Augmenting an Information Request

Patent metadata

Field	Value
Publication number	US-2016196264-A1
Application number	US-201514589110-A
Country	US
Kind code	A1
Filing date	Jan 5, 2015
Priority date	Jan 5, 2015
Publication date	Jul 7, 2016
Grant date	—

Abstract

An electronic device comprises a microphone for receiving an oral request for information about an unspecified object. A sensor receives augmentation information about the unspecified object. Combination logic combines information from the oral request with the augmentation information into a combined format information request. Information retrieval logic then retrieves an answer to the combined format information request.

First claim

What is claimed is:

1 . An electronic device comprising:
a microphone for receiving an oral request for information about an unspecified object; a sensor for receiving augmentation information about the unspecified object; combination logic for combining information from the oral request with the augmentation information into a combined format information request; and information retrieval logic for retrieving an answer to the combined format information request.

2 . The electronic device of claim 1 , further comprising:
a transmitter for transmitting the combined format information request to an information server.

3 . The electronic device of claim 1 , wherein the sensor is a camera.

4 . The electronic device of claim 1 , wherein the sensor is a chemical sensor.

5 . The electronic device of claim 1 , wherein the sensor is a camera that captures a video image, wherein the unspecified object is an object that does not appear in the video image, and wherein the electronic device accesses:
a metadata retrieving logic, wherein the metadata retrieving logic retrieves metadata from the video image captured by the camera that describes the video image; correlation logic that correlates information from the metadata to identify information about the unspecified object to generate an answer to the combined format request.

6 . A method for augmenting an information request, the method comprising:
receiving, by an information server, a request for information about an object, wherein the request for information is from an electronic device, and wherein the request for information is in a first format; receiving, by the information server, augmentation information about the object, wherein the augmentation information is generated by the electronic device, and wherein the augmentation information is in a second format that is different from the first format; and generating, by the information server, a response to the request for information based on the augmentation information.

7 . The method of claim 6 , wherein the first format is for speech recognition, and wherein the second format is for a video file that is generated by a camera on the electronic device.

8 . The method of claim 6 , wherein the first format is for speech recognition, and wherein the second format is for an audio file that is generated by a microphone on the electronic device.

9 . The method of claim 6 , wherein the first format is for speech recognition, and wherein the second format is for a text document that is received from the electronic device.

10 . The method of claim 6 , wherein the first format is for speech recognition, and wherein the second format is for a graph document that is stored on the electronic device.

11 . The method of claim 6 , wherein the first format is for speech recognition, and wherein the second format is for a chemical signature that is generated by a chemical sensor on the electronic device.

12 . The method of claim 6 , wherein the first format is for speech recognition, wherein the second format is for a photograph, wherein the object is shown in the photograph, and wherein the method further comprises:
retrieving, by the information server, embedded information in the photograph about the object shown in the photograph, wherein the embedded information describes the object shown in the photograph; and locating, by the information server, additional information about the object in the photograph based on the embedded information, wherein the additional information surpasses the embedded information.

13 . The method of claim 6 , wherein the first format is for speech recognition, wherein the second format is for a photograph, wherein the object is not shown in the photograph, and wherein the method further comprises:
utilizing, by the information server, embedded information in the photograph to retrieve additional information about the object not shown in the photograph, wherein the additional information surpasses the embedded information.

14 . The method of claim 6 , wherein the request for information is generated by a specific user, and wherein the method further comprises:
associating the request for information with a user profile for the specific user; and tailoring the response to the request for information based on the user profile.

15 . The method of claim 6 , further comprising:
receiving, by the information server, a physical gesture of a user; and utilizing, by the information server, the physical gesture as additional augmentation information about the object.

16 . A computer program product for augmenting an information request, the computer program product comprising a computer readable storage medium having program code embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, and wherein the program code is readable and executable by a processor to perform a method comprising:
receiving a request for information about an object, wherein the request for information is from an electronic device, and wherein the request for information is in a first format; receiving augmentation information about the object, wherein the augmentation information is generated by the electronic device, and wherein the augmentation information is in a second format that is different from the first format; and generating a response to the request for information based on the augmentation information.

17 . The computer program product of claim 16 , wherein the first format is for speech recognition, and wherein the second format is for a video file.

18 . The computer program product of claim 16 , wherein the first format is for speech recognition, and wherein the second format is for a chemical signature that is generated by a chemical sensor on the electronic device.

19 . The computer program product of claim 16 , wherein the first format is for speech recognition, wherein the second format is for a photograph, wherein the object is shown in the photograph, and wherein the method further comprises:
retrieving embedded information in the photograph about the object shown in the photograph, wherein the embedded information describes the object shown in the photograph; and locating additional information about the object in the photograph based on the embedded information, wherein the additional information surpasses the embedded information.

20 . The computer program product of claim 16 , wherein the first format is for speech recognition, wherein the second format is for a photograph, wherein the object is not shown in the photograph, and wherein the method further comprises:
utilizing embedded information in the photograph to retrieve additional information about the object not shown in the photograph, wherein the additional information surpasses the embedded information.

Assignees

• IBM

Inventors

• Bostick James E
• Ganci Jr John M
• Rakshit Sarbajit K
• Trim Craig M

Classifications

• G06F16/433

  using audio data · CPC title

• G06F16/48 Primary

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title

• G06F16/9032

  Query formulation · CPC title

• G06F16/5866

  using information manually generated, e.g. tags, keywords, comments, manually generated location and time information · CPC title

• G16C20/20

  Identification of molecular entities, parts thereof or of chemical compositions · CPC title