Method and device for automatically generating multimedia content in a vehicle

Abstract

The invention relates to a method and device for generating multimedia content in a vehicle (10). To this end, initial data representing a command to generate the multimedia content are received from an interface embedded in the vehicle (10). This initial data is then processed by a natural language processing method, known as NLP, to understand the command language and make it interpretable or usable by a language model. The text is generated by feeding the language model with command data obtained from the NLP method. The text thus generated is rendered by speech synthesis for one or more passengers in the vehicle (10). Figure 1 (for the abstract)

Description

Title of the invention: Method and device for automatically generating multimedia content in a vehicle Technical field

[0001] The invention relates to methods and devices for generating multimedia content in a vehicle, in particular a motor vehicle. The invention also relates to a method and a device for automatically generating an original story to be rendered via one or more rendering devices of a vehicle during a journey of the vehicle. Technological background

[0002] Journeys made by vehicle, for example by motor vehicle, can be long and boring for passengers, especially children.

[0003] A child who is bored during a long journey in a vehicle risks soliciting adults and in particular the driver of the vehicle, with a risk of distraction for the driver, which presents a safety risk for all passengers in the vehicle. Summary of the invention

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

[0005] Another object of the present invention is to reduce the risks of distraction of the driver of a vehicle.

[0006] According to a first aspect, the invention relates to a method for automatically generating multimedia content in a vehicle, the method comprising the following steps: - reception of first data representative of a command to generate multimedia content from an interface on board the vehicle; - processing at least part of the first data based on a natural language processing method to generate a set of control data; - generation of a text by feeding a language model with the command data, the language model having been learned in a first learning phase; - rendering by voice synthesis of the generated text via at least one loudspeaker on board the vehicle.

[0007] The use of a language model, for example a large language model, called LLM, (from the English “Large Language Model”), makes it possible to generate a text according to a command received via a vehicle interface (for example a voice command received from one or more microphones). According to the command expressed, this text corresponds for example to a story generated on demand using artificial intelligence on a subject that is pleasant for example to children. The rendering of the text by the vehicle's loudspeakers makes it possible to occupy the passengers, for example one or more children, with a story whose length can be adapted to the journey for example. This thus prevents the driver from being distracted by passengers who are bored during the journey, thereby improving the safety of the vehicle and its passengers.

[0008] According to one variant, the method further comprises the following steps: - generation of at least one image by feeding an image prediction model with second data representative of at least a first part of the text, the image prediction model having been learned in a second learning phase; - control of the display of at least one image on a display screen on board the vehicle in a manner synchronized with the rendering of at least a first part of the text.

[0009] According to another variant, the method further comprises the following steps: - generation of at least one sound content by feeding a sound content prediction model with third data representative of at least a second part of the text, the sound content prediction model having been learned in a third learning phase; - rendering of at least one sound content via at least one loudspeaker in a synchronized manner with the rendering of at least one second part of the text.

[0010] According to an additional variant, the method further comprises the following steps; - generation of haptic data representative of at least one haptic effect based on fourth data representative of at least a third part of the text; - rendering of at least one haptic effect as a function of the haptic data via at least one device of at least one on-board system of the vehicle, the at least one haptic effect being rendered in a synchronized manner with the at least one third part of the text, the at least one on-board system belonging to a set of on-board systems comprising: a heating system, a ventilation system, an air conditioning system, a massage system and a passenger compartment lighting system.

[0011] According to another variant, the first data are representative of a voice command.

[0012] According to an additional variant, the method further comprises a step of filtering the first data according to a set of determined filtering rules, the filtering being prior to the processing based on the language processing method natural.

[0013] According to a second aspect, the invention relates to a device for automatically generating multimedia content in a vehicle, the device comprising a memory associated with a processor configured for implementing the steps of the method according to the first aspect of the invention.

[0014] According to a third aspect, the invention relates to a vehicle, for example of the automobile type, comprising a device as described above according to the second aspect of the invention.

[0015] According to a fourth aspect, the invention relates to a computer program which comprises instructions adapted for executing the steps of the method according to the first aspect of the invention, in particular when the computer program is executed by at least one processor.

[0016] Such a computer program may use any programming language, and be in the form of source code, object code, or intermediate code between source code and object code, such as in a partially compiled form, or in any other desirable form.

[0017] According to a fifth aspect, the invention relates to a computer-readable recording medium on which is recorded a computer program comprising instructions for carrying out the steps of the method according to the first aspect of the invention.

[0018] On the one hand, the recording medium may be any entity or device capable of storing the program. For example, the medium may comprise a storage means, such as a ROM memory, a CD-ROM or a microelectronic circuit type ROM memory, or a magnetic recording means or a hard disk.

[0019] Furthermore, this recording medium may also be a transmissible medium such as an electrical or optical signal, such a signal being able to be conveyed via an electrical or optical cable, by conventional or hertzian radio or by self-directed laser beam or by other means. The computer program according to the invention may in particular be downloaded from an Internet-type network.

[0020] Alternatively, the recording medium may be an integrated circuit in which the computer program is incorporated, the integrated circuit being adapted to perform or to be used in the performance of the method in question. Brief description of the figures

[0021] Other characteristics and advantages of the invention will emerge from the description of the non-limiting embodiments of the invention below, with reference to the appended figures 1 to 3, in which:

[0022] [Fig.l] schematically illustrates a communication environment of a vehicle, according to a particular exemplary embodiment of the present invention;

[0023] [Fig.2] schematically illustrates a device configured for generation at automation of multimedia content in the vehicle of [Fig.l], according to a particular exemplary embodiment of the present invention;

[0024] [Fig.3] illustrates a flowchart of the different steps of a method for automatically generating multimedia content in the vehicle of [Fig.l], according to a particular exemplary embodiment of the present invention. Description of the embodiments

[0025] A method and a device for automatically generating multimedia content in a vehicle will now be described in the following with joint reference to Figures 1 to 3. The same elements are identified with the same reference signs throughout the description which follows.

[0026] The terms “first(s)”, “second(s)”, etc. are used in this document by arbitrary convention to enable the identification and potential distinction of different elements (such as operations, means, etc.) implemented in the embodiments described below.

[0027] According to a particular and non-limiting example of embodiment of the invention, the generation of multimedia content, which comprises for example a text corresponding to an imaginary story, comprises the reception, for example by one (or more) computer(s) of a vehicle, of first data representative of a command to generate the multimedia content from an interface embedded in the vehicle. The command corresponds for example to a voice command picked up by one or more microphones of the vehicle. This first data is then processed by a natural language processing method, known by the acronym NLP (from the English “Natural Language Processing”), to understand the language of the command and make it interpretable or usable by a language model implemented for example in the form of a deep neural network.The text is then generated by feeding the language model (for example a large language model, known by the acronym LLM) with control data obtained as output from the NLP method. Such a language model has advantageously been learned during a learning phase, as known to those skilled in the art. Finally, the text thus generated is rendered by voice synthesis to one or more passengers of the vehicle, for example one or more children, via one or more loudspeakers (for example the loudspeakers of the vehicle and / or loudspeakers of wired or wireless headphones worn by the passenger(s).

[0028] The text is for example generated automatically as the journey progresses. performed by the vehicle, the rendering of the text being for example also carried out as the text is automatically generated.

[0029] The story told in the text is generated based on the words contained in the query issued by the passenger (e.g. a child). Thus, the subject of the story is arbitrary and original, and corresponds for example to a tale, a science fiction story, an adventure story, etc.

[0030] According to alternative embodiments, one or more contents other than text are further generated and included in the multimedia content in addition to the text as described below. Such contents correspond for example to audio or sound content, video content and / or haptic content to improve the experience of the passenger(s) for whom the multimedia content is intended.

[0031] The use of artificial intelligence allows the automatic generation of multimedia content without limitation of length or duration of the text and any other content accompanying the text.

[0032] [Fig. 1] schematically illustrates a communication environment 1 of a vehicle 10, according to a particular and non-limiting exemplary embodiment of the present invention.

[0033] The vehicle 10 corresponds for example to a vehicle with a thermal engine, with electric motor(s) or even a hybrid vehicle with a thermal engine and one or more electric motors. The vehicle 10 thus corresponds for example to a land vehicle, for example an automobile, a truck, a bus, a motorcycle.

[0034] The vehicle 10 corresponds for example to a so-called connected vehicle and for this purpose carries a communication system configured to communicate with one or more remote devices 101 via an infrastructure of a wireless communication network. The remote device 101 advantageously corresponds to a device configured to process data, for example data stored in the memory of the remote device 101 and / or data received from the vehicle 10. The remote device 101 corresponds for example to a server of the “cloud” 100 (or “cloud” in French).

[0035] The communication system of the vehicle 10 comprises, for example, one or more communication antennas connected to a telematic control unit, called TCU (from the English “Telematic Control Unit”), itself connected to one or more computers of the on-board system of the vehicle 10. The antenna(s), the TCU unit and the computer(s) form, for example, a multiplexed architecture for the realization of different services useful for the proper functioning of the vehicle 10 and for assisting the driver and / or passengers of the vehicle 10 in the control of the vehicle 10 and / or for establishing a diagnosis on the functioning of one or more components of the vehicle 10. The computer(s) and the TCU unit communicate and exchange data with each other via one or more computer buses, for example a communication bus of the data bus type CAN (from the English "Controller Area Network" or in French "Réseau de contrôles"), CAN FD (from the English "Controller Area Network Flexible Data-Rate" or in French "Réseau de contrôles à débit de données flexible"), FlexRay (according to the ISO 17458 standard) or Ethernet (according to the ISO / IEC 802-3 standard).

[0036] The mobile communication infrastructure enabling wireless data communication between the vehicle 10 and the remote device 101 comprises, for example, one or more communication devices 110 of the relay antenna (cellular network) or roadside unit, known as UBR, type. In a communication mode using such a network architecture, the data is, for example, transmitted by the vehicle 10 to the remote device 101 of the “cloud” 100 via a relay antenna 110 (the antenna 110 being, for example, connected to the “cloud” 100 via a wired link).

[0037] The wireless communication system allowing the exchange of data between the vehicle 10 and the remote device 101 corresponds for example to: - a vehicle-to-infrastructure (V2I) communication system, for example based on the 3GPP LTE-V or IEEE 802.1 Ip standards of ITS G5; and / or - a cellular network type communication system, for example an LTE (Long-Term Evolution) or LTE-Advanced (LTE-Advanced) type network, also called LTE 3G, 4G or 5G; and / or - a Wifi type communication system according to IEEE 802.11, for example according to IEEE 802.lin or IEEE 802.1 lac.

[0038] The communication system of the vehicle 10 is further configured for data communication between the vehicle 10 and one or more mobile communication devices, such as for example a tablet, a smartphone, a connected object.

[0039] The vehicle communication system 10 is further configured for data communication with one or more mobile devices adapted for rendering sound content, such as wireless headphones (using Bluetooth® technology for example).

[0040] The vehicle 10 carries a set of computers forming the on-board system of the vehicle 10. The computers of the vehicle 10 are connected to each other via one or more computer buses, for example a communication bus of the CAN (Controller Area Network) type, CAN FD (Controller Area Network Flexible Data-Rate) type, FlexRay (according to the ISO 17458 standard) or Ethernet (according to the ISO / IEC 802-3 standard).

[0041] The vehicle 10 also incorporates, for example, one or more of the following systems: - a heating system configured to heat the passenger compartment and / or one or more seats of the vehicle; and / or - an air conditioning system configured to condition the air in the passenger compartment of the vehicle 10 and / or cool one or more seats of the vehicle 10; and / or - a ventilation system configured to blow air towards one or more occupants via a set of vents; and / or - a massage system configured to massage one or more parts of the body of one or more occupants each seated in a seat of the vehicle 10, the massage system comprising actuators in one or more seats of the vehicle 10; and / or - a passenger compartment lighting system, said lighting system comprising light emission means such as LEDs (from the English “Light-Emitting Diode” or in French “electroluminescent diode”), for example to provide ambient lighting in specific areas of the passenger compartment and / or to illuminate via a light beam one or more areas located in the passenger compartment; and / or - an infotainment system configured to render multimedia content(s) in the passenger compartment of the vehicle and comprising, for example, one or more display screens and a set of speakers controlled by an IVI type computer (from the English “In-Vehicle Infotainment” or in French “Infodivertissement monté”).

[0042] A process for automatically generating multimedia content in the vehicle 10 is advantageously implemented by the vehicle 10, for example by one or more processors of one or more computers of the vehicle 10. According to alternative embodiments, the process is implemented by a system comprising the vehicle 10 and the remote device 101 connected in communication with the vehicle 10 via a wireless connection or link, by a mobile communication device (telephone, tablet) on board the vehicle 10, by a system comprising the vehicle 10 and one or more mobile communication devices connected in wireless communication to the vehicle 10 or by a system comprising the vehicle 10, the remote device 101 and one or more mobile communication devices.

[0043] The content generation process uses one or more content generation or content prediction models learned in one or more learning phases within the framework of a machine learning method as known to 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 as well as the production phase(s) are for example implemented using one or more neural networks, for example so-called deep neural networks in the context of artificial intelligence.

[0045] The learning phase(s) are for example implemented by the remote device 101 using learning data for example obtained from one or more databases 102.

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

[0047] The parameters of each of the models learned during the learning phase(s) are for example transmitted to one or more devices (for example the vehicle 10 and / or one or more mobile communication devices on board the vehicle 10) for the implementation of the production phase.

[0048] According to a variant, the remote device 101 implements the production phase on the basis of production data received from the vehicle 10 (and / or from a mobile communication device on board the vehicle 10), the result of the prediction of each model then being transmitted by the remote device 101 to the vehicle 10 (and / or to the mobile communication device on board the vehicle 10).

[0049] In a first operation of the process, first data representative of a command for generating the multimedia content are received or obtained from an interface on board the vehicle 10.

[0050] This command for generating multimedia content corresponds for example to a voice command pronounced by an occupant of the vehicle 10, for example a child. This voice command begins for example with one or more determined keywords that the system implementing the process detects and recognizes as being the trigger for the implementation of the following operations. Such keywords correspond for example to words such as “tell me a story” or “Hello car” or any other expression.

[0051] The voice command is captured by one or more microphones arranged in the passenger compartment of the vehicle 10, the first data then being transmitted to the computer implementing the process (either directly by the microphone(s) or via a computer controlling the microphone(s).

[0052] According to another exemplary embodiment, the voice command is captured by a microphone of a mobile communication device held by or near the occupant pronouncing the voice command. The first data are for example transmitted by this mobile communication device to the computer of the vehicle 10 implementing the process via a wireless connection of the Bluetooth® type for example. When the process is implemented directly by the communication device mobile communication, the first data are received by a processor of this device and processed by this processor without being transmitted to the computer of the vehicle 10.

[0053] The voice command includes a series of words describing the story that the occupant wishes to have automatically generated, for example, words describing a type of content and / or a context of place and time and / or the characters to appear in the story, etc.

[0054] According to a variant, the command further comprises instructions on the length or duration of the content to be generated, for example a duration expressed in minutes or in hours and minutes.

[0055] According to an alternative embodiment, the first data are representative of a command entered by a touch interface of a screen (of the vehicle 10 or of a mobile communication device), the words of the command being for example written on the screen via a touch keyboard displayed on the screen.

[0056] In a second optional operation of the process, filtering is applied to the first data according to a set of determined filtering rules.

[0057] The filtering rules are for example determined within the framework of parental control to remove or censor some of the words included in the text generation command. Filtering makes it possible, for example, to subtract certain words included in a list of words to be filtered or removed.

[0058] According to another example, the filtering is done according to the type of content required in the order, a set of content types being for example selected by a user as to be censored and filtered.

[0059] At the end of the filtering, the first data are kept as is when no keyword to be filtered has been detected in the text generation command and / or when the required content type does not correspond to a content type to be filtered.

[0060] Otherwise, all or part of the words represented by the first data are subtracted or filtered and the rest of the process is implemented on the part of the remaining first data, if any.

[0061] In a third operation of the process, the first data (or part of it if filtering has been implemented) is processed according to a natural language processing method, noted NLP (from the English “Natural Language Processing”) to generate a set of control data.

[0062] Such processing is also known as natural language processing (NLP) and allows the command received to be understood and interpreted in the first operation.

[0063] Natural language processing includes, for example, operations such as lemmatization, syntactic analysis, morpho-syntactic labeling, stemming (from the English "stemming"), tokenization, and / or word separation.

[0064] The text of the command is for example represented in the form of a vector of command data 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.

[0065] In a fourth step of the process, the control data obtained in the third operation are provided as input to a language model learned during a learning phase, for example a large language model, noted LLM (from the English “Large Language Model”) to generate a text in accordance with the instructions associated with the first data received in the first operation (after possible filtering).

[0066] Such a language model is for example implemented by a deep neural network with an architecture corresponding to a transformer or a recurrent neural network.

[0067] The language models are known to those skilled in the art and for example described in the article entitled “Long text Generation by Modeling Sentence-Level and Discourse-Level Coherence” published by Jian Guan, Xiaoxi Mao, Changjic Fan, Zitao Liu, Wenbiao Ding and Minlie Huang on May 19, 2021.

[0068] In a fifth step of the process, the text automatically generated by the model language in the fourth operation is rendered by voice synthesis to the person who issued the command to generate the multimedia content. The text is for example rendered in the passenger compartment of the vehicle 10 through one or more loudspeakers, for example the loudspeakers of the row of seats on which the person who issued the command is seated. According to another example, the text is rendered through the loudspeaker(s) of the mobile communication device in the possession of the person who issued the command to generate the content.

[0069] According to a variant, the text is rendered in wireless earphones worn by the person for personalized rendering without disturbing the other occupants of the vehicle 10.

[0070] According to another variant, the text is rendered in the manner of a song instead of a reading, making it possible to generate a calmer and more relaxing atmosphere for people listening to the rendering of the text.

[0071] According to a particular embodiment of the invention, the process further comprises the generation of one or more images, for example a sequence of images, by feeding an image prediction model with second data representative of at least a first part of the text, the image prediction model having been learned in a learning phase.

[0072] The second data correspond for example to the control data obtained in the third operation.

[0073] According to another example, the second data corresponds to all or part of the text generated by the language model or to data obtained by processing the data of the text generated by the language model in the fourth operation.

[0074] The processing of the generated text makes it possible, for example, to interpret the text in order to deduce second data or information representative of the atmosphere, the emotions of the characters, the context, etc.

[0075] The image generation model corresponds, for example, to the model created by the Midjourney® laboratory and known under the name Mijourney ai®, AI meaning “Artificial Intelligence” in English, or “Artificial Intelligence” in French.

[0076] According to another example, the image generation model corresponds to the model known as DALL-E from OpenAI®.

[0077] The image(s) associated with the text generated by the language model are thus generated automatically, for example as the text is automatically generated, the multimedia content then comprising the text and the image(s).

[0078] The automatically generated image(s) are displayed on one or more screens for the person(s) who requested the generation of the multimedia content, advantageously in a synchronized manner with each part of the text to which the generated image or sequence of images corresponds. The screens correspond, for example, to one or more screens fitted to the vehicle 10 (for example, screens integrated into the rear of the headrests of the front seats visible to the passengers seated in the row 2 seats (behind the front seats) of the vehicle 10) and / or the screen of each mobile communication device on which the text is rendered.

[0079] According to another particular embodiment of the invention, one or more sound contents (for example ambient music or background music) are generated by feeding a sound content prediction model with third data representative of at least a second part of the text, the sound content prediction model having been learned in a third learning phase.

[0080] The second part of the text corresponds to all or part of the text generated automatically by the language model, this second part being identical to or different from the first part of the text on which the generation of the image(s) described in the previous particular embodiment is based.

[0081] Thus, the third data correspond for example to the control data obtained in the third operation.

[0082] According to another example, the third data correspond to all or part of the text generated by the language model or to data obtained by processing the data from the text generated by the language model in the fourth operation.

[0083] The processing of the generated text makes it possible, for example, to interpret the text in order to deduce third data or information representative of atmosphere, emotions of the characters, context, rhythm, tone, etc.

[0084] The sound content generation model corresponds to any model for generating or composing music by artificial intelligence, such as AIVA® for example.

[0085] Each sound content associated with a part of the text generated by the language model is thus generated automatically, for example as the text is automatically generated, the multimedia content then comprising the text and the sound content(s) (and alternatively the image(s) as well).

[0086] The automatically generated sound content is rendered by one or more loudspeakers, as for the text, advantageously in a synchronized manner with each part of the text to which the sound content refers. The generated multimedia content then comprises the text, the sound content(s) and, according to a variant, the image(s).

[0087] According to another particular embodiment of the invention, haptic data representative of at least one haptic effect are generated as a function of fourth data representative of at least a third part of the text.

[0088] The third part of the text corresponds to all or part of the text generated automatically by the language model, this third part being identical to or different from the first and / or second part of the text on which the generation of the image(s) and / or the sound content(s) described in the previous particular embodiments is based.

[0089] Thus, the fourth data correspond for example to the control data obtained in the third operation of the process.

[0090] According to another example, the fourth data corresponds to all or part of the text generated by the language model or to data obtained by processing the data of the text generated by the language model in the fourth operation.

[0091] The processing of the generated text makes it possible, for example, to interpret the text in order to deduce fourth data or information representative of atmosphere, emotions of the characters, context, rhythm, tone, particular events, etc.

[0092] The haptic data are for example representative of temperature(s), expressed for example in degrees Celsius, of intensity and / or direction of an air flow, of intensity of a massage, of location of the massage, of light intensity, of lighting color, of a type of lighting (continuous and constant lighting, pulsed light), of location of the lighting.

[0093] According to one variant, the haptic data are representative of vibrations, and correspond for example to intensity levels and / or frequencies. This variant is for example implemented when the generated multimedia content is rendered on one or more mobile communication devices such as smartphones or tablets and configured to vibrate.

[0094] The haptic data is advantageously transmitted to one or more of the following systems, depending on the equipment of the vehicle 10 and depending on the nature of the haptic data generated: a heating system, a ventilation system, an air conditioning system, a massage system and / or a passenger compartment lighting system.

[0095] For example, if the generated text describes a cold or snowy landscape, the air conditioning system is controlled to lower the temperature in the passenger compartment of the vehicle 10 during the rendering of the passages of the text relating to such a landscape. If the generated text describes an erupting volcano or a desert, the heating system (for example with seat heating) is controlled to increase the temperature. The feeling of a windy environment is obtained by controlling the ventilation via the ventilation system.

[0096] According to this embodiment, the generated multimedia content further comprises data representative of one or more haptic effects to be rendered in a synchronized manner with the part or parts of the text to which the haptic effects refer.

[0097] According to yet another particular embodiment, the data representative of the generated multimedia content (i.e. the data of the generated text with, where appropriate, the image data, sound content, haptic effects) are recorded in a memory of the vehicle 10 or in a memory of the mobile communication device (for example when the multimedia content has been generated by such a mobile communication device). The storage of the data of the multimedia content makes it possible to replay or render the content again on demand.

[0098] [Fig. 2] schematically illustrates a device 2 configured to automatically generate multimedia content in a vehicle, for example the vehicle 10, according to a particular and non-limiting exemplary embodiment of the present invention. The device 2 corresponds for example to a device on board the vehicle 10, for example a computer. According to another example, the device 2 corresponds to a computing or data processing device, for example the remote device 101. According to yet another example, the device 2 corresponds to a mobile communication device.

[0099] The device 2 is for example configured for the implementation of the operations described with regard to [Fig.l] and / or the steps of the method described with regard to [Fig.3]. Examples of such a device 2 include, but are not limited to, on-board electronic equipment such as an on-board computer of a vehicle, an electronic calculator such as an ECU (“Electronic Control Unit”), a telematic control unit, called TCU (from the English "Telematic Control Unit"), a smartphone, a tablet, a laptop, a server, or a combination of several of the devices listed above. The elements of the device 2, individually or in combination, can be integrated in a single integrated circuit, in several integrated circuits, and / or in discrete components. The device 2 can be produced in the form of electronic circuits or software (or computer) modules or even a combination of electronic circuits and software modules.

[0100] The device 2 comprises one (or more) processor(s) 20 configured to execute instructions for carrying out the steps of the method and / or for executing the instructions of the software(s) 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 a volatile and / or non-volatile memory and / or comprises a memory storage device which may comprise volatile and / or non-volatile memory, such as EEPROM, ROM, PROM, RAM, DRAM, SRAM, flash, magnetic or optical disk.

[0101] The computer code of the embedded software(s) comprising the instructions to be loaded and executed by the processor is for example stored in the memory 21.

[0102] According to various particular embodiments, the device 2 is coupled in communication with other similar devices or systems and / or with communication devices, for example a TCU (from the English “Telematic Control Unit” or in French “Telematic Control Unit”), for example via a communication bus or through dedicated input / output ports.

[0103] According to a particular and non-limiting embodiment, the device 2 comprises a block 22 of interface elements for communicating with external devices, for example a remote server or the “cloud”, a TCU unit. The interface elements of the block 22 comprise one or more of the following interfaces: - RF radio frequency interface, for example Bluetooth® or Wi-Fi®, LTE (Long-Term Evolution), 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”).

[0104] According to another particular embodiment, the device 2 comprises an interface communication interface 23 which makes it possible to establish communication with other devices (such as other computers of the on-board system or other servers) 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), FlexRay (standardized by the ISO 17458 standard) or Ethernet (standardized by the ISO / IEC 802-3 standard).

[0105] According to an additional particular embodiment, the device 2 can provide output signals to one or more external devices, such as a display screen 240, one or more speakers 250 and / or other peripherals 260 (vibrating system) via respective adapted output interfaces 24, 25, 26. According to a variant, one or other of the external devices is integrated into the device 2.

[0106] [Fig. 3] illustrates a flowchart of the different steps of a method for automatically generating multimedia content in a vehicle, for example the vehicle 10, according to a particular and non-limiting exemplary embodiment of the present invention. The method is for example implemented by a device on board the vehicle 10 such as the device 2, by the remote device 101, by a mobile communication device on board the vehicle 10 or by a system comprising the vehicle 10 and the remote device 101 and / or the mobile communication device.

[0107] In a first step 31, first data representative of a command for generating the multimedia content are received from an interface on board the vehicle.

[0108] In a second step 32, at least a portion of the first data is processed based on a natural language processing method to generate a set of control data.

[0109] In a third step 33, a text is generated by feeding a language model with the control data, the language model having been learned in a first learning phase.

[0110] In a fourth step 34, the generated text is rendered by voice synthesis via at least one loudspeaker on board the vehicle.

[0111] According to an alternative embodiment, the variants and examples of the operations described in relation to [Fig.l] apply to the process steps of [Fig.3].

Claims

Claims

1. Method for automatically generating multimedia content in a vehicle (10), said method comprising the following steps: - receiving (31) first data representative of a command for generating said multimedia content from an interface on board said vehicle (10); - processing (32) at least part of said first data based on a natural language processing method to generate a set of command data; - generating (33) a text by feeding a language model with said command data, said language model having been learned in a first learning phase; - rendering (34) by voice synthesis of said generated text via at least one loudspeaker on board said vehicle (10).

2. Method according to claim 1, further comprising the following steps: - generating at least one image by feeding an image prediction model with second data representative of at least a first part of said text, said image prediction model having been learned in a second learning phase; - controlling the display of said at least one image on a display screen on board said vehicle (10) in a manner synchronized with the rendering of said at least a first part of said text.

3. Method according to one of claims 1 to 2, further comprising the following steps: - generating at least one sound content by feeding a sound content prediction model with third data representative of at least a second part of said text, said sound content prediction model having been learned in a third learning phase; - rendering said at least one sound content via said at least one loudspeaker in a synchronized manner with the rendering of said at least a second part of said text.

4. Method according to one of claims 1 to 3, further comprising the following steps; - generation of haptic data representative of at least one haptic effect as a function of fourth data representative of at least a third part of said text; - rendering of said at least one haptic effect as a function of said haptic data via at least one device of at least one on-board system of said vehicle (10), said at least one haptic effect being rendered in a synchronized manner with said at least one third part of said text, said at least one on-board system belonging to a set of on-board systems comprising: a heating system, a ventilation system, an air conditioning system, a massage system and a passenger compartment lighting system.

5. Method according to one of claims 1 to 4, for which said first data are representative of a voice command.

6. Method according to one of claims 1 to 5, further comprising a step of filtering the first data according to a set of determined filtering rules, said filtering being prior to said processing based on the natural language processing method.

7. Computer program comprising instructions for implementing the method according to any one of the preceding claims, when these instructions are executed by a processor.

8. A computer-readable recording medium on which is recorded a computer program comprising instructions for carrying out the steps of the method according to one of claims 1 to 6.

9. Device (2) for automatically generating multimedia content in a vehicle, said device (2) comprising a memory (21) associated with at least one processor (20) configured for implementing the steps of the method according to any one of claims 1 to 6.

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

Images