DE102013210509A1 - Method and device for operating an infotainment device of a vehicle - Google Patents

Abstract

The infotainment device (20) of the vehicle comprises a selection module (22) for media pieces, which is designed to select media pieces from a set of predetermined media pieces for signaling by the infotainment device (20), depending on predetermined rules. At least one physiological parameter is determined as a function of at least one biosignal of a vehicle user detected with a given sensor, which is detected during and / or after the signaling of a selected piece of media. At least one characteristic feature is determined in each case for the physiological parameter (s) determined, depending on the respective predetermined physiological parameter. Depending on the determined characteristic features, the selected media piece is assigned an emotion rating from a given emotion rating range or from a set of predetermined emotion rating classes.

Description

The invention relates to a method and a device as well as a computer program for operating an infotainment device of a vehicle. Furthermore, the invention relates to a computer program product.

Infotainment devices are commonly used in motor vehicles to reproduce given infotainment data. An output of the infotainment data is predominantly acoustic and / or optical. The vast wealth of music, such as MP3 songs and podcasts, in many media databases available today (music collection on a hard disk and / or in an online music store) wakes up the desire of some operators for an automated selection of music pieces. Therefore, recommendation systems for personalized program preparation are used for the user, in particular in the music sector. However, such music piece and / or podcast recommendation systems typically include a variety of operations and are therefore not, for example, in the automotive environment, where the operator primarily concerned with the driving task may devote only a fraction of his or her overall attention to the operation of a music playback system or practicable only in part.

The object underlying the invention is to provide a method, a device and a computer program for operating an infotainment device as well as a computer program product which enable a simple and efficient improvement and / or adaptation and / or personalization of the provision of Media tracks through the infotainment facility allow.

The object is solved by the features of the independent claims. Advantageous developments of the invention are characterized in the subclaims.

The invention is characterized according to a first and second aspect by a method and a corresponding device for operating an infotainment device of a vehicle. The infotainment device comprises a selection module for media pieces, which is designed to select media pieces from a set of predetermined media pieces for signaling by the infotainment device, depending on predetermined rules. At least one physiological parameter is determined as a function of at least one biosignal of a vehicle user detected with a given sensor, which is detected during and / or after the signaling of a selected piece of media. At least one characteristic feature is determined in each case for the physiological parameter (s) determined, depending on the respective predetermined physiological parameter. Depending on the determined characteristic features, the selected media piece is assigned an emotion rating from a given emotion rating range or from a set of predetermined emotion rating classes.

Advantageously, emotional reactions of the vehicle user can be quantified with the aid of the detected biosignals. Here, emotion-specific patterns from the biosignals are extracted and classified. The emotion rating is preferably forwarded to the selection module via a predetermined interface. Depending on the reaction to the current piece of media, the playback of the selected piece of media may be interpreted as desired or undesired. It is not necessary for the vehicle user to provide explicit feedback. The vehicle user is therefore not distracted by the task of giving feedback from other tasks, in particular from a control of the vehicle. In particular, the emotional response can be used as a quantitative input variable for the selection module and the selection module can be adapted. In particular, a classification of the media pieces by the selection module can be adapted.

Advantageously, it is possible to automatically and non-invasively recognize during driving which media contents the vehicle user likes. Such feedback detection and riding does not cause driver distraction because the driver does not need to provide active feedback, such as driving. B. when listening to music with a recommendation system equipped with a smartphone, where the user can give a binary rating, "like" or "dislike" for the individual pieces and the smartphone correspondingly adjusts a playlist of the user. Further, this feedback detection and arbitration reduces interactions with the infotainment facility, as the driver does not have to pick out the media pieces in a menu himself. But the media pieces are suggested to him pro-actively. The driver can concentrate on the primary task, driving.

The biosignals advantageously allow the emotional responses to be quantified with greater accuracy than a binary quantification. The emotional reactions can be very non-invasively determined while driving so that the driver does not notice and / or without the driver being distracted. Since the selection system automatically learns the user parameters over time, an initial parameterization of the selection system can be dispensed with.

Biosignals include autonomous physical quantities that can be measured by the living organism. One or more sensors are used for detecting the biosignals, for example an electrocardiogram sensor and / or an electromyogram sensor and / or a respiration sensor and / or skin conductance sensor. The sensors record the biosignals and transducers convert them into electrical quantities that can be automatically processed later on. Functional measures derived from biosignals, such as heart rate or respiratory rate, are referred to as indicators, parameters or characteristics.

For the assignment of the emotion rating to the selected media piece on the basis of the determined characteristic features, different classification methods from the field of machine learning can be used.

For example, a piece of media may include a piece of music, a podcast, a Twitter message, point-of-interest information, traffic information, and / or e-mail, and so on. Alternatively, the term infotainment piece can be used.

In an advantageous embodiment of the first and second aspects, the determined characteristic features are compared with respective example instances of a set of given example instances and depending on the comparison, the emotion evaluation is assigned to the signaled piece of media. The example instances may also be referred to as example feature vectors. This has the advantage that algorithms of instance-based learning can be used. Instance-based learning is based on a very simple idea: to predict the class of a new, unknown object, the object to be classified is compared with the given example instances, the instance closest to the object to be classified is determined and the or the objective function and / or function value stored for this instance is assigned to the unknown object. The advantage is that no information contained in a training set will be abstracted and thus the information will not be lost. The training set here includes in particular the set of example instances.

In a further advantageous embodiment of the first and second aspects, the emotion evaluation is assigned to the selected media piece as a function of a predetermined instance-based classification algorithm. For example, a k-nearest neighbor algorithm or a K * algorithm can be used or an eigenvalue determination.

In a further advantageous embodiment of the first and second aspects, a distance measure between a feature vector and the respective example instance is determined for at least a portion of the example instances of the set, wherein the distance measure is determined according to a predetermined rule and the feature vector at least one part comprising the determined characteristic features. Depending on the determined distance measurements, the evaluation is assigned to the media piece. The distance measure may include a Euclidean distance and / or a weighted Euclidean distance and / or a Minkowski distance and so forth. This has the advantage that it is very easy to quantitatively evaluate a similarity between the feature vector and the respective example instances.

In a further advantageous embodiment of the first and second aspects, the emotion evaluation comprises a valence value or a valence class which respectively characterizes how pleasant the signaling of the piece of media is perceived by the vehicle user. This has the advantage that the emotion rating can be evaluated very easily and further processed. It is advantageous if the emotion rating can be projected on a valence scale. That is, when the valence value or the valence class is present after the classification.

In a further advantageous embodiment of the first and second aspects, the at least one characteristic feature is determined depending on a time-based waveform of the physiological parameter. This makes it possible to determine the time-dependent characteristic properties of the biosignal, whereby a normalization of the biosignals to a baseline can be dispensed with, and at the same time a performance of the classification algorithm can be increased.

In a further advantageous embodiment of the first and second aspects, the at least one characteristic feature is determined depending on a frequency-based waveform of the physiological parameter. This makes it possible to determine frequency-dependent characteristic properties of the biosignal, whereby a performance of the classification algorithm can be increased.

In a further advantageous embodiment of the first and second aspects, the distance measure comprises an entropy-based distance measure. Advantageously, this allows a more reliable assignment of emotion rating to the recognized patterns in the biosignals. It is assumed that the emotion and / or the change of emotion during the listening of the media pieces is due to the respective piece of media. Since the valence value of the emotion is present after the classification, it can be concluded whether the currently playing media content pleases the driver.

According to a third aspect, the invention is characterized by a computer program for operating an infotainment device, wherein the computer program is designed to carry out the method for operating an infotainment device or an advantageous embodiment of the method on a data processing device.

According to a fourth aspect, the invention is characterized by a computer program product comprising executable program code, wherein the program code, when executed by a data processing device, executes the method for operating an infotainment device or an advantageous embodiment of the method.

Embodiments of the invention are explained below with reference to the schematic drawings.

Show it:

1 an exemplary block switching system of an infotainment system,

2 an exemplary flowchart for a program for operating an infotainment device and

3 an example of an emotion model.

Elements of the same construction or function are provided across the figures with the same reference numerals.

1 shows an infotainment system 10 , The infotainment system 10 has an infotainment facility 20 on. The infotainment facility 20 includes, for example, a media piece database 24 and / or a receiving unit for receiving media pieces from predetermined off-board databases and / or from predetermined off-board servers. The media piece database 24 For example, it is designed to store a large number of pieces of music and / or podcasts and / or electronic messages.

The infotainment facility 20 has, for example, a control unit 26 on for controlling the output and / or for evaluating operating presets.

The infotainment facility 20 is for example an acoustic and / or optical output unit 29 . 28 assigned. Alternatively, the infotainment facility 20 the acoustic and / or optical output unit 29 . 28 include. The infotainment facility 20 is formed, the media pieces given by means of the acoustic and / or optical output unit 29 . 28 issue.

Furthermore, the infotainment facility 20 a selection module 22 on. The selection module 22 can also be referred to as a recommendation module. The selection module 22 For example, it is designed for the personalized, automated selection of the media pieces that come from the infotainment device 20 be signaled. The selection module selects here 22 depending on predetermined rules, media pieces from a set of predetermined media pieces, for example from the media piece database 24 ,

The selection module 22 For example, it is designed to analyze and classify media pieces, in particular pieces of music, which are actively selected by the vehicle user. The selection module 22 can use different algorithms of machine learning and / or different input variables to learn user preferences for media piece selection. In particular, the selection module 22 use different input variables for the respective media piece selection, for example, detected operating variables of the vehicle and / or environment variables of the vehicle and / or biosignals of the vehicle user.

The selection module 22 For this purpose, it may be configured, for example, to classify the media pieces according to predetermined moods and to determine a current mood of the driver as a function of detected biosignals of a vehicle user and to select a media piece as a function of the determined mood, which then from the infotainment device 20 is signaled.

The selection module 22 is preferably formed, depending on one or more emotional ratings, each in response to signaling each previously selected media pieces at a given interface of the selection module 22 be provided to select the media pieces.

The infotainment system 10 is a detection device 15 assigned. Alternatively, the infotainment system 10 the detection device 15 include. The detection device 15 includes one or more predetermined sensors for detecting one or more biosignals.

The detection device 15 For example, it is designed to detect electrocardiogram signals and / or electroencephalogram signals, blood pressure signals, respiratory signals, body temperature signals, sweat secretion signals and / or electrical conductivity signals of the skin of a vehicle user. The detection of the biosignals is preferably non-invasive.

Furthermore, the infotainment system points 10 an evaluation device 30 also known as a device for operating an infotainment device 20 can be designated.

The evaluation device 30 is formed, a program for operating the infotainment facility 20 perform. The evaluation device 30 has for this purpose, for example, a computing unit and a program memory. The evaluation device 30 is signal technology coupled with the detection device 15 and with the infotainment facility 20 , in particular with the selection module 22 ,

2 shows an exemplary flowchart of the program.

The program is started in a step S10. For example, the program will start when the selection module 22 the infotainment facility 20 is activated. It can be provided that the selection module 22 upon activation of the infotainment facility 20 is activated and / or after a given operation of the infotainment facility 20 by the vehicle user.

In a step S12, at least one physiological parameter is determined as a function of at least one detected biosignal of the vehicle user, which is detected during and / or after the signaling of a selected piece of media and by the detection device 15 provided. Preferably, at least one physiological parameter is determined for each detected biosignal.

For example, in step S12, a heart rate and / or a blood pressure and / or a respiratory rate and / or a body temperature and / or an electrical conductivity of the skin of the vehicle user are determined.

The step S12 includes, for example, a normalization and / or scaling of the biosignals and / or a removal and / or at least reduction of noise components.

In a step S14, in each case at least one characteristic feature is determined for the physiological parameter (s) determined, depending on the respective predetermined physiological parameter. In step S14, a feature vector for the currently selected and signaled piece of media is preferably determined. In this case, it is preferable to provide both characteristic features which are determined as a function of a frequency-based signal curve of the physiological parameter and characteristic features which are determined as a function of a time-based signal course, as well as characteristic combination features which characterize both time-dependent and frequency-dependent properties.

In a step S16, depending on the characteristic features determined, an emotion evaluation from a predetermined emotion evaluation value range or from a set of predetermined emotion evaluation classes is assigned to the selected media piece.

For this purpose, for example, the determined characteristic features which form a feature vector are compared with respective example instances of a set of given example instances. The selected media piece is assigned the emotion rating depending on a given instance-based classification algorithm. For the respective example instance of the set, a distance measure is determined between the feature vector and the respective example instance. For example, a k-nearest neighbor algorithm is used as the classification algorithm, and the respective distance measure represents, for example, the Euclidean distance between the feature vector and the respective example instance. Depending on the determined distance measurements, the media score is assigned the emotion rating. Alternatively or additionally, for example, an entropy-based distance measure is used.

The emotion rating is provided, for example, at a given interface for forwarding to the selection module 22 ,

For example, the program is used for each piece of media that is selected by the selection module 22 is selected, go through again. In a step S18, the program is ended. The program becomes, for example, with a deactivation of the selection module 22 completed.

3 shows an example of a two-dimensional emotion model. In this case, a valence is assigned to a first axis. Valence characterizes how positive or negative an emotion is. In other words, the valence characterizes how pleasant something is perceived by a person. A second axis is assigned an activity. The activity characterizes an arousal triggered by an event. The combination of both values gives the emotion. This in 3 Emotional model shown includes eight basic emotions: anger, fear, surprise, joy, anticipation, acceptance, grief, disgust.

Basic emotions are emotions that can not be traced back to other emotions or emotions that make up all other - more complex - emotions.

In particular, the emotion evaluation comprises a valence value, which in each case characterizes how pleasant the signaling of the piece of media is perceived by the vehicle user. The valence value can thus be used as feedback from the vehicle user by the selection module 22 be used to better adapt a selection of the media pieces to the preferences of the vehicle user.

LIST OF REFERENCE NUMBERS

10

Infotainment system

15

detector

20

Infotainment device

22

selection module

24

Media piece database

26

control unit

28

optical output unit

29

acoustic output unit

30

evaluation

S10 ... S18

program steps

Claims (11)

Method for operating an infotainment device ( 20 ) of a vehicle having a selection module ( 22 ) for media pieces which is designed, depending on predetermined rules, to select media pieces from a set of predetermined media pieces for signaling by the infotainment device ( 20 ), in which - at least one physiological parameter is determined as a function of at least one biosignal of a vehicle user detected with a given sensor, which is detected during and / or after the signaling of a selected piece of media, respectively - at least one for the respectively determined physiological parameter (s) characteristic feature is determined depending on the respective predetermined physiological parameter, - depending on the determined characteristic features, the selected media piece is assigned an emotion rating from a given emotion evaluation value range or from a set of predetermined emotion rating classes. The method of claim 1, wherein The determined characteristic features are compared with respective example instances of a set of given example instances and - Depending on the comparison of the signaled media piece is associated with the emotion rating. Method according to Claim 1 or 2, in which the emotion evaluation is assigned to the selected media piece as a function of a predetermined instance-based classification algorithm. Method according to one of the preceding claims, in which A distance measure between a feature vector and the respective example instance is determined for at least a part of the example instances of the set, wherein the distance measure is determined according to a predetermined rule and the feature vector comprises at least part of the determined characteristic features and - Depending on the determined distance measurements the media piece is assigned the rating. Method according to one of the preceding claims, in which the emotion evaluation comprises a valence value or a valence class which respectively characterizes how pleasant the signaling of the piece of media is perceived by the vehicle user. Method according to one of the preceding claims, in which the at least one characteristic feature is determined as a function of a time-based signal curve of the physiological parameter. Method according to one of the preceding claims, wherein the at least one characteristic feature is determined depending on a frequency-based waveform of the physiological parameter. The method of any one of the preceding claims, wherein the distance measure comprises an entropy-based distance measure. Device for operating an infotainment device ( 20 ) of a vehicle, wherein the infotainment device ( 20 ) a selection module ( 22 ) for media pieces which is designed, depending on predetermined rules, to select media pieces from a set of predetermined media pieces for signaling by the infotainment device ( 20 ) and the device is designed to carry out a method according to one of claims 1 to 8. Computer program for operating an infotainment device ( 20 ) of a vehicle, wherein the computer program is adapted to perform a method according to one of claims 1 to 8 when executed on a data processing device. Computer program product comprising executable program code, wherein the program code executes the method according to one of claims 1 to 8 when executed by a data processing device.

Images