CN-122029545-A - Context and profile based generated AI system automation

Abstract

Various embodiments include systems and methods for generating hints for generating an Artificial Intelligence (AI) model. A processing system including at least one processor may be configured to identify a user of a computing device, obtain user context information from a source of physical context information in the computing device, receive a user prompt for a large-scale generated AI model (LXM), select a user profile from a plurality of user profiles based on the user, the user context information, and the user prompt, generate an enhanced prompt based on the user prompt and information included in the selected user profile, and submit the enhanced prompt to the LXM.

Inventors

• V. GUPTA
• Z. Asgar
• W.J. HOLLAND
• V. Sukumar
• K. H. Al Mali
• R. Memisiewicz

Assignees

• 高通股份有限公司

Dates

Publication Date

20260512

Application Date

20240904

Priority Date

20231023

Claims (20)

1. 1. A method performed by a computing device for generating hints for a large-scale generated artificial intelligence model (LXM), the method comprising: Identifying a user of the computing device; obtaining user context information from a source of physical context information in the computing device; receiving a user prompt for the LXM; Selecting a user profile from a plurality of user profiles based on the user, the user context information, and the user prompt; Generating an enhanced prompt based on the user prompt, the user context information, and information included in the selected user profile, and Submitting the enhanced hint to the LXM.
2. 2. The method of claim 1, further comprising determining an activity of the user based on the user context information, Wherein selecting the user profile from the plurality of user profiles based on the user, the user context information, and the user prompt includes selecting the user profile based at least in part on the determined activity of the user.
3. 3. The method of claim 1, further comprising determining a location of the user based on the user context information, Wherein selecting the user profile from the plurality of user profiles based on the user, the user context information, and the user prompt includes selecting the user profile based at least in part on the determined location of the user.
4. 4. The method of claim 1, further comprising determining an output device used by the user based on the user context information, Wherein selecting the user profile from the plurality of user profiles based on the user, the user context information, and the user prompt includes selecting the user profile based at least in part on the determined output device.
5. 5. The method of claim 1, the method further comprising: determining an output device used by the user based on the user context information, and One LXM of the plurality of LXMs is selected based on the determined output device, Wherein submitting the enhanced hint to the LXM comprises submitting the enhanced hint to the selected LXM.
6. 6. The method of claim 1, further comprising determining from the user context information whether the user is communicating with another person, Wherein selecting the user profile from the plurality of user profiles based on the user, the user context information, and the user prompt includes selecting a user profile suitable for communicating with another person regarding a topic in the user prompt.
7. 7. The method of claim 1, the method further comprising: determining from the user context information whether the user is communicating with another person; determining a relationship or identity of the other person from the user context information in response to determining that the user is communicating with the other person, and Selecting another person profile from a plurality of other person profiles based on the determined relationship or identity of the other person, Wherein generating the enhanced alert based on the user alert, the user context information, and information included in the selected user profile includes generating the enhanced alert based on the user alert, the user context information, information included in the selected user profile, and information included in the selected other personal profile.
8. 8. The method of claim 1, the method further comprising: determining an urgency from one or both of the user prompt and the user context information, and The user profile is selected based on the degree of urgency.
9. 9. The method of claim 8, further comprising selecting one LXM of a plurality of LXMs based at least in part on one or more of: degree of urgency; The selected user profile; The user context information, and One or more of the input or output devices, Wherein submitting the enhanced hint to the LXM comprises submitting the enhanced hint to the selected LXM.
10. 10. The method of claim 1, further comprising updating the selected user profile based on how the user responds to output received from the LXM in response to the enhanced prompt.
11. 11. The method of claim 1, the method further comprising: Obtaining a user profile associated with a user of a device in communication with the computing device; generating the enhanced alert based on the selected user profile, the obtained user profile associated with the user of the device in communication with the computing device, the user context information, and the received user alert; Generating one or more LXM parameters to be transmitted with the enhanced hint, and Submitting the enhanced hint and the one or more LXM parameters to the LXM.
12. 12. A computing device, the computing device comprising: a memory; at least one processor coupled to the memory and configured to: Identifying a user of the computing device; obtaining user context information from a source of physical context information in the computing device; Receiving a user prompt for a large-scale generated artificial intelligence model (LXM); Selecting a user profile from a plurality of user profiles based on the user, the user context information, and the user prompt; Generating an enhanced prompt based on the user prompt, the user context information, and information included in the selected user profile, and Submitting the enhanced hint to the LXM.
13. 13. The computing device of claim 12, wherein the at least one processor is further configured to: determining an activity of the user based on the user context information, and The user profile is selected from the plurality of user profiles based on the user, the user context information, the user prompt, and based at least in part on the determined activity of the user.
14. 14. The computing device of claim 12, wherein the at least one processor is further configured to: Determining a location of the user based on the user context information, and The user profile is selected from the plurality of user profiles based on the user, the user context information, the user prompt, and based at least in part on the determined location of the user.
15. 15. The computing device of claim 12, wherein the at least one processor is further configured to: Determining an output device used by the user based on the user context information; the user profile is selected from the plurality of user profiles based on the user, the user context information, the user prompt, and at least in part on the determined output device.
16. 16. The computing device of claim 12, wherein the at least one processor is further configured to: determining an output device used by the user based on the user context information, and Selecting one of the plurality of LXMs based on the determined output device, and Submitting the enhanced hint to the selected LXM.
17. 17. The computing device of claim 12, wherein the at least one processor is further configured to: Determining from the user context information whether the user is communicating with another person, and The user profile is selected from the plurality of user profiles based on the user, the user context information, the user prompt, and a user profile adapted to communicate with another person regarding a topic in the user prompt.
18. 18. The computing device of claim 12, wherein the at least one processor is further configured to: determining from the user context information whether the user is communicating with another person; determining a relationship or identity of the other person from the user context information in response to determining that the user is communicating with the other person, and Selecting another person profile from a plurality of other person profiles based on the determined relationship or identity of the other person, The enhanced prompt is generated based on the user prompt, the user context information, information included in the selected user profile, and information included in the selected other personal profile.
19. 19. The computing device of claim 12, wherein the at least one processor is further configured to: determining an urgency from one or both of the user prompt and the user context information, and The user profile is selected based on the degree of urgency.
20. 20. The computing device of claim 19, wherein the at least one processor is further configured to: selecting one LXM of the plurality of LXMs based at least in part on one or more of: degree of urgency; The selected user profile; The user context information or One or more input or output devices, and Submitting the enhanced hint to the selected LXM.

Description

Context and profile based generated AI system automation RELATED APPLICATIONS The present application claims priority from U.S. non-provisional application Ser. No. 18/492,379, filed on 10/23 of 2023, the entire contents of which are incorporated herein by reference. Background Recent advances in Artificial Intelligence (AI) and Machine Learning (ML) technology have enabled the development of increasingly complex models that can understand and interpret complex data structures. These models, commonly referred to as large-scale generative AI models (LXMs), have numerous applications across various fields, ranging from natural language processing to computer vision and speech recognition. The efficacy of these models results from the ability of these models to learn from a large number of data sets, thereby achieving unprecedented depth of understanding and applicability. LXMs have grown in capabilities, including but not limited to Large Language Models (LLMs), large Speech Models (LSMs), and Large Visual Models (LVMs) (also known as language visual models or Visual Language Models (VLMs)), to provide enhanced functionality in a variety of applications, such as natural language understanding, speech recognition, visual analysis, text generation, speech generation, and/or image generation, among others. Among the various types of LXMs, LLM is generally known for its ability to understand and generate human language. These models may be trained based on a broad set of literal data and may perform tasks such as machine translation, literal abstracts, and/or questions and answers. LLM has been used in a wide range of industries including healthcare, financial and customer services, and the like. LSM is an LXM that processes and understands auditory data specifically. LSM may translate spoken language into text form and vice versa. LSMs are adept at tasks such as speech-to-text conversion, speech recognition, natural language understanding in a spoken context, and/or providing spoken word responses in machine-generated speech. The efficacy of LSMs is that LSMs can learn from a vast dataset containing diverse accents, language variants, and languages. LVMs are LXMs that are trained to interpret and analyze visual data. The LVM model may use convolutional neural networks or similar architecture to process visual input and derive meaningful conclusions therefrom. From image classification to object detection, to generating new images in response to natural language cues, LVMs are growing in popularity and use in a wide variety of fields such as medical imaging, autonomous vehicles, surveillance systems, advertising and entertainment. Disclosure of Invention Various aspects include a method performed by a computing device for generating hints for a large-scale generated artificial intelligence model (LXM), the method may include identifying a user of the computing device, obtaining user context information from a source of physical context information in the computing device, receiving a user hint for the LXM, selecting a user profile from a plurality of user profiles based on the user, the user context information, and the user hint, generating an enhanced hint based on the user hint, the user context information, and information included in the selected user profile, and submitting the enhanced hint to the LXM. Some aspects may include determining an activity of the user based on the user context information, wherein selecting a user profile from a plurality of user profiles based on the user, the user context information, and the user prompt may include selecting the user profile based at least in part on the determined activity of the user. Some aspects may include determining a location of the user based on the user context information, wherein selecting the user profile from the plurality of user profiles based on the user, the user context information, and the user prompt may include selecting the user profile based at least in part on the determined location of the user. Some aspects may include determining an output device for use by the user based on the user context information, wherein selecting the user profile from the plurality of user profiles based on the user, the user context information, and the user prompt may include selecting the user profile based at least in part on the determined output device. Some aspects may include determining an output device for use by the user based on the user context information, and selecting one of a plurality of LXMs based on the determined output device, wherein submitting the enhanced alert to the LXM may include submitting the enhanced alert to the selected LXM. Some aspects may include determining from the user context information whether the user is communicating with another person, wherein selecting the user profile from the plurality of user profiles based on the user, the user context information, and the user prompt may include selecting a user profile