DEVICE AND METHOD FOR MODIFYING A USER'S EMOTIONAL STATE

Abstract

The device (100) for modifying a user's emotional state comprises: - a real-time reader (105) of electroencephalographic signals, - a module (110) for determining an emotional state based on a read electroencephalographic signal, - a means (115) for determining a target emotional state, - an automatic selector (120) of a sequence of at least one sound file from a pre-constituted list of sound files, based on the determined target emotional state, the read electroencephalographic signal, and at least one parameter associated with each sound file, and - an electroacoustic transducer (125) configured to read the selected sequence of sound files. Figure for the abbreviation: Figure 1

Description

Title of the invention: DEVICE AND METHOD FOR MODIFYING A USER'S EMOTIONAL STATE Technical field of the invention

[0001] The present invention relates to a device and a method for modifying a user's emotional state. It is applicable, in particular, to the field of improving well-being and controlling an individual's emotional state. State of the art

[0002] The development of cognitive, motor, and sensory skills is part of a broader effort to increase human life expectancy. In this pursuit of performance and well-being, neurotechnology is an essential solution. This field of research stems from the convergence of neuroscience and computer science, which leads to modifications in mental patterns and models.

[0003] One of the objectives of neuro-technologies is the increase of human performance and the improvement of human well-being.

[0004] Currently, the following solutions are known: - Melomind (registered trademark): a system consisting of headphones that deliver sounds to monitor an individual's relaxation level in real time. - Muse (registered trademark): a system composed of EEG (electroencephalogram) sensors that measure tiny electrical fields in the brain, heart rate, respiration, and oximetry sensors; - Dreem-Urgo (registered trademark): a system composed of a physiological data sensor and EEG sensors;

[0005] - Emotiv (registered trademark): a system composed of an EEG sensor and earphones allowing an indication of the user's stress and distraction level.

[0006] However, all these solutions have the following drawbacks: - Failure to consider user preferences in sound stimuli: The algorithms for providing sound stimuli only take into account the individual's brain activity by imposing noises to which they are not accustomed, resulting in disinterest or even rejection of the solutions.

[0007] - No real-time adaptability: even if these technologies perceive in time Because they accurately reflect brain activity signals, the algorithms used are unable to adapt to unanticipated variations in the user's desires throughout their use of the system. They were designed in such a way that the user goes from one point A to point B by a single path, often based on: brain activity and / or the physiology of the individual (heart rate). - Highly constrained emotional trajectories: Currently, users cannot target the emotional state they wish to achieve. Indeed, if they purchase a Melomind or Muse headset, it is solely for the purpose of relaxation. While some systems like Emotiv can detect different emotions, they do not allow the user to transition from one emotion to another. These technologies are often unidirectional. They start with stress and lead to a state of relaxation or concentration. The reverse is therefore not possible.

[0008] Object of the invention

[0009] The present invention aims to remedy all or part of these drawbacks.

[0010] To this end, according to a first aspect, the present invention relates to a device for modifying a user's emotional state, comprising: - a real-time reader of electroencephalographic signals, - a module for determining an emotional state based on a read electroencephalographic signal, - a means for determining a target emotional state, - an automatic selector of a sequence of at least one sound file, from a pre-constituted list of sound files, based on the determined target emotional state, the read electroencephalographic signal, and at least one parameter associated with each said sound file and - an electroacoustic transducer configured to play the selected sequence of sound files.

[0011] Thanks to these provisions, a user can voluntarily determine an emotional state to be achieved, the device determining an optimal sound file vector and playing each sound file in succession to gradually adapt the user's emotional state.

[0012] The use of a real-time reader of electroencephalographic signals allows for a dynamic adaptation of the sequence based on its success on the evolution of the individual's emotional state or actions, such as the unplanned reading of a sound file requiring an update of the sound file vector.

[0013] The use of pre-constructed sound files, in particular those produced by artists preferred by the user, helps to minimize the risk of rejection of the device by the user.

[0014] In some embodiments, the device of the present invention further comprises a secondary selector for a sound file and a means for updating the succession based on the sound file manually selected by the secondary selector.

[0015] These embodiments allow the user to voluntarily select a sound file to play, interrupting the selected sequence, while allowing the device to adapt the sequence of sound files to this interruption.

[0016] In embodiments, the device of the present invention comprises: - a sound file identifier collector and - a sound file classifier configured to associate, with at least one sound file identifier, a parameter representative of an emotional state promoted by said sound file.

[0017] These embodiments make it possible to associate with pre-constructed sound files indicators used in the selection of the sequence of sound files to be read.

[0018] In some embodiments, the classifier is a trained machine learning system.

[0019] These embodiments allow for the automatic classification of new sound files, ensuring efficient updating of the pre-constructed sound file list.

[0020] In embodiments, the classifier is configured to classify a sound file by assigning a value to at least one of three characteristics: - valence, - arousal and - dominance, at least one characteristic being implemented to determine an emotional state favored by a sound track.

[0021] In embodiments, at least one sound file is associated with an indicator of user behavior with respect to each said sound file, the automatic selector being configured to select a succession of at least one sound file according to a value of said indicator for at least one sound file.

[0022] These embodiments make it possible to quantify a user's preference for a sound file in order to minimize the risk of rejecting the selected sequence.

[0023] In embodiments, the automatic selector includes a sound file filter based on at least one indicator of user behavior with respect to at least one sound file, the selector being configured to select a sequence of sound files from a list of sound files filtered by the filter.

[0024] These embodiments make it possible to quantify a user's preference for a sound file in order to minimize the risk of rejecting the selected sequence.

[0025] In embodiments, a parameter used by the automatic selector to select a sequence of sound files is a representative indicator of an emotional state value associated with at least one sound file.

[0026] In embodiments, the sequence of sound files is configured to present an increasing gradient of emotional state value corresponding to the determined target emotional state.

[0027] These embodiments make it possible to determine a succession of increasing intensity, associated with a target emotional state.

[0028] According to a second aspect, the present invention relates to a method for modifying a user's emotional state, which comprises: - a step of determining a target emotional state, then, iteratively, at least part of the following steps: - a real-time reading stage of electroencephalographic signals, - a step of determining an emotional state based on a read electroencephalographic signal, - an automatic selection step of a sequence of at least one sound file, from a pre-established list of sound files, based on the determined target emotional state, the electroencephalographic signal read, and at least one parameter associated with each said sound file and - a reading step, by an electroacoustic transducer, of the selected sequence of sound files.

[0029] The advantages of the process which is the subject of the present invention being identical to those of the device which is the subject of the present invention, they are not recalled here. Brief description of the figures

[0030] Other advantages, purposes and particular features of the invention will become apparent from the following non-limiting description of at least one particular embodiment of the device and method of the present invention, with reference to the accompanying drawings, in which:

[0031] [Fig. 1] schematically represents a first particular embodiment of the device that is the subject of the present invention,

[0032] [Fig.2] schematically represents a second particular embodiment of the device which is the subject of the present invention,

[0033] [Fig.3] represents, schematically and in the form of a flowchart, a succession of a particular step in the process that is the subject of the present invention,

[0034] [Fig.4] schematically represents a distribution of a sample of files musical in terms of energizing nature, distributed between values ​​of 0.1 and 1,

[0035] [Fig.5] schematically represents a distribution of a sample of files musical in terms of danceable nature, distributed between values ​​of 0.1 and 1 and

[0036] [Fig.6] schematically represents a distribution of sound files to be read corresponding to a determined logarithmic vector of emotional state modification,

[0037] [Fig.7] schematically represents a distribution of sound files to be played corresponding to a specific linear vector of change in emotional state,

[0038] [Fig.8] schematically represents a distribution of values ​​of an acoustic nature of sound files corresponding to distinct emotional states and

[0039] [Fig.9] schematically represents a distribution of sound volume values of sound files corresponding to distinct emotional states. Description of the implementation methods

[0040] The present description is given by way of non-limiting grammar, each feature of an embodiment being able to be advantageously combined with any other feature of any other embodiment.

[0041] It should be noted from the outset that the figures are not to scale.

[0042] The result of the interaction of subjective factors and objectives, achieved by neural or endocrine systems, which can: - induce experiences such as feelings of arousal, pleasure or displeasure; - generate cognitive processes such as perceptually relevant reorientations, evaluations, labeling; - activate global physiological adjustments; - to induce behaviors that are, most often, expressive, goal-directed and adaptive.

[0043] Such an emotional state is, for example, for a human: - Stress (difficulty concentrating, chaotic and disrupted thought processes due to the source of stress, excitement, fear), - Relaxation (calm state, absence or low level of thought activity, ideas flow slowly), - Concentration (intense brain activity, non-receptivity to external signals) and - Interest / engagement (measures the level of immersion in any stimulus. Engagement can increase when immersed in stimuli that can be positive or negative in nature. It has been found in experimental brain research that engagement decreases in boring, banal and automatic cognitive processes).

[0044] Figure 1, which is not to scale, shows a schematic view of one embodiment of the device 100 that is the subject of the present invention. This device 100 for modifying a user's emotional state comprises: - a real-time reader 105 of electroencephalographic signals, - a module 110 for determining an emotional state based on a read electroencephalographic signal, - a means of determining a target emotional state, - an automatic selector of 120, from a sequence of at least one sound file, chosen from a pre-defined list of sound files, based on the determined target emotional state, the electroencephalographic signal read, and at least one parameter associated with each sound file and - a 125 electroacoustic transducer configured to play the selected sequence of sound files.

[0045] The reader 105 is, for example, an electroencephalogram-type headset equipped with earphones acting as an electroacoustic transducer 125. The type of electroencephalogram considered may be any type known to a person competent in the field of neurotechnology. Preferably, a non-invasive type of electroencephalogram is used.

[0046] An electroencephalogram (EEG) is designed to capture electrical signals resulting from the summation of synchronous postsynaptic potentials originating from a large number of neurons. Such a signal can be representative of the neurophysiological activity of the individual wearing the reader 105 and, thus, of that individual's emotional state.

[0047] The acquisition is for example made from seven dry electrodes placed on the skull of a user, preferably in positions A1, T3, C3, CZ, C4, T4, A2, T5 and T6 according to the 10-20 system. These electrodes measure the potential difference (in Volts) between the different locations and “ground”, placed on the nearest ear.

[0048] The choice of positioning these electrodes is mainly linked to the geometry of the helmet and the comfort of use, but also to the selection of certain points less subject to motor artifacts (blinking, sniffing, etc.).

[0049] The electrodes are connected to a digital board. This board is configured to transmit the signal to the determination module 110 or to a computer, for example via Bluetooth to a USB receiver connected to the computer.

[0050] The chosen sampling duration is, for example, 5 seconds (every 5 seconds, the signal from the last 5 seconds is retrieved). This value could be increased to 8 seconds, or even 10 seconds, 5, 8 and 10 being the sampling durations allowing the best inference of emotions.

[0051] From the raw signal, the intensity of the different frequencies can be calculated by Fourier transform. A first pre-processing of the signal can be applied to remove frequencies close to 50 Hz (49 to 51 Hz) or 60 Hz (59 to 61 Hz) which are intensely affected by interference in the presence of electrical devices plugged into the mains near the recording device (the headphones).

[0052] A second bandpass filter can be applied to retain only the frequencies in the range of 2 to 58 Hz, in order to eliminate low-frequency parasitic noise, and the high-frequency gamma bands (60 Hz and above) which Bluetooth does not allow us to properly describe.

[0053] The two filters used are, for example, of the 5th order Butterworth type.

[0054] The determination module 110 is, for example, a computer software program executed by an electronic computing circuit. This determination module 110 is configured, for example, to determine an individual's emotional state in the following way:

[0055] The three-variable system commonly used and called the “VAD” model for the axes of Valence, Arousal (translated as “excitation”), and Dominance in English is chosen as a model to describe emotions.

[0056] Valence describes the negative, neutral, or positive character associated with an emotion.

[0057] Excitement measures the passive, neutral or active nature of the emotional state described.

[0058] Dominance describes the assertive or submissive nature of the emotional state described. This axis allows, for example, the discrimination of rage from fear (which are both characterized by low valence and high excitation), or relaxation from joy.

[0059] For each axis, we define 3 possible discrete values:

[0060] Valence: -1 for negative, 0 for neutral, 1 for positive,

[0061] Arousal: -1 for passive, 0 for neutral, 1 for active and

[0062] Dominance: -1 for low, 0 for medium, 1 for high.

[0063] The following labels are assigned to the VAD value triplets: - Excited: (1, 1, 1) - Happy: (1,0,1) - Content: (1,0,0) - Relaxed, Relaxed: (1,-1,0) - Calm: (0,-1,0) - Sad, Depressed :(-1,-1,-1) - De-stressed: (0,1,0) - Neutral: (0,0,0) - Deep sorrow: (-1,0,-1)

[0064] Other emotional descriptors can be used in addition to VAD values, as they are easy to detect and recognize from brain recordings, such as relaxation and concentration.

[0065] Each sound track can be placed according to these coordinates so as to calculate a vector step by step allowing, starting from determined coordinates, to expect other coordinates corresponding to a target emotional state.

[0066] The determination module 110 can be implemented locally or remotely and accessed via a data network. For example, the determination module 110 can be implemented on a smartphone connected to the reader 105 by wire or, preferably, wirelessly.

[0067] The means 115 for determining a target emotional state is, for example, a human-machine interface (e.g., a graphical interface associated with an input device) or a software interface (e.g., an API, for Application Programming Interface). This determination means 115 is configured to receive, as input, a signal that varies between several possible emotional states.

[0068] These emotional states can be predetermined, that is to say, form a finite list of possibilities from which an implemented interface selects.

[0069] These emotional states can be determined based on the content of input made on an interface. For example, a human-machine interface allows the free input of alphanumeric characters representing human language, a user of the device 100 entering keywords describing an emotional state to be achieved, the determination means 115 being configured to associate defined emotional states with these keywords.

[0070] The determination means 115 can be implemented locally or remotely and accessed via a data network. For example, the determination means 115 can be implemented on a smartphone associated with the determination module 110.

[0071] The automatic selector 120 is, for example, a computer program executed by an electronic computing circuit. The automatic selector 120 is configured, for example, to execute an algorithm that measures the distance between the emotional state read from a user of the device 100 and the target state determined by the determination means 115. Based on the distance thus measured, a sequence of at least one sound file is selected according to at least one parameter associated with at least one of said sound files.

[0072] Such a parameter may be, for example: - a technical parameter, such as the duration, mode, key, time signature or tempo of the sound file or - an acoustic or psychoacoustic parameter representative of: - the acoustic nature of the sound file, that is to say the use or not of electronic instruments and / or the proportion of such use, - the energizing, or invigorating, nature of the sound file, that is, a perceptual measure of intensity and activity - the perceptual characteristics contributing to this attribute include dynamic range, perceived loudness, timbre, rate of occurrence, and overall entropy, - the instrumental nature of the sound file, that is to say, the use or not of voice on said sound file, - the danceable nature of the sound file, measured for example according to the tempo, the stability of the rhythm, the strength of the beat and the overall regularity of the audio file, - the valence of the sound file, that is to say the positivity of the sound file, - the nature of the sound file recording, i.e., studio recording or live performance of the sound file, - the nature of the speech density, that is to say the proportion of words and music in an audio file and / or - the intensity of the sound file, that is to say the average intensity, measured in decibels, of the sound file.

[0073] Each of these parameters can be directly associated with an emotional state and thus, depending on the target emotional state, be a candidate for inclusion in the sequence of sound files.

[0074] The association between values ​​for these parameters and emotional state (via, for example, a VAD profile) can be achieved, for example, by implementing a learning algorithm, obtained in a similar way to the IADS-E dataset from the Center for the Study of Emotions and Attention at the University of Florida.

[0075] Alternatively, an expert system can be implemented, associating particular values ​​of the VAD profile with an emotional state. An example of such an implementation is provided above.

[0076] In a simplified mode, the energizing nature and the dancing nature are associated with excitation, the mode and valence with valence and intensity with dominance.

[0077] For each sample, a statistical model is then constructed for each acoustic descriptor. The chosen model is, for example, a Gaussian mixture, that is, a weighted set of one to five Gaussian curves (“bell curves”) whose means and standard deviations are recorded, as well as the weights associated with each Gaussian. The resulting Gaussian mixture model describes a probability density curve, which associates with each value of the acoustic parameter considered the probability of being observed for an audio track of the given group (high or low valence, high or low arousal, high or low dominance).

[0078] We have therefore obtained an approximation of the probability that an audio track with given acoustic characteristics is in each quadrant of the VAD space.

[0079] The average probability of belonging to the positive and negative quadrants is calculated for each audio track along each axis. This yields the coordinates of the audio file in question within the VAD space. This position in the VAD space will be read when determining which audio tracks to add to a playlist.

[0080] We observe, in [Fig.4], schematically, a distribution of a sample of music files in terms of energizing nature, distributed between values ​​of 0.1 and 1.

[0081] We observe, in [Fig.5], schematically, a distribution of a sample of music files in terms of dance nature, distributed between values ​​of 0.1 and 1.

[0082] In [Fig.8], schematically, we observe a distribution of the quantification of the acoustic nature of a sample of sound files corresponding in particular to two distinct states: - a calm emotional state 805 and - an emotional state of concentration 810.

[0083] In [Fig.9], schematically, we observe a distribution of the quantization of the sound volume of a sample of sound files corresponding in particular to two distinct states: - an emotional state of concentration 905 and - an emotional state of intense physical activity 910.

[0084] Preferably, a parameter used by the automatic selector 120 to select a sequence of sound files is an indicator representing an emotional state value associated with at least one sound file. Each sound file is then associated with a vector quantifying the impact for at least one emotional state. For example, a sound file may have a first value corresponding to the impact of that sound file on a listener's stress level and a second value corresponding to the impact of that sound file on a listener's relaxation level.

[0085] Preferably, the sequence of sound files is configured to present an increasing gradient of emotional state value corresponding to the determined target emotional state.

[0086] In other words, the current and determined target emotional states are described by coordinates on axes which constitute all or part of the parameters listed above, in a multi-dimensional space.

[0087] Such a vector can be constructed from at least one of the parameters described above.

[0088] Such a vector, in a determined dimensional space, can correspond to an affine or logarithmic function.

[0089] According to a first algorithm, a theoretical straight-line trajectory between the two points in the VAD space is first calculated. This does not yet physically correspond to a list of sound files. Then, the algorithm samples regularly spaced points along this theoretical line (depending on the desired number of sound files, itself a function of the desired playlist length). Finally, the sound files from the database whose coordinates in this space are closest to each of the theoretical points are selected, resulting in an ordered list of sound files.

[0090] According to a second algorithm, the selection of audio tracks is performed iteratively, systematically searching for the file closest to the midpoint between the bounds of the search interval. The process begins by calculating the theoretical midpoint between the two points (current and target states). Next, the audio file in the database closest to this point in the VAD space is determined using its coordinates. This file allows the interval to be split in two, producing two new intervals, on which the procedure is repeated, optionally until a maximum number of audio tracks are obtained.

[0091] The final trajectory obtained is less linear than with algorithm 1, but allows for smoother transitions between tracks.

[0092] The automatic selector 120 can be implemented locally or remotely and accessed via a data network. For example, the automatic selector 120 can be implemented on a smartphone associated with the determination means 115 and the determination module 110.

[0093] The sequence of sound files is sent to an electroacoustic transducer 125. This transmission can be carried out via the motherboard or a sound card of a smartphone interfaced with the automatic selector 120.

[0094] In particular embodiments, such as that shown in [Fig. 1], the device 100 of the present invention comprises: - a collector 140 of sound file identifiers and - a sound file classifier 145 configured to associate, with at least one sound file identifier, a parameter representative of an emotional state favored by said sound file.

[0095] The identifier collector 140 is, for example, computer software executed by an electronic computing circuit. This collector 140 is, for example, configured to collect the identifiers of sound files whose playback is controlled by at least one user associated with the device 100 from a third-party sound file playback application.

[0096] In variants, the identifier collector 140 is a software for reading metadata of identifiers of sound files stored in local or remote computer storage.

[0097] The identifier collector 140 can be implemented locally or remotely and accessed via a data network.

[0098] Classifier 145 is, for example, a computer software program executed by an electronic computing circuit. This classifier 145 is configured to assign, based on parameters of the sound files, as described above, a quantitative value of the impact of the sound file on the emotional state of a listener of the sound file.

[0099] In particular embodiments, the classifier 145 is a trained machine learning system. Such a classifier 145 may be, for example, a supervised or unsupervised machine learning algorithm and of the deep learning type or not.

[0100] For example, such a machine learning system is a supervised neural network device configured to receive as input layer parameter values, as mentioned above, and as output layer emotional state indicators corresponding to the input layer.

[0101] In some embodiments, classifier 145 is configured to classify a sound file by assigning a value to at least one of three characteristics: valence, arousal, and dominance, with at least one characteristic being implemented to determine an emotional state favored by a sound track. Optionally, concentration and / or relaxation may be assigned a value, via classifier 145 or another assignment mechanism.

[0102] In an example of an implementation of such a classifier 145, a computer program allows the user to signal when they deeply feel, in their body, that they are in one of the emotional states listed above. If they confirm their state, the recorded sample is sent to the classification model, which reinforces its learning.

[0103] Frequent use of this reinforcement tool is necessary for the model to learn correctly. Before the user has used this tool sufficiently (several dozen times, with representation of all emotions), the model's performance progresses from random to poor, then mediocre, and finally acceptable. It is possible to implement a pre-trained classifier 145 using a non-user-specific dataset to start with acceptable performance.

[0104] The model is trained to recognize an emotion not from the raw signal, but from transformations of it, which are called features.

[0105] Calculated from a sample recorded over a time t, on the 7 channels listed above: For each channel: - spatial characteristics: the intensity of the alpha [7-13 Hz], beta [14-30 Hz] and gamma [31-90 Hz] frequency bands obtained by Fourier transform, and the differential entropy and - temporal characteristics: approximate entropy, sample entropy, and fractal dimension. Taking into account all channels: - Multi-scale entropy features and - Renyi entropy (or more precisely, a non-parametric estimate of Renyi entropy).

[0106] A classification algorithm can be an ensemble method (a method that averages the predictions of several classifiers) called a “Random Forest”, where the classifiers used are decision trees. For example, a population of one hundred decision trees is used.

[0107] A decision tree is a series of rules that use thresholds on the values ​​of the characteristics.

[0108] The algorithm training phase consists of varying these thresholds until sufficient prediction quality is obtained. Each new sample obtained, for which the associated emotional state is known, allows the thresholds to be refined a little further.

[0109] Model performance varies from one individual to another and cannot be estimated in general. The scientific literature reports average accuracy rates ranging from 60% to 85%, depending on the individual.

[0110] Thus, the computer program that constitutes the training means performs the following steps: - receive the raw signal from the EEG headset (5-second sample), - calculate the signal characteristics, - estimate the valence, arousal, and dominance values ​​of the user's current emotional state, using an average of the decision tree predictions.

[0111] - transform the coordinates (V, A, D) obtained into a percentage of each emotion whose label is known, by calculating the Euclidean distance to the position of these known emotions in the VAD space and normalizing the inverse of these distances, - if the user indicates, via an input device (keyboard, touchscreen), that they are in a known emotional state, offer them the option to use the last sample for participate in training the model and, if it is successful, adjust the thresholds of the decision trees using this new sample and - wait for the receipt of a new sample.

[0112] When the training program is stopped, the population of decision trees is saved, to be loaded at the next start.

[0113] In particular embodiments, at least one sound file is associated with an indicator of user behavior with respect to each said sound file, the automatic selector 120 being configured to select a succession of at least one sound file according to a value of said indicator for at least one sound file.

[0114] Such behavior is, for example, a parameter representing the number of listens, the number of playback interruptions in favor of another audio track, or any other parameter representing a user's preference. This behavioral indicator can be implemented in the selection of the audio file sequence, for example, by assigning a lower weight to candidate audio files whose number of playback interruptions is higher than average, reflecting user dissatisfaction when playing said files.

[0115] In some embodiments, at least one parameter used by the automatic 120 selector is a parameter representing a musical similarity between sound files. Such a musical similarity can be established, for example, based on metadata representing a musical genre or based on one of the parameters described above, with respect to the automatic 120 selector.

[0116] A musical proximity is determined as a function of the Euclidean distances in the parameter space (normalized by their units) exemplified above.

[0117] In particular embodiments, such as that shown in [Fig. 1], the automatic selector 120 includes a sound file filter 121 based on at least one indicator of user behavior with respect to at least one sound file, the selector being configured to select a succession of sound files from a list of sound files filtered by the filter.

[0118] Such a filter 121 is, for example, a software filter allowing a sample of sound files to be established as candidates for selection in the succession of sound files upstream of the actual selection.

[0119] In particular embodiments, such as that shown in [Fig. 1], the device 100 of the present invention further comprises a secondary selector 130 of a sound file and a means 135 of updating the sequence according to the sound file manually selected by the secondary selector.

[0120] The secondary selector 130 is, for example, a human-machine interface (for example, a graphical interface associated with an input device) or a software interface (e.g., API type). This secondary 130 selector is configured to receive, as input, an audio file identifier to be played. A variant of such a secondary 130 selector is, for example, a touchscreen associated with a graphical user interface (GUI) allowing the input of an audio file identifier.

[0121] This selector 130 allows a user to force the playback of a sound file, regardless of the beneficial or negative effect of that sound file on the determined target emotional state.

[0122] However, the quantification of this beneficial or negative effect allows the means 115 of determination to determine a new sequence of sound files allowing the subsequent target emotional state to be reached as a function of the deviation caused by the reading of the sound file selected by the secondary selector 130.

[0123] The secondary selector 130 can be implemented locally or remotely and accessed via a data network.

[0124] Figure 2 schematically illustrates a particular embodiment of a technical ecosystem 200 enabling the implementation of the device 100 that is the subject of the present invention. This technical ecosystem 200 comprises: - a central terminal 205, of the electronic computing circuit type configured to execute sequences of algorithmic instructions in software form, such as for example a computer, a server or a smartphone, - a database 215 of audio files accessible from the central terminal 205, - an EEG headset 210 equipped with earphones allowing the playback of audio files, connected to the central terminal 205 so as to: - receive an audio file to play (or a resource location to read on a data network) and - sending to said terminal 205 an indicator representative of a read EEG signal, said terminal 205 locally determining an emotional state of the wearer of the headset 210 or transmitting this indicator for remote determination, via the use of a computer server for example, - a database 220 for classifying emotional states associated with sound files, linked to a computing resource (not referenced) configured to run a classification algorithm, this database 220 being able to be populated as audio files are played by the central terminal 205 or directly connected to the audio file database 215, - an interface 225 for accessing the classification database 220, via the central terminal 205 (or another computing resource), configured to produce, based on a predetermined target emotional state, a list of sound files candidates for inclusion in the sequence to be produced to modify the user's emotional state, or alternatively directly the sequence of sound files to be played and - optionally, a 230 monitoring and control interface allowing the display of statistics and a 100 device configuration interface.

[0125] Figure 3 schematically illustrates a particular embodiment of the method 300 that is the subject of the present invention. This method 300 for modifying a user's emotional state comprises: - a step 305 of determining a target emotional state, then, iteratively, at least part of the following steps: - a step 310 of real-time reading of electroencephalographic signals, - a step 315 of determining an emotional state based on a read electroencephalographic signal, - a step 320 of automatic selection of a sequence of at least one sound file, from a pre-constituted list of sound files, according to the determined target emotional state, the electroencephalographic signal read and at least one parameter associated with each said sound file and - a step 325 of reading, by an electroacoustic transducer, the selected sequence of sound files.

[0126] Examples of implementation of the steps of process 300 are described with regard to the corresponding means, as described with regard to figures 1 and 2.

Claims

Demands

1. Device (100) for modifying a user's emotional state, comprising: - a real-time reader (105) of electroencephalographic signals, - a module (110) for determining an emotional state based on a read electroencephalographic signal, - a means (115) for determining a target emotional state, - an automatic selector (120) of a sequence of at least one sound file, from a pre-constituted list of sound files, based on the determined target emotional state, the read electroencephalographic signal and at least one parameter associated with each said sound file, - an electroacoustic transducer (125) configured to read the selected sequence of sound files, characterized in that the device further comprises a secondary selector (130) of a sound file and a means (135) for updating the sequence based on the sound file manually selected by the secondary selector.

2. Device (100) according to claim 1, comprising: - a sound file identifier collector (140) and - a sound file classifier (145) configured to associate, with at least one sound file identifier, a parameter representative of an emotional state favored by said sound file.

3. Device (100) according to claim 2, wherein the classifier (145) is a trained machine learning system.

4. Device (100) according to claim 3, wherein the classifier (145) is configured to classify a sound file by assigning a value to at least one of three characteristics: - valence, - excitation and - dominance, at least one characteristic being implemented to determine an emotional state favored by a sound track.

5. Device (100) according to any one of claims 1 to 4, wherein at least one sound file is associated with an indicator of user behavior with respect to each said sound file, the automatic selector (120) being configured to select a succession of at least one sound file based on a value of said indicator for at least one sound file.

6. Device (100) according to claim 5, wherein the automatic selector (120) includes a sound file filter (121) based on at least one indicator of user behavior with respect to at least one sound file, the selector being configured to select a succession of sound files from a list of sound files filtered by the filter.

7. Device (100) according to any one of claims 1 to 6, wherein a parameter used by the automatic selector (120) to select a succession of sound files is a representative indicator of an emotional state value associated with at least one sound file.

8. Device (100) according to claim 7, wherein the succession of sound files is configured to present an increasing gradient of emotional state value corresponding to the determined target emotional state.

Images