IP Library Granted Patent US 11,048,713
Granted Patent B2
US 11,048,713 · App. 15/719,321 · Granted Jun 29, 2021

System and method for visual exploration of search results in two-mode networks

Inventors: Jian Zhao (Cupertino, CA); Francine Chen (Menlo Park, CA); Patrick Chiu (Mountain View, CA)
Assignee: FUJI XEROX CO., LTD.
G06F16/248G06F16/27G06Q30/0625
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,048,713
App. No.
15/719,321
Granted
Jun 29, 2021
Kind
B2
Abstract

A method of visualizing search results is provided. The method includes receiving a content feature, detecting, within a network, a subnetwork pattern representing a relationship satisfying a condition and associated with an entity of a first or a second type, the entity being associated with the content feature, and generating a visualization based on the detected subnetwork pattern. The visualization includes a first region representative of the first type of entity, a second region representative of the second type of entity, and a linking region connecting the first region to the second region and providing information about the represented relationship.

Claims (76)

1. A method of visualizing search results, the method comprising:

receiving a content feature extracted from a media content item;

detecting, within a network, a plurality of subnetwork patterns each representing a relationship satisfying a condition and associated with either an entity selected from a plurality entities of a first type or an entity selected from a plurality of entities of a second type, the entity being associated with the received content feature, wherein the network comprises a plurality of relationships, each relationship being associated with an entity selected from a plurality of entities of the first type and an entity selected from a plurality of entities of the second type;

generating a visualization based on the detected subnetwork pattern, wherein the visualization comprises:

a first region representative of the first type of entity;

a second region representative of the second type of entity; and

a linking region connecting the first region to the second region and providing information about the represented relationship,

wherein the visualization comprises a plurality of rows, each row associated with one of the plurality of detected subnetwork patterns satisfying the condition; and

displaying the generated visualization on a display device;

receiving a first input signal identifying an entity of the first type; and

updating the visualization based on the identified entity, wherein the updating the visualization comprises:

detecting a first entity of the second type associated with a relationship associated with the identified entity of the first type;

detecting a second entity of the first type associated with a relationship associated with the detected first entity of the second type; and

repositioning at least one row associated with a subnetwork pattern representing a relationship associated with at least one of the detected first entity of the second type and the detected second entity of the first type.

2. The method of claim 1 , wherein the first type of entity is representative of creators of content in a content management system; and

wherein the second type of entity is representative of items of content in a content management system.

3. The method of claim 2 , wherein the information provided in the linking region of the visualization comprises a content summary representative of one or more entities of the second type associated with the relationship represented by each of plurality of subnetwork patterns.

4. The method of claim 3 , further comprising receiving a second input signal identifying an entity of either the first type and the second type; and

updating the visualization based on the identified entity,

wherein the updating the visualization comprises repositioning at least one row associated with a subnetwork pattern representing a relationship associated with the identified entity.

5. The method of claim 3 , further comprising receiving a second input signal identifying an entity of either the first type and the second type; and

updating the visualization based on the identified entity,

wherein the updating the visualization comprises repositioning at least one row associated with a subnetwork pattern representing a relationship not associated with the identified entity.

6. The method of claim 1 , wherein the first type of entity is representative of customers of a retailer; and

wherein the second type of entity is representative of items sold by the retailer.

7. The method of claim 1 , wherein the repositioning at least one row associated with a subnetwork pattern comprises:

identifying at least one row associated with a subnetwork representing a relationship both not associated with the identified entity and associated with the detected second entity of the first type.

8. The method of claim 1 , wherein the received content feature is extracted based in part on at least one of an object recognition technique and an audio recognition technique.

9. The method of claim 1 , wherein the plurality of rows are a plurality of horizontal rows comprising a plurality of horizontally arranged nodes, each horizontal row including a node representative of the first type of entity, a node representative of the second type of entity, and a node of the linking region, wherein each horizontal row is associated with one of the plurality of detected subnetwork patterns satisfying the condition in order to visualize maximal subnetworks within the network, each node representative of an entity of the first type in the subnetwork having a connecting relationship with each node representative of an entity of the second type in the subnetwork.

10. The method of claim 9 , wherein the first region comprises a plurality of first nodes representative of the first type of entity and the second region comprises a plurality of second nodes representative of the second type of entity, wherein the node of linking region comprises controls to scroll or toggle through either the plurality of first nodes or the plurality of second nodes.

11. The method of claim 9 , wherein each node is associated with an entity of either the first type or second type, wherein at least one node comprises:

a first bar indicating a first number of subnetwork patterns of the detected plurality of subnetwork patterns that the entity associated with the at least one node is part of; and

a second bar representing a second number subnetwork patterns that both the entity associated with the at least one node is a part of and identified entity is part of.

12. A non-transitory computer readable medium having stored therein a program for making a computer execute a method of visualizing search results, the method comprising:

receiving a content feature extracted from a media content item;

detecting, within a network, a plurality of subnetwork patterns each representing a relationship satisfying a condition and associated with either an entity selected from a plurality entities of a first type or an entity selected from a plurality of entities of a second type, the entity being associated with the received content feature, wherein the network comprises a plurality of relationships, each relationship being associated with an entity selected from a plurality of entities of the first type and an entity selected from a plurality of entities of the second type;

generating a visualization based on the detected subnetwork pattern, wherein the visualization comprises:

a first region representative of the first type of entity;

a second region representative of the second type of entity; and

a linking region connecting the first region to the second region and providing information about the represented relationship,

wherein the visualization comprises a plurality of rows, each row associated with one of the plurality of detected subnetwork patterns satisfying the condition; and

displaying the generated visualization on a display device;

receiving a first input signal identifying an entity of the first type; and

updating the visualization based on the identified entity, wherein the updating the visualization comprises:

detecting a first entity of the second type associated with a relationship associated with the identified entity of the first type;

detecting a second entity of the first type associated with a relationship associated with the detected first entity of the second type; and

repositioning at least one row associated with a subnetwork pattern representing a relationship associated with at least one of the detected first entity of the second type and the detected second entity of the first type.

13. The non-transitory computer readable medium of claim 12 , wherein the first type of entity is representative of creators of content in a content management system; and

wherein the second type of entity is representative of items of content in a content management system.

14. The non-transitory computer readable medium of claim 13 , wherein the information provided in the linking region of the visualization comprises a content summary representative of one or more entities of the second type associated with the relationship represented by each of plurality of subnetwork patterns.

15. The non-transitory computer readable medium of claim 14 , further comprising receiving a second input signal identifying an entity of either the first type and the second type; and

updating the visualization based on the identified entity,

wherein the updating the visualization comprises repositioning at least one row associated with a subnetwork pattern representing a relationship associated with the identified entity.

16. The non-transitory computer readable medium of claim 14 , further comprising receiving a second input signal identifying an entity of either the first type and the second type; and

updating the visualization based on the identified entity,

wherein the updating the visualization comprises repositioning at least one row associated with a subnetwork pattern representing a relationship not associated with the identified entity.

17. The non-transitory computer readable medium of claim 12 , wherein the first type of entity is representative of customers of a retailer; and

wherein the second type of entity is representative of items sold by the retailer.

18. The non-transitory computer readable medium of claim 12 , wherein the repositioning at least one row associated with a subnetwork pattern comprises:

identifying at least one row associated with a subnetwork representing a relationship both not associated with the identified entity and associated with the detected second entity of the first type.

19. A computer apparatus configured to visualize search results, the computer apparatus comprising:

a memory storing relationship data comprising a plurality of relationships, each relationship being associated with an entity selected from a plurality of entities of the first type and an entity selected from a plurality of entities of the second type; and

a processor executing a process comprising:

receiving a content feature extracted from a media content item;

detecting, within a network, a plurality of subnetwork patterns each representing a relationship satisfying a condition and associated with either an entity selected from a plurality entities of a first type or an entity selected from a plurality of entities of a second type, the entity being associated with the received content feature, wherein the network comprises a plurality of relationships, each relationship being associated with an entity selected from a plurality of entities of the first type and an entity selected from a plurality of entities of the second type; and

generating a visualization based on the detected subnetwork pattern, wherein the visualization comprises:

a first region representative of the first type of entity;

a second region representative of the second type of entity; and

a linking region connecting the first region to the second region and providing information about the represented relationship,

wherein the visualization comprises a plurality of rows, each row associated with one of the plurality of detected subnetwork patterns satisfying the condition;

receiving a first input signal identifying an entity of the first type; and

updating the visualization based on the identified entity, wherein the updating the visualization comprises:

detecting a first entity of the second type associated with a relationship associated with the identified entity of the first type;

detecting a second entity of the first type associated with a relationship associated with the detected first entity of the second type; and

repositioning at least one row associated with a subnetwork pattern representing a relationship associated with at least one of the detected first entity of the second type and the detected second entity of the first type; and

a display device configured to display the generated visualization.

Assignments (2)
CHANGE OF NAME Recorded May 25, 2021
From: FUJI XEROX CO., LTD.
To: FUJIFILM BUSINESS INNOVATION CORP.
Reel/Frame 056392/0541 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 28, 2017
From: ZHAO, JIAN; CHEN, FRANCINE; CHIU, PATRICK
To: FUJI XEROX CO., LTD.
Reel/Frame 043731/0294 →
Continuity (1)
Related Publication 20190095503A1 · Mar 28, 2019