A method for personalizing a motor vehicle, associated computer program, electronic device for personalizing a motor vehicle, and an assembly comprising such a device

Abstract

Method for personalizing a motor vehicle, associated computer program, electronic device for personalizing a motor vehicle, and assembly comprising such a device. The present invention relates to a method (100) for personalizing a vehicle. The vehicle includes a cockpit domain controller configured to identify a vehicle user, connect to user equipment, and collect social network data from the user.The method (100) comprises: - a step (102) of acquiring, by the cockpit domain controller, social network data associated with a respective user; - a step (104) of constructing a model of a user profile, called the user model, from the social network data associated with said user; and - a step (106) of transmitting the user model to at least one electronic device embedded in the vehicle, for the purpose of performing an action dependent on the user model by the embedded electronic device. Figure 2 for the abbreviation.

Description

Title of the invention: Method for personalizing a motor vehicle, associated computer program, electronic device for personalizing a motor vehicle, and assembly comprising such a device

[0001] The present invention relates to a method for personalizing a motor vehicle, implemented by an electronic personalization device. It also relates to a computer program for implementing such a personalization method, as well as such an electronic device for personalizing a motor vehicle and an assembly comprising such a personalization device.

[0002] Devices integrated into electric vehicles are known that provide recommendations based on data collected from user equipment.

[0003] However, these recommendations are limited to specific applications, such as in-vehicle infotainment. Other issues related to road transport, such as improving safety, are not addressed by these applications.

[0004] The aim of the invention is therefore to propose a method of personalizing a motor vehicle allowing new applications related to driving the vehicle, in particular to improve safety on board the vehicle.

[0005] To this end, the invention relates to a method for personalizing a motor vehicle, implemented by an electronic vehicle personalization device intended to be installed on board the motor vehicle, the vehicle comprising a cockpit domain controller configured to identify a vehicle user, connect to user equipment and collect social network data from the user, the method comprising:

[0006] - an acquisition step, by the cockpit domain controller, of the social media data associated with a respective user;

[0007] - a step in constructing a model of a user profile, called a model user, based on social network data associated with said user; and

[0008] - a step of transmitting the user model to at least one piece of equipment embedded electronics in the vehicle, for the purpose of carrying out an action dependent on the user model by the embedded electronic equipment.

[0009] Thanks to the invention, the data collected are used to build a user model intended to be used by a wide variety of electronic equipment embedded in the vehicle, including driving and navigation systems.

[0010] In addition, the development of the user model makes it possible to avoid storing social network data, thus allowing for optimization of storage as well as data confidentiality.

[0011] According to other advantageous aspects of the invention, the personalization process comprises one or more of the following features, taken individually or in all technically possible combinations:

[0012] - social network data includes one or more data points from the group comprising:

[0013] - a list of social networks frequently used by the user;

[0014] - a history of actions performed by the user on each social network;

[0015] - keywords associated with content viewed by the user on each network social ;

[0016] - a history of the time periods of use of each social network by the user;

[0017] - a language for using at least one social network; and

[0018] - a location of the user when using at least one social network;

[0019] - the user model does not contain social network data and is registered in a memory device intended to be stored only in the vehicle;

[0020] - the construction step is carried out via the implementation of an algorithm artificial intelligence;

[0021] - the artificial intelligence algorithm has a type architecture transformer;

[0022] - the construction step involves determining a social group of the user based on social network data and recommendations for merging data from the social networks considered.

[0023] The invention also relates to a computer program comprising software instructions which, when executed by computer, implement a personalization process as defined above.

[0024] The invention also relates to an electronic device for personalizing a motor vehicle, intended to be installed on board the motor vehicle, the vehicle comprising a cockpit domain controller configured to identify a vehicle user, connect to user equipment and collect social network data from the user, the electronic device comprising:

[0025] - an acquisition module, from the cockpit domain controller, of social media data associated with a respective user;

[0026] - a module for constructing a model of a user profile, called a model user, based on social network data associated with said user; and

[0027] - a user model transmission module to at least one piece of equipment embedded electronics in the vehicle, for the purpose of carrying out an action dependent on the user model by the embedded electronic equipment.

[0028] The invention also relates to an assembly comprising:

[0029] - a cockpit domain controller configured to identify a user, se connect to a user's device and collect the user's social network data;

[0030] - an electronic personalization device according to the preceding claim; and

[0031] - at least one on-board electronic device, configured to receive the model user transmitted by the electronic personalization device and to implement an action dependent on said user model.

[0032] According to another advantageous aspect of the invention, the assembly is such that at least one on-board equipment is chosen from the group comprising:

[0033] - the cockpit domain controller, configured to return to the user a information or a recommendation relating to driving the vehicle or using on-board equipment, depending on the user model;

[0034] - an equipment controller configured to control the activation of one or several other pieces of equipment, such as headlights or windshield wipers; and

[0035] - an emotion detector, configured to detect at least one emotion of the user using a context provided by the user model and to generate a control signal from another piece of equipment based on the detected emotion.

[0036] The invention will become clearer upon reading the following description, given solely by way of non-limiting example, and made with reference to the drawings in which:

[0037] [Fig-1] [Fig.1] is a schematic representation of a motor vehicle including an electronic personalization device according to the invention;

[0038] [Fig.2] [Fig.2] is a diagram of a method, according to the invention, for personalizing a motor vehicle, implemented by the electronic personalization device of [Fig.1].

[0039] In [Fig. 1], a motor vehicle 1 includes an electronic personalization device 3 and on-board electronic equipment 5, 7 and 9. One of the on-board electronic equipment is a cockpit domain controller 5, for example located in a dashboard 11 at the front of the motor vehicle 1, near a driver of the vehicle 1. In addition or alternatively, the on-board electronic equipment is an equipment controller 7, or even an emotion detector 9.

[0040] The cockpit domain controller 5 is configured to control a set of infotainment functions within a vehicle cockpit 1. In addition, the cockpit domain controller 5 is configured to connect to a user device 13, for example a smartphone (from the English "smar" or "iphone"), belonging to a user of the vehicle 1. The user uses the user device 13, in particular, to browse social networks, which generates social network data D, stored on the user device 13 and / or on a social network to which the user device 13 is advantageously connected. Once connected to the user device 13, the cockpit domain controller 5 is further configured to collect the user's social network data D.

[0041] As seen in [Fig.1], the electronic personalization device 3 includes a data acquisition interface from the cockpit domain controller 5 and data transmission interfaces respectively to the onboard electronic equipment 5, 7 and 9. The electronic personalization device 3 includes an acquisition module 15, a construction module 17 and a transmission module 19.

[0042] The acquisition module 15 is configured to acquire, from the cockpit domain controller 5, the social network data D associated with the user whose user equipment 13 is connected to the cockpit domain controller 5. This acquisition is done via the aforementioned acquisition interface.

[0043] Social network data represents the user's usage habits on social networks, as well as the tasks performed by the user on these networks. In particular, social network data includes one or more data items from the group comprising: • a list of social networks frequently used by the user; • a history of actions performed by the user on each social network; • keywords associated with content viewed by the user on each social network; • a history of the time periods during which the user used each social network; • a language used on at least one social network; and • user location when using at least one network social.

[0044] The construction module 17 is configured to construct a model of a user profile, referred to as user model M, from the social network data D associated with the aforementioned user. "Constructing a model" means both a construction of a new model, i.e. the construction of a model ex nihilo, rather than an enrichment of a pre-existing model.

[0045] The user model M represents a social profile of the user. In particular, the user model M represents the user's social habits, while avoiding the storage of social network data D itself. This resolves data privacy issues that would arise from storing social network data D.

[0046] In addition, the social network data D is preferably anonymized by the acquisition module 15 or by the construction module 17. Advantageously, the user model M also represents a social group of the user, obtained from the social network data D and recommendations for merging data from the social networks considered.

[0047] Advantageously, the construction module 17 is configured to construct the user model M via the implementation of an artificial intelligence algorithm. The artificial intelligence algorithm typically has a transformer-type architecture. The artificial intelligence algorithm is, for example, a neural network, receiving as input social network data D and delivering as output the user model M.

[0048] During a preliminary learning phase, also called the training phase, the artificial intelligence algorithm is trained with training data comprising, for each training dataset, social network data D as input to the algorithm and a corresponding user model M as output to the algorithm. During this learning, the adaptation of the artificial intelligence algorithm's parameters, such as the synaptic weights of the neural network, is performed, for example, via backpropagation of the gradient, and the parameters of the artificial intelligence algorithm are then adapted according to the gradient of an error between a predicted user model and a target user model.

[0049] The transmission module 19 is configured to transmit the user model M to at least one of the on-board electronic equipment 5, 7 and 9, in order to carry out an action dependent on the user model M by the on-board electronic equipment 5, 7 or 9, as will be explained in the rest of the description.

[0050] In the example of [Fig.1], the electronic personalization device 3 is made in the form of an information processing unit formed for example of a memory 21 and a processor 23 associated with the memory 21.

[0051] In the example of [Fig. 1], the acquisition module 15, the construction module 17 and the transmission module 19 are each implemented in the form of software, or of a software component, executable by the processor 23. The memory 21 of the electronic personalization device 3 is then capable of storing acquisition software, construction software, and transmission software. The processor 23 is then capable of executing each of the following software components: acquisition software, construction software, and transmission software.

[0052] Advantageously, the user model M is stored in memory 21, intended to be disposed of only in vehicle 1.

[0053] Advantageously, the memory 21 stores different user models M, each user model M corresponding to a respective user of the vehicle 1.

[0054] In an alternative not shown, the acquisition module 15, the construction module 17 and the transmission module 19 are each implemented as a programmable logic component, such as an FPGA (Field Programmable Gate Array), or as a dedicated integrated circuit, such as an ASIC (Application-Specific Integrated Circuit).

[0055] When the electronic personalization device 3 is implemented in the form of one or more software programs, i.e., in the form of a computer program, it is also capable of being stored on a computer-readable medium (not shown). A computer-readable medium is, for example, a medium capable of storing electronic instructions and being connected to a bus of a computer system. For example, a readable medium is an optical disc, a magneto-optical disc, a ROM, a RAM, any type of non-volatile memory (e.g., EPROM, EEPROM, FLASH, NVRAM), a magnetic card, or an optical card. A computer program comprising software instructions is then stored on the readable medium.

[0056] The on-board electronic equipment 5, 7 and 9 each include an interface for receiving the user model M from the electronic personalization device 3, in particular from the transmission module 19, and are configured to implement an action dependent on the received user model M.

[0057] The cockpit domain controller 5 is, for example, configured to control the infotainment functions of vehicle 1. Depending on the user model M, the cockpit domain controller 5 anticipates, for example, the user's destinations or travel habits and suggests routes corresponding to these habits, thus reducing the driver's mental workload for route management. Advantageously, the cockpit domain controller 5 selects and recommends a charging or maintenance location for vehicle 1 based on the user's consumption habits, thereby anticipating breakdowns. The cockpit domain controller 5 is also capable of suggesting personalized entertainment content to a passenger user, allowing to limit distractions for the driver. According to another example, if the user model M has been trained on social network data D showing that the user does not listen to music while driving or during a specific time period, the cockpit domain controller 5 disables music recommendations respectively when the vehicle 1 is running or during the time periods in order not to distract the driver, and therefore limit a risk of accident.

[0058] The equipment controller 7 is configured to control the activation of one or more other pieces of equipment, such as headlights or windshield wipers. Thanks to the user model M, this control is, for example, adapted to the user's habits, which reduces the driver's cognitive load while driving, and thus improves safety on board vehicle 1, as the driver can focus more attention on driving vehicle 1.

[0059] The emotion detector 9 is configured to detect at least one user emotion using a context provided by the user model M and to generate a control signal for another piece of equipment based on the detected emotion. The emotion detector 9 is generally used to secure the vehicle 1, for example by detecting an event generating the emotion of surprise, but currently suffers from errors in interpreting emotions due to a lack of context. The use of the user model M overcomes this limitation.

[0060] In an alternative not shown, the on-board equipment 5, 7 and 9 may be any other type of on-board electronic equipment performing at least one action dependent on the user model M.

[0061] A personalization process 100, implemented by the electronic personalization device 3, is shown in [Fig.2], and includes an acquisition step 102, a construction step 104 and a transmission step 106.

[0062] Acquisition step 102 is implemented by the acquisition module 15, and consists of acquiring, from the cockpit domain controller 5, the social network data D associated with a respective user.

[0063] Construction step 104 is implemented by construction module 15 and consists of constructing the user model M from social network data D. Construction step 104 is preferably performed by an artificial intelligence algorithm, which advantageously has a transformer-type architecture. Construction step 104 advantageously includes determining the user's social group.

[0064] The transmission step 106 is implemented by the transmission module 19, and consists of transmitting the user model M to at least one of the on-board electronic equipment 5, 7 and 9, in order to carry out the action dependent on the user model M by the on-board electronic equipment 5, 7 or 9.

[0065] It is thus understood that the electronic personalization device 3 and the personalization process according to the invention make it possible to improve safety on board the motor vehicle 1, in particular by reducing the cognitive load for the driver of the motor vehicle 1 who can then focus more on driving the vehicle 1.

Claims

Demands

1. A method for personalizing (100) a motor vehicle (1), implemented by an electronic vehicle personalization device (3) intended to be installed on board the motor vehicle (1), the vehicle (1) comprising a cockpit domain controller (5) configured to identify a user of the vehicle (1), connect to a user device (13) and collect social network data (D) from the user, the method (100) comprising: • a step (102) of acquiring, by the cockpit domain controller (5), the social network data (D) associated with a respective user; characterized in that it further comprises: • a step (104) of constructing a model of a user profile, called the user model (M), from the social network data (D) associated with said user;and • a step (106) of transmitting the user model (M) to at least one electronic device (5,7,9) on board the vehicle (1), with a view to carrying out an action dependent on the user model (M) by the on-board electronic device (5, 7, 9).

2. A method (100) according to claim 1, wherein the social network data (D) comprises one or more data items from the group comprising: • a list of social networks frequently used by the user; • a history of actions performed by the user on each social network; • keywords associated with content viewed by the user on each social network; • a history of the time periods of use of each social network by the user; • a language of use of at least one social network; and • a location of the user when using at least one social network.

3. Method (100) according to any one of the preceding claims, wherein the user model (M) does not contain the social network data (D) and is stored in a memory (21) intended to be disposed of only in the vehicle (1).

4. A method (100) according to any one of the preceding claims, wherein the construction step (102) is carried out via the implementation of an artificial intelligence algorithm.

5. Method (100) according to claim 4, wherein the artificial intelligence algorithm has a transformer-type architecture.

6. A method (100) according to any one of the preceding claims, wherein the construction step (104) comprises determining a user's social group from social network data (D) and recommendations for merging data from the social networks in question.

7. Computer program comprising software instructions which, when executed by computer, implement a method (100) according to any one of the preceding claims.

8. Electronic device (3) for personalizing a motor vehicle (1), intended to be installed on board the motor vehicle (1), the vehicle (1) comprising a cockpit domain controller (5) configured to identify a user of the vehicle (1), connect to a user device (13) and collect social network data (D) from the user, the electronic device (3) comprising: • a module (15) for acquiring, from the cockpit domain controller (5), the social network data (D) associated with a respective user; • a module (17) for constructing a model of a user profile, called the user model (M), from the social network data (D) associated with said user;and • a module (19) for transmitting the user model (M) to at least one electronic device (5, 7, 9) on board the vehicle (1), for the purpose of carrying out an action dependent on the user model (M) by the on-board electronic device (5, 7, 9).

9. Set comprising: • a cockpit domain controller (5) configured to identify a user, connect to a user device (13) and collect the user's social network data (D); • an electronic personalization device (3) according to the preceding claim; and • at least one on-board electronic device (5, 7, 9), configured to receive the user model (M) transmitted by the electronic personalization device (3) and to implement an action dependent on said user model (M).

10. Assembly according to the preceding claim, wherein at least one on-board equipment (5, 7, 9) is selected from the group comprising: • the cockpit domain controller (5), configured to provide the user with information or a recommendation relating to driving the vehicle (1) or using on-board equipment, depending on the user model (M); • an equipment controller (7) configured to control the activation of one or more other pieces of equipment, such as headlights or windshield wipers; and • an emotion detector (9), configured to detect at least one emotion of the user using a context provided by the user model and to generate a control signal from another piece of equipment based on the emotion detected.

Images