AI in electronic devices

The user-specific terminal uses a generative AI model to create personalized content based on user preferences and age, offering adaptable playback modes for enhanced user interaction and engagement.

DE202024104680U1Active Publication Date: 2024-12-05INFINITISPARK GMBH

Patent Information

Application Number
DE202024104680
Authority / Receiving Office
DE · DE
Patent Type
Utility models
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-12-05
Estimated Expiration
2034-08-31

AI Technical Summary

Technical Problem

Existing user-specific electronic terminals fail to adapt content playback to individual user preferences and age, lacking personalization and dynamic adjustment.

Method used

A user-specific electronic terminal using a generative AI model generates content based on a user-specific template, incorporating user preferences, age, and feedback, with adaptable playback modes for acoustic, optical, and haptic experiences.

Benefits of technology

Enables personalized and age-appropriate content generation and playback, allowing real-time adaptation and user interaction, enhancing user engagement and content relevance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000000_0000_ABST
    Figure 00000000_0000_ABST
Patent Text Reader

Abstract

User-specific electronic device, in particular a device adapted to the user's age, for the acoustic and / or optical and / or haptic reproduction of content generated using a generative model based on artificial intelligence, wherein the generated content is adapted to the user. where the content is generated using the generative model based on a user-specific template, where the user-specific template contains a user preference assigned to the user profile as well as the user's age.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] The invention relates to a user-specific or user-specific electronic terminal for reproducing content.

[0002] Electronic devices for playing content are common practice, such as tablets for playing images, videos, or text content. Adapting an electronic device to the user's needs is also common practice. User-specific electronic devices that play content include, for example, plush toys with electronic playback functions for small children or personalized tablets for playing content on a display. These user-specific devices access the media pool generally known in practice (e.g., from the internet) to serve as an entertainment device for the user.

[0003] Content creation, especially in the media sector, has always been an essential part of the entertainment industry. Content creation using generative artificial intelligence is gaining increasing importance. Using generative AI to generate content instantly and in large numbers enables a particularly fast and efficient way to create content that can be personalized for different audiences and purposes.

[0004] This principle of using generative artificial intelligence is described, for example, in DE 10 2023 120 666 A1. The aforementioned document describes a method for generating content using a generative model. The content is assigned to a user profile, so that the generative model generates the content based on a user preference associated with the user profile. A target user device for displaying the content is also described.

[0005] Content generated using a generative model is typically displayed on commonly used devices, such as computers, tablets, or smartphones. Customization of the device to the user is not currently practiced.

[0006] The invention provides a remedy here. The invention is therefore based on the technical problem of further developing such an electronic terminal in order to provide a terminal adapted to the user.

[0007] To solve this technical problem, the invention provides a user-specific electronic terminal, in particular a terminal adapted to the user's age, for the acoustic and / or optical and / or haptic reproduction of content that is generated using a generative model based on artificial intelligence, wherein the generated content is adapted to the user, wherein the content is generated using the generative model on the basis of a user-specific template, and wherein the user-specific template contains a user preference assigned to the user profile as well as the user's age.

[0008] The term "generative model based on artificial intelligence" refers, in the broadest sense, to a content-generating and at least partially self-learning model that generates content in real time. The invention, among other things and not limited to, uses so-called large language models (LLMs). This type of artificial intelligence ensures that the content displayed or reproduced by the invention is generated in real time and can theoretically be continued indefinitely. These so-called large language models are generally computational linguistic probability models that have learned statistical word and sentence sequence relationships from a large number of text documents through previous training processes. These can generate and output corresponding content of theoretically infinite length.

[0009] According to the invention, the content to be reproduced includes, for example, texts, images, videos, audio content and combinations of the aforementioned examples.

[0010] According to the invention, the content is generated using the generative model on the basis of a user-specific template. This user-specific template contains a user preference assigned to the user profile as well as the user age. In addition, further characteristics can be integrated into the user profile, for example gender, personality traits or moods. The invention therefore works, for example, in such a way that the user enters the user age and a user preference, for example a preference for animal stories, into the user profile. This user profile is then made available to the generative model in the form of the user-specific template, wherein the user-specific template can contain, in addition to the user profile, further user-related data, e.g. factory-preset data. It is also conceivable for the user profile to contain a usage history orhas a playback history and continuously updates it. Furthermore, it is possible for the user to provide user feedback on the generated content in the user profile after and / or during use. Furthermore, the user profile is preferably designed so that it automatically adapts to the user's preferences with continued use, and possibly depending on the generated content and the feedback provided.

[0011] The generated content preferably comprises user-specific stories, in particular narrative stories. Also conceivable are learning stories and - e.g., for older users - stories to promote memory. According to the invention, stories, in particular narrative stories, are to be understood as a literary form that describes a coherent, self-contained plot. The described plot can be closed or open-ended. As a rule, a narrative story has a clear structure with an introduction, main part, and conclusion. In narrative stories, characters are introduced, an initial situation is described, conflicts or challenges are presented, and, if appropriate, a solution or an ending to the story is presented. Inventive stories can contain both realistic and fictional elements and convey values ​​​​by using specific themes, moral concepts, or human experiences.The narrative style of stories based on the invention can vary, from a first-person narrator who tells the story from their own perspective to an omniscient narrator who describes the events from a higher-level viewpoint. The invention works particularly advantageously in that the user-specific default, along with the user preference assigned to the user profile and the user's age, ensures that preferred themes and / or characters can be adapted to the user and implemented into the story.

[0012] The invention preferably works in such a way that the generated stories are particularly adapted to the user's age and follow user-age-specific framework parameters, for example, those defined on the terminal device. According to the invention, the user's age represents the most relevant framework parameter for the content to be generated and defines a large part of the story to be told. For example, a certain user age, e.g., under 16, leads to the exclusion of adult content and topics. In principle, these framework parameters are not to be understood as static, but rather as dynamic parameters that can change over time.

[0013] The language model is preferably user-oriented, with the narrative style and language complexity being adapted to the user's age. A device suitable for small children, for example, where the user's age is already preset on the device or integrated into the user profile, selects a simple narrative style. The story complexity and / or language complexity are adapted depending on the user's age, which is preferably preset on the device.

[0014] Furthermore, the end device is preferably designed so that the user-specific content can be influenced by the user during playback through user input. User input can occur in various ways, for example through voice input, keystrokes, or through an external medium. Influencing the user-specific content during playback makes it particularly advantageous to directly intervene in the content or story progression. For example, the user can change the main character after the story has begun. The generative model is able to adapt the story progression to the requirements immediately after the user input. Also included is the option of restarting a partially or completely completed story through user input, but with changes influenced by the user input.The invention also encompasses the possibility for the user, after completing a story, to attach a user input, a save request, and / or a marker, such as a favorite marker, to the completed story so that this story can be referred to at a later time. A user input, for example, where the main protagonist of a completed story is to be replaced, can then be consumed again at a later time with the changes tailored to the user input.

[0015] The user profile mentioned above preferentially takes exclusion criteria into account. These exclusion criteria are already at least partially integrated into the user profile through the user's age. Additional exclusion criteria can be added manually by the user, for example by entering data on the device. The content generated by the generative model then takes the added exclusion criteria into account. For example, a user with a certain phobia of animals and / or topics can enter these as exclusion criteria in the user preference to ensure that the generated content or story does not deal with these animals or topics. User age-specific rejection criteria are preferably already preset on the device, for example the exclusion of adult content for devices that appeal to a minor user group.

[0016] Preferably, the end device is so well-developed that user preferences are based on a questionnaire-based definition of framework parameters. This questionnaire-based definition preferably includes topics, literary genres such as crime or fantasy, favorite authors, favorite animals and colors, favorite music, etc. Based on this user preference, a user profile is created which contains the user's age as an additional framework parameter, which in turn is entered into the user-specific template, on the basis of which the generative model generates the content. Advantageously, the questionnaire used to define framework parameters can also be AI-generated. It is also conceivable for the questionnaire to be adaptable by the user while they are completing it. For example, it is possible that as soon as the user expresses their preference for a particular topic in the questionnaire, AI-generated further sub-questions orSubtopics related to the user's preferred topic area can be created and queried. This makes it particularly advantageous to provide a detailed user preference with specific framework parameters.

[0017] Preferably, the terminal device has user-specific form factors. Form factors in the context of the invention broadly refer to physical characteristics and / or distinguishing features with recognition value, which are particularly adapted to the user's age.

[0018] The user-specific form factors preferably include avatars and / or animals and / or color accents. The user-specific form factors are preferably based on the user's age. Avatars as form factors refer, for example, to figures, such as professions such as astronauts, doctors, soccer players, etc. Form factors such as animals can be various animal species, particularly plush toys or similarly distinctive animal species. The user-specific form factors are preferably designed as form factors that are at least partially integrated into the device. Form factors that represent the entire device are also included.

[0019] Furthermore, the terminal device preferably has a user-specific or user-specific button control. The user-specific button control is largely based on the user's age. In one form, the button control is variably adaptable in size and complexity. A button control suitable for small children, for example, can be a simple layout with a few, easy-to-use buttons. A terminal device with button control for adults, for example, can be more complex and have comparatively more setting options. Sensors for controlling the terminal device, for example, through gestures or movements on the part of the user, are also encompassed by the invention.

[0020] The generated content is preferably reproduced via optical content reproduction, for example, via a display and / or LEDs. Such a display is particularly preferably arranged in a central position. Optical content reproduction in the form of LED light signals can, for example, be carried out externally on the end device. Optical content reproduction via a display in combination with LEDs is preferably coordinated with each other.

[0021] Furthermore, haptic playback is preferably performed via vibrations and / or movements on the part of the device. The movements on the part of the device can, for example, be movements of a device designed as a plush toy, in which, for example, certain body parts are moved. Haptic playback advantageously ensures that the user experiences the most stimulating content playback possible.

[0022] According to the invention, the terminal device is designed such that the acoustic reproduction of the content preferably takes place as voice output, for example via at least one loudspeaker. The voice output preferably takes into account the user-specific template, so that the user's age is also taken into account in the voice output. The voice output generated taking into account the user-specific template can preferably be expressed as a voice or optionally as a voice imitation. Voice imitations of, for example, dubbing artists or other public figures are conceivable. Furthermore, other acoustic content appropriate to the content can be reproduced, for example noises such as animal noises, engine noises or the like. The loudspeakers performing the acoustic reproduction are preferably located centrally on the terminal device. Also conceivable are multiple loudspeakers located externally.

[0023] User input is preferably provided via voice input, for example, using a microphone. The microphone is preferably located centrally on the device, but can also be externally located and present in multiple versions. User input can, for example, take the form of commands or complete sentences. Voice input preferably includes the option of AI-based speech recognition.

[0024] Furthermore, according to the invention, the terminal device is designed such that content playback occurs within a user-specified framework, particularly a time frame. The time frame can be optionally entered into the user profile or, for example, specified as a voice input before content generation begins. The time frame is particularly important with regard to narrative stories as the content to be output, as it defines the story length and thus the literary narrative pace.

[0025] Preferably, a control unit that can be coupled to the terminal device is provided, which is capable of generating the user-specific template and transferring it to the terminal device. The invention also encompasses the generation and processing of the user-specific template on the terminal device. The coupleable control unit is preferably designed as a smartphone or tablet. The coupling between the terminal device and the control unit is preferably accomplished via Wi-Fi and / or Bluetooth or generally wirelessly. With the aid of the control unit, external operation by, for example, a parent or guardian with access to the user profile is possible. Internal operation is of course also included. In this way, it is particularly easy and immediate to react to the content output without having to directly control the terminal device itself. Furthermore, any changes to the user profile can be made in a simple and clear manner.

[0026] Preferably, the terminal device is capable of storing user-specific data on the terminal device and / or on the control unit, wherein the data optionally influences the content output. User-specific data in the sense of the invention relates, for example, to photos, self-created images and / or works, self-authored literary works, or data relating to the user themselves. Storing data on the terminal device and / or on the control unit can, for example, represent an upload process via Wi-Fi and / or Bluetooth and subsequent storage directly on the terminal device and / or control unit. Cloud storage is also encompassed according to the invention for this user-specific data and / or the digital components of the invention.For example, the device can optionally and at least partially integrate the uploaded user data into the user profile in order to create, for example, a story about the souvenir photos based on the user-specific template. Direct communication between the device and the cloud storage and the generative model that preferentially operates on it is also included.

[0027] The invention is explained in more detail below with reference to drawings that merely represent exemplary embodiments. It shows: Fig. 1 a terminal according to the invention in the form of a teddy bear with loudspeaker output and internal control unit, Fig. 2 a terminal in the form of an animal with a centrally located display, Fig. 3 a terminal in the form of a tablet with large button control and Fig. 4 a schematic representation of the user-specific adaptations.

[0028] In the Fig. 1 schematically shows a terminal device 1 according to the invention in the form of a plush teddy bear. This version of the terminal device 1 is suitable, for example, for small children under two years of age. The teddy bear 1 has a loudspeaker 2 located in the teddy bear's mouth for outputting audio content. Also located on the head, and in this example in the teddy bear's nose, is a microphone 3 suitable for voice input. In addition to the voice input, a button control 4 is also provided centrally on the teddy bear's stomach. For particularly simple operation, only three buttons are provided: Play, Pause, and Stop. Furthermore, the teddy bear 1 has a control unit 5 inside, particularly in the abdominal cavity, a control unit 5 (only sketched here).

[0029] The control unit 5 is designed so that it can be operated, for example, by a simple battery 6. The control unit 5 is equipped with an opening on the back of the teddy bear, for example, for replacing the battery. Furthermore, the control unit 5 has an interface 7, for example, designed as a USB interface. Furthermore, the control unit 5 is designed to be coupled to a mobile control unit 8. The mobile control unit 8 is designed here as a smartphone. The coupling takes place in the Fig. 1 example using a Wi-Fi connection, i.e. wirelessly.

[0030] The procedure for generating a narrative story and / or learning story is as follows. First, a user profile 17 is created using an app 9 installed in the mobile control unit 8. For this purpose, a parent or guardian first completes a questionnaire in the app 9. The questionnaire is particularly designed for topics that are of interest to small children under two years of age. For example, the interest of the user (the child) is defined here such that the child likes stories about rabbits, for example. Based on this questionnaire, a user preference 16 is defined. The user preference 16 and the user age 15, which is also entered in the app 9, together form the user profile 17. This user profile 17 is transferred from the smartphone 8 to the control unit 5, where it forms the user-specific template 18 for the generative model.The user-specific template 18 now specifies that the child, with a user age of two, particularly prefers stories about rabbits. Subsequently, a narrative story is generated by the generative model based on this user-specific template 18. This can be done, for example, by a voice input from the child using the microphone 3, such as "Tell me a story," or by pressing the play button on the keypad 4.

[0031] The user profile 17 can already contain preset preferences depending on the physical form factor of the device. For the specific example, this means that a teddy bear device 1 already prefers to play stories involving teddy bears. It is also conceivable, for example, that the form factor of the device 1, in this case the teddy bear, acts as a narrator and tells, for example, a learning story. This example preset is, of course, optional and can be deactivated.

[0032] To create the narrative, control unit 5 uses a generative model based on artificial intelligence. Here, control unit 5 is designed so that the required computing power or generation of the narrative is accomplished with the help of a cloud server 10. Control unit 5 therefore communicates with cloud server 10 using the existing Wi-Fi connection and generates the required narrative there. This is subsequently transmitted to control unit 5 and / or mobile control unit 8. The output from end device 1 via loudspeaker 3 then occurs with virtually no delay.

[0033] In addition to the audio output via speaker 2, additional visual outputs are also planned in connection with the narrative. This occurs via LEDs 11 and is coordinated with the content of the narrative.

[0034] Additionally, it is intended that the teddy bear 1 can also perform movements, such as arm movements of the arms 12, in conjunction with and depending on the content of the narrative. For example, if the narrative tells of a running rabbit, it is conceivable that the teddy bear will perform rapidly flashing LED signals and / or rapid, short movements of the arms 12.

[0035] If the parent / guardian finds this exemplary narrative about a running rabbit too upsetting, for example, they can influence the subsequent narrative process using app 9 by inputting something like "Story should be calmer." This input is transmitted to cloud server 10 via smartphone 8, so that, based on this input, the generative model adapts the story flow so that the narrative becomes calmer overall. This adjustment is transmitted to control unit 5 with virtually no delay, and subsequently, the narrative is played back over loudspeaker 2 in a calmer and / or possibly quieter volume.

[0036] The Fig. Figure 2 shows a terminal device according to the invention, here specifically for users of toddler age, for example, six years old. The terminal device is broadly composed of two main components. First, the control unit 5, designed as a tablet, constitutes the largest part of the device. In addition, the terminal device 1 has user-specific form factors, here specifically plastic extensions in the shape of a butterfly 13. The control unit 5 is equipped with a display, in particular a touch display 14.

[0037] Similar to the previous statements, the Fig. 1, the terminal 1 of the Fig. 2 with a generative model based on artificial intelligence operating on a cloud server 10, wherein commands and / or changes can be transmitted to the generative model using both the terminal device 1 and the mobile control unit 8.

[0038] The tablet 1 has two speakers 2, each located on the side, and a microphone 3, also located on the outside, for audio output or voice input. The battery-operated tablet 1 has an interface 7, in particular a USB interface 7, for charging and / or data transfer.

[0039] In addition to the ability to input data using the touchscreen 5, the tablet 1 also features a simple keypad 4. This allows the content output to be started, paused, and stopped even when the display 14 is locked.

[0040] The display 14 allows, in addition to the information already provided in connection with the Fig. 1, the narrative story described can be worked with not only acoustic and visual accents, but the display 14 can also be used to play back video or image content. It is intended that the generative model can, in addition to the narrative story tailored to the user's wishes, also present a video consistent with the narrative story or, for example, comic-like image sequences.

[0041] Coming back to the Fig. 1, this means that the tablet 1, in addition to the narrative story output via the loudspeakers 2, also presents sequences of images on the display 14 that are coordinated with the narrative story.

[0042] Furthermore, the Tablet 1 is equipped with a vibration function to provide haptic feedback in addition to the visual and acoustic content playback.

[0043] Fig. Figure 3 shows a terminal device 1 that is particularly aimed at older users, such as seniors. The terminal device 1 has a tablet-shaped control unit 5 with a display 14 and a form factor 13. The form factor 13, oriented toward seniors, is designed as a simple multimedia panel with buttons 4, a loudspeaker 2, and a microphone 3, specifically as a plastic and / or metal element located on the outside of the tablet device 1. Furthermore, the terminal device 1 has an interface 7, in particular a USB interface 7, suitable for charging and / or data transmission.

[0044] The terminal device 1 described in this case, which is particularly suitable for seniors, is characterized by the fact that the output content is oriented towards the user's own data. In the specific example, this means that the user and / or a second user, such as a family member or relative, integrates their own data into the user profile directly using the interface 7 or indirectly using the mobile control unit 8. Personal data can be, for example, mementos such as photos, stations / phases such as places of residence, occupations, partners, or other life events. The data is integrated, for example, by the user entering their own souvenir photos into the user profile 17 using the app 9 from the smartphone 8 or the control unit 5. These souvenir photos are then integrated into the user-specific template 18 and uploaded to the cloud server 10.The user profile 17 with the uploaded souvenir photos is also simultaneously transferred to the terminal device 1 and updated.

[0045] On the one hand, this makes it possible to simply play these souvenir photos on command, thus using device 1 as a kind of digital photo frame. On the other hand, the generative model can now be used to create a narrative story based on the uploaded souvenir photos.

[0046] If a subfolder is created in user profile 17 with, for example, grouped vacation photos from a specific vacation, the user can then refer to the subfolder name to generate a narrative based solely on these images. The generative model based on artificial intelligence is then able to analyze the uploaded images in such a way that a story can be output in narrative format based on the motifs and events recognized therein.

[0047] Furthermore, using user-related data, it is possible to create retrospective stories to strengthen one's own memory. Learning stories to retain basic characteristics and knowledge, for example, for people with dementia, are also conceivable.

[0048] In addition to the acoustic reproduction of the narrative story, the tablet 1 displays on the display 14 the souvenir photos corresponding to the narrative story and / or additionally generated images or videos based on the uploaded souvenir photos.

[0049] The Fig. Figure 4 schematically shows the organizational structure of the various hierarchies, particularly with regard to the information used to generate the content. According to the invention, the input of information by the user is designed such that the user preference 16 is first determined. This occurs, as already described. Fig. 2, using a questionnaire as an example. The user age (15) is already set in the device (1), at least within an age range, but can be subsequently adjusted by the user. This serves, for example, to prevent the display of content that is not suitable for users of that specific age.

[0050] The user age 15 specified on the end device in combination with the user preference 16 forms the user profile 17. The user profile 17 optionally also contains user-specific data, such as souvenir photos, which can be entered via the app 9. The user profile 17 is stored and continuously updated both on the end device and on the cloud server 10, and if necessary, also on the mobile control unit 8. Based on the user profile 17, a user-specific template 18 suitable for the generative model is subsequently created, which ultimately serves as the basis for the generated content. QUOTES CONTAINED IN THE DESCRIPTION

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

[0000] DE 10 2023 120 666 A1

[0004]

Claims

[1] User-specific electronic terminal, in particular a terminal adapted to the user's age, for the acoustic and / or optical and / or haptic reproduction of content generated using a generative model based on artificial intelligence, wherein the generated content is adapted to the user, where the content is generated using the generative model based on a user-specific template, whereby the user-specific template contains a user preference assigned to the user profile as well as the user age. [2] Terminal according to claim 1, characterized by that the content includes user-specific stories, in particular narrative stories and / or learning stories. [3] Terminal according to claim 1 or 2, characterized bythat the stories generated are particularly adapted to the user's age and follow user-age-specific framework parameters, for example those defined on the end device. [4] Terminal according to one of claims 1 to 3, characterized by that the user-specific content can be influenced by the user through user input during playback. [5] Terminal according to one of claims 1 to 4, characterized by that the user profile takes exclusion criteria into account. [6] Terminal according to one of claims 1 to 5, characterized by that user preference is based on a questionnaire-based definition of framework parameters. [7] Terminal according to one of claims 1 to 6, characterized by that the device has user-specific form factors. [8] Terminal according to one of claims 1 to 7, characterized by that the user-specific form factors include avatars and / or animals and / or color accents. [9] Terminal according to one of claims 1 to 8, characterized by that the terminal device has user-specific key control. [10] Terminal according to one of claims 1 to 9, characterized by that the optical content reproduction takes place, for example, via a display and / or LEDs. [11] Terminal according to one of claims 1 to 10, characterized by that the haptic reproduction takes place, for example, via vibrations and / or movements on the part of the end device. [12] Terminal according to one of claims 1 to 11, characterized by that the acoustic reproduction of the content takes place as voice output, for example via at least one loudspeaker. [13] Terminal according to one of claims 1 to 12, characterized by that the user input is provided as voice input, for example using a microphone. [14] Terminal according to one of claims 1 to 13, characterized bythat the content is reproduced within a framework, in particular a time frame, specified by the user. [15] Terminal according to one of claims 1 to 14, characterized by that a control unit that can be coupled to the terminal device generates the user-specific template and transfers it to the terminal device. [16] Terminal according to one of claims 1 to 15, characterized by that user-specific data can be stored on the terminal device and / or on the control unit, whereby the data can optionally influence the content output.

Citation Information

Patent Citations

  • Content speed and hyper-personalization through regenerative AI

    DE102023120666A1

Cited By

  • Computer-implemented method for generating and playing back an individualized, child-friendly AI-based audio file in a vehicle, computer program and vehicle

    DE102024139204A1