System and method for context map generation

• US 8,538,958 B2
• Filed: 07/11/2008
• Issued: 09/17/2013
• Est. Priority Date: 07/11/2008
• Status: Expired due to Fees

• Current Assignee: Satyam Computer Services Limited of Mayfair Centre
• Original Assignee: Satyam Computer Services Limited of Mayfair Centre
• Inventors: Varadarajan, Sridhar, Gopalan, Srividya, Kurup, Swetha Mukunda, Kumar, G. S. Praveen
• Primary Examiner(s): Mofiz, Apu
• Assistant Examiner(s): MINCEY, JERMAINE A
• Application Number:
  US12/171,669
• Publication Number:
  US 20100011021A1
• Time in Patent Office: 1,894 Days
• Field of Search: None
• US Class Current: 707/732
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Personalized services and targeted services demand the exploitation of context—say, context of an environment, context of a product, context of a service, and context of a customer or user or individual. In order for the personalized and targeted services to have a greater impact, the identified context used by a context aware processing engine needs to be accurate and current. Such an up-to-date context is called as context map and a system and method for generating a customer-specific context map involves the processing of customer transactions, abstracting and generalizing these transactions into entities, and inter-relating these entities. The context map, for example, is useful in ad targeting in mobile environments, and in quicker and efficient problem resolution in contact center environments.

Claims

1. A method for the creation of a context map with respect to a customer based on a customer ontology and a plurality of transactions of said customer, wherein said plurality of transactions comprises a plurality of keywords, said customer ontology comprises a plurality of entities and a plurality of relationships, wherein each of said plurality of relationships is among a plurality of relationship entities of said plurality of entities, said method comprising the steps of:

computing a plurality of customer related possible entities based on said plurality of entities and said plurality of keywords, wherein said means for computing further comprises;

mapping a plurality of mapped keywords of said plurality of keywords with respect to an entity of said plurality of customer related possible entities,

computing a count based on said plurality of mapped keywords, wherein said count exceeds a pre-defined threshold,

mapping a plurality of mapped attribute keywords of said plurality of keywords with respect of an attribute of a plurality of attributes of an entity of said plurality of customer related possible entities, and

computing an attribute count of a plurality of attribute counts based on said plurality of mapped attribute keywords, wherein said plurality of attribute counts is associated with said plurality of attributes and each of said plurality of attribute counts exceeds a pre-defined threshold;

computing a plurality of customer related entities based on said plurality of customer related possible entities, wherein computing further comprises;

determining a count of said plurality of counts associated with a selected entity of said plurality of customer related possible entities,

selecting said selected entity based on said count and said plurality of counts, and,

making said selected entity a part of said plurality of customer related entities;

computing a plurality of customer related relationships based on said plurality of relationships and said plurality of customer related entities, wherein a relationship of said plurality of relationships comprises a plurality of relationship entities of said plurality of entities, a plurality of entity attributes of each of said plurality of relationship entities, and a plurality of expected correlations among a plurality of entity relationship attributes, wherein said plurality of entity attributes is a part of said plurality of entity relationship attributes, wherein computing further comprises;

generating a plurality of matched entities of said relationship based on said plurality of relationship entities and said plurality of customer related entities,

computing a plurality of correlated relationships based on said plurality of relationships and said plurality of customer related entities,

computing an absolute correlation coefficient of a plurality of absolute correlation coefficients of a customer related relationship of said plurality of customer related relationships, wherein said absolute correlation coefficient is based on a plurality of tuples satisfying said customer related relationship and a plurality of tuples and a plurality of matched entities satisfying said customer related relationship and said absolute correlation coefficient exceeds a pre-defined threshold,

computing a relative correlative coefficient of said customer related relationship based on said absolute correlation coefficient and said plurality of absolute correlation coefficients, wherein said relative correlation coefficient exceeds a pre-defined threshold;

making said plurality of plurality of customer related entities a part of said context map; and

making said plurality of plurality of customer related relationships a part of said context map.