Systems and methods for generating smart responses for natural language queries

• US 10,162,853 B2
• Filed: 02/29/2016
• Issued: 12/25/2018
• Est. Priority Date: 12/08/2015
• Status: Active Grant

• Current Assignee: Rovi Guides, Inc. (Adeia Inc.)
• Original Assignee: Rovi Guides, Inc. (Adeia Inc.)
• Inventors: Venkataraman, Sashikumar, Siddiq, Abubakkar, Mohaideen P, Ahmed Nizam, Ardhanari, Sankar
• Primary Examiner(s): Cao, Phuong Thao
• Application Number:
  US15/056,828
• Publication Number:
  US 20170161320A1
• Time in Patent Office: 1,030 Days
• Field of Search: 707722
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: H04N 21/25833 involving client hardware characteristics, e.g. manufacturer, processing or storage capabilities allocation of resources considering hardware capabilities in multiprogramming arrangements G06F9/5044; allocation of resources considering software capabilities in multiprogramming arrangements G06F9/5055
• CPC Class Codes: H04N 21/25841 involving the geographical location of the client retrieval from the Internet by querying based on geographical locations G06F16/9537; arrangements for identifying locations of receiving stations in broadcast systems H04H60/51; location of the user terminal in data switching networks H04L67/52; services making use of the location of users or terminals in wireless networks H04W4/02; locating users or terminals in wireless networks H04W64/00
• CPC Class Codes: H04N 21/4828 for searching program descriptors retrieval of video data G06F16/739

Abstract

Methods and systems are described for responding to natural language queries. Specifically a natural language query is received and a query template that corresponds to the natural language query is determined. One or more search results corresponding to the natural language query are retrieved. One or more attributes associated with the user equipment device are identified and based on those attributes a first response template associated with an audio-only response to the natural language query, a second response template associated with a visual-only response to the natural language query, or a third response template associated with an audio-visual response to the natural language query is selected. A response to the natural language query is generated based on the selected response template and the retrieved one or more search results.

Claims

1. A system for generating a response to a natural language query, the system comprising:

a user input interface of a user equipment device, wherein the user input interface is configured to receive the natural language query; and

control circuitry configured to;

receive, from the user input interface, the natural language query;

identify which query template of a plurality of query templates corresponds to the natural language query, wherein the identified query template comprises;

an associated first response template for providing an audio-only response to the natural language query, an associated second response template for providing a visual-only response to the natural language query, and an associated third response template for providing an audio-visual response to the natural language query;

retrieve one or more search results corresponding to the natural language query;

determine whether the user equipment device is associated with an audio component and a display;

in response to determining that the user equipment device is associated with the audio component and the display, update one or more attributes associated with the user equipment device to indicate that the user equipment device is associated with the audio component and the display;

select the associated third response template for providing the audio-visual response to the natural language query based on the one or more attributes indicating that the user equipment device is associated with the audio component and the display; and

generate the response to the natural language query based on the selected response template and the retrieved one or more search results.

2. The system of claim 1, wherein the one or more attributes associated with the user equipment device comprise:

a plurality of characteristics associated with the user equipment device, a location of the user equipment device, a date associated with the location of the user equipment device, an orientation of the user equipment device, and a time of day associated with the user equipment device.

3. The system of claim 1, wherein the control circuitry configured to identify the one or more attributes associated with the user equipment device comprises control circuitry configured to:

retrieve a plurality of attributes associated with the user equipment device;

determine a weight associated with each attribute of the plurality of attributes associated with the user equipment device; and

identify the one or more attributes based on the weight associated with each attribute of the plurality of attributes.

4. The system of claim 1, wherein the control circuitry configured to identify the one or more attributes associated with the user equipment device comprises control circuitry configured to:

identify an application of the user equipment device that the user interacted with last; and

add the application to the one or more identified attributes.

5. The system of claim 1 wherein the control circuitry is further configured to:

receive a generic response template associated with the natural language query;

determine whether the generic response template may be converted into at least one of an audio response template, a visual response template, and a mixed audio and visual response template;

based on determining that the generic response template can be converted into the audio response template, convert the generic response template into the associated first response template;

based on determining that the generic response template can be converted into the visual response template, convert the generic response template into the associated second response template; and

based on determining that the generic response template can be converted into an audiovisual response template, convert the generic response template into the associated third response template.

6. The system of claim 1, wherein the control circuitry is further configured to:

identify a user that is associated with the natural language query;

determine whether the user prefers to receive one of an audio-only response, a visual-only response, and an audio-visual response from the user equipment device; and

based on the determining, overwrite the one or more attributes with the user'"'"'s preference for the user equipment device.

7. The system of claim 1, wherein the control circuitry configured to identify the one or more attributes associated with the user equipment device comprises control circuitry configured to:

determine an orientation of the user equipment device; and

add the orientation of the user equipment device to the one or more attributes.

8. A method for generating a response to a natural language query, the method comprising:

receiving, using a control circuitry of a user equipment device, the natural language query;

identifying, using the control circuitry, which query template of a plurality of query templates corresponds to the natural language query, wherein the identified query template comprises;

an associated first response template for providing an audio-only response to the natural language query, an associated second response template for providing a visual-only response to the natural language query, and an associated third response template for providing an audio-visual response to the natural language query;

retrieving, using the control circuitry, one or more search results corresponding to the natural language query;

determining, using the control circuitry, whether the user equipment device is associated with an audio component and a display;

in response to determining that the user equipment device is associated with the audio component and the display, updating, using the control circuitry, one or more attributes associated with the user equipment device to indicate that the user equipment device is associated with the audio component and the display;

selecting, using the control circuitry, the associated third response template for providing the audio-visual response to the natural language query based on the one or more attributes indicating that the user equipment device is associated with the audio component and the display; and

generating the response to the natural language query based on the selected response template and the retrieved one or more search results.

9. The method of claim 8, wherein the one or more attributes associated with the user equipment device comprise:

a plurality of characteristics associated with the user equipment device, a location of the user equipment device, a date associated with the location of the user equipment device, an orientation of the user equipment device, and a time of day associated with the user equipment device.

10. The method of claim 8, wherein identifying the one or more attributes associated with the user equipment device comprises:

retrieving a plurality of attributes associated with the user equipment device;

determining a weight associated with each attribute of the plurality of attributes associated with the user equipment device; and

identifying the one or more attributes based on the weight associated with each attribute of the plurality of attributes.

11. The method of claim 8, wherein identifying the one or more attributes associated with the user equipment device comprises:

identifying an application of the user equipment device that the user interacted with last; and

adding the application to the one or more identified attributes.

12. The method of claim 8, further comprising:

receiving a generic response template associated with the natural language query;

determining whether the generic response template may be converted into at least one of an audio response template, a visual response template, and a mixed audio and visual response template;

based on determining that the generic response template can be converted into the audio response template, converting the generic response template into the associated first response template;

based on determining that the generic response template can be converted into the visual response template, converting the generic response template into the associated second response template; and

based on determining that the generic response template can be converted into an audiovisual response template, converting the generic response template into the associated third response template.

13. The method of claim 8, further comprising:

identifying a user that is associated with the natural language query;

determining whether the user prefers to receive one of an audio-only response, a visual-only response, and an audio-visual response from the user equipment device; and

based on the determining, overriding the one or more attributes with the user'"'"'s preference for the user equipment device.

14. The method of claim 8, wherein identifying the one or more attributes associated with the user equipment device comprises:

determining an orientation of the user equipment device; and

adding the orientation of the user equipment device to the one or more attributes.