# US 2022/0301042 A1 · Method and system for navigating within and determining non-binary, subjective preferences within very large and specific data sets having objectively characterized metadata

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

- Number: US 2022/0301042 A1
- Document ID: US20220301042A1
- Status: Published application
- Kind: A1
- Application number: 17/635,530
- Filed: 2020-08-16
- Published: 2022-09-22
- Earliest claimed: 2019-08-16
- Assignees: Subfiber OÜ
- Applicants: Subfiber OÜ
- Inventors: Ahto Ahas
- Web page: https://patentgrep.com/patent/US20220301042A1

## CPC

- G06Q 30/0631: {Recommending goods or services}
- G06Q 30/0643: {graphically representing goods, e.g. 3D product representation}
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06Q 30/0603: {Catalogue creation or management}
- G06Q 30/0629: {by pre-processing results, e.g. ranking or ordering results}
- 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

Determining a visual preference of a user by selecting a display set of item images from at least one item database and causing the item images of the display set to be displayed at a user interface. Engagement events at the user interface between the user and engaged-with item images are detected and used to determine a visual preference hypothesis for the user based on visual features extracted from the engaged-with item images. New item images are selected from the database(s) by comparing their visual features with the visual preference hypothesis. This is an iterative process, in which the visual preference hypothesis is refined and the display set continues to be updated accordingly. In another aspect, an improved user interface facilitates efficient item selection based on active and/or passive engagement events (of various possible types) with an item array, providing a rich source of visual preference information.

## Claims

### Claim 1

A computer-implemented method of determining visual preference of a user for selecting item images from at least one item database according to the visual preference of the user, the method being implemented by one or more computer processors and comprising:
selecting a display set of item images from the at least one item database;
causing the item images of the display set to be displayed at a user interface in a scrollable item array at respective array positions, wherein the item images are arranged in item groups within the item array based on at least one visual feature type, such that item images with similar visual features of that visual feature type are grouped together;
detecting engagement events at the user interface between the user and engaged-with item images of the display set, wherein the engagement events comprise at least one passive engagement event which indicates passive engagement with one of the item groups without the user selecting any image of the passively engaged-with item group;
using the detected engagement events to determine a visual preference hypothesis for the user based on visual features extracted from the engaged-with item images; and
updating the display set with new item images selected from the at least one item database by comparing visual features extracted from the new item images with the at least one visual preference hypothesis;
wherein subsequent engagement events between the user and engaged-with new item images of the display set continue to be detected and used to refine the at least one visual preference hypothesis, and the display set continues to be updated as the visual preference hypothesis is refined, wherein the at least one passive engagement event comprises a scroll event and the visual preference hypothesis is determined or updated based on a direction of the scroll event at the user interface relative to the passively-engaged-with item group.

### Claim 2 (depends on 1)

The method of claim 1, wherein the visual preference hypothesis corresponds to a type of visual feature or visual feature combination, and biases the selection of the new item images toward item images having visual features or combinations of visual features of that corresponding type which match the visual preference hypothesis but which exhibit variation in at least one additional visual feature type for testing the visual preference hypothesis.

### Claim 3 (depends on 2)

The method of claim 2, wherein at least a first visual preference hypothesis and a second visual preference hypothesis are determined using the engagement events;
wherein the first visual preference hypothesis corresponds to a first type of visual feature or visual feature combination, and biases the selection of a first subset of the new item images toward item images having visual features or combinations of visual features of that corresponding first type which match the first visual preference hypothesis but which exhibit variation in a second type of visual feature or visual feature combination; and
wherein the second visual preference hypothesis corresponds to the second type of visual feature or visual feature combination, and biases the selection of a second subset of the new item images toward item images having visual features or combinations of visual features of that corresponding second type which match the second visual preference hypothesis but which exhibit variation in the first type of visual feature or visual feature combination.

### Claim 4 (depends on 3)

The method of claim 3, wherein the first and second visual hypothesis are determined in response to the user engaging with at least one item image of the display set;
wherein the at least one engaged-with item image has a visual feature or combination of visual features of the first type which is used to determine the first visual preference hypothesis; and
wherein the at least one engaged-with item image has a visual feature or combination of visual features of the second type which is used to determine the second visual preference hypothesis;
whereby the biased selection of the first and second subsets tests whether the user has a preference for (i) the visual feature or combination of visual features of the at least one engaged-with item image of the first type based on a response of the user to the first subset, or (ii) the visual feature or combination of visual features of the at least one engaged-with item image of the second type based on a response of the user to the second subset.

### Claim 5 (depends on 1)

The method of claim 1, wherein the engagement events comprise at least one active engagement event in which the user selects an item image of the display set at the user interface.

### Claim 6 (depends on 5)

The method of claim 5, wherein, in response to the active engagement event, at least one item image is removed from the display set, and replaced with one of the new item images displayed at the array position of the removed item image.

### Claim 7 (depends on 6)

The method of claim 6, wherein the removed item image is removed from the display set based on the array position of the removed item image relative to the selected item image.

### Claim 8 (depends on 6)

The method of claim 6, wherein the item array is zoomable.

### Claim 9 (depends on 8)

The method of claim 8, wherein the at least one passive engagement event additionally comprises at least one of: a zoom event, and an item inspection event pertaining to the item array.

### Claim 10 (depends on 1)

The method of claim 1, wherein the visual preference hypothesis is determined or updated to indicate a preference for a visual feature of that visual feature type which matches the item group when the scroll event is directed toward that item group and/or when a scroll speed towards that item group is reduced by the user and/or when a scroll action past or through that item group is reversed.

### Claim 11 (depends on 10)

The method of claim 10, wherein the visual preference hypothesis is determined or updated to indicate a dislike of a visual feature of that visual feature type which matches the item group when the scroll event is directed away from that item group and/or when a scroll speed away past, through or away from that item group is increased or maintained by the user.

### Claim 12 (depends on 1)

The method of claim 1, wherein the new item images are selected dynamically in response to zoom events and/or scroll events at the user interface so as to dynamically populate previously unpopulated array positions within the item array based on the at least one visual preference hypothesis.

### Claim 13 (depends on 1)

The method of claim 1, wherein the visual preference hypothesis is determined based on one or more visual features of one or more item images of the display set with which the user has not engaged.

### Claim 14 (depends on 13)

The method of claim 13, wherein a lack of engagement with at least one item image of the display set is detected based on at least one negative interaction event at the user interface relating to the at least one item image.

### Claim 15 (depends on 14)

The method of claim 14 wherein the negative interaction event is a scroll event directed away from the item image.

### Claim 16 (depends on 1)

The method of claim 1, wherein the display set is additionally updated with one or more escape item images from the item database having visual features which are selected because they do not match the visual features of the engaged-with item images.

### Claim 17

(canceled)

### Claim 18 (depends on 1)

The method of claim 1, wherein the visual features extracted from each item image comprise visual features which have been extracted by applying one or more trained machine learning visual feature extractors to image data of that item image.

### Claim 19 (depends on 1)

The method of claim 1, wherein the visual features extracted from each item image comprise one or more visual hyperparameters extracted from that item image.

### Claim 20 (depends on 1)

The method of claim 1, wherein visual features of or extracted from item details or metadata associated with the item images are used in combination with the extracted visual features.

### Claim 21 (depends on 1)

The method of claim 1, wherein at least one derived visual preference hypothesis is determined based on the at least one visual preference hypothesis, by applying a transformation to at least one visual feature of the at least one visual preference hypothesis, the derived visual preference hypothesis pertaining to the transformed visual feature, wherein the at least one visual preference hypothesis and the derived visual preference hypothesis are used to update the display set.

### Claim 22 (depends on 1)

The method of claim 1, wherein the or each visual preference hypothesis is stored with associated information about a level of exposure, via item images of the display set, to visual features for testing that visual preference hypothesis and a level of engagement with item images having such visual features, wherein the display set is updated in dependence on the associated information, and the associated information is, in turn, updated as the user continues to engage with the new item images of the updated display set.

### Claim 23

(canceled)

### Claim 24 (depends on 9)

The method of claim 9, wherein the at least one scroll event additionally denotes at least one of:
a scroll speed,
a change in scroll speed,
a change in scroll direction.

### Claim at position 25

25-42. (canceled)
