# US 2021/0241346 A1 · Systems for Generating Recommendations

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

- Number: US 2021/0241346 A1
- Document ID: US20210241346A1
- Status: Published application
- Kind: A1
- Application number: 16/779,074
- Filed: 2020-01-31
- Published: 2021-08-05
- Earliest claimed: 2020-01-31
- Assignees: Adobe Inc.
- Applicants: Adobe Inc.
- Inventors: Georgios Theocharous; Sridhar Mahadevan; Anup Bandigadi Rao
- Web page: https://patentgrep.com/patent/US20210241346A1

## CPC

- G06Q 30/0631: {Recommending goods or services}
- G06F 16/9535: Search customisation based on user profiles and personalisation
- H04L 67/306: User profiles
- H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)}
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

In implementations of systems for generating recommendations, a computing device implements a recommendation system to receive prior interaction data describing prior interactions of entities with items. The recommendation system processes the prior interaction data and segments the entities into a first set and a second set. The entities included in the first set have greater numbers of prior interactions with the items than the entities included in the second set. The recommendation system then generates subset data describing a subset of the entities in the first set. This subset excludes entities having numbers of the prior interactions with the items below a threshold. The recommendation system forms a recommendation model based on the subset data and the system uses the recommendation model to generate a recommendation for display in a user interface.

## Claims

### Claim 1

In a digital medium environment to generate a recommendation, a method implemented by a computing device, the method comprising:
receiving, by the computing device, prior interaction data describing entities and prior interactions of the entities with items;
processing, by the computing device, the prior interaction data to segment the entities into a first set and a second set, entities included in the first set having greater numbers of the prior interactions with the items than entities included in the second set;
generating, by the computing device, subset data describing a subset of the entities in the first set, the subset excluding entities having numbers of the prior interactions with the items below a threshold;
forming, by the computing device, a recommendation model based on the subset data; and
generating, by the computing device, the recommendation for display in a user interface using the recommendation model.

### Claim 2 (depends on 1)

The method as described in claim 1, wherein the forming the recommendation model includes sampling from a Dirichlet multinomial distribution.

### Claim 3 (depends on 1)

The method as described in claim 1, wherein the forming the recommendation model includes Thompson sampling.

### Claim 4 (depends on 1)

The method as described in claim 1, wherein the items are items of digital content.

### Claim 5 (depends on 1)

The method as described in claim 1, further comprising scaling numbers of the prior interactions with the items of the entities in the first set between 0 and 1.

### Claim 6 (depends on 5)

The method as described in claim 5, further comprising determining the threshold based on the scaling.

### Claim 7 (depends on 1)

The method as described in claim 1, further comprising generating a global vector by aggregating numbers of the prior interactions with the items of entities in the subset.

### Claim 8 (depends on 7)

The method as described in claim 7, further comprising scaling the global vector to be within a preference range.

### Claim 9 (depends on 1)

The method as described in claim 1, wherein the generating the recommendation includes receiving current interaction data describing a current interaction with an item of the items.

### Claim 10

One or more computer-readable storage media comprising instructions stored thereon that, responsive to execution by a computing device in a digital medium environment to generate a recommendation, cause operations of the computing device including:
receiving prior interaction data describing entities and prior interactions of the entities with items;
processing the prior interaction data by segmenting the entities into a first set and a second set, entities included in the first set having greater numbers of the prior interactions with the items than entities included in the second set;
generating subset data describing a subset of the entities in the first set, the subset excluding entities having numbers of the prior interactions with the items below a threshold;
forming a recommendation model based on the subset data;
receiving current interaction data; and
generating the recommendation for display in a user interface using the recommendation model and the current interaction data.

### Claim 11 (depends on 10)

The one or more computer-readable storage media as described in claim 10, wherein the forming the recommendation model includes sampling from a Dirichlet multinomial distribution.

### Claim 12 (depends on 10)

The one or more computer-readable storage media as described in claim 10, wherein the forming the recommendation model includes Thompson sampling.

### Claim 13 (depends on 10)

The one or more computer-readable storage media as described in claim 10, wherein the current interaction data describes a current interaction of an entity with an item.

### Claim 14 (depends on 10)

The one or more computer-readable storage media as described in claim 10, the operations further including:
scaling numbers of the prior interactions with the items of the entities in the first set between 0 and 1; and
determining the threshold based on the scaling.

### Claim 15 (depends on 10)

The one or more computer-readable storage media as described in claim 10, the operations further including generating a global vector by aggregating numbers of the prior interactions with the items of entities in the subset.

### Claim 16

In a digital medium environment to generate a recommendation, a system comprising:
one or more processors of a processing system; and
a computer-readable storage medium having instructions stored thereon that, responsive to execution by the processing system, causes the one or more processors to perform operations including:
receiving prior interaction data describing entities and prior interactions of the entities with items;
segmenting the entities into a first set and a second set, entities included in the first set having greater numbers of the prior interactions with the items than entities included in the second set;
generating subset data describing a subset of the entities included in the first set, the subset excluding entities having numbers of the prior interactions with the items below a threshold;
forming a recommendation model based at least partially on the subset data; and
generating the recommendation for display in a user interface using the recommendation model and current interaction data, the current interaction data describing a current interaction of an entity of the entities with an item of the items.

### Claim 17 (depends on 16)

The system as described in claim 16, wherein the forming the recommendation model includes sampling from a Dirichlet multinomial distribution.

### Claim 18 (depends on 16)

The system as described in claim 16, wherein the forming the recommendation model includes Thompson sampling.

### Claim 19 (depends on 16)

The system as described in claim 16, wherein the operations further include:
scaling numbers of the prior interactions with the items of the entities in the first set between 0 and 1; and
determining the threshold based on the scaling.

### Claim 20 (depends on 16)

The system as described in claim 16, wherein the items are products or services.
