Search system, media, and method for providing communications-based compatibility features

Patent metadata

Field	Value
Publication number	US-12159018-B2
Application number	US-201916682306-A
Country	US
Kind code	B2
Filing date	Nov 13, 2019
Priority date	Nov 13, 2019
Publication date	Dec 3, 2024
Grant date	Dec 3, 2024

Abstract

Methods, systems, and computer storage media for providing supplementary item information on communications-based compatibility features for a primary item in an item listing platform. In particular, communications-based compatibility features are extracted from user communications about the primary item to identify additional features of the item. In operation, a supplementation engine of an item listing platform, accesses user communications for the primary item. Supplementary item information is generated for the item, where the supplementary item information includes a communications-based compatibility feature associated with the item. The communications-based compatibility feature indicates that the primary item is compatible with the secondary item, a non-standard feature (e.g., a feature not provided in a feature set of the primary item), or a demographic feature (e.g., age). The supplementary item information is provided to cause presentation of a user interface element corresponding to the communications-based compatibility feature on a user interface of the item listing platform.

First claim

What is claimed is:

1. A computerized system comprising:
one or more computer processors; and
one or more computer-storage media storing computer-useable instructions that, when used by the one or more computer processors, cause the one or more computer processors to perform operations comprising:
accessing a plurality of communications, wherein the plurality of communications include information about a primary item;
accessing a supplementary item information model, wherein the supplementary item information model is trained with a supplementation engine to support extracting each of operational compatibility features, sub-feature compatibility features, demographic-based compatibility features associated with corresponding user element interface elements that include a compatible item interface element, a sub-feature interface element, and an age-range interface element,
wherein supplementary item information model is trained based on:
accessing training data comprising a plurality of communications of an item listing platform;
identifying one or more neural network algorithms for training the supplementary item information model, wherein the one or more neural network algorithms train supplementary item information model operations comprising:
(1) identifying question features and answer features;
(2) determining a threshold number of question features and corresponding answer features to identify communications-based compatibility features;
(3) comparing question features and answer features to identify the communications-based compatibility features, wherein comparing the question features and the answer features is based on a comparison logic of a comparison logic neural network model that generates a similarity score between question features and answer features; and
(4) based on similarity scores associated with the comparison logic, identifying the communications-based compatibility features as any of the following: operational compatibility features, sub-feature compatibility features, and demographic-based compatibility features; and

using the one or more neural network algorithms, training the supplemental item information model to determine the communications-based compatibility features for items that are not provided in standard features in feature sets of the items;

based on the plurality of communications and the supplementary item information model, generating supplementary item information, wherein the supplementary item information comprises a communications-based compatibility feature associated with the primary item, wherein the communications-based compatibility feature is not a standard feature in a feature set of the primary item, wherein a standard feature is a manufacturer-identified feature; and
providing the supplementary item information generated from the plurality of communications to cause presentation of a user interface element corresponding to the communications-based compatibility feature, wherein causing presentation of the user interface element comprises presenting the user interface element proximate to one or more standard features in the feature set of the primary item, the user interface element and the one or more standard features are selectable to execute a search.

2. The system of claim 1 , wherein the plurality of communications include questions, answers, and descriptions provided via user interfaces associated with an item listing platform, wherein the item listing platform provides interfaces for presenting user interface elements corresponding to the communications-based compatibility features.

3. The system of claim 1 , wherein the communications-based compatibility feature is an operational compatibility feature that indicates that the primary item is compatible with a secondary item.

4. The system of claim 1 , wherein the communications-based compatibility feature is a demographic-based compatibility feature that indicates a derived demographic value associated with the primary item.

5. The system of claim 1 , wherein the communications-based compatibility feature is a sub-feature compatibility feature that indicates a sub-feature of the primary item, wherein the sub-feature is configured to be listed as a feature of the feature set of the primary item.

6. The system of claim 1 , wherein generating the supplementary item information is based on determining that one or more communications in the plurality of communications indicates one or more of the following: an operational compatibility feature, a demographic-based compatibility feature, or a sub-feature compatibility feature based on a supplementary item information model that supports:
identifying question features from the plurality of communications;
identifying answer features from the plurality of communications; and
determining that a threshold number of question features and corresponding answer features identify the communications-based compatibility feature.

7. The system of claim 1 , wherein causing presentation of the user interface element comprises presenting the user interface element proximate to one or more standard features in the feature set of the primary item, wherein the user interface element explicitly identifies a category associated with the supplementary item information.

8. One or more computer-storage media having computer-executable instructions embodied thereon that, when executed by a computing system having a processor and memory, cause the processor to:
access a plurality of communications, wherein the plurality of communications include information about a primary item;
communicate the plurality of communications to cause generation of supplementary item information based on the plurality of communications and a supplementary item information model, wherein the supplementary item information comprises a communications-based compatibility feature associated with the primary item, wherein the communications-based compatibility feature is not a standard feature in a feature set of the primary item, wherein a standard feature is a manufacturer-identified feature,
wherein the supplementary item information model is trained with a supplementation engine to support extracting each of operational compatibility features, sub-feature compatibility features, demographic-based compatibility features associated with corresponding user element interface elements that include a compatible item interface element, a sub-feature interface element, and an age-range interface element,
wherein supplementary item information model is trained based on:
accessing training data comprising a plurality of communications of an item listing platform;
identifying one or more neural network algorithms for training the supplementary item information model, wherein the one or more neural network algorithms enable supplementary item information model operations comprising:
(1) identifying question features and answer features;
(2) determining a threshold number of question features and corresponding answer features to identify communications-based compatibility features;
(3) comparing question features and answer features to identify the communications-based compatibility features, wherein comparing the question features and the answer features is based on a comparison logic of a comparison logic neural network model that generates a similarity score between question features and answer features; and
(4) based on similarity scores associated with the comparison logic, identifying the communications-based compatibility features as any of the following: operational compatibility features, sub-feature compatibility features, and demographic-based compatibility features; and

using the one or more neural network algorithms, train

Assignees

• Ebay Inc

Inventors

• Sonnenberg Alexander Binyamin Sagiv
• Guy Ido
• Novgorodov Viatcheslav

Classifications

• G06Q30/0627 Primary

  by specifying product or service characteristics, e.g. product dimensions · CPC title

• G06Q30/0643

  graphically representing goods, e.g. 3D product representation · CPC title

• G06F9/451

  Execution arrangements for user interfaces · CPC title

• G06Q30/0625

  by formulating product or service queries, e.g. using keywords or predefined options · CPC title

• G06F16/9538

  Presentation of query results · CPC title