Automated product personalization based on multiple sources of product information

Abstract

In an approach to customer-product matching, a computing device receives textual information related to a product. The computing device generates a set of product personality traits based on analyzing the textual information by a natural language processor. The computing device identifies a set of customer personality traits for a target customer group. The computing device determines whether a degree of correlation between a first trait from the set of product personality traits and a second trait from the set of customer personality traits meets or exceeds a predetermined threshold value. Responsive to determining that the degree of correlation does not meet or exceed a predetermined threshold value, the computing device revises the textual information based on a psycholinguistic dictionary. The computing device continues to revise the set of product personality traits until the degree of correlation meets or exceeds the predetermined threshold value.

What is claimed is: 
     
         1 . A computer-implemented method for automated product personalization based on product personality, the computer-implemented method comprising:
 receiving, by one or more computer processors, textual information related to a product, wherein the textual information comprises one or more of an initial product description, purchase history information, a product review, a user survey, product attribute information, a product name, a catalog hierarchy, and a product category description;   generating, by the one or more computer processors, a set of product personality traits based on analyzing the textual information by a natural language processor;   identifying, by the one or more computer processors, a set of customer personality traits for a target customer group, wherein the target customer group is defined based on a user input;   determining, by the one or more computer processors, a degree of correlation between a first trait from the set of product personality traits and a second trait from the set of customer personality traits;   determining, by the one or more computer processors, whether the degree of correlation meets or exceeds a predetermined threshold value, wherein the predetermined threshold value is based on the user input;   revising, by the one or more computer processors, responsive to determining that the degree of correlation does not meet or exceed the predetermined threshold value, the textual information based on a psycholinguistic dictionary;   extracting, by the one or more computer processors, one or more words from the textual information;   determining, by the one or more computer processors, that the one or more words do not exist in the psycholinguistic dictionary;   adding, by the one or more computer processors, the one or more words to the psycholinguistic dictionary;   determining, by the one or more computer processors, one or more replacement words in the psycholinguistic dictionary for one or more words in the textual information;   replacing, by the one or more computer processors, the one or more words in the textual information with the one or more replacement words to generate revised textual information;   generating, by the one or more computer processors, a revised set of product personality traits based on analyzing the revised textual information by a natural language processor;   determining, by the one or more computer processors, a degree of correlation between a first trait from the set of revised product personality traits and a second trait from the set of customer personality traits;   determining, by the one or more computer processors, whether the degree of correlation meets or exceeds the predetermined threshold value; and   repeating, by the one or more computer processors, until the degree of correlation meets or exceeds the predetermined threshold value, the revising.