公开(公告)号：US20250077549A1

公开(公告)日：2025-03-06

申请号：US18459081

申请日：2023-08-31

Applicant: Adobe Inc.

Inventor： William Brandon GEORGE ,  Wei Zhang ,  Tyler Rasmussen ,  Tung Mai ,  Tong Yu ,  Sungchul Kim ,  Shunan Guo ,  Samuel Nephi Grigg ,  Said Kobeissi ,  Ryan Rossi ,  Ritwik Sinha ,  Eunyee Koh ,  Prithvi Bhutani ,  Jordan Henson Walker ,  Abhisek Trivedi

IPC: G06F16/28 ,  G06F16/242 ,  G06F40/205 ,  G06F40/40

Abstract: Graphic visualizations, such as charts or graphs conveying data attribute values, can be generated based on natural language queries, i.e., natural language requests. To do so, a natural language request is parsed into n-grams, and from the n-grams, word embeddings are determined using a natural language model. Data attributes for the graphic visualization are discovered in the vector space from the word embeddings. The type of graphic visualization can be determined based on a request intent, which is determined using a trained intent classifier. The graphic visualization is generated to include the data attribute values of the discovered data attributes, and in accordance with the graphic visualization type.

公开(公告)号：US12265557B2

公开(公告)日：2025-04-01

申请号：US18459081

申请日：2023-08-31

Applicant: Adobe Inc.

Inventor： William Brandon George ,  Wei Zhang ,  Tyler Rasmussen ,  Tung Mai ,  Tong Yu ,  Sungchul Kim ,  Shunan Guo ,  Samuel Nephi Grigg ,  Said Kobeissi ,  Ryan Rossi ,  Ritwik Sinha ,  Eunyee Koh ,  Prithvi Bhutani ,  Jordan Henson Walker ,  Abhisek Trivedi

IPC: G06F40/00 ,  G06F16/242 ,  G06F16/28 ,  G06F40/205 ,  G06F40/40

Abstract: Graphic visualizations, such as charts or graphs conveying data attribute values, can be generated based on natural language queries, i.e., natural language requests. To do so, a natural language request is parsed into n-grams, and from the n-grams, word embeddings are determined using a natural language model. Data attributes for the graphic visualization are discovered in the vector space from the word embeddings. The type of graphic visualization can be determined based on a request intent, which is determined using a trained intent classifier. The graphic visualization is generated to include the data attribute values of the discovered data attributes, and in accordance with the graphic visualization type.

公开(公告)号：US20240320421A1

公开(公告)日：2024-09-26

申请号：US18338033

申请日：2023-06-20

Applicant: Adobe Inc.

Inventor： Victor Soares Bursztyn ,  Wei Zhang ,  Prithvi Bhutani ,  Eunyee Koh ,  Abhisek Trivedi

IPC: G06F40/186

CPC classification number: G06F40/186

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating naturally phrased insights about data charts using light language models distilled from large language models. To synthesize training data for the light language model, in some embodiments, the disclosed systems leverage insight templates for prompting a large language model for generating naturally phrased insights. In some embodiments, the disclosed systems anonymize and augment the synthesized training data to improve the accuracy and robustness of model predictions. For example, the disclosed systems anonymize training data by injecting noise into data charts before prompting the large language model for generating naturally phrased insights from insight templates. In some embodiments, the disclosed systems further augment the (anonymized) training data by splitting or partitioning data charts into folds that act as individual data charts.