Determining user retention values using machine learning and heuristic techniques
US11341514B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 26, 2019 |
| Grant date | May 24, 2022 |
| Priority date | — |
| Expiry date | Jan 1, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N7/01
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods, apparatus, and processor-readable storage media for determining user retention values using machine learning and heuristic techniques are provided herein. An example computer-implemented method includes processing multiple forms of input data pertaining to interactions between a user and an enterprise; generating one or more user sentiment values from the processed input data by applying machine learning techniques to the processed input data; determining a user-specific estimate for the enterprise retaining the user, wherein determining the user-specific estimate comprises combining the one or more sentiment values with one or more storage system heuristics-based values derived from enterprise-related data; and outputting the user-specific estimate to at least one entity within the enterprise for use in connection with user-support actions.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.