Search engine inference based virtual assistance

• US 8,214,344 B2
• Filed: 03/16/2010
• Issued: 07/03/2012
• Est. Priority Date: 03/16/2010
• Status: Expired due to Fees

• Current Assignee: Streamline Licensing LLC (IP Edge LLC)
• Original Assignee: Empire Technology Development LLC (Allied Inventors Management, LLC)
• Inventors: Kruglick, Ezekiel
• Primary Examiner(s): BOCCIO, VINCENT F
• Application Number:
  US12/724,660
• Publication Number:
  US 20110231379A1
• Time in Patent Office: 840 Days
• Field of Search: 707/3, 707/6, 707/0.003, 707/705, 707/706, 707/708, 707/759, 707/769, 707/771, 706/47
• US Class Current: 707/705
• CPC Class Codes: G06F 16/9035 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/957 Browsing optimisation, e.g. caching or content distillation
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

Techniques described herein generally relate to real time inference based systems. Example embodiments may set forth devices, methods, and computer programs related to search engine inference based virtual assistance. One example method may include a computing device adapted to receive text as input and a computer processor arranged to determine at least one inference regarding subject matter of the text based on one or more web searches of one or more terms within the text. The inference(s) may then be automatically displayed upon the inference(s) being determined. The text may be automatically received as input from a voice-to-text converter as voice-to-text conversion producing the text is occurring.

Claims

1. A method for automatically determining inferences comprising:

receiving streaming text as input to a computing device;

determining, with the computing device, at least one inference regarding subject matter of the text based on one or more web searches of one or more terms within the text as the text is being streamed as input, wherein determining at least one inference comprises;

automatically performing at least one web search of one or more terms within the text;

analyzing web search results of the at least one web search to determine a number of hits;

using the web search results to determine one or more topics when the number of hits is below a predetermined threshold; and

determining at least one inference based on the one or more topics; and

automatically displaying the at least one inference upon the at least one inference being determined.

2. The method of claim 1 further comprising using a computer processor to determine a larger combination of terms within the text than previously used in the at least one web search when the number of hits is above the predetermined threshold, and determining the at least one inference using the larger combination of terms within the text.

3. The method of claim 2 further comprising waiting for further text to be received as input to be used in creating the larger combination of terms within the text when larger combinations of terms within the text are determined to be unavailable.

4. The method of claim 1 wherein the text is automatically received as input from a voice-to-text converter as voice-to-text conversion producing the text is occurring.

5. The method of claim 4 further comprising providing, via a processor, the at least one inference to the voice-to-text converter to aid in performance of the voice-to-text converter interpreting subsequent voice signals.

6. A non-transitory computer readable storage medium containing instructions for automatically determining inferences, which when executed by a computer processor, cause the processor to:

receive streaming text as input to a computing device;

determine at least one inference regarding subject matter of the text based on one or more web searches of one or more terms within the text as the text is being streamed as input, wherein instructions that cause the processor to determine at least one inference comprise instructions that cause the processor to;

automatically perform at least one web search of one or more terms within the text;

analyze web search results of the at least one web search to determine a number of hits;

use the web search results to determine one or more topics when the number of hits is below a predetermined threshold; and

determine at least one inference based on the one or more topics; and

automatically display the at least one inference upon the at least one inference being determined.

7. The non-transitory computer readable storage medium of claim 6 further containing additional instructions, which when executed by the processor, cause the processor to:

use as search terms in at least one next web search a larger combination of terms within the text than previously used in the at least one web search when the number of hits returned by the at least one web search is above the predetermined threshold.

8. The non-transitory computer readable storage medium of claim 7 further containing additional instructions, which when executed by the processor, cause the processor to:

wait for further text to be received as input to be used in creating the larger combination of terms within the text when larger combinations of terms within the text are determined to be unavailable.

9. The non-transitory computer readable storage medium of claim 6 wherein the instructions that cause the processor to receive text as input comprise instructions that cause the processor to automatically receive text as input from a voice-to-text converter as voice-to-text conversion producing the text is occurring.

10. The non-transitory computer readable storage medium of claim 9 further containing additional instructions, which when executed by the processor, cause the processor to provide the at least one inference to the voice-to-text converter to aid in performance of the voice-to-text converter interpreting subsequent voice signals.

11. A computing device comprising:

a processor;

a memory coupled to the processor having executable instructions thereon that when executed configure the processor to;

receive text as streaming input;

determine at least one inference regarding subject matter of the text based on one or more web searches of one or more terms within the text as the text is being streamed as input, wherein the instructions that configure the processor to determine at least one inference comprise instructions that configure the processor to;

automatically perform at least one web search of one or more terms within the text;

analyze web search results of the at least one web search to determine a number of hits;

use the web search results to determine one or more topics when the number of hits is below a predetermined threshold; and

determine at least one inference based on the one or more topics; and

display the at least one inference upon the at least one inference being determined.

12. The computing device of claim 11 wherein the executable instructions, when executed, further configure the processor to:

use as search terms in at least one next web search a larger combination of terms within the text than previously used in the at least one web search when the number of hits returned by the at least one web search is above the predetermined threshold.

13. The computing device of claim 12 wherein the executable instructions, when executed, further configure the processor to:

wait for further text to be received as input to be used in creating the larger combination of terms within the text when larger combinations of terms with the text are determined to be unavailable.

14. The computing device of claim 11 wherein the executable instructions, when executed, further configure the processor to automatically receive text as input from a voice-to-text converter as voice-to-text conversion producing the text is occurring.

15. The computing device of claim 14 wherein the executable instructions, when executed, further configure the processor to provide the at least one inference to the voice-to-text converter to aid in performance of the voice-to-text converter interpreting subsequent voice signals.