Learning affinities through design variations

Patent metadata

Field	Value
Publication number	US-11822608-B2
Application number	US-202217972258-A
Country	US
Kind code	B2
Filing date	Oct 24, 2022
Priority date	Nov 15, 2019
Publication date	Nov 21, 2023
Grant date	Nov 21, 2023

Abstract

Disclosed herein are system, method, and computer program product embodiments for determining a user-preferred feature type. An embodiment operates by maintaining user-presented features associated with user-presented records, wherein the user-presented features comprise one or more user-presented feature types. After receiving a user-desired feature of the user-presented features, a user-preferred feature type of the user-presented feature types is determined based on the user-presented features and the user-desired feature. Thereafter, a new record and associated feature are to be presented with the new feature being of the user-preferred type.

First claim

What is claimed is:

1. A computer-implemented method for determining a user-preferred feature type, comprising:
maintaining, by at least one processor, one or more user-presented features associated with one or more user-presented records, wherein the one or more user-presented features comprise one or more user-presented feature types;
receiving, by the at least one processor, one or more user-desired features of the one or more user-presented features determined based on user interactions with the one or more user-presented features; and
determining, by the at least one processor, the user-preferred feature type of the one or more user-presented feature types based on the one or more user-presented features and the one or more user-desired features,
wherein a new record and a new feature associated with the new record are to be presented, the new feature being of the user-preferred feature type.

2. The computer-implemented method of claim 1 , the maintaining comprising:
receiving, by the at least one processor, the one or more user-presented features.

3. The computer-implemented method of claim 1 , further comprising:
receiving, by the at least one processor, one or more user-desired records of the one or more user-presented records,
wherein the one or more user-presented records comprises one or more user-presented record types, and
wherein the one or more user-desired records are determined based on user interactions with the one or more user-presented records; and

determining, by the at least one processor, a user-preferred record type of the one or more user-presented record types based on the one or more user-presented records and the one or more user-desired records,
wherein the new record is of the user-preferred record type.

4. The computer-implemented method of claim 1 , further comprising:
receiving by the at least one processor, one or more user-desired records of the one or more user-presented records,
wherein the one or more user-desired records are determined based on user interactions with the one or more user-presented records; and

determining, by the at least one processor, a user-preferred record type based on the one or more user-presented records and the one or more user-desired records,
wherein the new record is of a type different from the one or more user-presented records.

5. The computer-implemented method of claim 1 , wherein:
the one or more user-presented records comprise a first and second user-presented record, and
the first user-presented record is presented concurrently with the second-user-presented record.

6. The computer-implemented method of claim 1 , wherein:
the one or more user-presented records comprise a first and second user-presented record, and
the first user-presented record is presented before or after the second-user-presented record.

7. The computer-implemented method of claim 6 , wherein:
the one or more user-presented features comprise a first and second user-presented feature having a first and second user-presented feature type, respectively, and
the first user-presented record and the second-user-presented record are associated with the first user-presented feature and the second user-presented feature, respectively,
wherein the user-preferred feature is the first user-presented feature or the second user-presented feature.

8. The computer-implemented method of claim 7 , wherein the second user-presented record and the second user-presented feature are presented after the first user-presented record and the first user-presented feature.

9. The computer-implemented method of claim 8 , wherein the user-preferred feature type is the second user-presented feature type.

10. The computer-implemented method of claim 1 , wherein the one or more user-desired features are determined by one or more of:
monitoring a location of a hover box over the one or more user-presented features,
monitoring a viewing time of the one or more user-presented features, and
receiving a selection of the one or more user-presented features.

11. The computer-implemented method of claim 1 , the determining of the user-preferred feature type comprising:
performing an analysis of variance (ANOVA) based on the one or more user-desired features and the one or more user-presented features;
determining a variance of the one or more user-desired features based on the ANOVA;
determining that the variance of the one or more user-desired features meets or exceeds a predetermined variance; and
identifying the one or more user-desired features being of a specific feature type, wherein the specific feature type is the user-preferred feature type.

12. The computer-implemented method of claim 11 , wherein the ANOVA utilizes an f-test.

13. The computer-implemented method of claim 12 , the determining of the variance comprising:
determining a z-score of the user-preferred feature type based on the ANOVA; and
determining that the z-score meets or exceeds a predetermined z-score threshold.

14. The computer-implemented method of claim 1 , further comprising:
providing, by the at least one processor, the user-preferred feature type to a first source, wherein the one or more user-presented features are provided by a second source different from the first source.

15. The computer-implemented method of claim 1 , further comprising:
providing, by the at least one processor, the user-preferred feature type to a first provider providing the one or more user-presented features.

16. The computer-implemented method of claim 15 , further comprising:
receiving, by the at least one processor, the one or more user-presented features from the first provider.

17. The computer-implemented method of claim 15 , further comprising:
receiving, by the at least one processor, the one or more user-presented features from a second provider different from the first provider.

18. The computer-implemented method of claim 1 , wherein the user-preferred feature type and the user-desired feature relate to a price, a review, a description, a design, or a location.

19. A system, comprising:
a memory; and
at least one processor coupled to the memory and configured to:
maintain one or more user-presented features associated with one or more user-presented records, wherein the one or more user-presented features comprise one or more user-presented feature types;
receive one or more user-desired features of the one or more user-presented features determined based on user interactions with the one or more user-presented features; and
determine a user-preferred feature type of the one or more user-presented feature types based on the one or more user-presented features and the one or more user-desired features,
wherein a new record and a new feature associated with the new record are to be presented, the new feature being of the user-preferred feature type.

20. A non-transitory computer-readable device having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations comprising:
presenting one or more features associated with one or more records to a user, wherein the one or more user-presented features comprise one or more user-presented feature types;
receiving a selection of the one or more user-desired features of the one or more user-presented features from the user;
receiving a user-preferred feature type based on the one or more user-presented features and the one or more user-desired f

Assignees

• Salesforce Com Inc
• Salesforce Inc

Inventors

• Lonsdorf Brian J
• Lundin Jessica
• Schoppe Owen Winne
• Rohde Sönke
• Ross Alan
• Woodward David James

Classifications

• G06F16/9035 Primary

  Filtering based on additional data, e.g. user or group profiles · CPC title

• G06F16/904

  Browsing; Visualisation therefor (for navigating the web G06F16/954; browsing optimisation for the web G06F16/957) · CPC title

• G06F16/9038

  Presentation of query results · CPC title

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title

• G06Q30/0201

  Market modelling; Market analysis; Collecting market data · CPC title