Systems and methods of providing enhanced contextual intelligent information

Patent metadata

Field	Value
Publication number	US-12555139-B2
Application number	US-202418949889-A
Country	US
Kind code	B2
Filing date	Nov 15, 2024
Priority date	Dec 1, 2021
Publication date	Feb 17, 2026
Grant date	Feb 17, 2026

Abstract

Some embodiments provide systems to determine contextual information comprising: an intent mining system that receive inquiry content that does not include personal identification information (PII) and is configured to determine an estimated intent information being sought by an intended recipient, identify a mapping to a sub-set of supplemental keywords corresponding to the intent information; and identify historic inquiries associated with actual historic product purchases relevant to the inquiry content and supplemental keywords, and obtain a listing of products associated with the inquiry content; a product association system that identifies a set of multiple products that each have a purchase threshold relationship with one or more products from the determined listing of products, and generate an enhanced listing of products; a topic extraction system that evaluates associations between product parameters of the enhanced listing of products to identify multiple associated topics and corresponding topic confidence scores.

First claim

The invention claimed is:

1 . A system providing contextual information comprising:
an intent mining system comprising a mining evaluation processor configured to receive inquiry content associated with an intended recipient and that does not include personal identification information (PII) or personal network cookie data, wherein the mining evaluation processor is configured to:
determine a set of supplemental keywords corresponding to intent information corresponding to the inquiry content; and
identify historic inquiries each having a threshold relationship with the set of supplemental keywords and obtain a listing of products corresponding to the historic inquiries;
a product association system comprising one or more association processors configured to, for each of the inquiry content: identify a set of multiple products that each have a purchase threshold relationship with one or more products from the listing of products, and generate an enhanced listing of products comprising the listing of products and the set of multiple products; a topic extraction machine learning model is applied to product parameters of the products of the enhanced listing of products and to identify, based on the product parameters, multiple associated topics wherein the topic extraction machine learning model is trained using a topics training corpus of product information and wherein the topic extraction machine learning model is retrained over time based on responses to previous inquiries by previous recipients; and a distribution system configured to: communicate the identified multiple associated topics to one or more target content sources.

2 . The system of claim 1 , wherein the mining evaluation processor is configured to determine the set of supplemental keywords associated with the intent information based on a mapping between terms.

3 . The system of claim 1 , wherein the mining evaluation processor is further configured to acquire intended recipient non-private information about the intended recipient as a function of a network connection and timing information corresponding to when the respective inquiry content is requested; and apply a set of relevance filters, based on the recipient non-private information and the timing information, to exclude from the listing of products a subset of actual historic products purchased that have the association with historic inquiries.

4 . The system of claim 1 , wherein the one or more association processors, in identifying the set of multiple products, identifies one or more products purchased a threshold number of times with a respective one of the set of multiple products.

5 . The system of claim 1 , further comprising:
a topic extraction system comprising a topic extraction processor executing instructions to provide for each topic, of the multiple associated topics, a topic confidence score defining an estimated relevance the respective topic has to the respective inquiry content based on levels of association between the product parameters of the enhanced listing of products and on a frequency of actual purchases of products specifically associated with a respective one of the identified multiple associated topics and is a product of at least one of the identified set of multiple products and the listing of products.

6 . The system of claim 5 , wherein the identified multiple associated topics comprise one or more types of products, brands of products, styles, and sources of the products.

7 . The system of claim 1 , wherein the topics training corpus of product information comprises product information of numerous groupings of related products; and
wherein the identified multiple associated topics are estimated to be relevant to the inquiry content and that have an increased relevance to a sub-set of the one or more target content sources.

8 . The system of claim 7 , wherein the topic extraction machine learning model further provides for each of the topics, of the multiple associated topics, a respective topic confidence score.

9 . The system of claim 1 , wherein the intent mining system in obtaining the listing of products is configured to execute a get clustering machine learning model trained using clusters of search keywords training corpus; and
wherein the intent mining system in identifying the listing of products is configured to input the inquiry content, the set of supplemental keywords, and contextual embedding to the get clustering machine learning model, and items in search clusters having a threshold relationship to the inquiry content along with products co-purchased within a purchase threshold of the identified items form at least part of the listing of products that are determined most relevant to the inquiry content.

10 . The system of claim 1 , wherein the distribution system in communicating the multiple associated topics is configured to communicate the multiple associated topics to the one or more target content sources configured to be utilized in determining a valuation in supplying to a first intended recipient enhanced contextually relevant content associated with a respective one of the one or more target content sources and relevant to the inquiry content associated with the first intended recipient.

11 . A method providing contextual information comprising:
receiving inquiry content associated with an intended recipient, wherein the inquiry content does not include personal identification information (PII) or personal network cookie data; determining, for each inquiry content, a set of supplemental keywords corresponding to intent information corresponding to the inquiry content; and identifying, for each inquiry content, historic inquiries each having a threshold relationship with the set of supplemental keywords; obtaining a listing of products corresponding to the historic inquiries; identifying a set of multiple products that each have a purchase threshold relationship with one or more products from the listing of products; generating an enhanced listing of products comprising the listing of products and the set of multiple products; applying a topic extraction machine learning model to product parameters of the products of the enhanced listing of products, wherein the topic extraction machine learning model is trained using a topics training corpus of product information; retraining over time the topic extraction machine learning model based on responses to previous inquiries by previous recipients; identifying, by the retrained topic extraction machine learning model, multiple associated topics that are estimated to be relevant to the inquiry content; and communicating the identified multiple associated topics to one or more target content sources.

12 . The method of claim 11 , further comprising;
determining the set of supplemental keywords associated with the intent information based on a mapping between terms.

13 . The method of claim 11 , further comprising:
acquiring intended recipient non-private information about the intended recipient as a function of a network connection and timing information corresponding to when the respective inquiry content is requested; and applying a set of relevance filters, based on the recipient non-private information and the timing information, to exclude from the listing of products a subset of actual historic products purchased that have the association with historic inquiries.

14 . The method of claim 11 , wherein the identifying the set of multiple products comprises identifying one or more products purchased a threshold number of times with a respective one of the set of mul

Assignees

• Walmart Apollo Llc

Inventors

• Kaddevarmuth Srujana
• Philip Denila B
• Das Amlan J
• Banerjee Debanjana
• Sinha Apurva
• Abraham Abin
• Hardy Mark A

Classifications

• G06F8/43

  Checking; Contextual analysis · CPC title

• G06Q30/0242 Primary

  Determining effectiveness of advertisements · CPC title

• G06F21/6263

  during internet communication, e.g. revealing personal data from cookies · CPC title

• G06Q30/0625

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

• G06Q30/0631

  Recommending goods or services · CPC title