Methods and systems for determining household characteristics

Patent metadata

Field	Value
Publication number	US-12154159-B2
Application number	US-202217589003-A
Country	US
Kind code	B2
Filing date	Jan 31, 2022
Priority date	Jan 31, 2022
Publication date	Nov 26, 2024
Grant date	Nov 26, 2024

Abstract

A system and method for recommending products based on characteristics of a customer's household. The system and method associates age dependent products with developmental stages on a universal developmental scale and determines a subset of age dependent products based on prior engagements by the customer's household. Using the development stages associated with the subset of age dependent products characteristics of the customer's household may determine specifically the number and ages of juveniles in the customer's household. Performing Gaussian mixture model or multivariate kernel density estimation on the developmental stages associated with the engagements of customer's household, the age(s) and number of juveniles respectively may be determined and recommendations of products and services to the customer or customer's household based upon these characteristics may be advantageously made.

First claim

What is claimed is:

1. A system for recommending products based on characteristics of a customer's household, comprising:
a processor operably connected to a database via a communication system, the processor configured to:
determine a plurality of types of attribute values used to measure a plurality of age dependent products belonging to different product types;
translate all of the plurality of types of attribute values into ranges on a universal developmental scale such that each age dependent product is associated with one or more development stages each corresponding to a range on the universal developmental scale, wherein the plurality of types of attribute values include at least: age range, product size, and product stage, each related to a different product type;
receive, from a computing device, a search query submitted by the customer;
determine, from the plurality of age dependent products, a subset of age dependent products based on prior engagements by the customer's household;
retrieve, from the database, the respective development stages associated with each of the age dependent products in the subset;
determine a probability the customer's household containing a child at one or more of the retrieved development stages by performing Gaussian mixture modeling upon the retrieved developmental stages;
determine a developmental stage associated with the customer's household based on the probability;
determine a number of children in the customer's household by performing multivariate kernel density estimation upon the retrieved developmental stages;
recommend selective ones of the plurality of age dependent products to the customer's household based upon the determined developmental stage associated with the customer's household, the determined number of children in the customer's household, and the search query;
transmit, in response to the search query, the selective age dependent products to the computing device as search results; and
validate performance of the Gaussian mixture model using an evaluation metric based on statistical reasoning.

2. The system of claim 1 , wherein:
the database is configured such that the determined developmental stage is stored and associated as a characteristic of the customer's household within the database.

3. A method for recommending products based on characteristics of a customer's household, comprising:
determining a plurality of types of attribute values used to measure a plurality of age dependent products belonging to different product types;
translating all of the plurality of types of attribute values into ranges on a universal developmental scale such that each age dependent product is associated with one or more development stages each corresponding to a range on the universal developmental scale, wherein the plurality of types of attribute values include at least: age range, product size, and product stage, each related to a different product type;
receiving, from a computing device, a search query submitted by the customer;
determining, from the plurality of age dependent products, a subset of age dependent products based on engagements by the customer's household;
retrieving the respective development stages associated with each of the age dependent products in the subset;
determining a probability the customer's household containing a child at one or more of the retrieved development stages by performing Gaussian mixture modeling upon the retrieved developmental stages;
determining a developmental stage associated with the customer's household based on the probability;
determining a number of children in the customer's household by performing multivariate kernel density estimation upon the retrieved developmental stages;
recommending selective ones of the plurality of age dependent products to the customer's household based upon the determined developmental stage associated with the customer's household, the determined number of children in the customer's household, and the search query;
transmitting, in response to the search query, the selective age dependent products to the computing device as search results; and
validating performance of the Gaussian mixture model using an evaluation metric based on statistical reasoning.

4. The method of claim 3 , wherein ones of the plurality of age dependent products are associated with a first scale.

5. The method of claim 4 , wherein others of the plurality of age dependent products are associated with a second scale different from the first scale.

6. The method of claim 5 , wherein the step of translating further comprises correlating the first and second scales with the universal developmental scale.

7. The method of claim 3 , wherein the each of the plurality of developmental stages represents a time period.

8. The method of claim 3 , wherein the engagements by the customer's household are selected from the group consisting of purchases, add to cart, click on, queries, search result, and views.

9. The method of claim 3 , wherein the step of recommending comprises presenting images of the selective age dependent products on a website to the customer.

10. The method of claim 3 , wherein selective ones of the age dependent products have a developmental stage on the universal developmental scale commensurate with the determined developmental stage.

11. The method of claim 3 , wherein the step of determining a probability the customer's household containing a child at one or more of the retrieved development stages further comprises, incrementing results of the Gaussian mixture model based upon a date the Gaussian mixture model was performed.

12. A non-transitory computer readable medium having instructions stored thereon, wherein the instructions, when executed by at least one processor, cause a device to perform operations comprising:
determining a plurality of types of attribute values used to measure a plurality of age dependent products belonging to different product types;
translating all of the plurality of types of attribute values into ranges on a universal developmental scale such that each age dependent product is associated with one or more development stages each corresponding to a range on the universal developmental scale, wherein the plurality of types of attribute values include at least: age range, product size, and product stage, each related to a different product type;
receiving, from a computing device, a search query submitted by the customer;
determining, from the plurality of age dependent products, a subset of age dependent products based on engagements by the customer's household;
retrieving the respective development stages associated with each of the age dependent products in the subset;
determining a probability the customer's household containing a child at one or more of the retrieved development stages by performing Gaussian mixture modeling upon the retrieved developmental stages;
determining a developmental stage associated with the customer's household based on the probability;
determining a number of children in the customer's household by performing multivariate kernel density estimation upon the retrieved developmental stages;
recommending selective ones of the plurality of age dependent products to the customer's household based upon the determined developmental stage associated with the customer's household, the determined number of children in the customer's household, and the search query;
transmitting, in response to the search query, the selective age dependent products to the computing device as search results; and
validating performance of the Gaussian mixture model using an evaluation me

Assignees

• Walmart Apollo Llc

Inventors

• Sinha Nimesh
• Gupta Sneha
• Rajasekaran Rishi
• Xu Yue
• Arora Yokila
• Cho Hyun Duk
• Kumar Sushant
• Achan Kannan

Classifications

• G06Q30/0271

  Personalized advertisement · CPC title

• G06Q30/0204

  Market segmentation · CPC title

• G06Q30/0201

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

• G06Q30/0631 Primary

  Recommending goods or services · CPC title