Intelligent sales clue recommendation reason generation method and system
The invention relates to an intelligent sales clue recommendation reason generation method and system, and the method comprises the steps: obtaining M pieces of prediction sample data related to a target customer, and inputting the M pieces of prediction sample data into a recommendation model to ob...
Saved in:
Main Authors | , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
07.03.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention relates to an intelligent sales clue recommendation reason generation method and system, and the method comprises the steps: obtaining M pieces of prediction sample data related to a target customer, and inputting the M pieces of prediction sample data into a recommendation model to obtain M recommendation results; based on each piece of prediction sample data and the corresponding recommendation result, calculating N SHAP values corresponding to each piece of prediction sample data through an SHAP model; generating an SHAP matrix based on the N SHAP values corresponding to each piece of prediction sample data, calculating the correlation of N different types of sample data in each piece of prediction sample data to generate a feature correlation matrix, and replacing the SHAP value with the SHAP value being zero in the SHAP matrix based on the feature correlation matrix to generate a recommendation reason important coefficient matrix; and sorting the N different feature codes of each piece of p |
---|---|
Bibliography: | Application Number: CN202310025598 |