DE102017111443A1 - Autiosystem and method for selecting a content selection and / or setting a sound setting - Google Patents

Abstract

The present invention relates to an audio system comprising an audio system with at least one selection device and at least one sound adjustment device. Furthermore, a manipulation device is provided, which is designed to automatically select a content item to be played back via the audio system. Additionally or alternatively, the manipulation device is designed such that a sound setting can be adjusted automatically. Furthermore, an AI unit is provided, so that a manipulation of the content by automatic manipulation of the selector and / or the sound setting by an automatic manipulation of Soundeinstelleinrichtung based at least on past content selection and the current content selection, and / or at least based on a past, sound setting and / or a current sound setting. By means of this process, at least one further, first content selection for the selection device and / or at least one further, first sound setting for the sound adjustment device can / can be automatically determined, selected and / or adjusted by the manipulation device.

Description

Technical area

The present invention relates to an audio system, in particular an audio system for a vehicle. Most of the vehicles currently sold have an audio system as standard, which can be used to play a wide variety of types of acoustic content.

Prior art

Vehicle Hi-Fi systems, the so-called car radio, which are used for playing CDs, MP3 files and / or radio broadcasts are generally known. Furthermore, telephone calls can be made on such systems and acoustic navigation instructions can be reproduced.

According to various developments, modern vehicles include complete audio systems in which the audio system is firmly integrated, and which are further adapted to form a human-machine interface. For example, audio control systems for vehicles are known, with the help of which the driver or an existing person in the vehicle can transmit a series of control commands to the audio system and thus enter into the vehicle control.

In addition, audio systems of vehicles are known, wherein a variety of settings of the sound and the content can be made.

Disadvantages of the prior art

The previously known audio systems of vehicles usually have a complicated control with deep-detailed menu navigation, and are therefore targeted by users only with increased training and best to use.

problem

It is therefore an object of the present invention to provide an audio system for a vehicle which enables improved operability and an optimal acoustic experience for the consumer.

Inventive solution

The above object is achieved by an audio system according to claim 1, and by a method according to claim 8. Further embodiments of the mentioned objects or the method emerge from the dependent subclaims.

The audio system has an audio system with at least one selection device and at least one sound setting device.

The selection device is suitable for, in particular manual, selecting a content selection, in particular comprising at least one piece of content to be played back via the audio system.

In one embodiment, the selector is a human-machine interface or may be connected to one. Thus, a user can manually select a content selection via a piece of content, the piece of content to be played back via the audio system. A piece of content can be - not limited thereto - any kind of audio and / or video signal, such as a piece of music, an audiobook, a news program, a radio program, a video file. The manual selection can be done for example via a touch pad, buttons, knobs, gestures and / or voice control.

A content selection has at least one selected piece of content.

The term "manual selection" is to be understood here as meaning that the selection is actively made by the user in that the user actively inputs the result of his mental decision process via the person to be heard and / or sighted as a control signal into the audio system.

The furthermore provided sound setting device serves, not limited thereto, to set at least the sound, a volume and / or a sound direction of a piece of music to be reproduced acoustically, in particular manually. This includes, for example, amplifying and / or reducing the bass and / or heights of a piece of content using an equalizer, adjusting the stereo setting of the audio system to its seating position on a vehicle side, and / or making different adjustments to the acoustic setting of the audio system. Such sound settings can be made manually in particular by a user. In general, the sound direction is understood to be a subjective sense, from which a heard acoustic signal seems to originate.

The term "manual setting" in this context means that the acoustic setting of the sound setting device is actively made by the user, by the user the result of his mental decision processes on the acoustic expression of the listener and / or to Seeker actively enters as control signal in the Soundeinstelleinrichtung.

According to one embodiment, selectable, predetermined acoustic settings, hereinafter referred to as "soundset", are predetermined. These are optimized for different needs, so that the user is at least partially removed from the acoustic adjustment process by providing a preinstalled settings profile as a soundset and this is selected by the user.

• „Pure“ - es wird ein besonders klarer, direkter Klang gewährleistet;
• „Life“-die klangliche Einstellung soll ein akustisches Live-Erlebnis nachbilden;
• „Easy“ - der Klang wird in seiner Komplexität reduziert, so dass die akustische Beanspruchung beim Hörer gering ausfällt;
• „Surround“ - Bereitstellen eines umgebenden Klangs;
• „3D“ - Simulation eines räumlichen Klangs;
• „Authentic“ - Bereitstellen eines Klangs, welcher möglichst nah am und/oder identisch mit dem Klang während der Aufnahmesituation und/oder am bzw. mit dem vom Schöpfer des Inhaltsstücks vorbestimmten Klang ist.

For example, but not limited to, the following sound sets are conceivable, wherein the described sound characteristic can be achieved by means of defined settings of the equalizer and / or the sound direction:

• "Pure" - it ensures a very clear, direct sound;
• "Life" - the tonal setting is to emulate an acoustic live experience;
• "Easy" - the sound is reduced in its complexity, so that the acoustic stress on the listener is low;
• "Surround" - providing a surrounding sound;
• "3D" - simulation of a spatial sound;
• "Authentic" - providing a sound which is as close as possible to and / or identical to the sound during the recording situation and / or on or with the sound predetermined by the creator of the content piece.

In this connection, it is conceivable that different seat configurations may be acoustically preferred, i. that the sound direction of the audio system is optimized for a specific occupation of the vehicle with persons. If the vehicle is used, for example, for chauffeuring, for example, the rear left sitting position could be acoustically preferred, so that a person sitting on it experiences an optimal sound experience.

Furthermore, the audio system has an automatic manipulation device which is designed to automatically select a piece of content to be played back via the audio system. Additionally or alternatively, the manipulation device is designed such that a sound setting, in particular a sound, a volume and / or a sound direction of a piece of music to be reproduced acoustically, can be adjusted automatically by the manipulation device. This happens in particular by manipulation of the selection device and / or the sound adjustment device by the manipulation device. For this purpose, the automatic manipulation device is provided with an AI (Artificial Intelligence Unit) unit.

Furthermore, the manipulation device of the audio system is connected to the audio system, in particular for the transmission of signals. Such a connection, the manipulation device and / or optionally the audio system are designed such that by the manipulation means a momentary, future, and / or past content selection of the selection device, in particular a reproduced content, and / or a current, future and / or past Sound setting of Soundeinstelleinrichtung can be determined. Thus, for example, the manipulation device "notices" which song title is being played with which acoustic setting, next and / or in the past - the acoustic what and how of the audio system is thus monitored by the manipulation device.

The KI unit and the manipulation device according to the invention are designed so that the manipulation of the content by automatic manipulation of the selector and / or the sound setting by an automatic manipulation of Soundeinstelleinrichtung based at least on past, especially manual, content selection and the current and / or planned Content selection, and / or at least based on past, especially manual, sound setting and / or a current sound setting is done. By means of this process, at least one further, first content selection for the selection device and / or at least one further, first sound setting for the sound adjustment device can / can be automatically determined, selected and / or adjusted by the manipulation device.

For example, if the manipulation device recognizes with the aid of the AI unit that the audio system is to reproduce or reproduce a particular piece of music in which the user manually reduced the bass amplification during a previous listening, for example - since the piece of music may already be heavily mixed with bass) the manipulation device makes a corresponding automatic change of the sound setting of the sound setting device. The audio system thus automatically adjusts an instantaneous and / or future sound setting based on the detected past play or sound setting (experience) so that the music piece is provided to the user directly in his own personal preference without any intervention.

This also applies, for example, to automatic content selection. By using the AI unit to monitor and properly evaluate the rendered content pieces, the optimal selection of a piece of content to be played back by it can be anticipated using the experience built by the AI unit. The manipulation device thus already knows in front of the user which piece of content he would most likely like to hear next. In this context, it may be advantageous if different content pieces are divided into different categories and / or provided with different characteristics features.

For the first time, the audio system according to the invention makes it possible for a user of the audio system to achieve an optimum result with regard to the sound and / or the content to be reproduced with very little or no action on his part. Over time, the artificial intelligence of the audio system learns the user's content preferences, and / or the user's aural preferences relative to the corresponding content, and can use that information to enhance the user's current and future acoustic consumer experience.

1. a) Detektieren mindestens einer vergangenen oder geplanten, insbesondere manuellen, Inhaltsauswahl und einer momentanen Inhaltsauswahl und/oder mindestens einer vergangenen oder geplanten, insbesondere manuellen, Soundeinstellung und einer momentanen Soundeinstellung.
2. b) Bestimmen mindestens einer weiteren, ersten Inhaltsauswahl für die Auswahleinrichtung und/oder mindestens einer weiteren, ersten Soundeinstellung für die Soundeinstelleinrichtung mittels Verwendung der KI-Einheit, wobei die momentane oder geplante Inhaltsauswahl und/oder Soundeinstellung mit der detektierten Inhaltsauswahl und/oder Soundeinstellung durch die KI-Einheit abgeglichen wird, und eine dabei festgestellte Divergenz zwischen der detektierten Inhaltsauswahl und der momentanen oder geplanten Inhaltsauswahl und/oder eine dabei festgestellte Divergenz zwischen der detektierten Soundeinstellung und der momentanen oder geplanten Soundeinstellung zur Bestimmung der weiteren, ersten Inhaltsauswahl und/oder der ersten Soundeinstellung verwendet wird.
3. c) Manipulation der Auswahleinrichtung und/oder der Soundeinstelleinrichtung derart, sodass ein Abspielen eines Inhaltsstücks gemäß der ersten Inhaltsauswahl, wobei insbesondere ein Klang, eine Lautstärke und/oder eine Klangrichtung beim Abspielen des wiederzugebenden Inhaltsstücks gemäß der ersten Soundeinstellung durch die Audioanlage erfolgen kann.

In the described audio system, a method is used for selecting a content selection for the selection device and / or for setting a sound setting of the sound setting device of the audio system with the following steps:

1. a) detecting at least one past or planned, in particular manual, content selection and a current content selection and / or at least one past or planned, in particular manual, sound setting and a current sound setting.
2. b) determining at least one further, first content selection for the selection device and / or at least one further, first sound adjustment for the sound adjustment device by using the KI unit, wherein the current or planned content selection and / or sound setting with the detected content selection and / or sound setting by the KI unit is adjusted, and a detected divergence between the detected content selection and the current or planned content selection and / or a detected divergence between the detected sound setting and the current or planned sound setting for determining the further, first content selection and / or first sound setting is used.
3. c) manipulation of the selection device and / or the Soundeinstelleinrichtung such that a playback of a piece of content according to the first content selection, in particular a sound, a volume and / or a sound direction when playing the part to be played according to the first sound setting can be done by the audio system.

According to one embodiment, the audio system has a situation analysis device, which is connected to the manipulation device in a suitable manner for signal exchange. The situation analysis device is designed in such a way that a qualitative and / or quantitative assessment of the current and / or future driving situation of the driver and / or a passenger can be made. For this purpose, the situation analysis unit comprises a situation detection unit or is connected to it, with the aid of which at least one traffic situation of the vehicle and / or a scheduling situation of the driver and / or a rider (user) can be detected. In particular, the situation detection unit may be connected to an electronic calendar of the driver and / or a passenger, and / or with a traffic service.

The AI unit and the manipulation unit are designed such that on the basis of a past and / or a current situation evaluation, provided by the situation analysis device, a further, second content selection for the selection device and / or at least a second, further sound setting is automatically determined, selected and / or adjusted for the sound setting by the manipulation device.

Consequently, the audio system is able to evaluate the vehicle situation of the vehicle in traffic in connection with a scheduling situation of the driver and / or a rider, and draw conclusions about the sound setting and / or content selection.

If, for example, the situation analyzer recognizes that the vehicle will reach the target very shortly or too late in a planned trip, taking into account the current traffic on the selected route, then the sound setting and / or content selection for the audio system could be in support of the Driver and / or passenger are made.

It is conceivable, for example, that in a forecast scarce or too late reaching the desired goal, a chauffeured person or the driver, a soothing piece of music in a pleasant, restrained sound setting is played. This relaxes the perceived stress driving situation, possibly avoiding driving mistakes. Thus, the embodiment of the audio system according to the invention also serves to increase security.

Furthermore, it is possible for the manipulation device to carry out a further sound setting and / or a further content selection, if appropriate on the basis of the situation evaluation as well as on the basis of the previously described made detection of previously or currently played content pieces. For example, in the above short-term situation, the audio system or the AI unit of the manipulation device could determine that, in a past, similarly brief time situation, a content piece with a high tempo (high BPM) was manually selected by the user. Because of this experience, the manipulator would now also select a high-speed content item in the future and / or make an aggressive, loud and direct sound setting.

• d) Abfragen mindestens einer vergangenen Situations-Auswertung und einer momentanen Situations-Auswertung der Situations-Analyseeinrichtung. Es wird folglich von der Manipulationseinrichtung nach einer mit der momentanen Situation vergleichbaren vergangenen Situation gesucht, wobei eine damalige Inhaltsauswahl und/oder Soundeinstellung herangezogen wird, um den im folgenden beschriebenen Schritt auszuführen.
• e) Bestimmen mindestens einer weiteren, zweiten Inhaltsauswahl für die Auswahleinrichtung und/oder mindestens einer weiteren, zweiten Soundeinstellung für die Soundeinstelleinrichtung mittels Verwendung der KI-Einheit, wobei die momentane Situations-Auswertung mit der vergangenen Situations-Auswertung durch die KI-Einheit abgeglichen wird, und eine dabei festgestellte Divergenz zwischen vergangener und momentaner Situations-Auswertung zur Bestimmung der zweiten Inhaltsauswahl und/oder der zweiten Soundeinstellung verwendet wird.
• f) Weiterhin erfolgt eine Manipulation der Auswahleinrichtung und/oder der Soundeinstelleinrichtung derart, sodass ein Inhaltsstück gemäß der zweiten Inhaltsauswahl und/oder ein Klang, eine Lautstärke und/oder eine Klangrichtung eines akustisch wiederzugebenden Inhaltsstücks gemäß der zweiten Soundeinstellung durch die Audioanlage erfolgt.

In this context, the following process steps would be carried out:

• d) querying at least one past situation evaluation and a current situation evaluation of the situation analysis device. Consequently, the manipulation device searches for a past situation comparable to the current situation, using a content selection and / or sound setting prevailing at that time in order to carry out the step described below.
• e) determining at least one further, second content selection for the selection device and / or at least one further, second sound adjustment for the sound adjustment device by using the KI unit, wherein the current situation evaluation is compared with the past situation evaluation by the KI unit and a divergence detected between past and current situation evaluation is used to determine the second content selection and / or the second sound setting.
• f) Furthermore, a manipulation of the selection device and / or the Soundeinstelleinrichtung done such that a piece of content according to the second content selection and / or a sound, a volume and / or sound direction of an acoustically reproduced content in accordance with the second sound setting is performed by the audio system.

According to one embodiment of the method, a past content selection and / or sound setting, a past situation evaluation, the further first content selection and / or the further first sound setting can be used to select a content piece and / or a sound setting.

According to a further embodiment, it is conceivable that the manipulation device reduces the volume of the sound setting device and / or completely stops or switches off an instantaneous playback when the situation analysis device detects a critical and / or dangerous traffic situation.

Furthermore, it is disclosed that the audio system has a dynamic analysis device connected to the manipulation device. This dynamic analysis device is designed to evaluate a driving style of the driver and / or a dynamic driving situation of the vehicle quantitatively and / or qualitatively. For this purpose, the dynamic analysis device is provided with at least one dynamic detection unit. In addition, the KI unit and the manipulation device are designed such that on the basis of past and / or instantaneous dynamic evaluations of the dynamic analysis device, at least one further, third content selection device and / or at least one further, third sound setting for the sound adjustment device Manipulation device can be automatically determined, selected and / or set.

According to one embodiment, the dynamic detection unit includes, but is not limited to, sensor means for detecting the operation of the pedals (brake, clutch, accelerator pedal), detecting the operation of the steering wheel of the vehicle, acceleration sensors, and / or monitoring a compliance of the driver's driving style on the present traffic rules.

Accordingly, the dynamics analysis device can make a quantitative or qualitative assessment of the driving style, and with a similar to the above analog manipulation of Soundeinstelleinrichtung influence the driver, or take a passenger.

In particular, the manipulation device or the AI unit can thereby learn whether the driver and / or the passenger prefer to have a moderating engagement or a further reinforcing engagement. Conscious drivers could certainly benefit from the fact that the sound settings are chosen more aggressively in a sporty driving style, and also the content selection fails accordingly.

In this connection, but not reduced thereto, it must be added that the AI unit is able to recognize the preferences of the driver or another user, in particular in which counterproductive manipulations are carried out on a test basis. In the process, it is checked whether the user is making corrective or reinforcing manual adjustments in terms of content and / or sound setting. This will be explained in a non-limiting example:

If the dynamics analyzer determines a sporty to aggressive driving style of the driver, then the next successive content selection could fall on a moderating, reassuring content piece for test reasons, whereby, for example, the sound setting would also be alleviated. If the driver intervenes in response to the sound settings and / or content selection in opposite directions, this experience can be used by the AI unit to better serve the driver's preferences in a similar, future situation, and indeed not to select a moderating, reassuring piece of content.

• g) Abfragen mindestens einer vergangenen Dynamik-Auswertung und einer momentanen Dynamik-Auswertung der Dynamik-Analyseeinrichtung. Dabei kann beispielsweise die Art der Bedienung der Pedale, die dynamische Situation des Fahrzeugs (Beschleunigung, Bremsung, Kurvengeschwindigkeiten, Abruptheit von Spurwechseln) und/oder die Art des Lenkeingriffs mittels geeigneter Sensoren detektiert werden, und zu einer beispielsweise quantitativen Bewertung des Fahrstils verwendet werden.
• h) Bestimmen mindestens einer weiteren, dritten Inhaltsauswahl für die Auswahleinrichtung und/oder mindestens einer weiteren, dritten Soundeinstellung für die Soundeinstelleinrichtung mittels Verwendung der KI-Einheit. Dabei wird die momentane Dynamik-Auswertung mit der vergangenen Dynamik-Auswertung durch die KI-Einheit abgeglichen, und eine dabei festgestellte Divergenz zwischen vergangener und momentaner Dynamik-Auswertung zur Bestimmung der dritten Inhaltsauswahl und/oder der dritten Soundeinstellung verwendet.
• i) Manipulation der Auswahleinrichtung und/oder der Soundeinstelleinrichtung derart, sodass ein Inhaltsstück gemäß der dritten Inhaltsauswahl und/oder ein Klang, eine Lautstärke und/oder eine Klangrichtung eines akustisch wiederzugebenden Inhaltsstücks gemäß der dritten Soundeinstellung durch die Audioanlage erfolgt.

According to the embodiment, the method carried out comprises the following method steps:

• g) querying at least one past dynamic evaluation and one momentary dynamic evaluation of the dynamic analysis device. In this case, for example, the type of operation of the pedals, the dynamic situation of the vehicle (acceleration, braking, cornering speeds, abruptness of lane changes) and / or the type of steering intervention can be detected by means of suitable sensors, and used for example a quantitative assessment of the driving style.
• h) determining at least one further, third content selection for the selection device and / or at least one further, third sound adjustment for the sound adjustment device by using the KI unit. In this case, the instantaneous dynamic evaluation is compared with the past dynamic evaluation by the KI unit, and a divergence determined between past and current dynamic evaluation is used to determine the third content selection and / or the third sound setting.
• i) manipulation of the selection device and / or the Soundeinstelleinrichtung such that a piece of content according to the third content selection and / or a sound, a volume and / or a sound direction of an acoustically reproduced content in accordance with the third sound setting is performed by the audio system.

According to a further embodiment, the audio system comprises a sentiment analysis device with at least one sentiment detection unit. The sediment analysis unit is connected to the manipulation device and can make a quantitative and / or qualitative evaluation of a psychological mood of the driver and / or a passenger.

According to a non-limiting embodiment, the sentiment detection unit is designed, for example, as a camera for facial recognition, as a microphone and / or as a vital function sensor. In this way, based on known results of sentiment research, the psychological situation, ie the mood of the driver and / or a rider, can be assessed qualitatively and / or quantitatively (for example by providing a mood scale), for example by using methods facial recognition, voice recognition, by monitoring the pulse, etc.

Furthermore, the KI unit and the manipulation device are designed such that on the basis of past and / or instantaneous evaluations of the sentiment analysis device, at least one further, fourth content selection for the selection device and / or at least one further, fourth sound setting for the Sound setting by the manipulation automatically determined, selectable and / or adjustable.

In other words, the audio system is able to determine the mood of the driver and / or the passenger, and to make an appropriate content selection and / or sound setting. For this purpose, it is conceivable in particular - analogously to what has been described above - that the past selection of contents and / or sound setting is involved. For example, in a depressive mood, the manipulation device may provide encouraging music with a refreshing sound.

• j) Abfragen mindestens einer vergangenen Sentiment-Auswertung und einer momentanen Sentiment-Auswertung der Sentiment-Analyseeinrichtung. Auf diese Weise kann eine Referenzsituation festgestellt werden, die der KI-Einheit als Auswahlkriterium zur Verfügung gestellt wird.
• k) Bestimmen mindestens einer weiteren, vierten Inhaltsauswahl für die Auswahleinrichtung und/oder mindestens einer weiteren, vierten Soundeinstellung für die Soundeinstelleinrichtung mittels Verwendung der KI-Einheit, wobei die momentane Sentiment-Auswertung mit der vergangenen Sentiment-Auswertung durch die KI-Einheit abgeglichen wird, und eine dabei festgestellte Divergenz zwischen vergangener und momentaner Sentiment-Auswertung zur Bestimmung der vierten Inhaltsauswahl und/oder der vierten Soundeinstellung verwendet wird.
• I) Manipulation der Auswahleinrichtung und/oder der Soundeinstelleinrichtung derart, sodass ein Inhaltsstück gemäß der vierten Inhaltsauswahl und/oder ein Klang, eine Lautstärke und/oder eine Klangrichtung eines akustisch wiederzugebenden Inhaltsstücks gemäß der vierten Soundeinstellung durch die Audioanlage erfolgt.

A correspondingly applied method comprises the following steps:

• j) Querying at least one past sentiment evaluation and one momentary sentiment evaluation of the sentiment analysis device. In this way, a reference situation can be determined, which is provided to the AI unit as a selection criterion.
• k) determining at least one further, fourth content selection for the selection device and / or at least one further, fourth sound adjustment for the sound adjustment device by using the KI unit, wherein the current sentiment evaluation is compared with the past sentiment evaluation by the AI unit, and a detected divergence between past and present sentiment evaluation is used to determine the fourth content selection and / or the fourth sound setting.
• I) Manipulation of the selection device and / or the Soundeinstelleinrichtung such that a piece of content according to the fourth content selection and / or a sound, a volume and / or a sound direction of an acoustically reproduced content in accordance with the fourth sound setting is performed by the audio system.

In extension of this basic principle it is proposed according to the invention that the audio system has an identification device for determining an identity of the driver and / or the rider. For example, this can be done by fingerprint sensors, face recognition, weight measurement, etc. This is in turn connected to the manipulation device, so that the content selection and / or the sound setting can be specifically tailored to the respective driver and / or passenger in the vehicle.

This may mean that on the basis of a detected identity of the driver and / or the rider at least one further, fifth content selection for the selection device and / or at least one further, fifth sound setting for the sound adjustment by the manipulation device automatically determinable, selectable and / or adjustable ,

In carrying out the described extension according to the method, an identity of the driver and / or the rider is determined by means of the identification device, and using the KI unit, a further, fifth content selection for the selection device and / or a further fifth sound setting for the sound adjustment device are determined; wherein a corresponding manipulation of the selection device and / or the sound adjustment device takes place on the basis of the identified identity.

In the course of a further development of the described embodiments of the audio system and corresponding methods, the AI unit and the manipulation device can be designed such that at least one additional content selection is made possible by an at least partial merging of the first, second, third, fourth and / or fifth content selection or at least one additional sound setting is determinable, selectable and / or adjustable by an at least partial merging of the first, second, third, fourth and / or fifth sound setting.

This means that the AI unit of the manipulation device, both past, current, future content selections and / or sound setting, as well as assessments of the traffic situation, the scheduling situation, the mood of the driver and / or the passenger, the driving style at least partially in the overall rating to provide a current or future content selection or sound setting.

The specific design of the AI unit is in accordance with the knowledge of one skilled in the art of artificial intelligence. In particular, suitable algorithms and optimization targets are to be defined so that the provision of a sound setting and / or content selection by the manipulation device can be carried out with the aid of the AI unit.

In principle, it should be noted that the naming of the method steps based on Latin letters does not contain a restrictive statement about the sequence of the sequence of the corresponding methods. Rather, it is also possible that such steps proceed quasi-simultaneously or come in changed order to execute.

The above described embodiments may be arbitrarily, but in a meaningful way combined.

Brief description of the figures

The accompanying drawings illustrate embodiments and, together with the description, serve to explain the principles of the invention. The elements of the drawings are relative to one another and not necessarily to scale.

• 1 zeigt einen schematischen Aufbau eines Audiosystems,
• 2 in vereinfachter Weise unterschiedliche Soundeinstellungen,
• 3 eine Ausführungsform eines manuellen Interface des Audiosystems gemäß 1, und
• 4 beschreibt einen Einstellungsverlauf für das Interface gemäß 3.

Like reference numerals designate corresponding parts accordingly.

• 1 shows a schematic structure of an audio system,
• 2 in a simplified way different sound settings,
• 3 an embodiment of a manual interface of the audio system according to 1 , and
• 4 describes a settings history for the interface according to 3 ,

embodiments

To clarify the overall context is in 1 in an exemplary and schematic form an embodiment of an audio system 1 cited. The one shown in it Arrangement of the individual components and connections should not be understood as mandatory for all possible embodiments. In designing embodiments according to the invention, the person skilled in the art may be able to create and use other variants, not shown here, within the meaning of the invention.

The audio system 1 includes the audio system 2 , a manipulation direction 10 and a manual interface 3 , The audio system 2 also has, for example, an amplifier for amplifying an audio signal and a loudspeaker system or is at least connected to it for generating sound waves. Furthermore, the audio system 2 with suitable data media or media for providing content pieces - for example, music pieces, radio plays, radio broadcasts, videos, etc. - equipped or connected. For example, for this purpose, an internal memory, a memory access to a data cloud, the Internet or the like may be provided.

Furthermore, a manual interface 3 be provided, via which a user - the driver or a passenger of the vehicle - can make a choice with respect to a reproduced on the audio system content and / or a sound settings with respect to the sound, a volume and / or a sound direction of an acoustically reproduced content. The manual interface 3 is with a selection device 6 and a sound adjustment device 7 the audio system 2 connected. In this case, the control is carried out with the selection made by the user with regard to sound setting and / or content piece via the manual interface 3 in which a control signal corresponding to the control is subsequently selected by the selection device 6 and / or the sound adjustment device 7 is implemented.

The manual interface 3 ( 3 ) is according to an embodiment with a touch pad 5 provided and alternatively or additionally has a knob for intuitive setting of the sound setting 9 on. In particular, on the touch pad 5 Adjustment knobs are displayed, for example, specifically to adjust the treble, midtones, and / or the bass individually.

Furthermore, it is possible to provide a predetermined sound setting, in particular with regard to the speaker selection - and the sound direction influenced thereby. For example, on the touch pad 5 according to 3 Five prepared sound direction configurations selectable, in this case based on a seat configuration of a sedan with a driver and a passenger seat, and two or three seats on the vehicle rear bench: "All" corresponds to a uniform sound wave generation in all existing speakers in the vehicle, so everyone Seat in the vehicle with a similar possible sound is considered. The abbreviations "FA" and "BF" stand for specific sound direction settings for the driver or front passenger. Accordingly, the sound direction settings for the rear left vehicle seat (HiLi) and for the rear right vehicle seat (HiRe) can be optimized.

It is also possible via the manual interface 3 to make an intuitive sound setting. There is a knob 4 provided the sound setting 9 according to a predetermined course type ( 4 ) changes depending on the turning position or knob operation. In 4 is an example of the change in the sound setting 9 depending on the operation of the rotary control 4 shown, with the sound setting with a rotation of the rotary control 4 in the counterclockwise direction according to the left-hand portion of the trajectory 4 causes clockwise rotation of a sound setting according to the righthand area. This changes the sound setting 9 the played content of a darker, duller, generally perceived as mild sound setting (counterclockwise rotation) to a more dynamic and sharper, possibly more bass-heavy (possibly with kick-bass) sound setting 9 with increased firmness and contouring (clockwise rotation). The corresponding pre-tuning of this more intuitive sound setting, that is, the specification of the technical factors of the curve, is determined by a suitable hi-fi specialist depending on the desired application. Overall, the given embodiment is not to be considered as limiting. Rather, it serves the basic idea of an intuitive sound adjustment device, ie the idea of an intuitive manipulation of the sound setting 9 to present by means of predetermined curves and / or with a continuous transition of different preset sound settings.

In 1 is further shown schematically that selection device 6 this serves to different content selections C1 . C2 . C3 . CX for content to be played. Similarly, this also applies to the sound adjustment device 7 too, with these different sound settings in EQ1 . EQ2 . EQ3 , EQX to play the content pieces makes. The discrete naming of different sound settings serves in this context only to better illustrate the embodiment, in particular unlimited unlimited sound settings, for example by varying the treble, midtones, bass, the sound direction, etc., possible.

2 shows the exemplary sound settings EQ1 . EQ2 , and EQX, focusing on gaining different frequencies according to an equalizer. For example, the sound setting causes EQ1 an emphasis on the low and high tones, with a medium frequency range being reduced. Such a sound setting EQ1 used for example to play modern popular music. The EQX sound setting with enhanced midtones and lowered trebles and basses is useful for playing back spoken content. Should a piece of content be relatively weakly mixed in terms of bass tones, but overly strong in the mid-high range - for example, rock / pop music of the 1960s and 1970s - this could be the sound setting EQ2 be suitable.

This example in 2 shown sound settings EQ1 . EQ2 . EQX be through the sound adjustment device 7 realized, with a corresponding control, both through the manual interface 3 , as well as by the automatic manipulation device 10 can be done. Also the content selection - implemented by the selection device 6 - can by means of the manual interface 3 and also by the manipulation device 10 respectively. Consequently, the manipulation device has 10 also full control over content selection 8th and the sound setting 9 ,

The manipulation device 10 has an AI unit 11 depending on the input factors an appropriate content selection 8th and / or sound setting 9 meets and over the manipulation device 10 to the sound adjustment device 7 and selection device 6 communicated. This can be done by the AI unit 11 with a content analyzer 12 and a parameter analyzer 13 be equipped with both analyzers 12 and 13 can be designed objectively and / or purely logical.

The content analyzer 12 It is used to detect, document and analyze past, present or future content selections. The content analyzer can do this 12 Play or hold back the user's preferred or rejected content accordingly. The content analyzer 12 uses itself learning algorithms, in particular, the reaction of a user to a specific content selection is used as an input factor. If, for example, a particular piece of content is aborted during playback, and if there are no further input factors that conflict with it, it can be inferred that the user is more likely to reject the aborted piece of content. This information is stored as metadata and together with possibly further input factors with the content piece, so that the user is confronted in a comparable situation with a rather low probability again with this piece of content.

The parameter analyzer 13 monitors and evaluates, for example, different sound settings 9 , in particular in connection with a played content piece, off. Here, too, self-learning algorithms are used, with particular emphasis being placed on the user's response. Changes this, for example, when playing the content according to content selection C2 from the sound setting EQ1 to EQ2 ( 2 ), this change will in particular be made with the content according to content selection C2 documented. Thus, in the future, other content pieces with a similar sound profile by the manipulation device 10 more likely with the sound setting EQ2 be played.

The manipulation device 10 is thus suitable, using the AI unit 11 to learn from the behavior of a user regarding the content selection and / or sound setting and thus to anticipate future content selections and / or sound settings.

Furthermore, a situation analyzer 20 be provided with an appropriate situation detection unit 21 equipped or connected. It is conceivable, for example, the connection with an external service provider for traffic information, with an electronic calendar of the user, in particular the driver or a passenger, a camera 32 etc. With the aid of the information thus provided, in particular regarding the traffic situation, the scheduling situation of the user, the traffic situation directly surrounding the vehicle, and possibly in connection with a navigation system, the situation analysis device 20 evaluate the current situation, especially in a qualitative and / or quantitative way. It is conceivable to classify the current situation with regard to different stress levels.

By means of such an evaluation of the current situation, the AI unit is 11 being able to make a specific content selection and / or sound setting, in particular in the context of already learned experiences about user-selected content selections and / or sound settings. Represents the AI unit 11 the manipulation device 10 a subjectively stressful, stressful situation - for example, by a tense traffic situation and large shortage of schedules - so could the selection device 6 be driven so that it selects a quiet piece of content, for example, gentle classical music; at the same time the sound setting device becomes 7 controlled so that a suitable sound setting for this piece of content is made.

Using the situation analyzer 20 The assessment performed may be the manipulation device 10 using the AI unit 11 Make a content selection and / or sound adjustment that matches the current situation.

Furthermore, a dynamic analysis device 22 be provided, which analyzes the driving situation of the vehicle - and thus to some extent the stress situation of the driver - and evaluated. This is the dynamics analyzer 22 with a dynamic detection unit 23 provided, wherein the detection unit 23 for example, as different acceleration sensors 35 , Steering sensor 36 and / or pedal sensor 37 trained or connected.

If the driver makes abrupt accelerations, braking, lane changes or cornering at high speed, then the dynamics analyzer 22 an assessment of the driving style, or in particular also in connection with the situation analysis device 20 evaluate the overall situation more precisely. In turn, derived content selections and / or sound settings are derived and implemented. For example, it can be perceived by a sporty driver as pleasant when playing energetic content pieces with a sharp and contoured sound setting during a sporty ride.

In addition, a sentiment analysis facility 24 be provided, which can make a mental evaluation of a user. This is with a sentiment detection unit 24 equipped, again as a camera 32 with facial expression, microphone 33 and / or vital signs sensor 34 be trained or can be connected to it. Furthermore, it is conceivable that the sentiment analysis device 24 Data of the other analysis devices 20 and 22 receives and processes. A psychological assessment of the mental state of a user thus made is provided by the AI unit 11 used to make a customized content selection and / or sound selection. Represents the sentiment analyzer 24 determines that a mood of the user is considered to be depressive, so this can be the selection device 6 be prompted to play an encouraging piece of content with a corresponding sound setting.

By means of an identification device 26 with an identification detection unit 27 the identity of a user, for example of the driver and / or passengers, clearly identifiable, an optimally adapted content selection and / or sound setting can be made possible. That's how the AI unit learns 11 the manipulation device 10 to process different reactions via content selection, sound setting, driving style, stress resistance, etc. according to different user profiles.

Regardless of or in addition thereto, it is conceivable that the type of occupancy of the vehicle seats is detected by means of suitable sensor elements. Accordingly, the manipulation device could 10 make a sound setting in which the occupied vehicle seats experience an optimal sound in terms of sound direction. For example, in a saloon for chauffeured purposes, the manipulation device could change the sound settings to favor the passenger's vehicle seat, most often the rear left seat, at least directly with respect to the sound direction when the passenger is boarding the vehicle. When the passenger leaves the vehicle, the sound setting is changed by the manipulation device 10 changed so that the driver's seat of the chauffeur is preferred in terms of sound.

While specific embodiments have been illustrated and described herein, it is within the scope of the present invention to properly modify the illustrated embodiments without departing from the scope of the present invention.

According to possible embodiments, the ratings of the situation analyzer 20 , the dynamics analyzer 22 , the sentiment analysis facility 24 and / or the identification device 26 in turn serve as input information to each other, so that a more precise assessment of different driving situations, psychological situations, stressful situations can be made. For example, a sporty driving style - determined by the dynamics analyzer 22 - in connection with a determined stress situation - evaluated by the situation analysis unit 20 for example, should not be understood as an expression of driving pleasure; Rather, the user wants to relax by a rapid ride the scheduling situation. Therefore, the manipulation device would 10 in such a case, not make a stimulating, but a reassuring choice of content.

The following claims are a first, non-binding attempt to broadly define the invention.

LIST OF REFERENCE NUMBERS

1

Audio system

2

audio system

3

Manual interface

4

knob

5

Touch pad

6

selector

7

Soundeinstelleinrichtung

8th

content selection

9

sound setting

10

manipulation device

11

AI unit

12

Content Analyzer

13

Parameter Analyzer

20

Situations analyzer

21

Situation detection unit

22

Dynamic analyzer

23

Dynamic detection unit

24

Sentiment analysis means

25

Sentiment detection unit

26

identification device

27

Identification detection unit

30

external service provider

31

calendar

32

camera

33

microphone

34

Vital Function Sensor

35

accelerometer

36

steering sensor

37

pedal sensor

38

seat sensor

39

GPS

C1

further, first content selection

C2

another, second content selection

C3

another, third content selection

CX

additional content selection

EQ1

another, first sound setting

EQ2

another, second sound setting

EQ3

another, third sound setting

EX

additional sound setting

Claims (13)

Audio system (1) for a vehicle - An audio system (2) with at least one selection means (6) for, in particular manual, selecting a content selection (8), in particular comprising at least one via the audio system (2) to be reproduced content piece, and / or at least one Soundeinstelleinrichtung (7), in particular manually, setting a sound setting (9), in particular at least one sound, a volume and / or sound direction of an acoustically reproduced content, and - An automatic manipulation device (10) with an AI unit (11) adapted for automatically selecting a content selection (8), and / or for automatically setting a sound setting (9) by manipulation of the selector (6) and / or the Soundeinstelleinrichtung (7 ) - wherein the manipulation device (10) with the audio system (2) for detecting a past, current and / or planned content selection of the selector (6) and / or past, current and / or planned sound setting of Soundeinstelleinrichtung (7) is connected, and - wherein the KI unit (11) and the manipulation device (10) are designed such that at least one further, first content selection (C1) for the selection device (6), and / or at least based on at least based on a detected content selection a detected sound setting, at least one further, first sound setting (EQ1) for the Soundeinstelleinrichtung (7) automatically determinable, selectable and / or is adjustable. Audio system (1) after Claim 1 , comprising a situation analysis device (20) connected to the manipulation device (10), designed to evaluate a quantitative and / or qualitative momentary driving situation of the vehicle, with a situation detection unit (21) for detecting at least one traffic situation of the vehicle and / or a schedule Situation of the driver and / or a rider, wherein the KI unit (11) and the manipulation device (10) are designed such that on the basis of an evaluation of the situation analysis device (20), at least one further, second content selection (C2) for the selection device (6) and / or at least one further, second sound setting (EQ2) for the sound setting device (7) is automatically determinable, selectable and / or adjustable by the manipulation device (10). Audio system (1) after Claim 2 wherein the situation analysis device (20) is designed such that it can be connected to an external service provider (30) and / or to an electronic calendar (31) of the driver and / or the passenger. Audio system (1) according to one of the preceding claims, comprising a dynamic analysis device (22) connected to the manipulation device (10) for quantitatively and / or qualitatively evaluating a driving style of the driver, comprising at least one dynamic detection unit (23), wherein the AI Unit (11) and the manipulation device (10) are designed such that on the basis of evaluations of the dynamics analysis device, at least one further, third content selection (C3) for the selection device (6) and / or at least one further, third sound setting (EQ3) for the Soundeinstelleinrichtung (7) by the manipulation device (10) automatically determinable, selectable and / or is adjustable. Audio system (1) according to one of the preceding claims, comprising a sentiment analysis device connected to the manipulation device (10) for the quantitative and / or qualitative evaluation of a psychological mood of the driver and / or the rider, with at least one sentiment detection unit, in particular a camera , a microphone and / or vital signs sensor, wherein the KI unit (11) and the manipulation device (10) are designed such that on the basis of evaluations of the sentiment analysis device, at least one further, fourth content selection for the selection device (6) and / or at least one further, fourth sound setting for the sound setting device (7) is automatically determinable, selectable and / or adjustable by the manipulation device (10). Audio system (1) according to one of the preceding claims, comprising an identification device (26) connected to the manipulation device (10) for determining an identity of the driver and / or the passenger, the KI unit (11) and the manipulation device (10) being such are formed, so that on the basis of a detected identity of the driver and / or the rider at least one further, fifth content selection for the selection device (6) and / or at least one further, fifth sound setting for the Soundeinstelleinrichtung (7) by the manipulation device (10) automatically determinable, selectable and / or adjustable. Audio system (1) according to any one of the preceding claims, wherein the KI unit (11) and the manipulation device (10) are formed such that at least one additional by at least partially merging the first, second, third, fourth and / or fifth content selection Content selection, and / or that at least one additional sound setting is determinable, selectable and / or adjustable by an at least partial merging of the first, second, third, fourth and / or fifth sound setting. Method for selecting a content selection (8) for a selection device (6) and / or for setting a sound setting (9) of a sound setting device (7) of the audio system (2) of the audio system (1) according to one of the preceding claims, comprising the following steps: a. Detecting at least one momentary, in particular manually made, content selection (8) and / or at least one momentary, in particular manually made, sound setting (9); b. Determining at least one further, first content selection (C1) for the selection device (6) and / or at least one further, first sound adjustment (EQ1) for the sound adjustment device (7) by using the KI unit (11), wherein the detected content selection (8 ) and / or wherein the detected sound setting (9) is compared with a past and / or planned sound setting, and a detected divergence between the content selections and / or between the sound settings for determining the first content selection (C1) and / or the first sound setting (EQ1) is used; and c. Manipulation of the selection device (6) and / or the Soundeinstelleinrichtung (7) such that a reproduction of a piece of content according to the further, first content selection (C1) and / or with the further, first sound setting (EQ1) by the audio system (2). Method according to Claim 8 comprising the steps of: d) querying at least one past situation evaluation and a current situation evaluation of the situation analysis device (20), e) determining at least one further, second content selection (C2) for the selection device (6) and / or at least another, second sound setting (EQ2) for the Soundeinstelleinrichtung (7) using the KI unit (11), wherein the current situation evaluation with the past situation evaluation by the KIEinheit (11) is adjusted, and thereby determined divergence between past and current situation evaluation for determining the second content selection (C2) and / or the second sound setting (EQ2) is used, and f) manipulation of the selection means (6) and / or the Soundeinstelleinrichtung (7) such that a reproduction of a Content according to the second Content selection (C2) and / or with the second sound setting (EQ2) by the audio system (2). Method according to Claim 8 or 9 comprising the steps of: g) querying at least one past dynamic evaluation and one momentary dynamic evaluation of the dynamic analysis device (22), h) determining at least one further, third content selection for the selection device (6) and / or at least one further, third sound setting for the Soundeinstelleinrichtung (7) using the KI unit (11), wherein the instantaneous dynamic evaluation with the past dynamic evaluation by the KI unit (11) is adjusted, and thereby found a divergence between past and present Dynamic analysis for determining the third content selection and / or the third sound setting is used, and i) manipulation of the selection means (6) and / or the Soundeinstelleinrichtung (7) such that a reproduction of a piece of content according to the third content selection and / or with the third sound setting by the audio system (2). Method according to one of Claims 8 to 10 comprising the steps: j) querying at least one past sentiment evaluation and one momentary sentiment evaluation of the sentiment analysis device (24), k) determining at least one further, fourth content selection for the selection device (6) and / or at least one further, fourth sound setting for the Soundeinstelleinrichtung (7) using the KI unit (11), the current Sentiment evaluation is compared with the past Sentiment evaluation by the KI unit (11), and thereby found a divergence between past and present I) Manipulation of the selector (6) and / or the Soundeinstelleinrichtung (7) such that a reproduction of a content piece according to the fourth content selection and / or with the fourth Sound setting by the audio system (2) takes place. Method according to one of Claims 8 to 11 wherein an identity of the driver and / or the rider is determined by means of the identification device, and wherein, using the KI unit (11), a further, fifth content selection for the selection device (6) and / or a further fifth sound setting for the sound adjustment device ( 7) is determined, and a corresponding manipulation of the selection device (6) and / or the sound adjustment device on the basis of the identified identity. Method according to one of Claims 8 to 12 wherein, using the KIE unit (11), at least one additional content selection for the selection means (6) is determined by at least partially merging the first, second, third, fourth and / or fifth content choices, and / or using the KI unit (11) at least one additional sound setting for the sound setting device (7) is determined by an at least partial merging of the first, second, third, fourth and / or fifth sound setting, whereby a corresponding manipulation of the selection device (6) and / or the sound adjustment device takes place.

Images