US 2019/0080249 A1Published application

Reducing electronic resource consumption using data inference

AssigneeLinkedln Corporation

InventorsGloria Yang, Ming Yan

Life of this patent

Estimating the term…

Loading patent…

Abstract

Techniques for inferring data to improve the accuracy and completeness of information retrieval are disclosed herein. In some embodiments, a data inference system detects a lack of employment type data for a profile of a user on an online service, with the employment type data identifying at least one type of employment in which the user is interested. In some embodiments, based on the detecting of the lack of employment type data for the profile of the user, the data inference system generates the employment type data based on an inference model and inference data, with the inference data comprising at least one of profile data of the user and a history of the user's interactions with the online service, and the data inference system performs a function of the online service using the generated employment type data.

Claims20

Dependent claims

A computer-implemented method comprising:

detecting, by at least one hardware processor, a lack of employment type data for a profile of a user on an online service, the employment type data identifying at least one type of employment in which the user is interested;
based on the detecting of the lack of employment type data for the profile of the user, generating, by the at least one hardware processor, the employment type data based on an inference model and inference data, the inference data comprising at least one of profile data of the user and a history of the user's interactions with the online service;
performing, by the at least one hardware processor, a function of the online service using the generated employment type data;
retrieving, by the at least one hardware processor, instances of the inference data for a plurality of user profiles on the online service;
for each one of the plurality of user profiles, generating, by the at least one hardware processor, a predicted employment type data using the inference model;
for each one of the plurality of user profiles, retrieving, by the at least one hardware processor, a control employment type data;
and
using, by the at least one hardware processor, a machine learning algorithm to modify the inference model based on a comparison of the corresponding predicted employment type data of the plurality of user profiles with the corresponding control employment type data of the plurality of user profiles.

5 more elements

A system comprising:

at least one hardware processor;
and
a non-transitory machine-readable medium embodying a set of instructions that, when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:
detecting a lack of employment type data for a profile of a user on an online service, the employment type data identifying at least one type of employment in which the user is interested;
based on the detecting of the lack of employment type data for the profile of the user, generating the employment type data based on an inference model and inference data, the inference data comprising at least one of profile data of the user and a history of the user's interactions with the online service;
and
performing a function of the online service using the generated employment type data.

4 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/699,828Filed 8 Sep 2017
Published: 14 Mar 2019
Term ends: Not estimatedThe source records don’t support an estimate.

Classification6 codes

G06N 5/04
Computing arrangements using knowledge-based models: inference or reasoning models
G06N 20/00
Machine learning
G06Q 10/1053
Human resources: employment or hiring
G06Q 10/40
Administration; Management: business processes related to social networking or social networking services

Family

US 11,138,509 B2Related patent
US 2019/0080249 A1This patent

From the US filing history. Foreign family members aren’t listed.

Timeline

Citations

Open elsewhere

Building an agent or pulling many patents? Use the API or MCP server instead of scraping pages. Get an API key