# US 2023/0410189 A1 · Adaptive Timing Prediction For Updating Information

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0410189 A1
- Document ID: US20230410189A1
- Status: Published application
- Kind: A1
- Application number: 18/239,253
- Filed: 2023-08-29
- Published: 2023-12-21
- Earliest claimed: 2019-08-12
- Assignees: eBay Inc.
- Applicants: eBay Inc.
- Inventors: Ramesh Periyathambi; Manojkumar RANGASAMY KANNADASAN; Lakshimi DURAIVENKATESH; Sai Vipin SIRIPURAPU
- Web page: https://patentgrep.com/patent/US20230410189A1

## CPC

- G06Q 30/08: Auctions
- G06N 5/02: Knowledge representation; Symbolic representation
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Technologies are disclosed herein for distributing information. The disclosed technologies determine an application element configured to receive information that is updated at a variable rate, the information pertaining to an object. Feature data is received that is associated with the object and data associated with use of the application element. The feature data includes a time horizon for the object and supplemental information associated with the object. Based on the feature data and the data associated with use of the application element, a first rate is predicted for sending the information about the object to the application element. The information is sent to the application element at the first rate.

## Claims

### Claim 1

A method, comprising:
receiving, by a computing device, element data describing use of an application element of a user application and feature data describing features of an item of the application element, the application element configured to receive polled information at a variable rate;
determining, by the computing device, one or more associations between the feature data and the element data;
reducing, by the computing device, a polling frequency at which the polled information is communicated to the application element based on the element data and the one or more associations; and
communicating, by the computing device, the polled information to the application element at the reduced polling frequency.

### Claim 2 (depends on 1)

The method of claim 1, wherein the user application is an online auction application, and the application element is a web page hosting an online auction of the item via the online auction application.

### Claim 3 (depends on 2)

The method of claim 2, wherein the element data includes a number of bids for the item in the online auction of the item.

### Claim 4 (depends on 2)

The method of claim 2, wherein the element data includes a number of different users that have bid on the item in the online auction of the item.

### Claim 5 (depends on 2)

The method of claim 2, wherein the element data includes an average amount of time that users of the online auction application spend on the web page.

### Claim 6 (depends on 2)

The method of claim 2, wherein the element data includes a number of different users that have bid on the item during a specified time period.

### Claim 7 (depends on 2)

The method of claim 2, wherein the feature data includes an amount of time remaining in the online auction of the item.

### Claim 8 (depends on 2)

The method of claim 2, wherein the feature data includes a price of the item.

### Claim 9 (depends on 2)

The method of claim 2, wherein the feature data includes an indication of whether returns are accepted for the item.

### Claim 10 (depends on 2)

The method of claim 2, wherein the feature data includes feedback associated with a user of the online auction application submitting the item for auction.

### Claim 11 (depends on 1)

The method of claim 1, wherein the determining the one or more associations includes:
receiving additional feature data describing use of the user application and features of one or more items of the user application;
training a machine learning model on the additional feature data to generate polling frequencies predicted to increase a likelihood of one or more objectives of the user application; and
determining, using the machine learning model, the one or more associations between the feature data and the element data.

### Claim 12 (depends on 11)

The method of claim 11, wherein the training of the machine learning model is via unsupervised learning, and the machine learning model includes one or more of a clustering-based model, a forecasting-based model, and a smoothing-based model.

### Claim 13 (depends on 1)

The method of claim 1, further comprising identifying a pattern in the element data that is relevant to an objective of the user application, the reducing of the polling frequency being further based on the pattern.

### Claim 14

A computing system, comprising:
one or more processors; and
a computer-readable storage medium having computer-executable instructions that are executable by the one or more processors to perform operations including:
receiving element data describing use of an application element of a user application, the application element configured to receive polled information at a variable rate;
identifying a pattern in the element data that is relevant to an objective of the user application;
reducing a polling frequency at which the polled information is communicated to the application element based on the element data and the pattern; and
communicating the polled information to the application element at the reduced polling frequency.

### Claim 15 (depends on 14)

The computing system of claim 14, wherein the element data includes a number of different users that have interacted with the application element.

### Claim 16 (depends on 14)

The computing system of claim 14, wherein the element data includes a number of different users that have interacted with the application element during a specified time period.

### Claim 17 (depends on 14)

The computing system of claim 14, wherein the element data includes a number of user interactions with the application element that have resulted in an update to the polled information.

### Claim 18 (depends on 14)

The computing system of claim 14, wherein the application element is associated with a deadline, and the element data includes an amount of time remaining until the deadline occurs.

### Claim 19 (depends on 14)

The computing system of claim 14, wherein the identifying the pattern includes:
receiving feature data describing use of the user application and features of one or more items of the user application;
training a machine learning model on the feature data to generate polling frequencies predicted to increase a likelihood of one or more objectives of the user application; and
identifying, using the machine learning model, the pattern in the element data.

### Claim 20

A non-transitory computer-readable storage medium having computer-executable instructions that are executable by a computing device to perform operations comprising:
receiving element data describing use of an application element of a user application and feature data describing features of an item of the application element, the application element configured to receive polled information at a variable rate;
determining one or more associations between the feature data and the element data;
reducing a polling frequency at which the polled information is communicated to the application element based on the element data and the one or more associations; and
communicating the polled information to the application element at the reduced polling frequency.