Granted Patent B2

US 12,737,722 · App. 18/618,791 · Granted Sep 15, 2026

Inventors: Sarabdeep Singh Multani (San Jose, CA); Suhas Giridhar Danavandi (Pleasanton, CA); Prathihasth Rekabu (San Jose, CA)

Assignee: eBay Inc.

G06Q10/0875

Abstract

Claims (43)

1 . One or more computer storage media storing computer-useable instructions that, when used by one or more computing devices, cause the one or more computing devices to perform operations, the operations comprising:

accessing, for each of a plurality of part item listings on a listing platform, listing data comprising structured data and unstructured text;

for each part item listing, generating a metadata identifier comprising a combination of an inventory segment identifier, a category identifier, and fitment data identifying compatibility of a part item for the part item listing with one or more automobiles, wherein generating the metadata identifier for a first part item listing from the plurality of part item listings comprises: in response to determining structured data from listing data for the first part item listing lacks information to determine at least one of the segment identifier, the category identifier, or the fitment data for the first part item listing, performing natural language processing of the unstructured text from the listing data for the first part item listing to identify the at least one of the inventory segment identifier, the category identifier, and the fitment data for the first part item listing missing from the structured data for the first part item listing;

storing, in a datastore of the listing platform, associations between part item listings and metadata identifiers;

receiving an indication of a first metadata identifier comprising a combination of a first inventory segment identifier, a first category identifier, and a first fitment data;

identifying, from the plurality of part item listings using the associations between part item listings and metadata identifiers, a set of part item listings having metadata identifiers that match the first metadata identifier;

determining that part items of the set of part item listings are interchangeable based on the set of part item listings having metadata identifiers having the combination of the first inventory segment identifier, the first category identifier, and the first fitment data;

aggregating demand data and/or supply data for the set of part item listings to provide aggregated data; and

generating a user interface with one or more metrics using the aggregated data.

2 . The one or more computer storage media of claim 1 , wherein the inventory segment identifier for the metadata identifier for each part item listing is selected from the following: salvage, original equipment, after market, and private label.

3 . The one or more computer storage media of claim 1 , wherein the category identifier for the metadata identifier for each part item listing is selected from a category hierarchy for the listing platform.

4 . The one or more computer storage media of claim 1 , wherein the fitment data for the metadata identifier for each part item listing comprises one or more selected from the following: a make, a model, a trim, an engine, and a year.

5 . The one or more computer storage media of claim 1 , wherein receiving the indication of the first metadata identifier comprises:

receiving listing data for a new part item listing to be added to the listing platform; and

determining the first metadata identifier based on the listing data for the new part item listing.

6 . The one or more computer storage media of claim 1 , wherein receiving the indication of the first metadata identifier comprises:

identifying, in an item listing inventory of a seller, a first part item listing having the first metadata identifier.

7 . The one or more computer storage media of claim 1 , wherein receiving the indication of the first metadata identifier comprises:

identifying one or more categories of part item listings in an item listing inventory of a seller;

ranking a plurality of metadata identifiers having one of the one or more categories based on one or more metrics associated with the metadata identifiers; and

selecting the first metadata identifier based on ranking the plurality of metadata identifiers.

8 . A computer-implemented method comprising:

accessing listing data comprising structured data and unstructured text for each of a plurality of part item listings in a seller inventory on a listing platform;

generating metadata identifiers for the plurality of part item listings, each metadata identifier for each part item listing comprising a combination of an inventory segment identifier, a category identifier, and fitment data identifying compatibility of a part item for the part item listing with one or more automobiles, wherein generating the metadata identifier for a first part item listing from the plurality of part item listings comprises: in response to determining structured data from listing data for the first part item listing lacks information to determine at least one of the segment identifier, the category identifier, or the fitment data for the first part item listing, performing natural language processing of the unstructured text from the listing data for the first part item listing to identify the at least one of the inventory segment identifier, the category identifier, and the fitment data for the first part item listing missing from the structured data for the first part item listing;

storing, in a datastore of the listing platform, associations between the metadata identifiers and the plurality of part item listings;

for each of the metadata identifiers, determining one or more part item listings from one or more other seller inventories on the listing platform are interchangeable with one or more part item listings from the seller inventory based on data stored in the datastore of the listing platform identifying associations between the metadata identifiers and part item listings in the one or more other seller inventories;

accessing metrics for each of the metadata identifiers by aggregating metrics data for the one or more part item listings in the one or more other seller inventories for each metadata identifier; and

generating a user interface identifying each metadata identifier and the metrics for each metadata identifier.

9 . The computer-implemented method of claim 8 , wherein the inventory segment identifier for the metadata identifier for each part item listing is selected from the following: salvage, original equipment, after market, and private label.

10 . The computer-implemented method of claim 8 , wherein the category identifier for the metadata identifier for each part item listing is selected from a category hierarchy for the listing platform.

11 . The computer-implemented method of claim 8 , wherein the fitment data for the metadata identifier for each part item listing comprises one or more selected from the following: a make, a model, a trim, an engine, and a year.

12 . A computer system comprising:

a processor; and

a computer storage medium storing computer-useable instructions that, when used by the processor, causes the computer system to perform operations comprising:

accessing, for each of a plurality of part item listings on a listing platform, listing data comprising structured data and unstructured text;

for each part item listing, generating a metadata identifier comprising a combination of an inventory segment identifier, a category identifier, and fitment data identifying compatibility of a part item for the part item listing with one or more automobiles, wherein generating the metadata identifier for a first part item listing from the plurality of part item listings comprises: in response to determining structured data from listing data for the first part item listing lacks information to determine at least one of the segment identifier, the category identifier, or the fitment data for the first part item listing, performing natural language processing of the unstructured text from the listing data for the first part item listing to identify the at least one of the inventory segment identifier, the category identifier, and the fitment data for the first part item listing missing from the structured data for the first part item listing;

storing, in a datastore of the listing platform, associations between part item listings and metadata identifiers;

identifying one or more categories of part item listings in a seller inventory on the listing platform;

ranking metadata identifiers in the one or more categories using metrics for the metadata identifiers, the metrics for a first metadata identifier having been generated by aggregating data across part item listings on the listing platform having the first metadata identifier based on the associations in the datastore of the listing platform; and

generating a user interface with at least a subset of the metadata identifiers based on the ranking.

13 . The computer system of claim 12 , wherein the inventory segment identifier for the metadata identifier for each part item listing is selected from the following: salvage, original equipment, after market, and private label.

14 . The computer system of claim 12 , wherein the category identifier for the metadata identifier for each part item listing is selected from a category hierarchy for the listing platform.

15 . The computer system of claim 12 , wherein the fitment data for the metadata identifier for each part item listing comprises one or more selected from the following: a make, a model, a trim, an engine, and a year.

Assignments (1)

Continuity (1)

References Cited (15)