Method and device for automatically generating graphic content for a vehicle's human-machine interface

Abstract

The present invention relates to a method and device for the automatic generation of graphical content for a vehicle's human-machine interface. To this end, a set of questions is rendered (31) by speech synthesis to elicit user preferences. Initial data representing voice responses to the set of questions is received (32). This initial data is processed (33) using a natural language processing method to generate a set of initial control data, which feeds an artificial intelligence engine to generate (34) the graphical content. The generated graphical content is displayed (35) on a vehicle screen. (See Figure 3 for abbreviations.)

Description

Title of the invention: Method and device for automatically generating graphic content for a vehicle's human-machine interface technical field

[0001] The invention relates to methods and devices for the automatic generation of graphic content or themes for a human-machine interface (HMI) of a vehicle, particularly but not exclusively a motor vehicle. The invention also relates to a method and device for personalizing an HMI theme or background. Technological background

[0002] Contemporary vehicles are equipped with one or more display devices to display information useful to the driver for driving the vehicle as well as comfort information, such as information to interact with the vehicle's infotainment system, also called IVI (In-Vehicle Infotainment) system.

[0003] The information displayed on such a display device is presented via a user interface (UI) comprising several pages that provide access to different content, for example, to configure a set of the vehicle's onboard systems. Some vehicles allow users to personalize the UI's graphical appearance. However, such personalization is limited and often restricted to parameters such as background color or choices between several pre-configured graphical themes, which limits the user experience with the vehicle's UI. Summary of the present invention

[0004] One object of the present invention is to solve at least one of the problems of the technological background described above.

[0005] An object of the present invention is to improve the user experience with respect to the graphical human-machine interface of a vehicle.

[0006] According to a first aspect, the present invention relates to a method for automatically generating graphic content for a human-machine interface of a vehicle, the vehicle having a display system comprising a screen, the method being implemented by a processor and comprising the following steps: - rendering, by speech synthesis, of a set of questions to obtain user preferences for the automatic generation of graphic content; - receipt of initial data representative of voice responses to the set of questions; - processing of initial data based on a natural language processing method to generate a set of initial order data; - generation of graphic content by feeding a generative artificial intelligence engine with the initial order data; - control of the display of graphic content on the screen.

[0007] The use of a generative artificial intelligence engine makes it possible to generate graphical content based on the vehicle user's preferences, identified through responses to questions rendered in the vehicle's cabin by speech synthesis. This expands the possibilities for personalizing the vehicle's HMI by using artificial intelligence and the vehicle's voice interaction means, i.e., one or more microphones and speakers.

[0008] According to one variant, the method further includes a step of receiving second data representative of a voice command to generate graphic content, the rendering of the set of questions being triggered following a processing of the second data by a speech recognition method.

[0009] According to one variant, the set of questions is generated based on a set of graphic objects available in a database to generate the graphic content, a set of graphic content generation parameters defined by a vehicle manufacturer and / or third data representing a history of answers to at least one question preceding a current question.

[0010] According to another variant, the generation of the graphic content includes a selection of at least one graphic object from the set of graphic objects available according to the first command data.

[0011] According to yet another variant, the method further comprises the following steps: - receiving fourth data representing voice instructions to modify the graphic content displayed on the screen; - processing of the fourth data based on the natural language processing method to generate a set of second order data; - modification of the graphic content by feeding the generative artificial intelligence engine with the second set of command data to generate modified graphic content; - control of display of the modified graphic content on the screen, the steps of receiving fourth data, processing of fourth data, modification of the graphic content and control of display of the modified graphic content being repeated until receipt of fifth data representing a voice validation of the modified graphic content.

[0012] According to yet another variant, the method further includes a speech synthesis rendering step of a validation confirmation and application of the graphic content or the modified graphic content to the human-machine interface.

[0013] According to another variant, the method further includes a speech synthesis rendering step of a description of the graphic content displayed on the screen.

[0014] According to a second aspect, the present invention relates to a device for automatically generating graphic content for a human-machine interface of a vehicle, the device comprising a memory associated with a processor configured for implementing the steps of the process according to the first aspect of the present invention.

[0015] According to a third aspect, the present invention relates to a vehicle, for example of the automobile type, comprising a device as described above according to the second aspect of the present invention.

[0016] According to a fourth aspect, the present invention relates to a computer program which includes instructions adapted for carrying out the steps of the process according to the first aspect of the present invention, in particular when the computer program is executed by at least one processor.

[0017] Such a computer program may use any programming language, and be in the form of source code, object code, or an intermediate form between source code and object code, such as in a partially compiled form, or in any other desirable form.

[0018] According to a fifth aspect, the present invention relates to a computer-readable recording medium on which is recorded a computer program comprising instructions for carrying out the steps of the process according to the first aspect of the present invention.

[0019] On the one hand, the recording medium can be any entity or device capable of storing the program. For example, the medium can include a storage means, such as a ROM, a CD-ROM or a microelectronic circuit-type ROM, or a magnetic recording means or a hard disk drive.

[0020] On the other hand, this recording medium can also be a transmissible medium such as an electrical or optical signal, such a signal being able to be transmitted via an electrical or optical cable, by conventional or radio frequency, by self-directing laser beam, or by other means. The computer program according to the present invention can, in particular, be downloaded from an Internet-type network.

[0021] Alternatively, the recording medium may be an integrated circuit in which the computer program is incorporated, the integrated circuit being adapted to execute or to be used in the execution of the process in question. Brief description of the figures

[0022] Other features and advantages of the present invention will become apparent from the description of the particular and non-limiting embodiments of the present invention below, with reference to the attached Figures 1 to 3, in which:

[0023] [Fig-1] schematically illustrates part of a vehicle's passenger compartment, according to a example of a particular embodiment of the present invention;

[0024] [Fig.2] illustrates a device configured to automatically generate graphic content for a human-machine interface of the vehicle of [Fig.1], according to a particular and non-limiting embodiment of the present invention.

[0025] [Fig.3] illustrates a flowchart of the different stages of a process for automatically generating graphic content for a human-machine interface of the vehicle of [Fig.1], according to a particular and non-limiting embodiment of the present invention. Description of examples of achievements

[0026] A method and device for automatically generating graphic content for a vehicle human-machine interface will now be described in what follows with joint reference to Figures 1 to 3. The same elements are identified with the same reference signs throughout the following description.

[0027] The terms "first," "second" (or "firsts," "seconds"), etc., are used in this document by arbitrary convention to allow for the identification and distinction of different elements (such as operations, means, etc.) implemented in the embodiments described below. Such elements may be distinct or correspond to a single element, depending on the embodiment.

[0028] According to a particular and non-limiting embodiment of the present invention, the automatic generation of graphic content or a theme for a vehicle's HMI, for example, a graphic theme for the HMI or a wallpaper associated with the HMI or a part of the HMI, is implemented by one or more vehicle computers, in particular by one or more processors of this or these computers. This or these computers are advantageously configured to implement a method for generating graphic content using generative artificial intelligence, that is, via a generative model learned in a prior learning phase.

[0029] To this end, a set of questions comprising one or more questions is rendered in the vehicle's cabin, via one or more vehicle speakers, by speech synthesis. The purpose of this set of questions is to gather a set of user preferences for generating graphic content. Initial data representing voice responses to the questions asked are received, by An example of this involves one or more microphones arranged inside the vehicle. The initial data is processed using a natural language processing (NLP) method to understand the language of the voice responses and make it interpretable or usable by a generative artificial intelligence (GAI) engine, implemented, for example, as a deep neural network. The graphic content is then generated by feeding the generative model with initial control data obtained from the NLP process. Such a GAI engine includes, for example, one or more generative prediction models learned during a training phase, as understood by a person skilled in the art.Finally, the display of the generated graphic content is controlled so that this graphic content is displayed on a vehicle screen, for example to obtain validation from the vehicle user who requested the generation of the graphic content or to obtain commands to modify the proposed graphic content.

[0030] The use of artificial intelligence allows the automatic generation of graphic content in response to instructions spoken by a vehicle user, for example the driver, with a wide variety of graphic objects composing this graphic content and their arrangement in the screen space.

[0031] Fig. 1 schematically illustrates a part of the passenger compartment of vehicle 10, according to a particular and non-limiting embodiment of the present invention.

[0032] Vehicle 10 corresponds, for example, to a vehicle with an internal combustion engine, with electric motor(s), or even a hybrid vehicle with an internal combustion engine and one or more electric motors. Vehicle 10 thus corresponds, for example, to a land vehicle, for example a car, a truck, a bus.

[0033] The vehicle 10 includes a display system comprising a screen 12, for example with a touch interface, and a computer configured to control the display of content(s) of a graphic HMI on the screen 12. The computer corresponds for example to the computer of the infotainment system, called the IVI computer (from the English "In-Vehicle Infotainment" or in French "Infodivertissement étoilé") of the vehicle 10.

[0034] The screen 12 corresponds for example to an LCD type screen (from the English "Liquid Crystal Display" or in French "Affichage à cristals liquide"), for example of type TFT (from the English "Thin-Film Transistor" or in French "Transistor en film mince"), or OLED (from the English "Organic Light-Emitting Diode" or in French "Diode électroluminescente organique").

[0035] The screen 12 is configured to display content for the driver and passengers of the vehicle 10. The screen 12, particularly when it is a touchscreen, is also configured to allow the driver and / or passengers of the vehicle to interact with one or more systems embedded in the vehicle via a human-machine interface (HMI) displayed on the 12-inch touchscreen.

[0036] According to a particular embodiment, the display system includes one or more other screens, for example a screen of a device or system called a head-up display, corresponding for example to a transparent or semi-transparent blade arranged in such a way that a driver sitting in the seat 15 sees the content displayed or projected onto the transparent blade when the driver is driving the vehicle 10. The display system further includes, for example, a display screen called a combination or instrument panel and generally arranged in an area 13 behind the steering wheel 14 in the dashboard 11.

[0037] According to a particular embodiment, the display system including the touch screen 12 is for example provided or configured to reduce the number of screens present in the vehicle 10, allowing for example the removal of the display screen(s) called instrument cluster or instrument panel.

[0038] The vehicle 10 further includes one or more loudspeakers 16 arranged in the passenger compartment, for example at the front and rear of the passenger compartment for the rendering of sound content with any sound effect using the spatial distribution of the loudspeakers in the passenger compartment of the vehicle 10.

[0039] The speakers 16 belong to an audio and / or multimedia system of the vehicle 10 configured for rendering sound content, for example, music or ambient sound. The audio and / or multimedia system is further configured to implement a voice communication interface by rendering text using speech synthesis via the speakers 16. The text is, for example, automatically generated by a language model learned during a training phase, such a language model being known to a person skilled in the art.

[0040] The vehicle 10 also includes one or more microphones 16 arranged in the passenger compartment, for example near the interior rearview mirror and / or the front doors. The microphones belong, for example, to the voice communication interface of the vehicle 10 for acquiring commands or responses spoken by the user of the vehicle 10, particularly in the context of the automatic generation of graphic content as described in more detail below.

[0041] The computers controlling the display system (such as the infotainment system computer, known as the IVI computer (from the English "In-Vehicle Infotainment" or in French "Infodivertissement étoilé")), the audio system, the sound acquisition system, and any other embedded system of the vehicle 10 form, for example, a multiplexed architecture for the implementation of various services useful for the proper functioning of the vehicle and for the generation of graphic content of The vehicle's HMI 10. The computers communicate and exchange data with each other via one or more computer buses, for example a CAN data bus (from the English "Controller Area Network" or in French "Réseau de contrôlers"), CAN FD (from the English "Controller Area Network Flexible Data-Rate" or in French "Réseau de contrôlers à débit de données flexible"), FlexRay (according to the ISO 17458 standard), LIN (from the English "Local Interconnect Network" or in French "Réseau interconnecté local") or Ethernet (according to the ISO / IEC 802-3 standard).

[0042] An automatic generation process for graphical content of a vehicle HMI 10 is advantageously implemented by one or more processors, for example, one or more processors of one or more computers of a graphical content generation system embedded in the vehicle 10 and based on artificial intelligence (AI). Such a system is configured to implement so-called artificial intelligence methods, that is, to implement one or more models learned in one or more learning phases. These methods and associated prediction models are implemented, for example, in the form of neural network(s), for example, deep neural network(s).

[0043] The process of generating the graphic content or theme uses, in particular, a generative artificial intelligence engine implementing, for example, one or more content generation or content prediction models and one or more language models, such models being learned in one or more learning phases within the framework of a machine learning method as understood by those skilled in the art. The learning phase(s) are implemented prior to a so-called production, prediction, or inference phase using the models learned during the learning phase(s).

[0044] The production phase and the production phase(s) are for example implemented using one or more neural networks, for example deep neural networks in the context of artificial intelligence.

[0045] The learning phase(s) are for example implemented by one or more data processing devices of the server or computer type using training data obtained for example from one or more databases.

[0046] The learning of each model corresponds, for example, to supervised, self-supervised or semi-supervised learning, according to all learning methods known to a person skilled in the art.

[0047] The parameters of each of the models learned during the learning phase(s) are, for example, transmitted to the vehicle 10, for example via a wireless connection or via a wired connection, for the implementation of the production phase described below.

[0048] In a first operation of the process, data, called second data, representing a command to generate graphic content are received or obtained by the graphic content generation system from an interface embedded in the vehicle 10.

[0049] This command for generating graphical content corresponds, for example, to a voice command spoken by a user of the vehicle 10, for example, the driver. This voice command begins, for example, with one or more specific keywords that the system implementing the process detects and recognizes as the trigger for the execution of the subsequent operations. Such keywords correspond, for example, to words such as "generate me a new graphical interface," "customize my graphical interface," or any other expression.

[0050] The voice command is captured by one or more microphones 17 arranged in the passenger compartment of the vehicle 10, the second data then being transmitted to the computer(s) implementing the process (either directly by the microphone(s) or via a computer controlling the microphone(s).

[0051] According to one embodiment, the second data represents a command entered by a touch interface of the screen 12, for example the second data corresponds to data representing a touch press on a determined location of the screen 12, for example at the display location of a graphic object displayed on the screen 12 and intended to control the initiation of the generation of graphic content for the HMI of the vehicle 10.

[0052] In a second operation of the process, processing is applied to the second data by the graphic content generation system to interpret the received command (for example, voice) and trigger the process of generating graphic content or customizing the graphic interface of the vehicle's HMI 10.

[0053] When the command corresponds to a voice command, the processing of the second data is implemented by a voice recognition module embedded in the vehicle 10, which voice recognition module is included in the graphic content generation system.

[0054] In a third operation of the process, an interactive dialogue between the graphic content generation system for the vehicle HMI 10 and the vehicle 10 user who requested or ordered this generation is implemented.

[0055] Interactive dialogue is implemented for example by a conversational artificial intelligence (AI) module included in the graphic content generation system for the HMI.

[0056] This third operation includes the generation of a set of questions by the conversational AI module.

[0057] Each question in the generated question set is rendered by speech synthesis to obtain user preferences for the automatic generation of graphic content. The speech synthesis rendering is implemented by a speech synthesis rendering module of the graphic content generation system, with each question being rendered in the passenger compartment of the vehicle 10 via the vehicle's speaker(s) 16.

[0058] When the question set comprises several questions, the questions are rendered one after the other in a temporally sequential manner. A question in the sequence is rendered after the system has received and processed the answer to the previous question in the sequence.

[0059] The question generator formulates the question(s) necessary to obtain user preferences regarding the generation of the graphical content of the user interface (UI) in order to personalize this UI according to user preferences. The questions thus relate to personalization parameters such as the desired color(s), the desired dominant color, the desired graphic style, the desired pattern(s) or texture(s), etc.

[0060] The set of questions is, for example, dynamically generated based on one or more of the following criteria: - a set of graphic elements or objects (e.g., patterns or textures, icons, pictograms, color palettes, etc.) available in a database of graphic objects usable for generating graphic content for customizing the HMI, this database being, for example, stored in the vehicle's memory 10; and / or - a set of parameters defined by the vehicle manufacturer 10 to constrain the generation of graphic content and the personalization of the HMI according to manufacturer preferences, the set of parameters relating to particular shades or colors, specific fonts, a specific spatial organization of graphic objects, a particular graphic theme, etc.; and / or - the user's answers (represented as third data) to questions formulated and submitted previously, the dynamically generated questions adapting as answers to previous questions are given; according to this criterion, a current question is generated based on the answer(s) to one or more of the questions formulated and submitted prior to this current question in order to collect user preferences for the personalization of the HMI.

[0061] Following each question in the set of questions, initial data representing a voice response are received by the conversational AI module. The voice response is captured or acquired by the microphone(s) 17 arranged in the passenger compartment of the vehicle 10.

[0062] The first data is processed to analyze the response to each question formulated and submitted and to extract personalization parameters from the response to guide the generation of graphic content to personalize the HMI.

[0063] The first ones are processed according to a natural language processing method, noted NLP (from the English "Natural Language Processing") to generate a set of first control data.

[0064] Such processing is also known as natural language processing (NLP) and allows the understanding and interpretation of the response received.

[0065] Natural language processing includes, for example, operations such as lemmatization, syntactic analysis, morpho-syntactic tagging, stemming, tokenization, and / or word separation.

[0066] The text of the response is for example represented in the form of a command data vector and / or converted into a list of numbers, for example using a "tokenizer" which corresponds to a bijective function establishing a correspondence between words or texts and lists of integers.

[0067] In a fourth operation of the process, the first control data obtained in the third operation are provided as input to a generative artificial intelligence module or engine to generate the graphic content to personalize the HMI of vehicle 10, in accordance with the answers provided by the user of vehicle 10 to the questions formulated by the conversational AI module.

[0068] The graphic content corresponds, for example, to one or more wallpapers associated with a graphic theme generated by the generative model.

[0069] The generation of graphic content includes, for example, the selection of one or more graphic objects or elements available in the database, these graphic elements or objects being selected according to the instructions described by the first command data and corresponding to the user preferences or parameters extracted from the answers to the set of questions.

[0070] The generative AI engine assembles and spatially organizes the selected graphic elements or objects from the database to generate the graphic content which can then be applied to the GUI to visually personalize it.

[0071] The generative AI engine, for example, implements one or more artificial intelligence algorithms to create graphic content and visually optimize the various selected graphic objects, ensuring visual consistency between the different pages of the GUI to which the generated graphic content will be applied, i.e. the generated visual theme.

[0072] In a fifth operation of the process, a computer of the vehicle 10, for example the IVI computer, controls the display of the graphic content thus generated to display it on the screen 12 of the vehicle 10.

[0073] A display control for graphic content or any graphic object (text, pictogram, icon, etc.) includes rendering the graphic content or graphic object. Such rendering corresponds to a set of operations performed by one or more processors on the pixels of one or more images of the graphic content to be displayed on the screen 12. For example, rendering consists of associating pixel data (for example, color data expressed in an RGB (Red, Green, Blue) color space) with each graphic object. The display control of the graphic content thus includes transmitting control signals to the screen 12 to modify the values ​​associated with the pixels of the screen 12 at the location intended to display the indicator (or any graphic object).

[0074] The display of the graphic content on the screen 12 corresponds for example to a presentation of the graphic content generated to the user of the vehicle who requested the personalization of the HMI prior to the application of the graphic content or theme generated to the HMI of the vehicle 10.

[0075] According to a particular embodiment, the display of the generated graphic content is accompanied by the rendering of a voice description of the generated graphic content, for example, a voice description of the graphic elements or objects composing the generated graphic content. This voice description is automatically generated by a language model of the conversational AI module, the generated text being rendered in the vehicle's cabin 10 via the speakers 16.

[0076] The voice description is for example generated and rendered automatically in parallel with the display of the graphic content presented and offered to the user of the vehicle 10. According to another example, the voice description is generated and rendered on request from the user of the vehicle 10, for example after the pronunciation of a specific voice request or command, that is to say after the automatic generation of graphic content data is received by the system of automatic generation of graphic content obtained from the microphone(s) 17.

[0077] This user preview of vehicle 10 aims, for example: - to obtain feedback from the user with possible comments to be taken into account to refine the visual aspect of the graphic content; - to obtain validation of the generated graphic content or theme for application to the user interface.

[0078] Comments on the generated graphic content or validation of the generated graphic content are received, for example, in the form of instructions or voice commands captured by the microphone(s) of the vehicle 10.

[0079] When the user of vehicle 10 who requested the customization of the HMI provides feedback to modify the graphic appearance of the graphic content generated in the fourth operation, the process then continues with the following operations: - reception of fourth data representing voice instructions to modify the graphic content displayed on screen 12; - processing of the fourth data based on the natural language processing method to generate a set of second order data; - modification of the graphic content by feeding the generative AI engine with the second set of command data to generate modified graphic content; - control of display of modified graphic content on screen 12.

[0080] According to one embodiment, the conversational AI module generates one or more additional questions to clarify the voice instructions spoken by the user of the vehicle 10, for example to obtain additional information or clarifications on the changes to be made to the graphic content.

[0081] According to another embodiment, a voice description of the modified graphic content is generated and rendered in the passenger compartment of the vehicle 10 in parallel with the display of the modified graphic content, as described above.

[0082] The operations listed above are repeated until fifth data representing a voice validation of the modified graphic content spoken by the user of the vehicle 10 and acquired by the microphone(s) 17 are received.

[0083] In a final operation of the process, the vehicle 10 HMI is updated from the generated graphic content or the modified graphic content, as appropriate, after receiving voice validation from the vehicle 10 user. The graphic content representing the customized theme is applied to one or more pages of the HMI or to the entire HMI.

[0084] According to one embodiment, the final update of the HMI is accompanied by the rendering by speech synthesis of a voice confirmation that the content or graphic theme validated by the user has been successfully applied to the HMI.

[0085] Figure 2 schematically illustrates a device 2 configured to automatically generate graphic content or a theme for a vehicle's HMI, for example, vehicle 10, according to specific and non-limiting embodiments of the present invention. Device 2 corresponds, for example, to a device embedded in vehicle 10, such as a computer or set of computers.

[0086] Device 2 is, for example, configured to carry out the operations described opposite [Fig. 1] and / or the steps of the process described opposite [Fig. 3]. Examples of such a device 2 include, but are not limited to, embedded electronic equipment such as a vehicle's on-board computer, an electronic control unit such as an ECU (Electronic Control Unit), or a combination of several of the devices listed above. The elements of device 2, individually or in combination, may be integrated into a single integrated circuit, into several integrated circuits, and / or into discrete components. Device 2 may be implemented in the form of electronic circuits or software (or computer) modules, or a combination of electronic circuits and software modules.

[0087] The device 2 comprises one (or more) processor(s) 20 configured to execute instructions for carrying out the steps of the process and / or for executing instructions from the software embedded in the device 2. The processor 20 may include integrated memory, an input / output interface, and various circuits known to those skilled in the art. The device 2 further comprises at least one memory 21, corresponding, for example, to volatile and / or non-volatile memory, and / or includes a memory storage device that may include volatile and / or non-volatile memory, such as EEPROM, ROM, PROM, RAM, DRAM, SRAM, flash, magnetic disk, or optical disk.

[0088] The computer code of the embedded software(s) including the instructions to be loaded and executed by the processor is for example stored on memory 21.

[0089] According to various particular and non-limiting embodiments, the device 2 is coupled in communication with other similar devices or systems and / or with communication devices, for example a TCU (Telematic Control Unit), for example via a communication bus or through dedicated input / output ports.

[0090] According to a particular and non-limiting embodiment, the device 2 comprises a block 22 of interface elements for communicating with external devices. The interface elements of the block 22 comprise one or more of the following interfaces: - Radio frequency (RF) interface, for example, Wi-Fi® type (according to IEEE 802.11), for example in the 2.4 or 5 GHz frequency bands, or Bluetooth® type (according to IEEE 802.15.1), in the 2.4 GHz frequency band, or Sigfox type using UBN (Ultra Narrow Band) radio technology, or LoRa in the 868 MHz frequency band, LTE (Long- Long-term Evolution” or in French “Long-term Evolution”), LTE-Advanced (or in French LTE-advanced); - USB interface (from the English "Universal Serial Bus" or "Universal Serial Bus" in French); - HDMI interface (from the English "High Definition Multimedia Interface", or "High Definition Multimedia Interface" in French); - LIN interface (from the English "Local Interconnect Network", or in French "Réseau interconnecté local").

[0091] According to another particular and non-limiting embodiment, the device 2 includes a communication interface 23 which allows communication to be established with other devices (such as other computers in the embedded system) via a communication channel 230. The communication interface 23 corresponds, for example, to a transmitter configured to transmit and receive information and / or data via the communication channel 230. The communication interface 23 corresponds, for example, to a wired network of the CAN (Controller Area Network) type, CAN FD (Controller Area Network Flexible Data-Rate) type, FlexRay (standardized by ISO 17458) or Ethernet (standardized by ISO / IEC 802-3).

[0092] According to a particular and non-limiting embodiment, the device 2 can provide output signals to one or more external devices, such as a display screen 240, touch or not, one or more speakers 250 and / or other peripherals 260 (projection system) via output interfaces 24, 25 and 26 respectively. According to a variant, one or more of the external devices is integrated into the device 2.

[0093] Figure 3 illustrates a flowchart of the different steps in a method for automatically generating graphic content or a theme for a vehicle's HMI, for example, vehicle 10, according to a particular and non-limiting embodiment of the present invention. The method is implemented, for example, by one or more devices embedded in vehicle 10 or by device 2 of Figure 2.

[0094] In a first step 31, a set of questions is rendered by speech synthesis to obtain user preferences for the automatic generation of graphic content.

[0095] In a second step 32, initial representative data of voice responses to the set of questions are received.

[0096] In a third step 33, the first data is processed via a natural language processing method to generate a set of first order data.

[0097] In a fourth step 34, the graphic content or theme is generated by feeding a generative artificial intelligence engine with the first command data.

[0098] In a fifth step 35,1” display of the content or graphic theme is controlled to display this content or graphic theme on a screen of the vehicle.

[0099] According to one variant, the variants and examples of the operations described in relation to [Fig.1] apply to the steps of the process in [Fig.3].

Claims

Demands

1. Method for automatically generating graphical content for a human-machine interface of a vehicle (10), said vehicle (10) having a display system including a screen (12), said method being implemented by a processor and comprising the following steps: - rendering (31), by speech synthesis, of a set of questions to obtain user preferences for the automatic generation of said graphical content; - receiving (32) first data representing voice responses to said set of questions; - processing (33) of said first data based on a natural language processing method to generate a set of first control data; - generating (34) of said graphical content by feeding a generative artificial intelligence engine with said first control data; - display control (35) of said graphical content on said screen (12).

2. A method according to claim 1, further comprising a step of receiving second data representing a voice command for generating said graphic content, the rendering (31) of said set of questions being triggered following a processing of said second data by a speech recognition method.

3. A method according to claim 1 or 2, wherein said set of questions is generated based on a set of graphic objects available in a database to generate said graphic content, a set of generation parameters for said graphic content defined by a manufacturer of said vehicle and / or third data representing a history of answers to at least one question of said set of questions preceding a current question of said set of questions.

4. Method according to claim 3, wherein said generation of said graphic content comprises a selection of at least one graphic object from said set of graphic objects available according to said first command data.

5. A method according to any one of claims 1 to 4, further comprising the following steps: - receiving fourth data representing voice instructions to modify said graphic content displayed on said screen; - processing said fourth data based on the natural language processing method to generate a set of second command data; - modifying said graphic content by feeding said generative artificial intelligence engine with said second command data to generate modified graphic content; - display control of said modified graphic content on said screen (12), said steps of receiving fourth data, processing fourth data, modifying the graphic content and display control of the modified graphic content being repeated until receipt of fifth data representing a voice validation of said modified graphic content.

6. Method according to claim 5, further comprising a speech synthesis rendering step of a validation confirmation and application of said graphic content or said modified graphic content to said human-machine interface.

7. A method according to any one of claims 1 to 6, further comprising a speech synthesis rendering step of a description of said graphic content displayed on said screen (12).

8. Computer program comprising instructions for carrying out the method according to any one of claims 1 to 7, when such instructions are executed by at least one processor.

9. Device (2) for automatically generating graphic content for a human-machine interface of a vehicle (10), said device (2) comprising a memory (21) associated with at least one processor (20) configured for carrying out the steps of the method according to any one of claims 1 to 7.

10. Vehicle (10) comprising the device (2) according to claim 9.

Images