data and the stored audio data, which can be given as a percentage, for example in terms of pronunciation, pronunciation, word usage, etc. Therefore, the method can identify the occupant and the occupant setting profile associated with the occupant based on the stored audio data associated with the occupant setting profile. It should be noted that, although possible, it is not actually required to compare samples of audio recordings or complete audio recordings with each other to match them. For example, the method can be performed in a manner of preprocessing the received and / or stored audio data. For example, the characteristics or features of the speech recognized during the preprocessing of the audio data can be compared with each other to compare (particularly match) the received audio data with the stored audio data. In addition, the method includes providing a control instruction based on the identified occupant setting profile for controlling at least one occupant setting of the identified seat position of the occupant. The method can also include at least one occupant setting for controlling the identified seat position of the occupant based on the provided control instruction.

[0015] The control instructions may be determined on an individual basis (e.g., based on an individual occupant settings profile and / or current circumstances), or may be predetermined for each identified occupant settings profile. For example, when an occupant settings profile includes an air cabin temperature setting, but a window of a corresponding seat position is open, on an individual basis, the current circumstances that the window is open may be used to determine a control instruction not to control the air cabin temperature for efficiency purposes. However, when the control instructions are predetermined, the air cabin temperature setting may be adjusted according to the occupant settings profile despite the window being open.

[0016] In general, the method can be used to provide more than one control instruction. For example, the method can be used to provide some control instructions for controlling at least one occupant setting for a plurality of (particularly all) seat positions in the vehicle. In addition, the method can also be used to control a plurality of occupant settings that are different from each other, and a more detailed exemplary explanation will be given later.

[0017] In one example, the method may further include requesting confirmation from the occupant prior to providing the control instruction. Additionally, the control instruction may be provided after receiving confirmation from the occupant. The confirmation request may be an audio command request and / or a visual command request (e.g., on a display or the like). Thus, providing one or more identified occupant settings that may correspond to the occupant's preferred settings may be avoided in situations where the occupant wants to use other settings that differ from the occupant's generally preferred settings (e.g., for different seat positions or based on different situations).

[0018] In one example, confirmation may be requested when current occupant settings do not correspond to an identified occupant settings profile. For example, confirmation may be requested when at least one current occupant setting does not correspond to an occupant setting in an identified occupant settings profile (e.g., when cabin temperature settings as occupant settings do not correspond to each other (e.g., are not the same)). This is the case, for example, when a seat position is changed by an occupant. However, when the seat position is not changed, unnecessary requests may be avoided.

[0019] In one example, the comparison may include using an artificial intelligence model trained to match the received audio data with the stored audio data. The stored audio data may be based on at least one sound dataset and the received audio data. The at least one sound dataset may be a generic sound dataset covering different speakers and / or languages. The AI ​​model may be pre-trained with at least one sound dataset and may be trained with the received audio data during execution of the method to improve the accuracy of the match. For example, the AI ​​model may be a machine learning model, in particular a deep learning model.

[0020] In one example, the stored audio data may include an audio profile for an occupant generated by an artificial intelligence model. Thus, the AI ​​model can also be used to generate audio profiles from the stored audio data for different occupants, rather than comparing the corresponding audio data with each other in each case. An audio profile may be data characterizing the speech (in particular the sound) of the occupant, such as sound level, pronunciation, etc., but also word usage and the like, and is therefore a profile based on which the AI ​​model can quickly match the received audio data with the sound data of different occupants and the occupant setting profiles associated therewith. For example, an audio profile may be a sound profile associated with the voice of an occupant.

[0021] In one example, the received audio data may be based on a conversation between two or more occupants in a vehicle. The conversation may be a monologue, a two-party conversation, a three-party conversation, etc. In other words, the audio data may be based on natural speech, rather than keyword speech or command speech directed to, or in other words, intended to control vehicle settings. This allows the occupant setting control described herein to be implemented without the vehicle recognizing any keywords or commands, which many occupants tend not to use or the vehicle cannot correctly recognize, in which case the occupant needs to repeat. Using audio data based on the occupant's natural conversation, there is no need to repeat keywords or commands, even if the vehicle may not immediately recognize the occupant setting profile when the corresponding occupant speaks (e.g., the voice is too quiet to be recognized).

[0022] In one example, identification of the seat position of an occupant may include signal processing of the received audio data. For example, as explained above, when a microphone array is used to record the received audio data, or in other words, if the received audio data is based on recordings from one or more microphone arrays, the directions of articulation and / or sound levels recorded by the different microphones may be used to determine the seat position of the speaking occupant. In order to determine the directions of articulation and / or sound levels, signal processing may be applied to the audio data (e.g., determining high sound levels, low sound levels, average sound levels, directions of articulation, etc.), which thereby improves the accuracy with which the seat position may be identified.

[0023] In one example, the control instructions may be configured to control at least one comfort setting for the identified seat position. The at least one comfort setting may relate to adjusting the comfort of an occupant at the seat position.

[0024] In one example, at least one comfort setting may include at least one of: a temperature setting, an pronunciation setting, and a seat position. For example, the temperature setting may be a cabin temperature setting (particularly for the corresponding seat position), for example via one or more air ducts directed toward or towards the seat position or an occupant at the seat position. For example, the pronunciation setting may be a speaker sound level of one or more speaker pronunciations directed toward or towards an occupant at or near the seat position. The seat position may include one or more positions of several parts of the seat (such as the relative position of the seat in the vehicle cabin, the seat height, the backrest tilt angle, the headrest position, and / or the like). Further optional comfort settings may relate to display settings of one or more displays located toward or towards the occupant at or near the seat position (e.g., display on or off, display brightness, or window open or closed, sunroof open or closed, etc.).

[0025] In one example, the control instructions may be configured to control at least one driver setting for a driver's seat position that is an identified seat position. At least one further control instruction may be an addition or replacement for the exemplary control instructions described above. For the driver's seat position, there are more available settings than for a passenger seat position where the occupant is a passenger. The settings for the driver's seat position are referred to herein as driver settings, i.e., those related to the driving of the vehicle. Such driver settings may be the position and / or angle of the steering wheel, the position and / or angle of one or more mirrors (e.g., side mirrors), driving mode selection (e.g., sport or economy driving mode), etc.

[0026] According to a second aspect, there is provided a method for generating an occupant settings profile for an occupant in a vehicle, the method comprising:

[0027] - receiving audio data based on speech of an occupant in the vehicle;

[0028] - identifying a seat position of an occupant in the vehicle based on the received audio data; and

[0029] - generating an occupant settings profile associated with the received audio data, in particular indicating one or more occupant settings of the occupant, based on at least one current occupant setting in the identified seat position.

[0030] Therefore, the method of the second aspect is to generate the occupant setting profile identified in the method of the first aspect of the present disclosure. By using the method of the second aspect, the received occupant audio data can be conveniently associated with the occupant setting profile based on the occupant's voice. In other words, the occupant setting profile can be conveniently mapped to the occupant, in particular his or her way of speaking (e.g., the occupant's voice). This avoids the occupant having to manually set his or her setting profile. Instead, the generation of the occupant setting profile can be an automatic and seamless process.

[0031] The received audio data may be stored and form stored audio data. Therefore, in the method of the first aspect of the present disclosure, the received audio data may be used as stored audio data. In addition, the received audio data as stored audio data may also include an audio profile of the occupant generated by the artificial intelligence model, which may adopt the method as described in relation to the first aspect of the present disclosure.

[0032] In addition, the method of the second aspect of the present disclosure may include the step of generating at least one control instruction for controlling at least one occupant setting of the identified seat position of the occupant based on the generated occupant setting profile. Therefore, the method of the first aspect may provide the control instruction. The at least one control instruction may be configured as described with respect to the first aspect of the present disclosure, for example, for controlling at least one comfort setting of the identified seat position, wherein the at least one comfort setting may include at least one of the following: a temperature setting, a pronunciation setting, and a seat position, and / or for controlling at least one driver setting of the driver's seat position as the identified seat position.

[0033] In one example, the generation of the occupant settings profile may include using an artificial intelligence model for processing audio data to generate an audio profile for the occupant, and for associating the occupant settings profile with the generated occupant audio profile. The audio profile may correspond to the audio profile described above with respect to the method of the first aspect of the present disclosure.

[0034] In addition, any of the above aspects or examples explained with reference to the method of the first aspect may be applied to the method of the second aspect, and vice versa. For example, the audio data may be based on a conversation between two or more occupants in a vehicle, as explained with reference to the method of the first aspect of the present disclosure, which may also be the case with the method of the second aspect of the present disclosure. In addition, the two methods may be combined. Specifically, any steps of the two methods may be combined with each other.

[0035] According to a third aspect of the present disclosure, a computer program product is provided, comprising instructions, wherein when the program is executed by a computer, the instructions cause the computer to perform the method of the first aspect of the present disclosure and / or the method of the second aspect of the present disclosure. The computer program product may be a computer program, in particular in itself, or a product containing a computer program (e.g., a computer-readable medium having a computer program stored thereon).

[0036] According to a fourth aspect, a data processing device is provided, comprising a component for executing the method of the first aspect of the present disclosure and / or the method of the second aspect of the present disclosure. The data processing device may include one or more modules for executing the steps of the method described herein. For example, each step may be performed by a corresponding module of the data processing device. For example, each module may be implemented as hardware and / or software.

[0037] According to a fifth aspect, a vehicle comprising the data processing device of the fourth aspect of the present disclosure is provided.

[0038] It should be noted that the above examples can be combined with each other, regardless of the aspects involved. Thus, the methods can be combined with structural features, and likewise, the computer program product, the apparatus and the vehicle can be combined with the features described above with respect to the methods.

[0039] These and other aspects of the disclosure will be apparent from and elucidated with reference to the examples described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Examples of the present disclosure will be described below with reference to the accompanying drawings.

[0041] Figure 1 A schematic diagram showing the steps of a first method of the present disclosure;

[0042] Figure 2 A schematic diagram showing the steps of a second method of the present disclosure;

[0043] Figure 3 Shown by Figure 2 A schematic diagram of an occupant setting profile generated by a second method;

[0044] Figure 4 Shows the use of Figure 2 a schematic diagram of a vehicle of the second method; and

[0045] Figure 5 The use of the vehicle after an occupant of the vehicle changes the seat position within the vehicle is shown. Figure 1 The first method Figure 4 Schematic diagram of a vehicle. DETAILED DESCRIPTION

[0046] The accompanying drawings are merely schematic diagrams and are only used to illustrate examples of the present disclosure. The same or equivalent elements are in principle provided with the same reference numerals.

[0047] Figure 1 A method for providing control of a vehicle 10 (see Figure 4 and Figure 5 ) is a schematic diagram of a method 100 for setting control instructions CI of an OS for at least one occupant in a seat position 14 . Figure 2 A method 200 of generating an occupant settings profile OSP for an occupant 1 , 2 in a vehicle 20 is shown.

[0048] like Figure 4 and Figure 5 As shown, the vehicle 10 includes a cabin 12, in which occupants 1, 2 are seated in corresponding seat positions 14, which can be in the form of corresponding vehicle seats. In this example, the vehicle 10 is a passenger car. The passenger car in this example has five seat positions, of which only the two front passenger seats or seat positions 14 are occupied by the first occupant 1 and the second occupant 2.

[0049] The vehicle 10 includes a plurality of audio recording devices 18 (which may include microphones, for example) within the cabin 12. In this example, two audio recording devices 18 are provided within the cabin 12 and at different locations within the cabin 12. By way of example only, the audio recording devices 18 are located at the front of the cabin 12. Of course, the vehicle 10 may include more audio recording devices 18, and these devices may be located at various locations. Figure 4 and Figure 5 The examples shown are in different locations.

[0050] like Figure 5 As shown, the audio recording device 18 is connected to a data processing device 20, which is further connected to a control system for controlling the occupant settings OS (see Figure 3 ) of the control unit 16. Alternatively, there may be more than one control unit 16. Still alternatively, the data processing device 20 and the control unit 16 may be combined in one device. Specifically, the data processing device 20 may be configured to control the occupant to set the OS without using the control unit 16.

[0051] The data processing device 20 may include a processor and / or a computer program product. The computer program product may include instructions that, when executed by the processor, execute Figure 1 Method 100 and / or Figure 2 Method 200, as further explained below.

[0052] References in this article Figure 4In step 202 of the illustrated method 200 , speech 3 of the occupants 1 , 2 in the cabin 12 is recorded as audio data by the audio recording device 18 in the form of a conversation between the occupants 1 , 2 .

[0053] In step 204 of the method 200, the audio data recorded in step 202 is received as received audio data RAD by the data processing apparatus 20. Thus, the received audio data RAD may be sent to the data processing apparatus 20 (eg, by the audio recording device 18).

[0054] In step 206 of the method 200, the seat positions 14 of the occupants 1, 2 are identified based on the received audio data RAD. This can be done by signal processing of the received audio data RAD. For example, based on the received audio data RAD, it can be established by signal processing that the first occupant 1 is closer to the second occupant 2. Figure 4 The left audio recording assembly 18 of the vehicle 10 is located closer to the second passenger 2. Figure 4 The audio recording assembly 18 is located in the middle right side. Based on the signal processing, it can also be confirmed that the voice 3 does not come from any rear seat position 14 (e.g., based on the sound level of the voice 3). Thus, the method 200 can confirm that the first occupant 1 is seated in the left front seat position 14, and the second occupant 2 is seated in the right front seat position 14.

[0055] In step 208 of the method 200, an occupant setting profile OSP(1), OSP(2) is associated with the received audio data RAD for each occupant 1, 2 based on at least one current occupant setting OS at or for the identified seat position 14. Such one or more occupant settings OS may be set manually by the occupant 1, 2, for example.

[0056] from Figure 3 It can be seen that the occupant settings profile OSP may include a number of different occupant settings OS(1), OS(2) and OS(3), three of which are shown here as examples. The three different occupant settings OS(1), OS(2) and OS(3) may be comfort settings (e.g. temperature settings, sound settings and seat positions). The different occupant settings OS(1), OS(2) and OS(3) are Figure 4 and Figure 5 An occupant setup profile OSP is defined for each of the two front passenger seat positions 14 .

[0057] In step 210 of the method 200, the received audio data RAD may be stored as stored audio data SAD on a computer-readable storage medium, such as the data processing device 20. For example, the stored audio data SAD may include an audio profile generated for each of the occupants 1, 2, the audio profile being associated with the occupant setting profile OSP(1), OSP(2).

[0058] After executing method 200, if Figure 5 As shown, when the occupants 1, 2 change the seat position 14, the method 100 may be performed, and now referring to Figure 1 and Figure 5 Provide explanation.

[0059] In step 102 of the method 100 , speech 3 of the occupants 1 , 2 in the cabin 12 is recorded as audio data by the audio recording device 18 in the form of a conversation between the occupants 1 , 2 .

[0060] In step 104 of the method 100, the audio data recorded in step 202 is received as received audio data RAD by the data processing device 20. Thus, the received audio data RAD may be sent to the data processing device 20 (eg, by the audio recording component 18).

[0061] In step 106 of method 100, the occupant setting profiles OSP(1), OSP(2) of occupants 1, 2 are identified based on a comparison (in particular a match) of the received audio data RAD with stored audio data SAD from a previous audio data recording, the stored audio data SAD having been associated with different occupant setting profiles OSP(1), OSP(2) by method 200. Thus, based on the received audio data RAD, it is discerned whether occupant 1 or occupant 2 is seated in the vehicle. Figure 5 The left front seat position 14 and whether passenger 1 or passenger 2 is seated in Figure 5 14 in the right front seat position 14. Thus, it can be determined that the occupants 1, 2 switched the seat positions 14. However, the occupant setting OS at each seat position 14 may still be the same as before the seat position 14 was changed. This may make each occupant 1, 2 uncomfortable, requiring each occupant to manually change the occupant setting OS.

[0062] In step 108 of method 100 , when one or more occupant settings OS at the seat position 14 of occupants 1 , 2 are different from the identified occupant settings profiles OSP( 1 ), OSP( 2 ), confirmation of changing one or more occupant settings OS at their seat position 14 is requested from occupants 1 , 2 .

[0063] Once the occupant 1, 2 confirms the change of one or more occupant settings OS, in step 110 of the method 100, one or more control instructions CI are provided, which control one or more occupant settings OS of the identified seat position 14 of the occupant 1, 2 based on the identified occupant settings profiles OSP(1), OSP(2) of the occupant 1, 2. Figure 5 In the example of , control instructions CI are provided to one or more control units 16, which, when executed at the seat position 14, can adjust the temperature settings, pronunciation settings (e.g., sound level), and seat position (e.g., seat height) in the cabin.

[0064] Thus, the method 100 may provide for a convenient change of the occupant setting profiles OSP(1), OSP(2) when the occupant 1, 2 changes the seat position 14 and the previous occupant setting OS from the previous occupant 1, 2 does not correspond to the preferences of the new occupant 1, 2 at the seat position 14 according to the personal occupant setting profiles OSP(1), OSP(2) of the new occupant 1, 2. Of course, the change of the seat position 14 is only an example and the methods 100, 200 may of course involve more than two occupants 1, 2, more than two occupant setting profiles OSP(1), OSP(2) and different seat positions 14 in the vehicle 10.

[0065] As used herein, the phrase "at least one" when referring to a list of one or more entities should be understood to mean at least one entity selected from any one or more entities in the list of entities, but does not necessarily include at least one of each entity specifically listed in the list of entities, nor does it exclude any combination of entities in the list of entities. This definition also allows that entities may optionally exist in addition to the entities specifically identified in the list of entities referred to by the phrase "at least one", whether these specifically identified entities are related or unrelated. Thus, as a non-limiting example, "at least one of A and B" (or equivalently, "at least one of A or B", or equivalently, "at least one of A and / or B") may refer to at least one (optionally including more than one) A, and not including B (and optionally including entities other than B); in another example, may refer to at least one (optionally including more than one) B, and not including A (and optionally including entities other than A); in another example, means at least one (optionally including more than one) A, and at least one (optionally including more than one) B, and optionally including other entities. In other words, the phrases "at least one", "one or more", and "and / or" are open-ended expressions that are both conjunctions and antonyms in operation. For example, each of the expressions "at least one of A, B, and C", "at least one of A, B, or C", "one or more of A, B, and C", "one or more of A, B, or C", and "A, B and / or C" may represent A alone, B alone, C alone, A and B together, A and C together, B and C together, A, B, and C together, and optionally any of the foregoing in combination with at least one other entity.

[0066] Those skilled in the art can understand and implement other variations of the disclosed examples by studying the drawings and the disclosed contents when practicing the disclosed contents claimed for protection. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "one" or "an" does not exclude a plurality. A single processor or other unit can implement the functions of multiple items or steps. The fact of certain measures does not indicate that the combination of these measures cannot be fully utilized. The computer program can be stored / distributed on a suitable medium (such as an optical storage medium or solid-state medium provided with other hardware or as part of other hardware), but can also be distributed in other forms (such as via the Internet or other wired or wireless telecommunications systems). Any figure mark should not be interpreted as limiting the scope of the present disclosure.

[0067] Reference numerals list

[0068] 1,2 crew

[0069] 3 Voice

[0070] 10 Vehicles

[0071] 12 Cockpit

[0072] 14 Seat Position

[0073] 16 Control Unit

[0074] 18 Audio Recording Equipment

[0075] 20 Data processing device

[0076] 100 First Method

[0077] Steps 102-110

[0078] 200 Second Method

[0079] Steps 202-210

[0080] CI Control Instructions

[0081] OSP Crew Settings Profile

[0082] OS Crew Settings

[0083] Audio data received by the RAD

[0084] Audio data stored in SAD

Claims

1. A method (100) for providing a control instruction (CI) for controlling at least one occupant setting (OS) for a seat position (14) in a vehicle (10), the method (100) comprising: - receiving audio data (RAD) based on speech of an occupant (1, 2) in the vehicle (10); - identifying a seat position (14) of an occupant (1, 2) in the vehicle (10) based on the received audio data (RAD); - identifying an occupant setting profile (OSP) indicative of one or more occupant settings of said occupant (1, 2) based on a comparison of said received audio data (RAD) and stored audio data (SAD) associated with different occupant setting profiles (OSP); and - providing said control instructions (CI) for controlling said at least one occupant setting (OS) of said occupant (1, 2) in said identified seat position (14) based on said identified occupant setting profile (OSP).

2. The method (100) according to claim 1, further comprising requesting a confirmation from the occupant (1, 2) before providing the control instruction (CI).

3. The method (100) of claim 2, requesting the confirmation when a current occupant setting (OS) does not correspond to the identified occupant setting profile (OSP).

4. The method (100) of claim 1, wherein the comparing comprises using an artificial intelligence model trained to match the received audio data (RAD) with the stored audio data (SAD).

5. The method (100) of claim 4, the stored audio data (SAD) comprising an audio profile of the occupant (1, 2) generated by the artificial intelligence model.

6. The method (100) of claim 1, the received audio data (RAD) being based on a conversation between two or more occupants (1, 2) in the vehicle (10).

7. The method (100) of claim 1, the identification of the seat position (14) of the occupant (1, 2) comprising signal processing of the received audio data (RAD).

8. The method (100) of claim 1, the control instructions (CI) being configured for controlling at least one comfort setting for the identified seat position (14).

9. The method (100) of claim 8, wherein the at least one comfort setting comprises at least one of: Temperature settings, pronunciation settings and seat positions.

10. The method (100) according to any one of the preceding claims, the control instructions (CI) being configured for controlling at least one driver setting of a driver's seat position being the identified seat position (14).

11. A method (200) for generating an occupant setup profile (OSP) for an occupant (1, 2) in a vehicle (10), the method (200) comprising: - receiving audio data (RAD) based on speech of an occupant (1, 2) in the vehicle (10); - identifying a seat position (14) of the occupant (1, 2) in the vehicle (10) based on the received audio data (RAD); and - generating an occupant settings profile (OSP) associated with said received audio data (RAD) based on at least one current occupant settings (OS) at the identified seat position (14).

12. The method (200) according to claim 11, the generating of the occupant setting profile (OSP) comprising using an artificial intelligence model for processing the received audio data (RAD) to generate an audio profile of the occupant (1, 2), and for associating the occupant setting profile (OSP) with the generated audio profile of the occupant (1, 2).

13. A computer program product comprising instructions, wherein when the program is executed by a computer, the instructions cause the computer to perform the method (100) according to any one of claims 1-10 and / or the method (200) according to any one of claims 11-12.

14. A data processing device (20), comprising components for executing the method (100) of any one of claims 1-10 and / or the method (200) of any one of claims 11-12.

15. A vehicle (10) comprising a data processing device (20) as claimed in claim 14.

Images