Filtering document search results using contextual metadata

Patent metadata

Field	Value
Publication number	US-10929478-B2
Application number	US-201715637037-A
Country	US
Kind code	B2
Filing date	Jun 29, 2017
Priority date	Jun 29, 2017
Publication date	Feb 23, 2021
Grant date	Feb 23, 2021

Abstract

Receiving contextual data including a facial movement associated with an active document. A response associated with the active document is detected and associated with the received contextual data. A contextual metadata tag is generated based on the detected response to the active document. A contextual keyword is created that corresponds to the contextual metadata tag. Search results received in response to the query are filtered based on the contextual metadata tag.

First claim

What is claimed is:

1. A computer-implemented method for filtering document search results, the computer-implemented method comprising:
receiving contextual data comprising: (i) a facial movement associated with an active document, and (ii) one or more images of a face of a user viewing the active document;
detecting an emotional response associated with the active document based on the received contextual data, wherein the emotional response is detected based, at least in part, on respective shapes of a mouth, nose, eyebrows, and forehead lines of the user, and on respective positions, in relation to one another, of the mouth, nose, eyebrows, and forehead lines of the user;
responsive to detecting a change in location of a device displaying the active document, generating a contextual metadata tag, wherein generating the contextual metadata tag includes generating a movement tag indicating movement of the device when the user is accessing the active document over a period of time, and wherein access is determined by an eye movement tracker that analyzes eye movements of the user related to specific text within the active document, captured images of the face of the user while reading the active document, and extracted actions that the user was performing while reading the active document;
receiving a query comprising a contextual keyword corresponding to the contextual metadata tag;
filtering search results received in response to the query based on the contextual metadata tag; and
displaying a list of the filtered search results and a list of filters applied to the search results.

2. The method of claim 1 , wherein detecting the emotional response comprises detecting the facial movement based on the contextual data, the contextual data further comprising a received image of a face of a user reading the active document.

3. The method of claim 1 , wherein detecting the emotional response comprises detecting an emotional response based on the contextual data.

4. The method of claim 1 , comprising receiving, via a processor, contextual data comprising an image of a face of a user reading the active document.

5. The method of claim 1 , comprising receiving, via the processor, contextual data comprising a location and a time associated with the active document.

6. The method of claim 1 , wherein generating, via the processor, a contextual metadata tag comprises generating a mood tag corresponding to a mood of a user reading or editing the active document.

7. The method of claim 1 , wherein generating, via the processor, a contextual metadata tag comprises generating a movement tag indicating a movement of a device while the active document was read or edited.

8. A computer program product for filtering document search results, the computer program product comprising a computer readable storage medium having stored thereon:
program instructions programmed to receive contextual data comprising: (i) a facial movement associated with an active document, and (ii) one or more images of a face of a user viewing the active document;
program instructions programmed to detect an emotional response associated with the active document based on the received contextual data, wherein the emotional response is detected based, at least in part, on respective shapes of a mouth, nose, eyebrows, and forehead lines of the user, and on respective positions, in relation to one another, of the mouth, nose, eyebrows, and forehead lines of the user;
program instructions programmed to, responsive to detecting a change in location of a device displaying the active document, generate a contextual metadata tag, wherein generating the contextual metadata tag includes generating a movement tag indicating movement of the device when the user is accessing the active document over a period of time, and wherein access is determined by an eye movement tracker that analyzes eye movements of the user related to specific text within the active document, captured images of the face of the user while reading the active document, and extracted actions that the user was performing while reading the active document;
program instructions programmed to receive a query comprising a contextual keyword corresponding to the contextual metadata tag;
program instructions to filter search results received in response to the query based on the contextual metadata tag; and
program instructions to display a list of the filtered search results and a list of filters applied to the search results.

9. The computer program product of claim 8 , comprising program code executable by a processor to receive contextual data comprising a document accessed before or after the active document, a time, a global positioning satellite (GPS) location, or any combination thereof.

10. The computer program product of claim 8 , comprising program code executable by the processor to display categories of contextual metadata tags in response to detecting that the filter search results exceed a predetermined threshold.

11. The computer program product of claim 8 , comprising program code executable by the processor to generate a contextual metadata tag for the active document based on a previously active document and a subsequently active document, wherein the contextual data comprises previously active documents and subsequently active documents for the active document.

12. The computer program product of claim 8 , comprising program code executable by the processor to generate a mood tag based on the contextual data, wherein the contextual data further comprises images of a face associated with the active document.

13. The computer program product of claim 8 , comprising program code executable by the processor to generate a movement tag in response to detecting a change in location of a device displaying the active document.

14. A computer system for filtering document search results, the computer system comprising:
a processor(s) set; and
a computer readable storage medium;
wherein:
the processor set is structured, located, connected and/or programmed to run program instructions stored on the computer readable storage medium; and
the program instructions include:
program instructions programmed to receive contextual data comprising: (i) a facial movement associated with an active document, and (ii) one or more images of a face of a user viewing the active document;
program instructions programmed to detect an emotional response associated with the active document based on the received contextual data, wherein the emotional response is detected based, at least in part, on respective shapes of a mouth, nose, eyebrows, and forehead lines of the user, and on respective positions, in relation to one another, of the mouth, nose, eyebrows, and forehead lines of the user;
program instructions programmed to, responsive to detecting a change in location of a device displaying the active document, generate a contextual metadata tag, wherein generating the contextual metadata tag includes generating a movement tag indicating movement of the device when the user is accessing the active document over a period of time, and wherein access is determined by an eye movement tracker that analyzes eye movements of the user related to specific text within the active document, captured images of the face of the user while reading the active document, and extracted actions that the user was performing while reading the active document;
program instructions programmed to receive a query comprising a contextual keyword corresponding to the contextual metadata tag;
program instructions to filter search results received in response

Assignees

• IBM

Inventors

• Ben-Yair Yoav
• Fuchs Gil
• Gordon Itai
• Prager Ilan D

Classifications

• A61B5/1114 Primary

  Tracking parts of the body · CPC title

• G06V2201/10

  Recognition assisted with metadata · CPC title

• G06V40/20

  Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16) · CPC title

• G06V40/174

  Facial expression recognition · CPC title

• G06V40/176

  Dynamic expression · CPC title