EP4411722A1 - Providing an adaptive tonetrack depending on a user context - Google Patents

Abstract

The present invention is directed to a method which enables a human user to be provided with an interactive soundtrack or random music (aleatory music) depending on his geographical context and his movement behavior. The proposed method can be used in medical music therapy and enables, for example, a certain clinical picture to be recognized and thus treated. Certain diseases cause a predetermined movement pattern in the patient, which manifests itself, for example, in the patient performing a certain sequence of steps at different times and at certain intervals. This can be recognized and thus music can be played to the patient which supports his movement sequence. Another application scenario is exercising, in which suitable music is played to the athlete which is influenced by his movement sequence. A plurality of sensors are used for this, which in turn can be linked to one another in such a way that predetermined configuration parameters of music are implemented. The present invention is also directed to a system arrangement which is suitable for carrying out the method, as well as to a computer program product including a storage medium.

Description

The present invention is directed to a method which enables a human user to be provided with an interactive soundtrack or random music (aleatory music) depending on his geographical context and his movement behavior. The proposed method can be used in medical music therapy and enables, for example, a certain clinical picture to be recognized and thus treated. Certain diseases cause a predetermined movement pattern in the patient, which manifests itself, for example, in the patient performing a certain sequence of steps at different times and at certain intervals. This can be recognized and thus music can be played to the patient which supports his movement sequence. Another application scenario is exercising, in which suitable music is played to the athlete which is influenced by his movement sequence. A plurality of sensors are used for this, which in turn can be linked to one another in such a way that predetermined configuration parameters of music are implemented. The present invention is also directed to a system arrangement which is suitable for carrying out the method, as well as to a computer program product including a storage medium.

It is known from the state of the art that an athlete listens to music through headphones while jogging, for example, and the predetermined beat of the piece of music is intended to motivate the athlete to move. For example, during a sprint, particularly energetic music is suitable for this, as it motivates the athlete to adapt his movement to the energetic music or to maintain it constantly. It is therefore known from the state of the art that lively music is intended to generate dynamic behavior in the athlete.

Furthermore, various sensors are known from the state of the art, which measure, for example, acceleration or heart rate. It is known from the state of the art that sensors are provided in a smartphone which enable the number of steps a user takes per day to be In addition, it is known that an athlete's position can be measured using a smartphone and a running history can be used to show the distance the athlete has covered.

It is also known that certain illnesses cause a patient to have a specific motor function. Data collections already exist that document how a patient moves depending on the illness. This can, among other things, lead to the patient exhibiting a disturbed sequence of steps, which in turn results in certain sensor data.

It is also known that digital libraries contain pieces of music that can be downloaded and consumed by a user. The user can specify preferences and then individual pieces of music or collections of pieces of music are offered to the user. Here, too, the pieces of music are prefabricated and not adaptive. Only individual pieces of music can be grouped into collections.

There is a general need in the state of the art for methods that make it possible to provide situation-specific pieces of music for medical music therapy or for sports motivation. In general, the problem is that a large number of situations can potentially arise and therefore a method is required that does not provide generic pieces of music, but rather provides appropriate and targeted music for each individual situation or user context. Target guidance can be defined by supporting a patient in their movement sequence or by playing music appropriate to their performance to an athlete.

The problem with the current state of the art is that an enormous variety of pieces of music can be provided based on different situations, but these are not individually composed. A static playback of music does not reflect the specific situation in which the recipient finds himself.

It is therefore an object of the present invention to provide a method which provides a suitable soundtrack individually and in a context-specific manner. This should be done in such a way that the technical effort required is as low as possible and an existing hardware which is already accepted by the user is to be reused. According to the invention, it is to be avoided to provide a large number of music elements which have to be created in advance at great expense. Furthermore, it is an object of the present invention to provide a corresponding system arrangement which is set up to carry out the method. In addition, a correspondingly set up computer program product and a storage medium comprising the computer program product are to be proposed.

The object is achieved by a method having the features according to patent claim 1. Further advantageous embodiments are specified in the subclaims.

Accordingly, a method is proposed for providing an adaptive or adapted sound track depending on a user context and user inputs, comprising storing configurable music elements that can be adapted based on read sensor data; continuously reading sensor data that describe a user context and/or user inputs; adapting randomly selected music elements depending on the read sensor data; and sequentially outputting the adapted music elements to a user as a sound track.

According to one aspect of the present invention, interactive music (4D music) can be influenced and changed by commands. In relation to the invention, these commands are carried out by physical movements and gestures, or followed by compatible circumstances and situations in which the receiver finds himself. The change in the music brought about is perceived according to one aspect of the present invention by changing the volume, timbre, instrumentation, intensity, character and emotional expression without interrupting the playback sequence. According to one aspect of the present invention, interactive music can be repeated endlessly and thus has no fixed end. Since some musical building blocks are selected and played at random, the music will sound different on a new run than before.

An adaptive soundtrack can contain a piece of music that is individually configured, which means that a piece of music is generally provided along with metadata, which allows individual parameters of the piece of music to be adjusted during play. One parameter with respect to which the piece of music can be varied is, for example, the speed of the runner. According to the invention, it is therefore not only possible to select a piece of music based on the speed, but that a running piece of music can be played specifically faster or slower during the playback situation.

However, the present invention is by no means limited to the speed of the piece of music, but rather other parameters can be adjusted depending on the sensor data, such as the selection of instruments. The individual musical elements are strung together to create a potentially infinitely long piece of music.

This overcomes the disadvantage of the state of the art that a single piece of music is not statically reflected for a number of situations, but rather the piece of music as a whole is individualized based on many parameters.

A user context can be a geographical position or a certain time of day. The sensors can be used to determine whether it is light or dark, or a certain time of day can be taken into account. For example, if an athlete is on a sports field in the afternoon in bright surroundings, more intense and louder music should be played than if an athlete goes for a relaxed run after work in the dark. In addition, the music can be changed from a fast daytime rhythm to a slower nighttime rhythm during sunset. It is also possible to adjust the music so that when the user runs down a hill, the music is played faster than when the user slowly climbs a hill.

The user input can typically consist of simply reading the user's movement. An implicit input can therefore serve as the user, such as the characteristics of a certain sequence of steps. However, explicit user input can also be taken into account. such as a textual command. The user can also give explicit commands, which, for example, make the music more intense. An explicit instruction can also be provided by a gesture or a specific movement pattern.

In order to retain musical elements, they must be prepared in a preparatory process step. This means that musical components or musical elements must be composed and then stored in such a way that they can be influenced. Metadata is required for this, which enables the instruments to be configured, for example. Information must be provided that indicates when music should sound intense and when it should sound more moderate. This can be a selection of instruments or specific frequencies. Using this meta information, it is then possible to individually adapt the piece of music to the running time and movement intensity.

In addition, rules must be defined that specify which parameters are adjusted for which sensor data. For example, a faster step frequency can be linked to an increase in the playback speed. In this way, areas can be classified that describe a specific context or user behavior. In this way, it is possible to classify what is a walk and what is a sprint. A walk can then be assigned to slower speeds and moderate instruments, and a sprint can be assigned to an increased speed and particularly high-frequency instruments. Such a classification can be provided manually or determined empirically using a cluster ring. In this way, a corresponding library can be provided that specifies which configuration should be set for which sensor data. For this purpose, an existing library can be analyzed, which was named by a user as "jogging," for example. These pieces of music can be analyzed and it can be identified what the user expects when jogging. In this way, a data model can be created with little technical effort that describes the respective situation.

Within the parameter values, areas can be identified that describe a situation. This could be, for example, a certain step frequency.

In one example, a step frequency that is possible for a person can be divided into five areas and then a configuration parameter of the piece of music or several parameters can be assigned to each area. For example, if the user moves from step level 2 to step level 3, the music can also be adjusted at corresponding intervals and played faster if necessary. However, this does not have to be done at intervals; instead, each sensor information can be assigned directly to a music parameter. This means that the user receives individually adjusted music in every situation.

To adapt the music, sensor data is continuously read out, which describes a user context and/or user inputs. The continuous reading of the sensor data makes it possible to record at any time what the user's situation is or how he behaves. This means that each user's situation can be individually adapted at runtime and, if the situation changes, no new music element needs to be downloaded; instead, the music element currently being played is continuously adapted. This creates the advantage, among other things, that no bandwidth needs to be used for data communication; instead, the configuration parameters on the user's device can be taken into account directly in the piece of music to be played. The state of the art would provide for a new music element to be downloaded if the context changes or the user's situation changes. This is particularly advantageously avoided according to the invention and only the music element currently being played is adapted.

The music elements are randomly selected and then adapted, varied or configured during runtime. This terminology can be exchanged and refers to the fact that music elements are adapted in their metadata or their runtime configuration. Although it is possible according to the invention to create individual classifications of music elements in advance from which to select, it is also possible for all provided music elements to be treated uniformly. In this way, a music element is randomly selected and this is then adapted to the specific situation. When this music element ends, a Another music element is randomly selected and played seamlessly after the previous music element. It is generally possible to distinguish between simple music elements and music elements that create a particularly suitable transition. This makes it possible to play a music element and towards the end choose a transition that leads a first music element into a second music element.

In one example, one musical element is 1 minute long and a second musical element is 2 minutes long. There is also a transition element with a length of 10 seconds. According to the invention, it can now be recognized after 55 seconds that the first musical element is coming to an end and thus the 10-second transition can be faded in and then the second 2-minute musical element is played. In this way, the invention makes it possible to provide a soundtrack that is potentially infinitely long. The individual musical elements or transitions can partially overlap or can be seamlessly linked together. The only important thing here is that music that is appropriate to the situation is played at all times, i.e. music whose parameters are adapted to the specific situation.

The user is then presented with the generated soundtrack, which is played to him, for example, via headphones that he has connected to his smartphone. The proposed method can thus be carried out in the smartphone and uses headphones as output devices. The music elements can be stored locally on the smartphone or, preferably, can be provided via a remote server.

According to one aspect of the present invention, the music elements are adaptable with respect to a set of parameters, the set comprising a volume, a tone color, an instrumentation, an intensity, a rhythm, a frequency, a speed and/or a playback configuration. This has the advantage that the individual music elements can be adapted to specific situations and can be recomposed or configured in such a way that they can be played back in a particularly individual way. The individual parameters can have parameter values based on which a required property can be set. For example, certain Instruments can be assigned to specific situations and in this respect the same melody can be played in different ways. If a musical element is played during a sprint, a melody can be played using an electric guitar and during a slow walk the same melody can be played using a piano. In this way the same musical element is played in a situation-specific manner.

According to a further aspect of the present invention, the sensor data is read from a set of sensors, which includes a gyro sensor, a motion sensor, an acceleration sensor, a shock sensor, an optical and electrical heart rate sensor, an optical sensor, a humidity sensor, an altimeter, a depth gauge, a GPS sensor, a location sensor, a compass, a direction sensor, a micro-location sensor, a LiDAR scanner, an ambient light sensor, a microphone, a noise sensor, a user input sensor and/or a user context sensor. This has the advantage that different sensor data can be taken into account simultaneously when configuring the music element, so individual sensors can be read out or various sensors can be adaptively read out and the sensor data can thus be available as combined sensor data. The sensors are selected depending on the hardware provided and are also selected in such a way that it is checked which parameters can be adapted to which sensors. Sensors that are typically provided in commercially available hardware are particularly preferably used here.

According to a further aspect of the present invention, stored configuration rules are used which describe how the music elements are adapted depending on the sensor data read out. This has the advantage that the sensor data or combinations of sensor data can be assigned configurations which indicate in which situation which music configuration should be used. The rules therefore describe a mapping of sensor values to corresponding parameter assignments of the music elements. This means that it is clear at all times how the playback of the music element is to be configured in the respective situation.

According to a further aspect of the present invention, the user's behavior patterns are classified using sensor data and the behavior patterns are assigned to predefined music element configurations. This has the advantage that empirically determined data can be reused and thus, for example, a predefined illness or clinical picture can be recognized and the music elements can then be configured in such a way that they provide the patient with particularly preferential treatment. If, for example, it is recognized within the sensor data that the patient is exhibiting a particularly delayed sequence of steps and, for example, is always dragging one leg, it can be recognized that he needs support in his movement sequence and the music elements can accordingly set a predetermined rhythm.

According to a further aspect of the present invention, the read sensor data is compared with stored sensor data and a user context is recognized from this, to which music element configurations are assigned. This has the advantage that, for example, spatial conditions can also be taken into account and, for example, it can be recognized that the user is on a sports field. If the time of day is also recognized, a particularly suitable configuration can be played to the user. The sensor data can be saved in such a way that it is saved locally on the user's device and is the user's data, or remotely stored sensor data is downloaded and then compared on the user's device. The comparison can also take place on a remote server.

According to a further aspect of the present invention, an illness or a type of sport is recognized from the sensor data read out. This has the advantage that empirical experience values can be used and the user is given special support for his type of sport. For example, a profile for jogging or cycling can be available and the situation the user is in is then recognized.

According to a further aspect of the present invention, a warning signal is emitted or a warning signal is sent depending on the sensor data read out. This has the advantage that prevention is possible in that the user is protected from falling and, for example, the intensity of the Music element is increased when the user is in danger. If the user moves at a steady pace, moderate music can be played and as soon as the user starts to move in a dangerous manner (e.g. hypokinesis in Parkinson's disease), a warning can be given. The warning signal can be sent so far that not only acoustic information is provided, but a third party can also be warned via an air interface and help can be called if necessary. For this purpose, location sensors can also be used, which are coded in the warning signal and then tell a third party where the user is at the moment.

According to a further aspect of the present invention, the soundtrack has musical elements that overlap in time. This has the advantage that, for example, transitions can be faded in or musical elements can be combined in such a way that they are faded in using the volume without a preceding musical element already being terminated.

According to a further aspect of the present invention, the music elements and configuration parameters are provided by means of an air interface. This has the advantage that a remote server can be accessed and corresponding data can be loaded, for example, via the user's mobile phone.

According to a further aspect of the present invention, a haptic signal is emitted with the sound track. This has the advantage that the user can also be supported in such a way that he can be warned by means of a vibration or it is possible to reinforce the expression of the musical element or the configuration by means of the haptic signal.

According to a further aspect of the present invention, the music elements are classified in a preparatory method step as standard music elements or transition music elements, which are output alternately. This has the advantage that a transition between music elements can take place. A first music element can be played and before this music element is terminated, a transition, i.e. a transition music element, can be faded in, which converts the first music element into a second music element. The transition is thus between a first standard music element and a second standard music element is optimized in such a way that a transitional music element is played between the two music elements, possibly overlapping. In this way, a particularly advantageous sound track is provided.

The object is also achieved by a system arrangement for providing an adaptive sound track depending on a user context and user inputs, comprising an interface unit configured to store configurable music elements that can be adapted based on read sensor data; at least one sensor unit configured to continuously read sensor data that describe a user context and/or user inputs; an adaptation unit configured to adapt randomly selected music elements depending on the read sensor data; and an output unit configured to sequentially output the adapted music elements to a user as a sound track.

The problem is also solved by a computer program product with control commands which implement the proposed method or operate the proposed device.

According to the invention, it is particularly advantageous that the method can be used to operate the proposed devices and units. Furthermore, the proposed devices and devices are suitable for carrying out the method according to the invention. Thus, the device in each case implements structural features which are suitable for carrying out the corresponding method. However, the structural features can also be designed as method steps. The proposed method also provides steps for implementing the function of the structural features. In addition, physical components can also be provided virtually or in virtualized form.

Figur 1:

ein schematisches Ablaufdiagramm eines Verfahrens zum Bereitstellen einer adaptiven Tonspur in Abhängigkeit eines Benutzerkontext und von Benutzereingaben gemäß einem Aspekt der vorliegenden Erfindung;

Figur 2:

ein schematisches Schaltbild, welches das zugrundeliegende Wirkprinzip des vorgeschlagenen Verfahrens zum Bereitstellen einer adaptiven Tonspur verdeutlicht;

Figur 3:

ein weiteres schematisches Schaltbild, welches das Wirkprinzip des vorgeschlagenen Verfahrens zum Bereitstellen einer adaptiven Tonspur aufzeigt; und

Figur 4:

ein Klassifizieren von Sensordaten zum Erkennen eines bestimmten Musters gemäß einem weiteren Aspekt der vorliegenden Erfindung.

Further advantages, features and details of the invention emerge from the following description, in which aspects of the invention are described in detail with reference to the drawings. The features mentioned in the claims and in the description can each be used individually. or in any combination essential to the invention. Likewise, the features mentioned above and those further explained here can be used individually or in combinations. Parts or components with similar functions or identical components are sometimes provided with the same reference numerals. The terms "left", "right", "top" and "bottom" used in the description of the exemplary embodiments refer to the drawings in an orientation with a normally legible figure designation or normally legible reference numerals. The embodiments shown and described are not to be understood as exhaustive, but are exemplary in nature to explain the invention. The detailed description serves to inform the person skilled in the art, so known circuits, structures and methods are not shown or explained in detail in the description in order not to make it more difficult to understand the present description. The figures show:

Figure 1:

a schematic flow diagram of a method for providing an adaptive soundtrack depending on a user context and user inputs according to an aspect of the present invention;

Figure 2:

a schematic diagram illustrating the underlying operating principle of the proposed method for providing an adaptive sound track;

Figure 3:

another schematic diagram showing the operating principle of the proposed method for providing an adaptive sound track; and

Figure 4:

classifying sensor data to recognize a particular pattern according to another aspect of the present invention.

Figure 1 shows in a schematic block diagram a method for providing an adaptive soundtrack depending on a user context and user inputs, comprising a storage 100 of configurable music elements which can be adapted based on read sensor data; a continuous reading 101 of sensor data which describe a user context and/or user inputs; an adaptation 102 of randomly selected music elements depending on the read sensor data; and sequentially outputting 103 the adapted musical elements to a user as a soundtrack.

In the Figures 2 and 3 A sensor is shown on the left side and an example of what this sensor can detect. For example, a gyro sensor can detect that the user is circling his arm. This is referred to here as an impulse. The musical effect is then shown in another column and the user's perception in yet another column. In the present Figures 2 and 3 These are merely exemplary embodiments which illustrate the operating principle and can be expanded as desired.

In the exemplary embodiments, it can be seen that individual sensor data can be generated in different ways, which generally corresponds to a user input. Sensor data can be generated in such a way that the user moves and the movement itself is perceived, or the user moves in space, for example by changing his geographical position. In general, the inputs do not have to relate to the user per se, but rather it is also possible for ambient brightness to be recorded. This is therefore not a direct user input, but rather the user's context can also be taken into account. Which sensors are selected or which user input and which user context are processed can be determined using rules. Typically, all sensors continuously provide data and within the sensor data, for example, clustering is used to identify which sensor data is relevant. Empirical sensor data can be used for this purpose and particularly conspicuous behavior patterns can be extracted and then only those sensor data that contribute to this conspicuous behavior can be used.

Wearables, smartphones, headphones and other electronic devices can have sensors that the music composition adapts to. When these sensors are activated, they trigger the section in the music composed for the appropriate scenario.

According to one aspect of the present invention, the following sensors are responsible for regulating the music:

Gyro sensor:

According to one aspect of the present invention, the gyro sensor is crucial for the user to direct the interactive music. The numerous rotation options on the human body offer many active and passive impulses with which the building blocks of the music (harmony, melody, rhythm, timbre) can be modified.

With respect to the invention, actions such as "pushing" and changing the interactive title are carried out by means of such active impulses.

The dimension with which the arm is swung from front to back (and from back to front) in terms of speed and span while running is considered a passive impulse and is decisive for triggering the music for the corresponding movement state (standing, walking, jogging, sprinting) with the help of the gyro sensor in the wearable.

Even in the medical field, patients can influence music to their benefit with the help of active impulses.

In the private sector, the gyro sensor can also support dance movements or household activities with interactive music.

Motion sensor:

The motion sensors, which also include the gyro sensor and acceleration sensor, are also relevant.

Because motion sensors can be used to measure stability when walking and coordination, interactive music is used in the field of music therapy. Since patients suffering from Parkinson's disease can be helped out of a rigidity in movement by rhythmic elements in music, the supporting music should be played based on the evaluated data in order to prevent falls.

With regard to the invention, it requires the motion sensor, which measures the temporal and spatial distance at which the feet are in contact with the ground while running, in order to adjust the bpm in the music to the running step.

Acceleration sensor:

The accelerometer, like the motion sensor and the gyro sensor, is responsible for determining the movement status and causes the intensity of the music to adjust to the intensity of the movements.

Optical and electrical heartbeat sensor:

The heartbeat sensors measure the heartbeat per minute. If the heart rate exceeds a certain bpm limit, a short musical message is incorporated into the music already playing, according to one aspect of the present invention.

In the medical field, these musical cues can also serve as a warning.

Altimeter:

If the altimeter barometrically determines the altitude of the location, a high-pass filter or a low-pass filter can be activated in the music based on the data. The high-pass filter adds sound to the incline and the altitude, as the low frequencies are taken from the music, and the low-pass filter adds sound to the descent and the depth, as the high frequencies are taken from the music.

Depth gauge:

The depth gauge can be used when diving to regulate the strength of the low-pass filter to give the music a typical muted underwater effect depending on the depth.

This function should be able to be implemented as soon as a certain quality standard for perceiving music underwater has been achieved.

GPS:

The GPS makes it possible to recognize spatial objects and conditions that are musically relevant in advance and to play the necessary musical elements in good time. It can also work together with the altimeter to allow the music to influence the nature of the terrain in advance.

According to one aspect of the present invention, the musical cues that accompany each kilometer traveled use GPS.

Compass:

The compass can detect a change of direction and thus enables dynamic and practical binaural panning between the left and right headphones.

If there is a compass or a gyro sensor in the headphones, a distinction can also be made between a complete change of direction and the direction of view in order to regulate the intensity of the binaural panning.

Micro-location:

Micro-location, which uses Bluetooth to locate a receiver at a short distance, allows the music to adjust to the distance and viewing angle of the receiver. This is particularly useful for indoor spaces, where you can musically accompany turns and steps when dancing, or play music that has been specially composed for living rooms as soon as you enter them and cause changes in the sound character as you walk through the room.

LiDAR scanners:

With the LiDAR scanner - like with GPS - the distance to objects that are important for the music can be detected in advance (through the light reflected by laser pulses). The music can adapt to the speed at which the distance to the object decreases.

Ambient light sensor:

With the ambient light sensor, the music can adjust slowly to the time of day at sunrise and dusk, or react abruptly as soon as a room is illuminated.

Likewise, the music development can be directed and musical plugins activated through intentional darkening through objects or gestures.

Microphone:

The microphone can be used to fulfill verbally expressed wishes that can only be realized with interactive music. An instrument or a musical effect should be able to be introduced into the current playback dynamically, smoothly and without having to change the interactive title, based on a verbally expressed request.

One possibility of using the invention with great practical relevance is in the treatment of Parkinson's disease. Music therapy for this disease has an established status, is one of the most important accompanying therapies and is used in many rehabilitation clinics and also on an outpatient basis. Hearing and movement are closely linked.

Music not only activates nerve cells responsible for hearing, but also those that coordinate movement.

Parkinson's disease is characterized by severe movement disorders. It is caused by the death of nerve cells that are responsible for the bioelectrical impulse transmission from the brain to the muscles.

A particularly threatening situation for Parkinson's disease patients is the sudden freezing of movement. This "freezing" occurs suddenly and cannot be treated with medication.

Through rhythmic sounds from outside and frequent training in therapeutic facilities, it is possible to free the patient from this rigidity of movement. This rigidity of movement is one of the main reasons for the most frequent falls, with the corresponding risk of bone fractures. Two thirds of falls in Parkinson's disease, which fall twice as often as other patients without Parkinson's disease, occur in connection with a gait blockage.

Rhythmic auditory stimulation (RAS) helps the patient to adjust the length and pace of the stride to the tempo of the music. Here, the invention offers Parkinson's patients the chance to counteract an impending or existing blockage with individually coordinated music - for example by moving the hand. It will be possible to influence the tempo of the music and the intensity of the percussion through gestures and to maintain long-lasting musical variety through the random elements without having to change the interactive music track.

Since music therapy provides general stability, it is used to prevent falls in Parkinson's disease. Reducing the number of falls resulting in bone fractures would have major social, personal and economic consequences. It could help enable Parkinson's patients to lead an independent life for as long as possible.

The invention is intended to provide optimal, hand-conducted music for stability and mobility in order to prevent movement blockages ("freezing") and falls.

This is just one example of the medical fields in which the invention can develop its potential as a music therapy aid. Stroke patients, people with autism, depression or anxiety disorders and accident victims can also be helped specifically by this self-controlled music therapy, as music not only improves stability, coordination and motor skills, but can also generally restore or maintain physical and mental health and even have a pain-relieving effect. The invention should also find useful applications in other sporting and everyday activities. This includes influencing interactive music in the home for relaxation purposes and through dancing behavior.

Figure 4 shows a classification of sensor data. Each sensor provides certain values and these can be encoded as a set diagram in this example. The sensor data can therefore be arranged in a data space of any dimension. As shown in the figure, the individual classes can also overlap.

If, for example, a patient is unable to move a leg according to typical movement patterns, this can have many causes. For example, the user may be wearing a cast due to a broken leg or may not be able to move a leg correctly due to a stroke. Empirically determined data already exists for all of these diseases and thus the sensors or sensor data can be compared with existing data. Within a data cloud, it is thus possible to identify which class or disease this sensor data belongs to. Often, a disease is not recognized from a sensor, but rather it is Many characteristic behavioral patterns are shown and these are then assigned as a whole to a class or disease. This makes it possible to determine the situation the user is in based on a large amount of sensor data. Predefined music element configurations can be applied accordingly.

The example can be applied analogously to a sport. Each sport has a typical behavior pattern of the user and the sport can be recognized based on various sensor data. When jogging, for example, movement is typically linear and essentially in the same direction, while in a team sport there are often sudden changes in direction and the players are within a defined geographical area that they do not leave. In this way, user input and the user context can be combined and the typical behavior within a sport can be recognized. The music can be configured accordingly. List of reference symbols: 1 Gyro sensor 2 Accelerometer 3 Motion sensor 4 Shake wrist 5 Arm circles 6 Stretch your arm out to the side 7 Natural, intense arm swing during slow movement 8th Natural, moderate arm swing during slow movement 9 Viewing direction 10 Fine motor skills, rotation of the wrist 11 Accelerometer 12 Slowdown 13 Low foot-to-ground contact 14 Poor coordination and stability when walking, lack of mobility 15 High foot-to-ground contact 16 Strong crescendo 17 Weak crescendo 18 Change music track 19 Increased bpm, more instruments, higher volume, more percussion 20 Slower bpm, fewer instruments, lower volume, less percussion 21 Adjusting rhythm and tempo 22 Binaural Panning 23 Motivating "push" to sprint 24 Motivating "push" to jog 25 Next interactive music track 26 Louder, faster, more intense 27 Quieter, slower, less intense 28 Increased coordination and stability when walking, accident prevention 29 "Panning" between left and right earpiece 30 compass 31 GPS 32 Heart rate sensor 33 Altimeter 34 Depth gauge 35 iBeacon 36 LiDAR scanners 37 Ambient light sensor 38 microphone 39 change of direction 40 Overcoming one kilometer 41 High heart rate 42 pitch 43 Reduction 44 Water depth 45 Direction of view, proximity, body movement 46 Object distance 47 Sunset, sunrise, brightening, darkening 48 Verbal commands 49 Binaural Panning 50 Musical cues 51 High-pass filter 52 Low pass filter 53 Volume, instrumentation, ornaments 54 Spundscape, site-specific soundscapes 55 Crescendo, diminuendo, change of volume, instrumentation and musical style 56 All 57 "Panning" between left and right earpiece 58 Bell sound 59 Heartbeat sound 60 Fade out the low frequency 61 Hide the high frequency 62 Intensity, expression, interactive dance music, influenceable musical spatial installation 63 Objects gain an acoustic presence 64 Change in musical expression and character

Claims (15)

A method for providing an adaptive audio track depending on a user context and user inputs, comprising: - storing (100) configurable music elements which can be adapted based on read sensor data; - a continuous reading (101) of sensor data describing a user context and/or user inputs; - adapting (102) randomly selected music elements depending on the read sensor data; and - sequentially outputting (103) the adapted music elements to a user as a sound track. Method according to claim 1, characterized in that the musical elements are adaptable with respect to a set of parameters, the set comprising: a volume, a timbre, an instrumentation, an intensity, a rhythm, a frequency, a speed and/or a playback configuration. Method according to claim 1 or 2, characterized in that the sensor data is read from a set of sensors, the set comprising: a gyro sensor, a motion sensor, an acceleration sensor, a shock sensor, an optical and electrical heart rate sensor, an optical sensor, a humidity sensor, an altimeter, a depth gauge, a GPS sensor, a location sensor, a compass, a direction sensor, a micro-location sensor, a LiDAR scanner, an ambient light sensor, a microphone, a noise sensor, a user input sensor and/or a user context sensor. Method according to one of the preceding claims, characterized in that stored configuration rules are applied which describe how the music elements are adapted depending on the read sensor data. Method according to one of the preceding claims, characterized in that behavior patterns of the user are classified based on sensor data and predefined music element configurations are assigned to the behavior patterns. Method according to one of the preceding claims, characterized in that the read-out sensor data are compared with stored sensor data and a user context is recognized therefrom to which music element configurations are assigned. Method according to one of the preceding claims, characterized in that a disease or a sport is recognized from the read sensor data. Method according to one of the preceding claims, characterized in that a warning signal is output or a warning signal is sent depending on the sensor data read out. Method according to one of the preceding claims, characterized in that the sound track has temporally overlapping musical elements. Method according to one of the preceding claims, characterized in that the music elements and configuration parameters are provided by means of an air interface. Method according to one of the preceding claims, characterized in that a haptic signal is output with the sound track. Method according to one of the preceding claims, characterized in that the music elements are classified in a preparatory method step as standard music elements or transitional music elements, which are output alternately. System arrangement for providing an adaptive soundtrack depending on a user context and user inputs, comprising: - an interface unit configured to store (100) configurable music elements which can be adapted based on read sensor data; - at least one sensor unit configured to continuously read out (101) sensor data describing a user context and/or user inputs; - an adaptation unit configured to adapt (102) randomly selected music elements depending on the read sensor data; and - an output unit arranged to sequentially output (103) the adapted music elements to a user as a sound track. Computer program product comprising instructions which, when the program is executed by at least one computer, cause the computer to carry out the steps of the method according to one of claims 1 to 12. A computer-readable storage medium comprising instructions which, when executed by at least one computer, cause the computer to carry out the steps of the method according to any one of claims 1 to 12.

Images