Maintaining Dynamic Product Catalogs By Tracking Current Trends

Patent metadata

Field	Value
Publication number	US-2019172075-A1
Application number	US-201715828761-A
Country	US
Kind code	A1
Filing date	Dec 1, 2017
Priority date	Dec 1, 2017
Publication date	Jun 6, 2019
Grant date	—

Abstract

Input from a user is received about a product of interest to the user. A plurality of sources that monitor product trends is determined. The plurality of sources is ranked. A plurality of key concepts associated with the product of interest are extracted from the ranked sources. Relationships are extracted from the key concepts. A plurality of triples between the key concepts and the relationships are created. Each triple in the plurality of triples is weighted based on the ranking of the sources.

First claim

What is claimed is:

1 . A method comprising:
receiving, by one or more computer processors, an input from a user, wherein the input is associated with a product of interest to the user; determining, by one or more computer processors, a plurality of sources that monitor product trends; ranking, by one or more computer processors, the plurality of sources that monitor product trends; extracting, by one or more computer processors, a plurality of key concepts associated with the product of interest from the ranked sources; extracting, by one or more computer processors, relationships from the extracted plurality of key concepts; creating, by one or more computer processors, a plurality of triples between the extracted key concepts using the extracted relationships; and weighting, by one or more computer processors, the created triples based on the ranking of the plurality of sources.

2 . The method of claim 1 , further comprising:
creating, by one or more computer processors, a knowledge graph by annotating unstructured text from the ranked sources with the extracted relationships; embedding, by one or more computer processors, the knowledge graph and the weighted triples into an existing knowledge base; identifying, by one or more computer processors, a plurality of new attributes based on the existing knowledge base with the embedded knowledge graph and weighted triples; identifying, by one or more computer processors, a plurality of new relationships of the product of interest based on a densest neighborhood in the existing knowledge base that includes the embedded knowledge graph with the embedded weighted triples; and sending by one or more computer processors, a recommendation.

3 . The method of claim 1 , wherein the plurality of sources that monitor product trends are selected from the group consisting of: social media websites, forums, product blogs, review websites, and podcasts.

4 . The method of claim 1 , wherein the ranking of the plurality of sources that monitor product trends is based on a popularity, a quality, and an importance of each source in the plurality of sources.

5 . The method of claim 1 , wherein:
extracting the plurality of key concepts from the ranked sources utilizes keyword extraction; and extracting relationships from the extracted plurality of key concepts utilizes machine learning.

6 . The method of claim 1 , wherein a triple of the plurality of triples is a set of two key concepts of the extracted key concepts associated with one another by a relationship of the extracted relationships.

7 . The method of claim 2 , wherein creating the knowledge graph utilizes natural language processing.

8 . The method of claim 2 , wherein the recommendation is selected from the group consisting of: a first recommendation sent to a product manager of a product catalog to update the product catalog with the product of interest, a second recommendation sent to the product manager of the product catalog to update a description of the product of interest in the product catalog with a new attribute, a third recommendation sent to the product manager of the product catalog to remove an existing item from the product catalog, and a fourth recommendation to the user to purchase the product of interest based on a unique feature available in the product of interest.

9 . A computer program product comprising:
one or more computer readable storage media; and program instructions stored on the one or more computer readable storage media, the program instructions comprising:
program instructions to receive an input from a user, wherein the input is associated with a product of interest to the user;
program instructions to determine a plurality of sources that monitor product trends;
program instructions to rank the plurality of sources that monitor product trends;
program instructions to extract a plurality of key concepts associated with the product of interest from the ranked sources;
program instructions to extract relationships from the extracted plurality of key concepts;
program instructions to create a plurality of triples between the extracted key concepts using the extracted relationships; and
program instructions to weight the created triples based on the ranking of the plurality of sources.

10 . The computer program product of claim 9 , further comprising program instructions stored on the one or more computer readable storage media, to:
create a knowledge graph by annotating unstructured text from the ranked sources with the extracted relationships; embed the knowledge graph and the weighted triples into an existing knowledge base; identify a plurality of new attributes based on the existing knowledge base with the embedded knowledge graph and weighted triples; identify a plurality of new relationships of the product of interest based on a densest neighborhood in the existing knowledge base that includes the embedded knowledge graph with the embedded weighted triples; and send a recommendation.

11 . The computer program product of claim 9 , wherein the plurality of sources that monitor product trends are selected from the group consisting of: social media websites, forums, product blogs, review websites, and podcasts.

12 . The computer program product of claim 9 , wherein the ranking of the plurality of sources that monitor product trends is based on a popularity, a quality, and an importance of each source in the plurality of sources.

13 . The computer program product of claim 9 , wherein:
extracting the plurality of key concepts from the ranked sources utilizes keyword extraction; and extracting relationships from the extracted plurality of key concepts utilizes machine learning.

14 . The computer program product of claim 9 , wherein a triple of the plurality of triples is a set of two key concepts of the extracted key concepts associated with one another by a relationship of the extracted relationships.

15 . The computer program product of claim 10 , wherein creating the knowledge graph utilizes natural language processing.

16 . The computer program product of claim 10 , wherein the recommendation is selected from the group consisting of: a first recommendation sent to a product manager of a product catalog to update the product catalog with the product of interest, a second recommendation sent to the product manager of the product catalog to update a description of the product of interest in the product catalog with a new attribute, a third recommendation sent to the product manager of the product catalog to remove an existing item from the product catalog, and a fourth recommendation to the user to purchase the product of interest based on a unique feature available in the product of interest.

17 . A computer system comprising:
one or more computer processors; one or more computer readable storage media; and program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising:
program instructions to receive an input from a user, wherein the input is associated with a product of interest to the user;
program instructions to determine a plurality of sources that monitor product trends;
program instructions to rank the plurality of sources that monitor product trends;
program instructions to extract a plurality of key concepts associated with the product of interest from the ranked sources;
program instructions to extract relationships from the extracted plurality

Assignees

• IBM

Inventors

• Kenkre Sreyash D
• Bhattacharya Indrajit
• Raykar Vikas C
• Pandit Vinayaka

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06F16/9024

  Graphs; Linked lists (G06F16/9027 takes precedence) · CPC title

• G06F16/3334

  Selection or weighting of terms from queries, including natural language queries · CPC title

• G06F16/904

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

• G06Q30/0269

  based on user profile or attribute · CPC title