Methods for adding music to a reading process

Abstract

The invention relates to a method for providing background music to a vehicle occupant 7 reading an electronically provided text in a vehicle 1, in which a context-specific soundtrack is played for the vehicle occupant 7 in the vehicle 1 depending on a reading position in an electronically provided text. In a method that can be implemented in a more user-friendly way, the context-specific soundtrack to be played over the electronically provided text or text segment is generated by artificial intelligence.

Description

[0001] The invention relates to a method for providing background music to a reading process of an electronically provided text for a vehicle occupant in a vehicle, in which a context-specific soundtrack is output for the vehicle occupant depending on a reading position in the electronically provided text.

[0002] US patent 2012 / 0001923 A1 discloses an e-book with background music in which the music playback is determined by the reading speed. The e-books comprise text information and a variety of soundtracks, with predefined text information paired with predefined soundtracks.

[0003] US Patent 9,898,077 B2 discloses a method for playing a soundtrack while an e-book is being read. The soundtrack has different audio sections, which are played back during corresponding text sections. The playback of the audio sections of the soundtrack via an audio output system is based on a reading position counter that indicates the user's estimated reading position and increments based on a user reading speed variable.

[0004] The object of the invention is to provide a method for adding music to the reading process of an electronic text, which is implemented in a more user-friendly manner.

[0005] The invention is defined by the features of the independent claims. Advantageous further developments and embodiments are the subject of the dependent claims. Further features, applications, and advantages of the invention will become apparent from the following description and the explanation of exemplary embodiments of the invention illustrated in the figures.

[0006] The problem is solved by the subject matter of claim 1.

[0007] In the method described at the beginning, which involves providing background music for a vehicle occupant reading an electronically provided text, a context-specific soundtrack is played for the occupant depending on their reading position within the text. This context-specific soundtrack is generated by artificial intelligence. It is not necessary to generate a soundtrack for the entire text; it can also be generated for one or more electronically provided text sections. Providing a soundtrack generated by artificial intelligence thus allows for cost-effective and context-dependent music generation without the need to store numerous pre-made soundtracks in the e-books.This allows for the generation of a soundtrack that emotionally complements the reading content and makes the reading experience more engaging for the vehicle occupants. Furthermore, the generated music enhances comprehension of the text and underscores its content.

[0008] In one implementation, the vehicle occupant, as the reader of the electronically provided text or text passage in the vehicle, provides the artificial intelligence with a personal profile for sound generation. By indicating a preference for the soundtrack to be created by the AI, the occupant's personal reading experience is further enhanced. The occupant's preference can include information such as dynamics, intensity, or style / genre, such as instrument, jazz, classical, and similar. In particular, the emotional reading experience is enhanced by an interactive exchange between the occupant and the AI ​​during the soundtrack generation process.

[0009] In a further development, dynamic, word-accurate text position recognition is determined by a page turn in an electronic book, by the known reading speed of the vehicle occupant, or by eye-tracking the vehicle occupant. These methods can also be used in parallel. Comparing the results obtained increases the accuracy of the text position recognition.

[0010] In a further embodiment, the electronically provided text or text segment to be displayed on a vehicle's display unit is sent to an external backend containing artificial intelligence for sound generation. The soundtrack data generated by the AI ​​is then sent to the vehicle and played back there depending on the reading position. The online data transfer between the vehicle and the external backend can be limited to the text that is to be accompanied by appropriate music, thus accelerating the provision of the corresponding soundtrack data. This eliminates the need to send a data set containing a finished soundtrack, which would otherwise require the use of expensive, pre-made music tracks.

[0011] In a further embodiment, the electronically provided text transmitted to the vehicle comprises digital eBook content, which is adapted for display on the respective screen format in the vehicle. The processing of the externally provided reading content for in-vehicle use is then limited to adapting the text file to the display format of the vehicle's display unit.

[0012] In a further development, the generated soundtrack data is stored in the vehicle's external backend for reuse. This is particularly advantageous when user feedback is positive.

[0013] In a further embodiment, eye-tracking of the vehicle occupant during reading is monitored by a driver observation camera in the vehicle. This system determines the reading position within a text segment of the currently displayed passage, which is identified by assigning digital parameters describing the current text segment. The driver observation camera does not need to recognize the text itself. These digital parameters could include, for example, a chapter number, page number, line number, and / or word number. The driver observation camera helps determine the reading position within the displayed text by, for example, detecting when the eye moves to the next line. This allows for a simple way to track reading progress on the page.

[0014] In a further implementation, the start and end of the soundtrack playback are determined based on the direction the vehicle occupant is looking at the display unit, as detected by eye-tracking. Thus, the soundtrack can be started when the occupant looks at the display unit and stopped when the occupant looks away.

[0015] In another version, the soundtrack has a dynamic length and includes at least one music format that is played depending on the reading speed of the vehicle occupant. The soundtrack's length can thus be individually adjusted, allowing the user to switch from a first music format, which, for example, underscores a lighthearted passage of text, to a second music format, which accompanies a subsequent, more serious passage.

[0016] Further advantages, features, and details will become apparent from the following description, in which at least one exemplary embodiment is described in detail. The described features can, individually or in any meaningful combination, constitute the subject matter of the invention, optionally also independently of the claims, and can, in particular, also be the subject matter of one or more separate applications.

[0017] This shows: Fig. 1 a system for carrying out the method according to the invention.

[0018] In Fig.Figure 1 shows an embodiment of the method according to the invention in a vehicle 1. The vehicle 1 comprises a control unit 3, which is connected to a display unit 5. The display unit 5 can also be designed as a display-control unit. Advantageously, the display unit 5 can be designed as a touchscreen, thereby simultaneously serving as a control element for the vehicle occupant 7 to input commands to the control unit 3. Alternatively, the display unit and control unit can also be arranged as separate components in the vehicle 1. The display unit 5 can be designed as a central vehicle display, a passenger display, or a display for a vehicle entertainment system and can display electronic texts for the entertainment of the vehicle occupant 7, which can be read by the vehicle occupant 7. The driver can, of course, only read such texts during autonomous driving of the vehicle 1.Inside the vehicle 1, the control unit 3 is connected to a driver observation camera 9 and a loudspeaker 11.

[0019] Furthermore, the control unit 3 is wirelessly connected to an external database 13 and an external sound generator 15. The external database 13 stores electronic media content in digital form. The analysis of electronic media will henceforth focus on works in electronic book form, so-called e-books. The sound generator 15 is designed to generate a context-specific soundtrack for the digital text of an e-book using artificial intelligence.

[0020] To process files transferred to the control unit 3 from the database 13 and / or the sound generator 15, the control unit 3 includes an electronic text module 17, which adapts the digital text files downloaded from the database 13 to the display format of the display unit 5. A soundtrack playback module 19 stores the soundtrack generated by the sound generator 15 for the downloaded text. Based on the signals from the driver observation camera 9, a reading speed detection module 21 determines the reading speed of the vehicle occupant 7. These three modules 17, 19, and 21 can exchange data bidirectionally. Through the interaction of the text module 17, the soundtrack playback module 19, and the reading speed detection module 21, the soundtrack is synchronized with the displayed text section and the reading position.

[0021] If a vehicle occupant 7 wishes to listen to an e-book with background music while the vehicle 1 is in motion, they can launch a dedicated app displayed on the display unit 5 and thus signal to the control unit 3 which e-book they would like to read. The control unit 3 requests a corresponding digital text data set from the vehicle's external database 13 and configures the received digital text data for display on the display unit 5 in the text module 17. Simultaneously, the database 13 transmits the requested digital text data set to the sound generator 15. Based on textual content and keywords within the digital text, the artificial intelligence recognizes the emotional context of a sentence, text passage, or chapter. From this, a correspondingly emotionally appropriate soundtrack is generated, which is transmitted as an audio file to the control unit 3 and stored in its soundtrack playback module 19.Depending on the chapter or sentence currently being read on display unit 5, control unit 3 triggers the output of the corresponding soundtrack to the speaker 11 of the vehicle 1, depending on the result of the reading speed detection module 21.

[0022] Prior to generating the context-specific soundtrack by the sound generator 15, the vehicle occupants 7 can be presented with various music genres and / or pieces in the form of short sound samples, allowing them to select a genre for the context-specific background music. These preferences can be saved in a personal profile for the vehicle occupant 7 in the control unit 3 and, if necessary, transmitted from the vehicle 1 to the external sound generator 15 for artificial intelligence to generate a current context-specific soundtrack. Furthermore, the personal profile can also include the vehicle occupant's 7 preference for the dynamics and intensity of the music playback. The vehicle occupant 7 can dynamically modify the personal profile during the reading process and / or add further pieces or music genres.This also allows for interactive communication between the vehicle occupant and the vehicle's external sound generator 15 while reading.

[0023] To determine the current reading position, parameters such as chapter number, page breaks in the e-book, average and / or personal reading speed, or the results generated by eye-tracking from the driver observation camera 7 can be used. Eye-tracking makes line breaks particularly easy to detect. Once the text is available digitally, the system knows the current text position displayed on the display unit 5, for example, page 23, chapter 4, words 467 to 678.

[0024] In one example, let's assume an e-book describes a romantic situation that ends in an accident or murder. The musical theme generated by sound generator 15 must be different for these two scenarios. For the romantic scenario, the artificial intelligence will generate a slow and harmonious theme, while the theme generated for the dramatic scenario will be fast, staccato, and dissonant. Depending on their reading speed, a reader might need a minimum of 2:45 minutes and a maximum of 5:50 minutes of soundtrack for the romantic scenario. The same applies to the dramatic scenario. Therefore, the soundtrack for each scenario must be able to continue or end dynamically, depending on the individual and dynamic nature of the story.In the simplest case, the musical theme accompanying the romantic scene can be played in a continuous loop until a relevant textual point is reached that describes the dramatic events. The respective musical theme can thus be repeated or extended indefinitely until a digital trigger, activated by control unit 3, initiates the transmission of the next musical theme. Reference symbol list 1 vehicle 3 Control unit 5 Display unit 7 vehicle occupants 9 Driver observation camera 11 speakers 13 Database 15 Sound generator 17 Text Module 19 Soundtrack playback module 21 Reading speed detection module QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] US 2012 / 0001923 A1

[0002] US 9 898 077 B2

[0003]

Claims

[1] Method for providing background music to a reading process of an electronically provided text for a vehicle occupant (7) in a vehicle (1), in which, depending on a reading position in an electronically provided text, a context-specific soundtrack is output for the vehicle occupant (7) in the vehicle (1), characterized by , that the context-specific soundtrack to be played under the electronically provided text or text section is generated by an artificial intelligence. [2] Method according to claim 1, characterized by , that the artificial intelligence is given a personal profile for sound generation by the vehicle occupant (7) as reader of the electronically provided text. [3] Method according to claim 1 or 2, characterized by, that dynamic word-accurate text position recognition is determined by a page change in an electronic book or from a known reading speed of the vehicle occupant (7) or by eye-tracking of the vehicle occupant (7) in the vehicle (1). [4] Method according to any one of claims 1 to 3, characterized by , that the electronically provided text or text section to be displayed on a display unit (5) of a vehicle (1) is sent to a vehicle-external backend comprising artificial intelligence for sound generation, wherein the soundtrack data generated by the artificial intelligence is sent back to the vehicle (1) and played back there for the vehicle occupant (7) as reader depending on the reading position. [5] Method according to claim 4, characterized by, that the electronically provided text to the vehicle (1) includes digital eBook content transmitted which is adapted for display to the respective display format of the display unit (5). [6] Method according to claim 4 or 5, characterized by , that the generated soundtrack data is stored in the vehicle-external backend for reuse. [7] Method according to any one of claims 4 to 6, characterized by , that the eye-tracking of the vehicle occupant (7) during the reading process is monitored by means of a driver observation camera (9), by means of which the reading position is determined within a text set of the currently displayed text section, which is characterized by the assignment of the digital parameters describing the current text section. [8] Method according to claim 7, characterized by, that the start and end of the playback of the soundtrack is determined depending on the direction of gaze of the vehicle occupant (7) towards the display unit (5) as detected by eye tracking. [9] Method according to any one of the preceding claims 5 to 8, characterized by , that the soundtrack has a dynamic length and includes at least one music format which is played in the vehicle (1) depending on the reading speed of the vehicle occupant (7). [10] System which is provided for the use of a method for providing background music to a reading process of an electronically provided text for a vehicle occupant (7) in a vehicle (1) according to any one of claims 1 to 9.

Images