Expanding search engine capabilities using ai model recommendations

Patent metadata

Field	Value
Publication number	US-2020159856-A1
Application number	US-201816192685-A
Country	US
Kind code	A1
Filing date	Nov 15, 2018
Priority date	Nov 15, 2018
Publication date	May 21, 2020
Grant date	—

Abstract

Expanding search engine functionality using AI models. A method includes, as part of a search session, receiving user input at a search engine. One or more searches on a set of data using the user input. Search results are provided from the one or more searches to a user. Based on a history of the search session, suggestions are provided in a user interface of AI models that could be applied to expand potential search results for the search session. User input is received at the user interface selecting one or more of the suggested AI model. The one or more selected AI models are applied to expand the set of data. Search results to the user based on searching the expanded set of data.

First claim

What is claimed is:

1 . In a computing environment, a method of expanding search engine functionality using artificial intelligence (AI) models, the method comprising:
as part of a search session, receiving user input at a search engine; performing one or more searches on a set of data using the user input; providing search results from the one or more searches to a user; based on a history of the search session, providing in a user interface suggestions of AI models that could be applied to expand potential search results for the search session; receiving user input at the user interface selecting one or more of the suggested AI models; applying the one or more selected AI models to expand the set of data, by each of the AI models in the one or more selected AI models generating additional search data to augment the set of data to which the AI model is applied according to a predetermined augmentation goal, and wherein the additional search data is search data that is semantically consistent with the augmentation goals of the one or more AI models; and providing search results to the user based on searching the expanded set of data.

2 . The method of claim 1 , wherein the history of the search session includes a history of previous searches by a user.

3 . The method of claim 1 , wherein the history of the search session includes a history of previous AI models selected by a user.

4 . The method of claim 1 , wherein the history of the search session includes a set of search results that the user has identified as being particularly relevant.

5 . The method of claim 1 , wherein applying the one or more selected AI models causes additional search data to be added to a search index.

6 . The method of claim 1 , wherein applying the one or more selected AI models causes additional raw data to be added to the set of data.

7 . The method of claim 1 , wherein applying the one or more selected AI models causes additional refined data to be created for the set of data.

8 . The method of claim 1 , wherein applying the one or more selected AI models causes the set of data to be expanded to create one or more summaries of data from the set of data.

9 . The method of claim 1 , further comprising determining that search results from the one or more searches have fallen below a predetermined threshold, and wherein providing in a user interface suggestions of AI models that could be applied to expand potential search results for the search session is performed as a result.

10 . The method of claim 1 , further comprising, displaying a user interface element in the user interface that when selected causes providing in the user interface suggestions of AI models that could be applied to expand potential search results for the search session is performed as a result.

11 . The method of claim 1 , further comprising using history from other applications and hardware to determine suggested AI models.

12 . The method of claim 1 , further comprising, determining user frustration and as a result recommending AI models.

13 . The method of claim 12 , wherein determining user frustration comprises determining that a user is not clicking on results for a predetermined number of searches.

14 . The method of claim 12 , wherein determining user frustration comprises determining that a number of results is below a pre-determined threshold for a pre-determined number of searches.

15 . A computer system comprising:
one or more processors; and one or more computer-readable media having stored thereon instructions that are executable by the one or more processors to configure the computer system to expand search engine functionality using AI models, including instructions that are executable to configure the computer system to perform at least the following:
as part of a search session, receive user input at a search engine;
perform one or more searches on a set of data using the user input;
provide search results from the one or more searches to a user;
based on a history of the search session, provide in a user interface suggestions of AI models that could be applied to expand potential search results for the search session;
receive user input at the user interface selecting one or more of the suggested AI models;
apply the one or more selected AI models to expand the set of data, by each of the AI models in the one or more selected AI models generating additional search data to augment the set of data to which the AI model is applied according to a predetermined augmentation goal, and wherein the additional search data is search data that is semantically consistent with the augmentation goals of the one or more AI models; and
provide search results to the user based on searching the expanded set of data.

16 . The computer system of claim 15 , wherein applying the one or more selected AI models causes additional search data to be added to a search index.

17 . The computer system of claim 15 , wherein applying the one or more selected AI models causes the set of data to be expanded to create one or more summaries of data from the set of data.

18 . The computer system of claim 15 , wherein one or more computer-readable media further have stored thereon instructions that are executable by the one or more processors to configure the computer system to display a user interface element in the user interface that when selected causes providing in the user interface suggestions of AI models that could be applied to expand potential search results for the search session is performed as a result.

19 . The computer system of claim 15 , wherein one or more computer-readable media further have stored thereon instructions that are executable by the one or more processors to configure the computer system to determine user frustration and as a result recommend AI models.

20 . A search engine comprising:
an index indexing a set of data; an AI model recommender configured to identify AI models to recommend to a user; wherein the search engine is configured to display a user interface to a user and based on a history of a search session, provide in the user interface suggestions of AI models that could be applied to expand potential search results for the search session; wherein the search engine is configured to applying one or more selected AI model selected by a user, causing a set of data on which searches can be performed to be expanded, by each of the AI models in the one or more selected AI models generating additional search data to augment the set of data to which the AI model is applied according to a predetermined augmentation goal, and wherein the additional search data is search data that is semantically consistent with the augmentation goals of the one or more AI models; and wherein the search engine is further configured to provide search results to the user based on searching the expanded set of data.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Mital Vijay
• Du Liang
• Narayanan Ranjith
• Abraham Robin

Classifications

• G06F16/3328

  using graphical result space presentation or visualisation · CPC title

• G06F16/953 Primary

  Querying, e.g. by the use of web search engines · CPC title

• G06F16/3338 Primary

  Query expansion · CPC title

• G06F16/313

  Selection or weighting of terms for indexing · CPC title

• G06F16/9038

  Presentation of query results · CPC title