System for performing multi-level conversational and contextual voice based search

Patent metadata

Field	Value
Publication number	US-11429681-B2
Application number	US-201916361509-A
Country	US
Kind code	B2
Filing date	Mar 22, 2019
Priority date	Mar 22, 2019
Publication date	Aug 30, 2022
Grant date	Aug 30, 2022

Abstract

A system, method, and computer-readable medium are disclosed for improved text and voice based searching. In various embodiments, a multi-level voice search system is implemented. In various embodiments, a voice based search is converted to text, where the text is used to determine a user's intent and context of the search. The search can be for a particular object and for data or information related to the object. Subsequent searches, which can be from a conversation using voice based searching can change the context and be directed to a different more specific level of the object. Metadata can link data or information, such as documents to one another. Based on search history or patterns, data or information can be updated.

First claim

What is claimed is:

1. A computer-implementable method for multi-level conversational and contextual voice based searching comprising:
creating conversational search patterns as to search queries for particular objects through a multi-level voice search system, wherein the particular objects are related to products, services, and documents;
determining a context and a level of a search query based on the created conversational search patterns as to a user's intent, of the multi-level conversational and contextual voice based searching, wherein the search query includes different levels of query that includes a primary object and root objects, wherein the primary object is at a top level and root objects are at lower levels;
searching a contextual search database that includes the primary object correlated to a particular conversational search pattern, for relevant data as to the determined level of the search query;
deciding if a subsequent search query has changed the context and level;
providing the relevant data if the context and level have not changed;
identifying a particular root object and associated document set if the context and level has changed; and
performing another search query for relevant data based on the identified particular root object and associated document set, if the context and level have changed.

2. The method of claim 1 , wherein the determining further includes user intent.

3. The method of claim 1 , wherein the determining is directed to a primary object and the subsequent search is performed for root objects of the primary object.

4. The method of claim 1 , wherein the searching for relevant data is directed to a document set related to a particular object.

5. The method of claim 1 , wherein the subsequent search is directed to different levels of a hierarchy tree of a primary object and root objects.

6. The method of claim 1 , wherein the relevant data comprise document sets that include metadata linked document.

7. The method of claim 1 further comprising updating relevant data based on a history of search queries.

8. A system comprising:
a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations for multi-level conversational and contextual voice based searching and comprising instructions executable by the processor and configured for:
creating conversational search patterns as to search queries for particular objects through a multi-level voice search system, wherein the particular objects are related to products, services, and documents;
determining a context and a level of a search query based on the created conversational search patterns as to a user's intent, of the multi-level conversational and contextual voice based searching, wherein the search query includes different levels of query that includes a primary object and root objects, wherein the primary object is at a top level and root objects are at lower levels;
searching a contextual search database that includes the primary object correlated to a particular conversational search pattern, for relevant data as to the determined level of the search query;
deciding if a subsequent search query has changed the context and level;
providing the relevant data if the context and level have not changed;
identifying a particular root object and associated document set if the context and level has changed; and
performing another search query for relevant data based on the identified particular root object and associated document set, if the context and level have changed.

9. The system of claim 8 , wherein the relevant data includes metadata linked document sets.

10. The system of claim 8 , wherein the relevant data originates from one or more sources.

11. The system of claim 8 , wherein the object is a primary object and the subsequent query is directed to root objects of the primary object.

12. The system of claim 11 , wherein primary object and root object are part of a hierarchy tree of different levels of context.

13. The system of claim 8 further comprising updating relevant data based on a history of search queries.

14. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for:
creating conversational search patterns as to search queries for particular objects through a multi-level voice search system, wherein the particular objects are related to products, services, and documents;
determining a context and a level of a search query based on the created conversational search patterns as to a user's intent, of the multi-level conversational and contextual voice based searching, wherein the search query includes different levels of query that includes a primary object and root objects, wherein the primary object is at a top level and root objects are at lower levels;
searching a contextual search database that includes the primary object correlated to a particular conversational search pattern, for relevant data as to the determined level of the search query;
deciding if a subsequent search query has changed the context and level;
providing the relevant data if the context and level have not changed;
identifying a particular root object and associated document set if the context and level has changed; and
performing another search query for relevant data based on the identified particular root object and associated document set, if the context and level have changed.

15. The non-transitory, computer-readable storage medium of claim 14 , wherein the performing a voice based search query is implemented with one or more search engines.

16. The non-transitory, computer-readable storage medium of claim 14 , wherein the relevant data are documents sets.

17. The non-transitory, computer-readable storage medium of claim 16 , wherein the document sets comprise metadata linked documents.

18. The non-transitory, computer-readable storage medium of claim 14 , wherein the object is a primary object and subsequent searches are performed on root objects of the primary object.

19. The non-transitory, computer-readable storage medium of claim 14 , wherein the relevant data originate from one or more sources.

20. The non-transitory, computer-readable storage medium of claim 14 further comprising updating relevant data based on a history of search queries.

Assignees

• Dell Products Lp

Inventors

• Roy Mainak
• Gupta Chitrak
• Babu Rathi
• Nistala Amrita

Classifications

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/9532

  Query formulation · CPC title

• G06F16/243

  Natural language query formulation · CPC title

• G06F16/2246

  Trees, e.g. B+trees · CPC title

• G06F16/2425 Primary

  Iterative querying; Query formulation based on the results of a preceding query · CPC title