Adaptive prompt customization using brainwave activity data
A system for generating highly personalized image content with generative artificial intelligence (AI) that incorporates brainwave data collected from a Brain-Computer Interface (BCI) device worn by the user while they are immersed in their experiences. The system can identify a mood (i.e., cognitive, mental, and emotional states) felt by the user during that time. The system develops a prompt that describes the target scene and modulates the weights assigned to each parameter in the prompt based on the mood identified. The generative AI engine can then to apply the mood to the target scene by adjusting image attributes such as hue, saturation, and lighting. The outputted image can offer a visual representation not only of the objects that were in the user's environment, but also the user's general perception and experience of the occasion. The process is passive and requires no interaction from the user to define their emotional affect.
1 . A method of generating personalized image content, the method comprising:
receiving, at a computing device, a first image of a target scene captured by a camera at a first time;
receiving, at the computing device, a first bio-signal data stream for a first user collected at or around the first time;
identifying, at the computing device, a first mood associated with the first user based on the first bio-signal data;
creating a first prompt based on both the first image and the first mood as a user expression, the first prompt including a set of parameters, wherein a weight assigned to each parameter is modulated based on the identified first mood, wherein creating the first prompt comprises:
automatically collecting the first bio-signal data stream of a user, wherein the first bio-signal data stream serves as a proxy of the user expression,
converting the first bio-signal data stream into numerical values,
applying the numerical values to weigh one or more descriptive words associated with the target scene;
providing the first prompt based on determining an intensity of word from the one or more descriptive words associated with the target scene; and
passing the first prompt through a generative artificial intelligence (AI) engine to generate a second image that includes aspects of the target scene that have been imbued with stylistic elements that represent the first mood.
2 . The method of claim 1 , wherein the first bio-signal data stream is collected via a Brain-Computer Interface (BCI) device worn by the first user.
3 . The method of claim 1 , wherein identifying the first mood includes passing the first bio-signal data stream through an emotion recognition classifier.
4 . The method of claim 1 , wherein the set of parameters includes time of day, temperature, and weather.
5 . The method of claim 1 , wherein the set of parameters includes geolocation, date, and point of interest.
6 . The method of claim 1 , wherein modulation of the weight assigned to each parameter in the first prompt causes the generative AI to adjust values of one or more of a hue, saturation, and lightness associated with the target scene.
7 . The method of claim 1 , wherein modulation of the weight assigned to each parameter in the first prompt causes the generative AI to apply an image filter to the target scene.
8 . A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to generate personalized image content by:
receiving, at a computing device, a first image of a target scene captured by a camera at a first time;
receiving, at the computing device, a first bio-signal data stream for a first user collected at or around the first time;
identifying, at the computing device, a first mood associated with the first user based on the first bio-signal data;
creating a first prompt based on both the first image and the first mood, the first prompt including a set of parameters, wherein a weight assigned to each parameter is modulated based on the identified first mood, wherein creating the first prompt comprises:
automatically collecting the first bio-signal data stream of a user, wherein the first bio-signal data stream serves as a proxy of the user expression,
converting the first bio-signal data stream into numerical values,
applying the numerical values to weigh one or more descriptive words associated with the target scene;
providing the first prompt based on determining an intensity of word from the one or more descriptive words associated with the target scene; and
passing the first prompt through a generative artificial intelligence (AI) engine to generate a second image that includes aspects of the target scene that have been imbued with stylistic elements that represent the first mood.
9 . The non-transitory computer-readable medium of claim 8 , wherein the first bio-signal data stream is collected via a BCI device worn by the first user.
10 . The non-transitory computer-readable medium of claim 8 , wherein identifying the first mood includes passing the first bio-signal data stream through an emotion recognition classifier.
11 . The non-transitory computer-readable medium of claim 8 , wherein the set of parameters includes time of day, temperature, and weather.
12 . The non-transitory computer-readable medium of claim 8 , wherein the set of parameters includes geolocation, date, and point of interest.
13 . The non-transitory computer-readable medium of claim 8 , wherein modulation of the weight assigned to each parameter in the first prompt causes the generative AI to adjust values of one or more of a hue, saturation, and lightness associated with the target scene.
14 . The non-transitory computer-readable medium of claim 8 , wherein modulation of the weight assigned to each parameter in the first prompt causes the generative AI to apply an image filter to the target scene.
15 . A system for generating personalized image content comprising one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to:
receive, at a computing device, a first image of a target scene captured by a camera at a first time;
receive, at the computing device, a first bio-signal data stream for a first user collected at or around the first time;
identify, at the computing device, a first mood associated with the first user based on the first bio-signal data;
create a first prompt based on both the first image and the first mood, the first prompt including a set of parameters, wherein a weight assigned to each parameter is modulated based on the identified first mood, wherein creating the first prompt comprises:
automatically collecting the first bio-signal data stream of a user, wherein the first bio-signal data stream serves as a proxy of the user expression,
converting the first bio-signal data stream into numerical values, and
applying the numerical values to weight one or more descriptive words associated with the target scene;
providing the first prompt based on determining an intensity of word from the one or more descriptive words associated with the target scene; and
pass the first prompt through a generative artificial intelligence (AI) engine to generate a second image that includes aspects of the target scene that have been imbued with stylistic elements that represent the first mood.
16 . The system of claim 15 , wherein the first bio-signal data stream is collected via a BCI device worn by the first user.
17 . The system of claim 15 , wherein the instructions further cause the one or more computers to pass the first bio-signal data stream through an emotion recognition classifier.
18 . The system of claim 15 , wherein the set of parameters includes time of day, temperature, and weather.
19 . The system of claim 15 , wherein the set of parameters includes geolocation, date, and point of interest.
20 . The system of claim 15 , wherein modulation of the weight assigned to each parameter in the first prompt causes the generative AI to adjust values of one or more of a hue, saturation, and lightness associated with the target scene.