Scent selection system, vehicle comprising a scent device of a scent selection system and method to operate a vehicle

Abstract

A scent selection system 10 comprising a scent device 12 for a vehicle 14. Comprising a control unit 16 configured to: receive vehicle operation data, recorded during an operation of the vehicle by a specific driver. Classify the vehicle operation data using a first machine learning model 22 into predefined emotion categories, wherein the emotion categories are associated with respective emotional states of the specific driver during the operation of the vehicle. Classify the vehicle operation data of a predefined emotion category using a second machine learning model 24 into predefined fragrance categories, wherein the fragrance categories are associated with respective fragrance identities associated with the vehicle operation data of the predefined emotion category; associate the fragrance identity of a specific fragrance category with the specific driver. Control the fragrance injector unit to inject the specified scent into the cabin.

Description

FIELD OF THE INVENTION

[0001] The present invention relates to the field of automobiles. More specifically, the present invention relates to a scent selection system, a vehicle comprising a scent device of a scent selection system and a method to operate a vehicle comprising a scent device of a scent selection system. BACKGROUND INFORMATION

[0002] Smell is one of the strongest senses linked to emotions. So far the sense of smell is hardly used in personal vehicles. By taking advantage of the sense of smell it may be possible to provide outstanding customer experience. SUMMARY OF THE INVENTION

[0003] It is an object of the present invention to provide a scent selection system, a corresponding vehicle comprising a scent device of a scent selection system, as well as the corresponding method to select a smell to be provided to a driver of a vehicle.

[0004] This object is solved by the scent selection system, the corresponding vehicle comprising a scent device of a scent selection system, as well as the corresponding method according to the independent claims. Advantageous embodiments are presented in the dependent claims.

[0005] A first aspect of the present invention is related to a scent selection system. The scent selection system comprises a scent device for a vehicle comprising a control unit. The control unit is configured to receive vehicle operation data of the vehicle, recorded during an operation of the vehicle by a specific driver.

[0006] The control unit is configured to classify the vehicle operation data using a first machine learning model into predefined emotion categories, wherein the emotion categories are associated with respective emotional states of the specific driver during the operation of the vehicle.

[0007] The control unit is configured to classify the vehicle operation data of a predefined emotion category using a second machine learning model into predefined fragrance categories, wherein the fragrance categories are associated with respective fragrance identities associated with the vehicle operation data of the predefined emotion category.

[0008] The control unit is configured to associate the fragrance identity of a specific fragrance category with the specific driver.

[0009] The control unit is configured to control a fragrance injector unit of the scent device to inject a scent related to the fragrance identity associated with the specific driver into a cabin of the vehicle, when the control unit detects the specific driver in the cabin of the vehicle and a predefined condition is fulfilled.

[0010] According to an embodiment of the invention, the control unit is configured to receive the first machine learning model and / or the second machine learning model from a backend device of the scent selection system external to the vehicle.

[0011] According to an embodiment of the invention, the control unit is configured to provide the association of the fragrance identity with the specific driver to the backend device and / or to receive the association of the fragrance identity with the specific driver from the backend device.

[0012] According to an embodiment of the invention, the control unit is configured to provide the respective fragrance identities associated with the vehicle operation data of the predefined emotion category to the backend device.

[0013] The backend device is configured to receive the respective fragrance identities associated with the vehicle operation data of the predefined emotion category; and to provide scent formula data for producing the scent of the respective fragrance identity

[0014] According to an embodiment of the invention, the predefined condition comprises a detected specific emotion state of the specific driver.

[0015] According to an embodiment of the invention, the vehicle operation data comprise driver camera images showing the driver during the operation the vehicle.

[0016] According to an embodiment of the invention, the vehicle operation data comprise environment camera images showing an environment of the vehicle during the operation the vehicle.

[0017] A second aspect of the present invention is related to a vehicle comprising a scent device of a scent selection system. The scent device comprises a control unit and a fragrance injector unit.

[0018] A third aspect of the present invention is related to a method to operate a vehicle comprising a scent device of a scent selection system. The scent device comprises a control unit and a fragrance injector unit.

[0019] The method comprises the following steps performed by a control unit of the scent device.

[0020] The method comprises a step of receiving vehicle operation data of the vehicle, recorded during an operation of the vehicle by a specific driver.

[0021] The method comprises a step of classifying the vehicle operation data using a first machine learning model into predefined emotion categories, wherein the emotion categories are associated with respective emotional states of the specific driver during the operation of the vehicle.

[0022] The method comprises a step of classifying the vehicle operation data of a predefined emotion category using a second machine learning model into predefined fragrance categories, wherein the fragrance categories are associated with respective fragrance identities associated with the vehicle operation data of the predefined emotion category.

[0023] The method comprises a step of associating the fragrance identity of a specific fragrance category with the specific driver; and

[0024] The method comprises a step of controlling a fragrance injector unit of the scent device to inject a scent related to the fragrance identity associated with the specific driver into a cabin of the vehicle, when the control unit detects the specific driver in the cabin of the vehicle and a predefined condition is fulfilled.

[0025] The control unit may comprise a computing unit / electronic computing device. The computing unit may in particular be understood as a data processing device, which comprises processing circuitry. The computing unit can therefore in particular process data to perform computing operations. This may also include operations to perform indexed accesses to a data structure, for example a look-up table, LUT.

[0026] In particular, the computing unit may include one or more computers, one or more microcontrollers, and / or one or more integrated circuits, for example, one or more application-specific integrated circuits, ASIC, one or more field-programmable gate arrays, FPGA, and / or one or more systems on a chip, SoC. The computing unit may also include one or more processors, for example one or more microprocessors, one or more central processing units, CPU, one or more graphics processing units, GPU, and / or one or more signal processors, in particular one or more digital signal processors, DSP. The computing unit may also include a physical or a virtual cluster of computers or other of said units.

[0027] In various embodiments, the computing unit includes one or more hardware and / or software interfaces and / or one or more memory units.

[0028] A memory unit may be implemented as a volatile data memory, for example a dynamic random access memory, DRAM, or a static random access memory, SRAM, or as a non-volatile data memory, for example a read-only memory, ROM, a programmable read-only memory, PROM, an erasable programmable read-only memory, EPROM, an electrically erasable programmable read-only memory, EEPROM, a flash memory or flash EEPROM, a ferroelectric random access memory, FRAM, a magnetoresistive random access memory, MRAM, or a phase-change random access memory, PCRAM.

[0029] Further advantages, features, and details of the invention derive from the following description of preferred embodiments as well as from the drawings. The features and feature combinations previously mentioned in the description as well as the features and feature combinations mentioned in the following description of the figures and / or shown in the figures alone can be employed not only in the respectively indicated combination but also in any other combination or taken alone without leaving the scope of the invention.

[0030] A model can be understood as a software code or a compilation of several software code components, wherein the software code may comprise several software modules for different functions, for example one or more encoder modules and one or more decoder modules.

[0031] An artificial neural network can be understood as a non-linear model or algorithm that maps an input to an output, wherein the input is given by an input feature vector or an input sequence and the output may be an output category for a classification task or a predicted sequence.

[0032] Further advantages, features, and details of the invention derive from the following description of preferred embodiments as well as from the drawings. The features and feature combinations previously mentioned in the description as well as the features and feature combinations mentioned in the following description of the figures and / or shown in the figures alone can be employed not only in the respectively indicated combination but also in any other combination or taken alone without leaving the scope of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The novel features and characteristic of the disclosure are set forth in the appended claims. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and together with the description, serve to explain the disclosed principles. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the figures to reference like features and components. Some embodiments of system and / or methods in accordance with embodiments of the present subject matter are now described below, by way of example only, and with reference to the accompanying figures.

[0034] The drawings show in:

[0035] Fig. 1 a schematic illustration of a method to operate a scent selection system; and

[0036] Fig. 2 a schematic illustration of a scent selection system.

[0037] In the figures the same elements or elements having the same function are indicated by the same reference signs. DETAILED DESCRIPTION

[0038] In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration". Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

[0039] While the disclosure is susceptible to various modifications and alternative forms, specific embodiments thereof have been shown by way of example in the drawing and will be described in detail below. It should be understood, however, that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternatives falling within the scope of the disclosure.

[0040] The terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion so that a setup, device or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus preceded by “comprises” or “comprise” does not or do not, without more constraints, preclude the existence of other elements or additional elements in the system or method.

[0041] In the following detailed description of the embodiment of the disclosure, reference is made to the accompanying drawing that forms part hereof, and in which is shown by way of illustration a specific embodiment in which the disclosure may be practiced. This embodiment is described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.

[0042] Fig. 1 shows a schematic illustration of a method to operate a scent selection system 10.

[0043] Step S1 comprises a collecting of vehicle operation data during an operation of a vehicle 14. A specific driver may operate the vehicle 14.

[0044] During the operation of the vehicle 14, a driver camera device 26 in the vehicle 14 may record driver camera images S2. The driver camera device 26 may be directed to the driver. The driver camera device 26 may provide the vehicle operation data comprising the driver camera images of the driver to a control unit 16 of a scent device 12 of the scent selection system 10 inside the vehicle 14.

[0045] During the operation of the vehicle 14, a vehicle 14 device in the vehicle 14 may record telematic data related to the operation of the vehicle 14 S3. The telematic data may comprise telematic settings, radio settings and / or settings of a navigation device of the vehicle 14. The vehicle 14 device may provide the vehicle operation data comprising the telematic data to the control unit 16 of the scent device 12 inside the vehicle 14.

[0046] During the operation of the vehicle 14, a vehicle 14 control device in the vehicle 14 may record vehicle 14 driving data related to the driving of the vehicle 14 S4. The vehicle 14 driving data may comprise driving settings like a gear state, a speed and / or an acceleration of the vehicle 14. The vehicle 14 control device may provide the vehicle operation data comprising the vehicle 14 driving data to the control unit 16 of the scent device 12 inside the vehicle 14.

[0047] In a step S5, the control unit 16 of the scent device 12 inside the vehicle 14 may extract features of the vehicle operation data, using a first machine learning model 22. The first machine learning model 22 may be provided to the control unit 16 by a backend device 20 of the scent selection system 10. The first machine learning model 22 may be trained by the backend device 20 to extract predefined features of the vehicle operation data.

[0048] In a step S6, the control unit 16 of the scent device 12 inside the vehicle 14 may classify the vehicle operation data using a first machine learning model 22 into predefined emotion categories, wherein the emotion categories are associated with respective emotional states of the specific driver during the operation of the vehicle 14. In particular, the features extracted from the driver camera images may be used to categorize the vehicle 14 operating data. The features extracted from the driver camera images may allow a determination of a state of emotion of the specific driver during the operation of the vehicle 14.

[0049] In a step S7 the control unit 16 may check, whether the vehicle operation data are categorized in a specific emotion category.

[0050] If the specific emotion category comprises the vehicle operation data, the respective vehicle operation data may be stored in the control unit 16 in a step S8.

[0051] In a step S9, the control unit 16 may classify the vehicle operation data of the predefined emotion category using a second machine learning model 24 into predefined fragrance categories, wherein the fragrance categories are associated with respective fragrance identities associated with the vehicle operation data of the predefined emotion category. The second machine learning model 24 may be trained by the backend device 20 to extract predefined fragrance identities of the vehicle operation data.

[0052] In a step S10, the control unit 16 may associate the fragrance identity of a specific fragrance category with the specific driver; and

[0053] In a step S11, the control unit 16 may control a fragrance injector unit 18 of the scent device 12 to inject a scent related to the fragrance identity associated with the specific driver into a cabin of the vehicle 14, when the control unit 16 detects the specific driver in the cabin of the vehicle 14 and a predefined condition is fulfilled.

[0054] Fig. 2 shows a schematic illustration of a scent selection system 10.

[0055] The scent selection system 10 may comprise a scent device 12 for a vehicle 14 comprising a control unit 16.

[0056] The control unit 16 may be configured to receive vehicle operation data of the vehicle 14, recorded during an operation of the vehicle 14 by a specific driver. The vehicle operation data may be recorded by a vehicle 14 device, a vehicle 14 control device and / or a driver camera device 26. The driver camera device 26 may be configured to collect the vehicle operation data from monitoring driver’s face. A telematics ECUs of the vehicle 14 device may collect vehicle operation data of telematics settings, like a state of an air conditioning system of the vehicle 14. The vehicle 14 control device may collect vehicle operation data of the current driving style of the driver.

[0057] The control unit 16 may be configured to classify the vehicle operation data using a first machine learning model 22 into predefined emotion categories, wherein the emotion categories are associated with respective emotional states of the specific driver during the operation of the vehicle 14.

[0058] The control unit 16 may be configured to classify the vehicle operation data of a predefined emotion category using a second machine learning model 24 into predefined fragrance categories, wherein the fragrance categories are associated with respective fragrance identities associated with the vehicle operation data of the predefined emotion category.

[0059] The control unit 16 may be configured to associate the fragrance identity of a specific fragrance category with the specific driver; and to control a fragrance injector unit 18 of the scent device 12 to inject a scent related to the fragrance identity associated with the specific driver into a cabin of the vehicle 14, when the control unit 16 detects the specific driver in the cabin of the vehicle 14 and a predefined condition is fulfilled.

[0060] Therefore the control unit 16 may need the two machine learning models.

[0061] The first machine learning model 22 may be trained for emotion classification. The second machine learning model 24 may be configured for a determination of “categories that driver enjoys and can be associated to a scent.

[0062] The control unit 16 may be configured to collects and store all vehicle operation data for training the machine learning models. The machine learning models may get trained on the backend device 20. The machine learning models may run on the control unit 16. Output of the second the machine learning model may give “categories that customer enjoys and scent can be derived from” and may be sent to the backend device 20.

[0063] The scent may be stored in a container of the fragrance injector unit 18. The container may be connected to a nozzle. The fragrance injector unit 18 may be controlled to spray the scent of the fragrance identity once the specific driver enters the vehicle 14. The scent selection system 10 may comprise a backend device 20. The backend device 20 may be configured to train the first machine learning model 22 and / or the second machine learning model 24 and to provide the models to the control device of the scent device 12. The backend device 20 may be used as a Cloud storage and / or production device. Output of second machine learning model 24 may be a list of “categories that customer enjoys and scent can be derived from” and is sent to backend device 20. The list may include a confidence for each item. A list item with the highest confidence may be selected. A scent that may get associated with that item may be created

[0064] In the vehicle 14 comprising a scent device 12 of the scent selection system 10 vehicle 14, a first model learns from available user data for this particular vehicle 14 what factors improve a driver’s emotions or make the driver happy. Input data ,ay comprise driver camera images, telematics data e.g. radio, AC,..., and / or data related to a driving style.

[0065] The input data may be personalized for each driver. Based on this “positive things category” the scent selection system 10 may create and spray a fragrance that the driver associates to those positive things / circumstances. The scent may generate Positive / happy associations of the driver to the vehicle 14.

[0066] The control unit 16 may be configured to detect when the driver is in a positive mood.

[0067] During a “Training period” the control unit 16 may control the fragrance injector unit 18 to inject a spray comprising a fragrance very subtly. The fragrance may be a generic scent that’s proven to be liked by overall population, every time occupant is in positive mood. In this way, the driver may create an even stronger positive association with this particular scent. The above step may be repeated a defined number of times. After a defined "training period", this specific scent may be used to change the mood of the drivers. signs scent selection system scent device vehicle control unit fragrance injector unit backend device first machine learning model second machine learning model driver camera device vehicle device vehicle control device

Claims

1. A scent selection system (10) comprisinga scent device (12) for a vehicle (14) comprising a control unit (16) configured to:- receive vehicle operation data of the vehicle (14), recorded during an operation of the vehicle (14) by a specific driver;- classify the vehicle operation data using a first machine learning model (22) into predefined emotion categories, wherein the emotion categories are associated with respective emotional states of the specific driver during the operation of the vehicle (14);- classify the vehicle operation data of a predefined emotion category using a second machine learning model (24) into predefined fragrance categories, wherein the fragrance categories are associated with respective fragrance identities associated with the vehicle operation data of the predefined emotion category;- associate the fragrance identity of a specific fragrance category with the specific driver; and- control a fragrance injector unit (18) of the scent device (12) to inject a scent related to the fragrance identity associated with the specific driver into a cabin of the vehicle (14), when the control unit (16) detects the specific driver in the cabin of the vehicle (14) and a predefined condition is fulfilled.

2. The scent selection system (10) according to claim 1, characterized in thatthe control unit (16) is configured to receive the first machine learning model (22) and / or the second machine learning model (24) from a backend device (20) of the scent selection system (10) external to the vehicle (14).

3. The scent selection system (10) according to claim 1 or 2, characterized in thatthe control unit (16) is configured to provide the association of the fragrance identity with the specific driver to the backend device (20) and / or to receive the association of the fragrance identity with the specific driver from the backend device (20).

4. The scent selection system (10) according to any one of claims 1 to 3, characterized in thatthe control unit (16) is configured to provide the respective fragrance identities associated with the vehicle operation data of the predefined emotion category to the backend device (20); andthe backend device (20) is configured to receive the respective fragrance identities associated with the vehicle operation data of the predefined emotion category; and to provide scent formula data for producing the scent of the respective fragrance identity5. The scent selection system (10) according to any one of claims 1 to 4, characterized in thatpredefined condition comprises a detected specific emotion state of the specific driver.

6. The scent selection system (10) according to any one of claims 1 to 5, characterized in thatthe vehicle operation data comprise driver camera images showing the driver during the operation the vehicle (14).

7. The scent selection system (10) according to any one of claims 1 to 6, characterized in thatthe vehicle operation data comprise environment camera images showing an environment of the vehicle (14) during the operation the vehicle (14).

8. A vehicle (14) comprising a scent device (12) of a scent selection system (10).

9. A method to operate a scent selection system (10) comprising a scent device (12) for a vehicle (14) comprising, the method comprising the following steps performed by a control unit (16) of the scent device (12):- receiving vehicle operation data of the vehicle (14), recorded during an operation of the vehicle (14) by a specific driver;- classifying the vehicle operation data using a first machine learning model (22) into predefined emotion categories, wherein the emotion categories are associated with respective emotional states of the specific driver during the operation of the vehicle (14);- classifying the vehicle operation data of a predefined emotion category using a second machine learning model (24) into predefined fragrance categories, wherein the fragrance categories are associated with respective fragrance identities associated with the vehicle operation data of the predefined emotion category;- associating the fragrance identity of a specific fragrance category with the specific driver; and- controlling a fragrance injector unit (18) of the scent device (12) to inject a scent related to the fragrance identity associated with the specific driver into a cabin of the vehicle (14), when the control unit (16) detects the specific driver in the cabin of the vehicle (14) and a predefined condition is fulfilled.15

Images