FR3088462A1 - METHOD FOR DETERMINING A CONTEXTUAL INDICATION RELATING TO A SUGGESTION OF MULTIMEDIA CONTENT PROVIDED BY A MULTIMEDIA SYSTEM EMBEDDED IN A TERRESTRIAL VEHICLE - Google Patents

Description

DESCRIPTION

TITLE: Method for determining a contextual indication relating to a suggestion of multimedia content provided by an on-board multimedia system in a land motor vehicle

Technical field of the invention

The present invention relates to the field of multimedia systems for land motor vehicles.

The invention relates in particular to a method for determining at least one value representative of at least one contextual parameter with regard to a suggestion of multimedia content provided by a multimedia system 15 on board a land motor vehicle.

The invention applies in particular to motor vehicles.

State of the art

Today, multimedia systems for land motor vehicles include content prediction functionalities, based in particular on machine learning mechanisms which, among other things, make it possible to determine the most probable multimedia content taking into account, for example , user, date, time, location and / or number of passengers. These predictions / suggestions are generally based on the history of actions that have been carried out previously and look for the multimedia content (eg radio station, video on demand distribution platform) most often listened to and / or watched under the same conditions. of departure.

However, the success rate of prediction algorithms is not 100%. Errors may arise, in particular at the start of the learning phase, even when arrangements are made, for example, to ensure that a proposal is not made in the event of a too low calculated probability.

However, a key element for the acceptance by a user of any system based on artificial intelligence is related to the ability of the user to follow and understand what has been learned by the machine. It can therefore be seen that there is a need to formulate the propositions and results provided by such systems in conjunction with explanatory or contextual elements which aim to allow a user to understand the reasoning used and, where appropriate, the reasons possible errors. These additional informative elements indeed help to encourage the user to be more understanding with regard to errors and to listen to progress. It is at the cost of such functionality that a better acceptance rate of artificial intelligence mechanisms by end users can be achieved. So today's multimedia systems that don't

I do not take into account such aspects and provide content predictions without adding informative elements allowing the user to understand the framework of the reasoning implemented have certain disadvantages in terms of human-computer interaction.

Presentation of the invention

The invention aims to overcome these drawbacks.

The object of the invention is in particular to provide a method which is able to link a suggestion of multimedia content with a contextual indication which is presented to a user by means of a multimedia system on board a land vehicle. motor. More specifically, the invention aims to provide a method which allows any suggestion of content which is made on the basis of the implementation of artificial intelligence mechanisms to be embellished with at least one relevant contextual indication which allows the user to understand the reasoning that led to the suggestion. The invention also aims to provide a method which can extract certain influential distinctive parameters with regard to the results provided by using machine learning mechanisms and to process these distinctive parameters to provide explanatory information useful for the user.

To this end, the subject of the invention is a method for determining at least one value representative of at least one contextual parameter with regard to a suggestion of multimedia content provided by a multimedia system on board a land motor vehicle, the process comprising the steps of:

- constitute operating data, said operating data being generated following the emission of at least one signal by at least one first detection device arranged in the vehicle and configured to emit a signal according to a speed regime. operation of the vehicle, receiving location data, said location data being transmitted by a satellite positioning system and / or a remote data source, processing said location data to extract at least one relevant parameter, constituting data of identification relating to at least one passenger in the vehicle, said identification data being partly generated following the emission of a signal by at least one second detection device arranged in the vehicle and configured to emit a signal as a function of '' at least one component of a physical and / or psychological condition of said passenger, transmitting said operating data, said location data and said identification data to a machine learning module which, on the basis of said operating data, said location data and said identification data, establishes a predictive model 5 capable of processing at least one parameter d entry, use the predictive model to determine said suggestion, determine at least one distinctive parameter related to said suggestion, and

- determine the representative value using the distinctive parameter.

Alternatively, the method may include a step of using the representative value to determine a context indication.

According to another variant, the method may include a step of interaction with an information broadcasting interface capable of taking charge of the context indication to produce an audio message and / or an animation.

According to another variant, said information broadcasting interface can be an integral part of said multimedia system.

According to another variant, the step of determining the distinctive parameter can comprise a step consisting in varying the input parameter.

According to another variant, the step of using the predictive model may include a step of using location data to bring said suggestion to light.

The invention further relates to a computer system for determining at least one value representative of at least one contextual parameter with regard to a suggestion of multimedia content provided by a multimedia system on board a land motor vehicle in which are arranged at least a first detection device configured to emit a signal according to a vehicle operating mode, at least a second detection device configured to emit a signal according to at least one component of a physical and / or psychological condition of a passenger, a receiver for receiving location data provided by a satellite positioning system and allowing the time-stamped determination of the geographical position of the vehicle and a means of transmitting and receiving signals radio frequencies for communicating with a remote server and / or a portable electronic device, the system comprising means for setting up implementation of a process as defined above.

According to a variant, the system may include a calculation unit, an automatic learning module and storage means in which are stored at least one program for the execution of steps of the determination method as defined above.

The invention further relates to a computer program comprising instructions for the execution of the steps of a method as defined above.

The invention further relates to a vehicle comprising a system as defined above.

Brief description of the figures

Other characteristics and advantages of the invention will become apparent on examining the detailed description below, and the appended drawings, in which:

[Fig. 1] is a block diagram of a determination system according to the invention, and [Fig. 2] is a flowchart illustrating certain steps of a determination method according to

The invention.

Detailed description of the invention

The determination system 100 according to the present invention is illustrated in FIG. 1. The system comprises an information processing unit 101 comprising one or more processors, data storage means 102, input and output means 103 and a machine learning module 104. According to certain embodiments, the system 100 is on board a land motor vehicle and is distributed among one or more computers. According to other embodiments of the invention, the system 5 100 includes one or more computers, one or more servers, one or more supercomputers and / or any combination comprising one of these computer systems. It is also possible to envisage certain embodiments in which certain w elements of the system 100 are partially hosted on board a land motor vehicle, on one or more computers, while other elements are distributed on one or more remote servers. . Alternatively, the system 100 is an integral part of a multimedia system of a land motor vehicle.

Whatever the configuration chosen, the system

100 is able to interact with a vehicle, in particular to extract and / or receive data generated by one or more detection devices (not shown) arranged in the vehicle. Advantageously, the system

100 actually interacts with any system integrated into the vehicle, in particular the systems and sensors allowing the identification of the driver and any additional passengers, as well as the analysis of their physical and / or physiological condition. For some tasks, the system 100 interacts, for example ^- through its input means and output 103, with a receiver of a satellite navigation of the vehicle, with the car multimedia system in the vehicle and / or with a transmitter / receiver of radio frequency signals from the vehicle, in particular for extracting data from one or more remote servers. Preferably, the vehicle multimedia system is capable of extracting and broadcasting multimedia content, for example by means of a radio receiver and / or a communication interface capable of interacting with the means for transmitting radio frequency signals from the 10 vehicle to connect to the Internet.

All of these contribute to allow the system

100 to implement a method for determining at least one value representative of at least one contextual parameter is with regard to a suggestion of multimedia content provided by a multimedia system for a land motor vehicle, as described below. below.

As illustrated in FIG. 2, according to a step 201, the system 100 constitutes, ie extracts, records and / or establishes, operating data. Preferably, the operating data are generated when one of the detection devices arranged in the vehicle emits a signal according to an operating regime of the vehicle. Thus, during each journey, operating data are for example generated according to the signals received from detection devices which are capable of emitting signals as a function of the level of fuel in the tank ^- of the vehicle, as a function of the level of charge of a vehicle battery, as a function of the ambient light, as a function of the presence of drops on the windshield or as a function of an operating regime of a lighting member or of a vehicle wiper.

According to a step 202, the system 100 also receives location data. Conventionally, the location data is transmitted by a satellite positioning system ίο and / or a data source hosted on a remote server. This location data can thus contain elements of cartography, elements of road information or other information such as points of interest or is elements of road signs. Advantageously, the location data used by the system 100 does not go beyond the information elements currently available and used by current navigation systems.

According to a step 203, the location data is processed with regard to a prediction task to be performed, in particular to determine certain input parameters which supply the automatic learning module 104. During this step, the system 100 determines by example a current date, a current time and / or a current place.

According to a step 204, the system 100 constitutes identification data relating to at least one passenger in the vehicle. These identification data concern both the driver and, where applicable, the other passengers in the vehicle.

For a first part, the identification data are generated when the system 100 interacts with a portable identification device that the driver uses to unlock and start the vehicle (e.g.

remote control, electronic key, etc.).

Alternatively, or cumulatively, the system 100 constitutes another part of the identification data by interacting directly with a smartphone, for example by means of a bluetooth link made available by the means of transmission of radio frequency signals from the vehicle. Advantageously, the

system 100 use these means for extract the identifiers some devices electronic 20 laptops finding on board the vehicle, especially from smartphones.

On the basis of these data, the system 100 is able to determine certain information on the passengers of the vehicle, in particular the number of passengers transported. Advantageously, these identification data also allow the system 100 to find and extract a user profile, for example stored on the data storage means 102. In this user profile, information defines the identity of a passenger while d others are related to his age or driving experience. For another part, the identification data are generated following the emission of a signal by at least one detection device arranged in the vehicle and configured to emit a signal as a function of at least one component of a condition. physical and / or psychological of the passenger. For example, during each journey, identification data is generated according to the signals received from detection devices which are capable of emitting signals as a function of the pulse of a passenger, as a function of the body temperature of a passenger, as a function of the weight of a passenger, as a function of the intoxication of a passenger and / or as a function of the positioning of the gaze of a passenger, in particular that of the driver.

During a step 205, the operating data, the location data and the identification data are transmitted to the automatic learning module 104. Firstly, these data are used by the automatic learning module 104 to constitute a training base.

Gradually, the machine learning module

104 builds a predictive model which is refined over time. To do this, the system 100 implements, during each journey, a step of analyzing the input parameters, for example the current date, the current time or the current location, with regard to a multimedia content heard and / or watched using the vehicle's multimedia system.

During a step 206, the system 100 uses the predictive model established by the machine learning module 104 to determine a suggestion of multimedia content. Based on one or more current input parameters, the machine learning module 104 returns a suggestion of multimedia content.

According to a more particular embodiment, the system 100 carries out at the same time an additional step during which the suggestion is returned by the automatic learning module 104 is updated using the location data. By this mechanism, the system 100 is able to take into account that, in certain cases, the location data takes precedence over the suggestions 20 provided by the automatic learning module 104.

This is for example the case when, over time, the automatic learning module 104 has learned that certain places of departure irreparably imply certain multimedia content (for example: "departure = work" implies "multimedia content = station of radio X ";" departure = children's school "implies" multimedia content = new cartoon video available on the Internet ").

During a step 207, the system 100 determines at least one distinctive parameter in connection with the suggestion determined during step 2 06. To do this, the system 100 performs a step which consists in varying one or more parameters entry. In fact, by checking whether the prediction returned by the predictive model of the machine learning module 104,

i.e. the suggestion, is impacted by relative variations of certain input parameters, the ίο 100 system can determine at least one distinctive parameter which influences the suggestion. For example, the system determines, relative to a suggestion of multimedia content, whether it remains identical by varying the input parameter which corresponds to the current date. If, for example, a suggestion remains the same every day of the week except the weekend, or only every Monday morning, the system 100 then determines that the distinctive parameter is linked to the current date. Likewise, by varying the input parameter which corresponds to the current time, the system 100 can determine whether a suggestion of content remains identical for any hour of the day or according to certain particular time slots and thus establish whether the parameter distinctive is linked to the current time.

During a step 208, the system 100 determines the representative value using the distinctive parameter. For example, when the distinctive parameter relates to the current date as above, the system 100 determines that a representative value for this distinctive parameter corresponds to a verbal formulation "every day except the weekend" or, according to a another 5 example, "every Monday morning". Other representative values can however be envisaged. Thus, when the distinctive parameter relates to the current place, it can then be envisaged that the system 100 determines a representative value which corresponds to a verbal formulation such as "whenever this place is the place of departure". As we have understood, the representative value therefore defines a context parameter related to the suggestion.

is then, the system 100 uses the representative value determined in step 208 to deduce therefrom a contextual indication. For example, the contextual indication determined by the system 100 during this step may correspond to a series of words similar to the verbal formulations mentioned above. In other cases, the context indication corresponds to a set of digital data which define an image, a video and / or an audio message.

Finally, once the context indication has been determined, it is transmitted to an information dissemination interface. The information dissemination interface is configured to be able to use the context indication and produce a descriptive element, for example a sound message or a visual animation. Preferably, the information broadcasting interface is an integral part of the multimedia system of the vehicle. Alternatively, the information broadcasting interface 5 is in the form of an independent electronic device arranged in the console of the vehicle and which comprises a screen and / or a loudspeaker. In still other cases, one can imagine that it is one of the information dissemination interfaces of a smartphone 10 (eg screen, speakers) on board the vehicle which is used at this stage by the system 100.

The system 100 according to the invention therefore considerably improves the interaction with the user to the extent that it becomes possible to provide a multimedia system for a vehicle which is not content to learn the habits and offer relevant content but which is also able to justify the suggestions it provides. The user, who better understands the paths and reasoning implemented by the artificial intelligence functionalities, is then more understanding with regard to possible errors and more attentive to progress.

This advance in terms of human-machine interface in the field of multimedia systems for vehicles is based on the method and the system according to the invention which, as described above and defined by the claims, establish a specific choice of parameters and a particular way of dealing with these parameters in order to draw exploitable results in connection with the desired improvement goal.

The invention is not limited to the embodiments described above, presented only by way of examples,

m.ci i. s extends to other embodiments, in particular those by combining certain characteristics described in connection with certain embodiments with other characteristics described in connection with other embodiments which are within the reach of ordinary skill in the art. job.

Claims (8)

CLAIMS: 1. Method for determining by a computer system (100) at least a value representative of at least 5 a contextual parameter with regard to a suggestion of multimedia content provided by a multimedia system on board a land motor vehicle, characterized in that the method comprises the steps of: w - constitute operating data, said operating data being generated following the emission of at least one signal by at least one first detection device arranged in the vehicle and configured to emit a signal according to a speed vehicle operation, - receive location data, said location data being transmitted by a satellite positioning system and / or a remote data source, 20 - process said location data to extract at least one relevant parameter, - constitute identification data relating to at least one passenger in the vehicle, said identification data being partly generated following the emission of a signal by at least one second detection device arranged in the vehicle and configured to ^- emit a signal as a function of at least one component of a physical and / or psychological condition of said passenger, - transmit said operating data. said location data and said identification data to a machine learning module which, on the basis of said operating data, said location data and said identification data, establishes a predictive model capable of processing at least one parameter d entry, use the predictive model to determine the suggestion, - determine at least one distinctive parameter related to said suggestion, and - determine the representative value using the distinctive parameter. 2. Method according to claim 1, characterized in that it comprises a step of using the representative value to determine a textual indication. 3. Method according to one of the preceding claims, characterized in that it comprises a step of interaction with an information dissemination interface capable of taking charge of the context indication for producing a sound message and / or an animat i on. Method according to claim 3, characterized in that said information broadcasting interface is an integral part of said multimedia system. 2 0 5. Method according to one of the preceding claims, characterized in that the step of determining the distinctive parameter comprises a step consisting in varying the input parameter. 6. Method according to one of the preceding claims, characterized in that the step of using the predictive model comprises a step of using ίο location data to update said suggestion. Computer system for determining at least one value representative of at least one contextual parameter with regard to a suggestion of multimedia content provided by a multimedia system on board a land motor vehicle in which at least one first apparatus is arranged. detection configured to emit a signal as a function of a vehicle operating regime, at least a second detection device configured to emit a signal as a function of at least one component of a passenger's physical and / or psychological condition , a receiver for receiving location data supplied by a satellite positioning system and allowing the time-stamped determination of the geographical position of the vehicle and a means of transmitting and receiving radio frequency signals for communicating with a remote server and / or a portable electronic device, characterized in that it comprises means (101, 102, 103, 104) implementing a procedure é according to any one of the preceding claims. 8. System according to claim 7, characterized in that it comprises a calculation unit, a machine learning module and storage means in which at least one ίο program is stored for the execution of steps of the process of determination implemented by the system. 9. Computer program comprising instructions for carrying out the steps of a method according to one 15 any of claims 1 to 6. 10. Land motor vehicle, characterized in that it comprises a system according to one of claims 7 or 8.