Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Classifying activity using probabilistic models

A technology that supports systems and automatic systems, applied in the information field, can solve problems such as influence and measurement deviation

Active Publication Date: 2013-07-31
IBM CORP
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, measures of the usefulness of those automated customer support systems are often based on surveys or interviews with customers, which require the good intentions or compensation of customers
In such cases, metrics can become biased due to unhappy customers who receive surveys to vent their frustrations with using the system, or due to certain demographic characteristics of people who receive compensation
Especially when trying to measure how effective users are in their interactions, survey-based metrics can affect results in unpredictable ways

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Classifying activity using probabilistic models
  • Classifying activity using probabilistic models
  • Classifying activity using probabilistic models

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] As described herein, aspects of the invention include the use of probabilistic models to classify customer activity in an automated customer support system. Automated customer support systems may include, for example, voice response systems and Internet websites. The input to the classification system can include any observable metrics of the customer's interaction with the automated system. This can include, for example, the documents read by the customer / user, which options are selected from the menu, what information the system provides, and the perception of the customer / user's emotional state.

[0014] In contrast to existing methods, aspects of the present invention include modeling user activity to identify, for example, the user's success or failure in obtaining information from a website. Moreover, user activity classification is performed without user intervention. Therefore, probabilistic models are used to determine usage patterns that correspond to the succe...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A method, an apparatus and an article of manufacture for classifying customer activity in an automated customer support system. The method includes obtaining input from the automated customer support system, wherein the input comprises an observable measurement of customer activity in the automated customer support system, computing a probability that the input corresponds to one of one or more probabilistic models, and using the computed probability to classify the customer activity in the automated customer support system by considering the probabilistic model corresponding to a highest computed probability.

Description

Technical field [0001] The embodiments of the present invention generally relate to information technology, and more specifically to classification systems. Background technique [0002] Although a human agent can provide customer support in person or over the phone, a large number of automated systems have emerged in recent years that allow customers to obtain support without human contact. Examples include automated voice response systems (VRS) and Internet-based websites. However, the measurement of these automated customer support systems proved to be challenging. General metrics involve the classification of customer contacts with automated systems and include the need to classify contacts into specific categories such as success or failure. This is especially important in the case of technical support systems, where determining whether the customer has solved their problems is a key measure of success. [0003] In an agent-based computer support system, the success or fail...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F17/30
CPCG06Q10/00G06F17/30G06Q10/101
Inventor C·S·皮年泽
Owner IBM CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com