17933595. GENERATIVE PROMPT EXPANSION FOR IMAGE GENERATION simplified abstract (ADOBE INC.)

GENERATIVE PROMPT EXPANSION FOR IMAGE GENERATION

Organization Name

ADOBE INC.

Inventor(s)

Ritiz Tambi of San Francisco CA (US)

Ajinkya Gorakhnath Kale of San Jose CA (US)

GENERATIVE PROMPT EXPANSION FOR IMAGE GENERATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 17933595 titled 'GENERATIVE PROMPT EXPANSION FOR IMAGE GENERATION

Simplified Explanation

The abstract describes systems and methods for query processing that involve generating expanded queries based on an original query using a causal language model (CLM) and providing images associated with these expanded queries.

• Explanation of the patent:

- Identify original query - Generate expanded queries by adding additional phrases based on original query using CLM - Provide images related to expanded queries in response to original query

• • Potential Applications:**

This technology can be applied in search engines, e-commerce platforms, and content recommendation systems to improve query processing and enhance user experience.

• • Problems Solved:**

- Enhances search accuracy by generating expanded queries - Provides relevant images to assist users in finding information - Improves user engagement by offering a variety of search results

• • Benefits:**

- Increased search relevance and accuracy - Enhanced user experience with visual search results - Efficient query processing and retrieval of information

• • Potential Commercial Applications:**

"Enhancing Query Processing with Expanded Queries and Images: Commercial Applications"

• • Possible Prior Art:**

There may be prior art related to query expansion techniques using language models and image retrieval systems, but specific examples are not provided in the abstract.

1. 1. 1. Unanswered Questions:
         1. How does the causal language model determine which additional phrases to generate for the expanded queries?

The abstract does not detail the specific methodology or criteria used by the causal language model to generate additional phrases based on the original query.

1. 1. 1. 1. What types of images are provided in response to the original query, and how are they selected?

The abstract does not specify the criteria for selecting and providing images associated with the expanded queries, leaving room for further exploration into the image retrieval process.

Original Abstract Submitted

Systems and methods for query processing are described. Embodiments of the present disclosure identify an original query; generate a plurality of expanded queries by generating a plurality of additional phrases based on the original query using a causal language model (CLM) and augmenting the original query with each of the plurality of additional phrases, respectively; and provide a plurality of images in response to the original query, wherein the plurality of images are associated with the plurality of expanded queries, respectively.