# US 2018/0025087 A1 · Systems and methods for evaluating diversity of content based on content properties

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2018/0025087 A1
- Document ID: US20180025087A1
- Status: Published application
- Kind: A1
- Application number: 15/215,317
- Filed: 2016-07-20
- Published: 2018-01-25
- Earliest claimed: 2016-07-20
- Assignees: Facebook, Inc.
- Applicants: Facebook, Inc.
- Inventors: Shankar Kalyanaraman
- Web page: https://patentgrep.com/patent/US20180025087A1

## CPC

- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F 16/24578: {using ranking}
- G06F 16/9538: Presentation of query results
- G06Q 10/40: Business processes related to social networking or social networking services
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

Systems, methods, and non-transitory computer-readable media can acquire a set of properties associated with a set of content items. A plurality of property combinations can be selected from the set of properties. A plurality of numbers of unique properties associated with the plurality of property combinations can be determined. A diversity metric for the set of content items can be generated based on at least some of the plurality of numbers of unique properties associated with the plurality of property combinations.

## Claims

### Claim 1

A computer-implemented method comprising:
acquiring, by a computing system, a set of properties associated with a set of content items;
selecting, by the computing system, a plurality of property combinations from the set of properties;
determining, by the computing system, a plurality of numbers of unique properties associated with the plurality of property combinations; and
generating, by the computing system, a diversity metric for the set of content items based on at least some of the plurality of numbers of unique properties associated with the plurality of property combinations.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the set of content items is ranked based on an order produced from one or more content ranking algorithms, and wherein the set of properties is representable as a series of properties based on the order.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein the plurality of property combinations are selected to represent differing segments of the series of properties.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, wherein determining the plurality of numbers of unique properties associated with the plurality of property combinations further comprises:
identifying one or more sets of property combinations that are each associated with a respective segment length; and
determining one or more minimum numbers of unique properties associated with the one or more sets, wherein each of the one or more minimum numbers of unique properties is determined for each of the one or more sets, and wherein the plurality of numbers of unique properties includes the one or more minimum numbers of unique properties.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, wherein generating the diversity metric for the set of content items further comprises:
producing one or more normalized values based on dividing each of the one or more minimum numbers of unique properties by the respective segment length associated with each of the one or more sets;
generating a sum of the one or more normalized values; and
dividing the sum by a total segment length associated with the series of properties to produce a resulting value, wherein the diversity metric is based on the resulting value.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the plurality of property combinations are selected such that each of the plurality of property combinations includes a respective unique property from the set of properties.

### Claim 7 (depends on 6)

The computer-implemented method of claim 6, wherein determining the plurality of numbers of unique properties associated with the plurality of combinations of properties further comprises:
identifying a respective quantity of times each unique property is present in the set of properties, wherein the plurality of numbers includes the respective quantity of times for each unique property.

### Claim 8 (depends on 7)

The computer-implemented method of claim 7, wherein generating the diversity metric for the set of content items further comprises:
producing a respective probability value for each unique property based on dividing the respective quantity of times for each unique property by a total amount of properties in the set of properties; and
calculating an entropic value based on the respective probability value for each unique property, wherein the diversity metric is based on the entropic value.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein the set of properties includes at least one of an author, a topic, a tag, a location, an object, or a classification.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, further comprising:
performing at least one of: 1) a ranking, based on the diversity metric, for at least some content items out of the set of content items for presentation in a feed or 2) a comparison of the diversity metric with another diversity metric generated for another set of content items.

### Claim 11

A system comprising:
at least one processor; and
a memory storing instructions that, when executed by the at least one processor, cause the system to perform:
acquiring a set of properties associated with a set of content items;
selecting a plurality of property combinations from the set of properties;
determining a plurality of numbers of unique properties associated with the plurality of property combinations; and
generating a diversity metric for the set of content items based on at least some of the plurality of numbers of unique properties associated with the plurality of property combinations.

### Claim 12 (depends on 11)

The system of claim 11, wherein the set of content items is ranked based on an order produced from one or more content ranking algorithms, and wherein the set of properties is representable as a series of properties based on the order.

### Claim 13 (depends on 12)

The system of claim 12, wherein the plurality of property combinations are selected to represent differing segments of the series of properties.

### Claim 14 (depends on 11)

The system of claim 11, wherein the plurality of property combinations are selected such that each of the plurality of property combinations includes a respective unique property from the set of properties.

### Claim 15 (depends on 11)

The system of claim 11, wherein the set of properties includes at least one of an author, a topic, a tag, a location, an object, or a classification.

### Claim 16

A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:
acquiring a set of properties associated with a set of content items;
selecting a plurality of property combinations from the set of properties;
determining a plurality of numbers of unique properties associated with the plurality of property combinations; and
generating a diversity metric for the set of content items based on at least some of the plurality of numbers of unique properties associated with the plurality of property combinations.

### Claim 17 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, wherein the set of content items is ranked based on an order produced from one or more content ranking algorithms, and wherein the set of properties is representable as a series of properties based on the order.

### Claim 18 (depends on 17)

The non-transitory computer-readable storage medium of claim 17, wherein the plurality of property combinations are selected to represent differing segments of the series of properties.

### Claim 19 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, wherein the plurality of property combinations are selected such that each of the plurality of property combinations includes a respective unique property from the set of properties.

### Claim 20 (depends on 16)

The non-transitory computer-readable storage medium of claim 16, wherein the set of properties includes at least one of an author, a topic, a tag, a location, an object, or a classification.
