# US 2025/0147940 A1 · Ai story platform with customizable personality for education, entertainment, and therapy

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0147940 A1
- Document ID: US20250147940A1
- Status: Published application
- Kind: A1
- Application number: 19/013,423
- Filed: 2025-01-08
- Published: 2025-05-08
- Earliest claimed: 2017-11-21
- Inventors: Maria Emma; Gregory Alexander D'Amico
- Web page: https://patentgrep.com/patent/US20250147940A1

## CPC

- G06F 16/22: Indexing; Data structures therefor; Storage structures
- G06F 16/3329: Natural language query formulation
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- G06N 5/041: {Abduction}
- G06N 20/00: Machine learning
- G10L 15/08: Speech classification or search
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 13/00: Speech synthesis; Text to speech systems
- G10L 15/16: using artificial neural networks
- G10L 17/18: Artificial neural networks; Connectionist approaches
- G10L 25/63: for estimating an emotional state
- G10L 2015/088: {Word spotting}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

System, methods, and apparatuses for an artificial intelligence (AI) toy with improved conversational dialogue and personality development. The AI toy determines responses to stimuli based on user profiles and personality profiles that are developed through user interaction and external media inputs. Natural Language Processing (NLP) and other semantic interaction processing is paired with the profiles to develop AI personality and conversational ability.

## Claims

### Claim 1

An artificial intelligence (AI) system for interactive entertainment, comprising:
a software platform including a server including at least one processor and at least one memory including at least one database;
wherein the software platform implements a virtual assistant (VA) service;
wherein the VA service is operable to construct at least one user profile and at least one artificial personality profile, wherein the at least one user profile and the at least one artificial personality profile are stored on the at least one database;
wherein the artificial personality profile is based on a historical, public, fictional, or non-fictional figure;
wherein the VA service is operable to construct the at least one artificial personality profile from media inputs created by and/or about the historical, public, fictional, or non-fictional figure, including a video, an audio, and/or text;
wherein the VA service receives at least one video recording and/or at least one audio recording of a voice sample of the historical, public, fictional, or non-fictional figure, wherein the at least one audio recording of a voice sample is used to create a voice model;
wherein the VA service stores the voice model in the at least one database;
wherein the VA service receives a stimulus, wherein the stimulus includes a movement, a sound, an image, or a second video;
wherein the VA service is operable to construct a response to the stimulus using the voice model, wherein the response is based on the at least one artificial personality profile; and
wherein the response is an audio response.

### Claim 2 (depends on 1)

The system of claim 1, wherein the VA service is operable to determine an emotional state of a user based on the input using a natural language processing (NLP) engine.

### Claim 3 (depends on 1)

The system of claim 1, wherein the at least one database is configured to store a plurality of artificial personalities, wherein the VA service is further configured to combine the plurality of artificial personalities to create a merged personality, wherein the merged personality includes one voice model.

### Claim 4 (depends on 1)

The system of claim 1, wherein the software platform is implemented on a smart home device, a toy, and/or a vessel, wherein the software platform sends a selected story to the smart home device, the toy, and/or the vessel, wherein the selected story is selected or created based on inputs received via the smart home device, the toy, and/or the vessel, wherein the inputs include an audio input, a touchscreen input, and/or a click select input, wherein a text-to-speak (TTS) engine converts a text of the selected story into an audio output using the voice model, wherein the audio output is played through the smart home device, the toy, and/or the vessel.

### Claim 5 (depends on 1)

The system of claim 1, wherein the VA service processes the audio input using natural language processing (NLP).

### Claim 6 (depends on 1)

The system of claim 1, wherein the system is operable to connect to an external server and database and load information from the external server, wherein the external server is operable to hold personality profiles, user profiles, and raw data corresponding to a specific user, or extracted data from the raw data corresponding to the specific user.

### Claim 7 (depends on 6)

The system of claim 6, wherein the system is operable to offer a plurality of different specific personalities, wherein when selected, the system is further operable to converse with a user in the voice and personality of the specific personality selected.

### Claim 8 (depends on 1)

The system of claim 1, wherein the VA service creates at least two voice models, wherein the at least one database stores the at least two voice models, wherein a server platform is operable to receive a selection of at least one of the at least two voice models, and wherein the at least one selected voice model is enabled for the VA service.

### Claim 9

An artificial intelligence (AI) system for interactive storytelling, comprising:
a software platform including a server including at least one processor and at least one memory including at least one database;
wherein the software platform is constructed and configured for communication with a user device;
wherein the software platform implements a virtual assistant (VA) service;
wherein the VA service is operable to construct at least one user profile and at least one user personality profile, wherein the at least one user profile and the at least one user personality profile are stored on the at least one database;
wherein the VA service receives at least one video recording and/or at least one audio recording of a voice, wherein the at least one audio recording of a voice sample is used to create a voice model;
wherein the VA service stores the voice model on the at least one database;
wherein the software platform sends a selected story to the user device, wherein the selected story is selected or created based on inputs received via the user device, wherein the inputs include an audio input, a touchscreen input, and/or a click select input;
wherein a text-to-speak (TTS) engine converts a text of the selected story into an audio output using the voice model; and
wherein the audio output is played through the user device.

### Claim 10 (depends on 9)

The system of claim 9, wherein the VA service receives at least one audio file from the user device, wherein the at least one audio file is an audio recording of a specific story section, a story page, and/or a set of words, wherein the VA service stores the at least one audio file and the voice model on the at least one database.

### Claim 11 (depends on 9)

The system of claim 9, wherein the software platform is implemented on a smart home device, a toy, and/or a vessel, wherein the smart home device, the toy, and/or the vessel is in network communication with the user device.

### Claim 12 (depends on 9)

The system of claim 9, wherein the VA service creates at least two voice models, wherein the at least one database stores the at least two voice models, wherein the server is operable to receive a selection of at least one of the at least two voice models from the user device, and wherein the at least one selected voice model is enabled for the VA service.

### Claim 13 (depends on 9)

The system of claim 9, wherein the VA service is configured to suggest a story to be converted using the TTS engine and the voice model based on a semantic category.

### Claim 14 (depends on 9)

The system of claim 9, wherein a stimulus is analyzed using natural language processing (NPL) and matched to a predetermined semantic category, wherein the VA service is configured to suggest a story to be converted using the TTS engine and the voice model based on the predetermined semantic category matched to the stimulus, wherein the story is categorized within the same predetermined semantic category as the stimulus.

### Claim 15 (depends on 9)

The system of claim 9, the at least one database is configured to store a plurality of artificial personalities, wherein the VA service is further configured to combine the plurality of artificial personalities to create a merged personality, wherein the merged personality includes one voice model.

### Claim 16

A method for using an artificial intelligence (AI) system for interactive storytelling comprising:
providing a software platform including a server including at least one processor and at least one memory including at least one database, wherein the software platform is constructed and configured for network communication with a user device;
the software platform implementing a virtual assistant (VA) service;
the VA service constructing at least one user profile including personally identifiable information;
the VA service constructing at least one artificial personality profile from media inputs including a video clip, an audio clip, and/or text, wherein the at least one artificial personality profile is based on a historical, public, fictional, or non-fictional figure, wherein the at least one artificial personality profile is stored on the at least one database;
the VA service receiving at least one audio recording and/or at least one video recording of a voice sample from the user device, wherein the at least one audio recording and/or the at least one video recording of a voice sample is from the historical, public, fictional, or non-fictional figure;
the VA service creating a voice model for a text-to-speech (TTS) engine from the audio clip of the media inputs, the video clip of the media inputs, the at least one audio recording and/or the at least one video recording of the voice sample;
the VA service storing the voice model on the at least one database;
the software platform sending a selected story to the user device, wherein the selected story is based on an input received via a graphic user interface (GUI) of the user device, wherein the input includes an audio input, a touchscreen input, and/or a click select input;
the TTS engine converting a text of the selected story into an audio output using the voice model; and
the user device playing the audio output.

### Claim 17 (depends on 16)

The method of claim 16, further comprising a smart home device, a toy, and/or a vessel implementing the software platform and the smart home device, the toy, and/or the vessel wirelessly communicating with the user device.

### Claim 18 (depends on 16)

The method of claim 16, further comprising the at least one database storing the voice model, the software platform receiving a selection of the voice model and enabling the selected voice model for the VA service.

### Claim 19 (depends on 16)

The method of claim 16, further comprising the VA service receiving at least one audio file from the user device, wherein the at least one audio file is an audio recording of a specific section, page, and or set of words of a story, wherein the VA service stores the at least one audio file and the voice model on the at least one database.

### Claim 20 (depends on 16)

The method of claim 16, the at least one database is configured to store a plurality of artificial personalities, wherein the VA service is further configured to combine the plurality of artificial personalities to create a merged personality, wherein the merged personality includes one voice model.
