Systems and methods for searching databases by sound input

• US 8,694,534 B2
• Filed: 08/23/2010
• Issued: 04/08/2014
• Est. Priority Date: 07/29/2010
• Status: Active Grant

• Current Assignee: Soundhound AI IP LLC
• Original Assignee: SoundHound Incorporated
• Inventors: Mohajer, Keyvan
• Primary Examiner(s): Bullock, Joshua
• Application Number:
  US12/861,775
• Publication Number:
  US 20120030199A1
• Time in Patent Office: 1,324 Days
• Field of Search: 707/723, 707/769, 705/14
• US Class Current: 707/769
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/957 Browsing optimisation, e.g. caching or content distillation
• CPC Class Codes: G06Q 30/0256 User search

Abstract

Systems and methods for searching databases by sound data input are provided herein. A service provider may have a need to make their database(s) searchable through search technology. However, the service provider may not have the resources to implement such search technology. The search technology may allow for search queries using sound data input. The technology described herein provides a solution addressing the service provider'"'"'s need, by giving a search technology that furnishes search results in a fast, accurate manner. In further embodiments, systems and methods to monetize those search results are also described herein.

Claims

1. A method for providing hosting for speech recognition database query handling, the method comprising:

receiving a database on a computer system over a network, the database comprising a plurality of items for recognition;

processing the database using the computer system, the processing comprising;

generating corresponding features for each of one or more of the plurality items for recognition; and

generating corresponding rankings for each of one or more of the plurality of items for recognition;

receiving on the computer system over the network a sound data input comprising a query for the processed database;

determining one or more search results in the processed database using the computer system based on the query, the corresponding features, and the corresponding rankings, the processed database being the processed database that is processed to generate each of the corresponding features and the corresponding rankings; and

transmitting the one or more search results from the computer system to a remote computer system, the corresponding rankings affecting an organization of the one or more search results.

2. The method of claim 1, further comprising storing the processed database.

3. The method of claim 1, wherein the receiving further comprises receiving text associated with the query, the determining one or more search results in the processed database being further based on the received text.

4. The method of claim 1, wherein the sound data input comprises spoken words.

5. The method of claim 1, wherein the receiving further comprises receiving an image associated with the query, the determining one or more search results in the processed database being further based on the received image.

6. The method of claim 1, wherein processing the database further comprises processing the database to produce phonetic data for each of the plurality of items for recognition.

7. The method of claim 1, wherein determining one or more search results in the processed database comprises matching the query with the corresponding features of the processed database.

8. The method of claim 1, further comprising receiving account information from a service provider, the account information comprising authentication information, billing information and contact information.

9. The method of claim 1, wherein each item for recognition comprises at least one of a destination web address field, a record description field, a record image field, and a record rich content field.

10. The method of claim 1, wherein each corresponding ranking comprises a ranking priority based on a desired search result order.

11. The method of claim 10, further comprising organizing the one or more search results based upon the ranking priority.

12. The method of claim 1, wherein the receiving further includes receiving a command and the method further comprises performing a search action of the processed database based upon the received command.

13. The method of claim 1, further comprising receiving data from a service provider to add, delete, or modify the database.

14. A system for providing hosting for speech recognition database query handling, the system comprising:

a communications module configured to receive a database on a computer system over a network, the database comprising a plurality of items for recognition; and

a processor for executing instructions stored in memory to;

process the database using the computer system, the processing comprising;

generating corresponding features for each of one or more of the plurality items for recognition; and

generating corresponding rankings for each of one or more of the plurality of items for recognition;

receive on the computer system over the network a sound data input comprising a query for the processed database;

determine one or more search results in the processed database using the computer system based on the query, the corresponding features, and the corresponding rankings, the processed database being the processed database that is processed to generate each of the corresponding features and the corresponding rankings; and

transmit the one or more search results from the computer system to a remote computer system, the corresponding rankings affecting an organization of the one or more search results.

15. A method for providing for speech recognition database query handling, the method comprising:

receiving a database on a computer system over a network, the database comprising a plurality of items for recognition;

processing the database using the computer system, the processing comprising generating corresponding phonetic data for each of one or more of the plurality of items for recognition, the generating corresponding phonetic data comprising transforming text data from an item for recognition into phonetic data;

receiving on the computer system over the network a sound data input comprising a query for the processed database;

processing the query by dividing the query into a plurality of query chunks;

determining one or more search results in the processed database using the computer system based on one or more of the plurality of query chunks and the corresponding phonetic data; and

selectively transmitting, for display in real time to a remote computer system from the computer system, one or more fields of the one or more search results, the one or more fields being related to the one or more search results.

16. The method of claim 15, wherein the selectively transmitted one or more fields of the one or more search results comprises text.

17. The method of claim 15, wherein the selectively transmitted one or more fields of the one or more search results comprises one or more images.

18. The method of claim 15, wherein the selectively transmitted one or more fields of the one or more search results comprises rich content.

19. The method of claim 15, wherein the one or more search results are organized in a search result list.

20. The method of claim 15, wherein each of the one or more search results are rendered to the end user one by one.

21. The method of claim 15, wherein selectively transmitting for display in real time to the remote computer system from the computer system, the one or more fields of the one or more search results further comprises:

transmitting rich content of the one or more search results while the selectively transmitted one or more fields of the one or more search results is being displayed.

22. A system for providing for speech recognition database query handling, the system comprising:

a communications module configured to receive a database on a computer system over a network, the database comprising a plurality of items for recognition; and

a processor for executing instructions stored in memory to;

generate corresponding phonetic data for each of one or more of the plurality items for recognition by transforming text data from an item for recognition into phonetic data;

store the corresponding phonetic data in the database, thereby resulting in a processed database;

receive on the computer system over the network a sound data input comprising a query for the processed database;

process the query by dividing the query into a plurality of query chunks;

determine one or more search results in the processed database using the computer system based on one or more of the plurality of query chunks and the corresponding phonetic data; and

selectively transmit, for display in real time to a remote computer system from the computer system, via the network, one or more fields of the one or more search results, the one or more fields being related to the one or more search results.