Systems and methods for identifying semantically and visually related content

• US 10,726,297 B2
• Filed: 05/21/2018
• Issued: 07/28/2020
• Est. Priority Date: 01/23/2015
• Status: Active Grant

• Current Assignee: HighSpot, Inc.
• Original Assignee: HighSpot, Inc.
• Inventors: Hoffman, Raphael, Dire, Nate, Christensen, Erik, Sharp, Oliver, Wortendyke, David, Gellock, Scot, Wahbe, Robert
• Primary Examiner(s): Azima, Shaghayegh
• Application Number:
  US15/985,222
• Publication Number:
  US 20180268253A1
• Time in Patent Office: 799 Days
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/23 Clustering techniques
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06V 10/761 Proximity, similarity or dissimilarity measures
• CPC Class Codes: G06V 10/762 using clustering, e.g. of similar faces in social networks
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
• CPC Class Codes: G06V 30/418 Document matching, e.g. of document images

Abstract

Systems and methods for identifying semantically and/or visually related information among a set of content items, such content items that include similar concepts or that have similar visual aspects, are disclosed. The disclosed techniques provide tools for identifying related information among various content items, such as text pages and documents, presentation slides and slide decks, etc. The disclosed techniques provide improved methods for searching among content items, organizing content items into categories, and pruning redundant content. Furthermore, the disclosed techniques provide improvements to computation of various metrics, including usage, performance, and impact metrics.

Claims

1. A computer-implemented method of identifying information of interest within an organization comprising:

determining use data that represents interactions by at least some of multiple users within the organization with information items in the organization, the use data characterizing relationships among the information items in the organization and relationships between the information items and the users within the organization, the organization including a structured body of users with associated roles within the organization and who have access to at least a subset of the information items within the organization, wherein each information item is at least a portion of a document, a presentation, a video, an image, a profile of a user, or a webpage;

generating interest data indicating affinity among the information items based on the determined use data, wherein generating the interest data includes;

identifying, based on the use data, at least one set of two or more information items that are frequently interacted with together by a plurality of the users in the organization, where each set of information items includes a first information item from the set of information items and a second, different information item from the set of information items, and where each of the plurality of users interacted with both the first information item and the second information item, and

determining the affinity among the information items based on the identification of the at least one set of information items;

receiving a request for a feed or set of information items from a particular user; and

responding to the request by providing one or more items selected from the corpus of information items in the organization based on the generated interest data.

2. The computer-implemented method of claim 1,

wherein the organization is a business enterprise or a legal entity.

3. The computer-implemented method of claim 1,

wherein a relationship between a first user and a respective information item corresponds to an activity performed by the first user on the respective information item,

wherein the activity is querying, browsing, opening, viewing, editing, critiquing, bookmarking, liking, sharing, downloading, collecting, or curating the information item,

wherein determining the use data includes tracking the activity, and

wherein tracking the activity is performed using web browser software without downloading additional software or documents.

4. The computer-implemented method of claim 1, wherein a relationship between two users corresponds to:

an organizational relationship between the two users with respect to the roles of the two users with the organization,

an activity performed by the two users together within the organization,

a pair of relationships respectively between the two users and a respective information item, or

any combination thereof.

5. The computer-implemented method of claim 1, wherein responding to the request comprises:

combining multiple, similar results into one result;

ordering multiple results by;

a recency of an information item,

a popularity of an information item,

a popularity of a collection of information items,

an authority of the particular user,

the interest data, or

any combination thereof; and

presenting the multiple results based on the ordering,

wherein the request is generated automatically, and

wherein responding to the request comprises generating a message to be sent by email or other messaging system.

6. The computer-implemented method of claim 5, further comprising:

generating automated requests for feeds based on;

a user-specified frequency,

the number of items provided based on the generated interest data,

the popularity of the relevant information items,

the popularity of the users who own or performed activities on the provided information items, or

any combination thereof.

7. The computer-implemented method of claim 5, further comprising:

determining the recency of a respective information item based on the number of activities performed on the respective information item in the last hour, day, week, or other time period.

8. The computer-implemented method of claim 5, further comprising:

determining the popularity of a respective information item based on;

a number of activities performed on the respective information item,

an authority of users who performed activities on the respective information item,

a popularity of collections of information items to which the respective information item belongs, or

any combination thereof.

9. The computer-implemented method of claim 5, further comprising:

determining the authority of the particular user based on a number of activities performed on information items created by the particular user.

10. The computer-implemented method of claim 5, further comprising:

determining the popularity of a first collection of information items based on a number of activities performed on the information items in the first collection of information items.

11. The computer-implemented method of claim 1, further comprising:

determining an affinity between a first user and a second user based on;

a relationship between the first user and the second user,

an interest indicated by the first user with respect to the second user,

an affinity between the first user and a second user and a relationship between the second user and the first information item,

an affinity between the first user and a collection to which the first information item belongs, or

any combination thereof.

12. The computer-implemented method of claim 1, further comprising:

determining an affinity between a user and a collection of information items based on a relationship between the user and the collection.

13. The computer-implemented method of claim 1, further comprising determining additional use data characterizing relationships among users and information items across the organization and at least one other, independent organization.

14. A system to identify information of interest within an organization, the system comprising:

at least one hardware processor;

at least one memory having contents configured to, when executed by the at least one processor, perform a method comprising;

gathering use data that represents interactions by at least some of multiple users within the organization with information items in the organization, the use data characterizing relationships among the information items within the organization and relationships between the information items and a group of users within the organization, the organization including a group of users on a private network and sharing an internet domain;

computing interest data indicating affinity among the information items based on the determined use data to generate interest graph data structures,

wherein at least one interest graph data structure expresses an affinity between at least one user and one information item, which represents a likelihood that the one information item is of interest to the at least one user, and

wherein at least some interest graph data structures express affinities among at least two information item, which represents a likelihood that the at least two information items are frequently interacted with together by each of a plurality of users in the organization;

receiving a request for a set of information items from a particular user that are related to a first information item; and

responding to the request by providing one or more information items selected from the corpus of information items based on a determination that each of the one or more selected information items and the first information item are frequently interacted with together by a same user.

15. The system of claim 14 wherein the user data includes user profile data specifying access control privileges of at least one user and wherein the means for responding provides only results for which the user has access control privileges.

16. A computer-implemented method of identifying information of interest within an organization, wherein the organization includes a structured body of users with associated roles within the organization and who have access to information items, the method comprising:

determining use data that represents interactions by at least some of multiple users within the organization with the information items, the use data characterizing relationships among the information items and relationships between the information items and the users within the organization;

generating for each of a plurality of the information items based on the determined use data, an affinity that indicates a degree to which a respective information item in the plurality of information items is related to another information item;

receiving, from a first user, a request to display a first subset of the information items; and

in response to the request,

identifying the first subset of the information items,

ranking the first subset of the information items based on the generated affinities,

detecting the first subset of information items includes at least a first information item and a second information item that is a duplicate of the first information item and that has a lower rank than the first information item,

ordering the first subset of information items based on the ranking, and

providing a list of the ordered first subset of information items, the provided list including the first information item and excluding the second information item.

17. The computer-implemented method of claim 16, wherein the provided list of the ordered first subset of information items includes at least two related items, and wherein the at least two related items have a similarity measure that is greater than a predetermined threshold.

18. The computer-implemented method of claim 16, wherein the request is generated automatically, and responding to the request comprises:

generating a message to be sent by email or other messaging system.

19. The computer-implemented method of claim 16, further comprising:

determining the recency of the first information item based on the number of activities performed on the first information item in the last hour, day, week, or other time period.