5 results about "Penetration rate" patented technology

A device may receive data identifying characteristics, location dependent characteristics, and a network service associated with target consumers, such as households or businesses, and may process the data, with one or more propensity models, to determine propensities of the target consumers to utilize the network service. The device may process the data and the propensities, with a state transition model, to calculate probabilities that the target households will utilize the network service, and may determine utilization states of the target consumers over time based on the probabilities that the target consumers will utilize the network service. The device may aggregate the utilization states of the target consumers to determine penetration rates for the network service, and may perform one or more actions based on the penetration rates for the network service.

A device may receive data identifying characteristics, location dependent characteristics, and a network service associated with target consumers, such as households or businesses, and may process the data, with one or more propensity models, to determine propensities of the target consumers to utilize the network service. The device may process the data and the propensities, with a state transition model, to calculate probabilities that the target households will utilize the network service, and may determine utilization states of the target consumers over time based on the probabilities that the target consumers will utilize the network service. The device may aggregate the utilization states of the target consumers to determine penetration rates for the network service, and may perform one or more actions based on the penetration rates for the network service.

This invention discloses a boundary condition trend prediction method, device, and non-volatile storage medium. The method includes: acquiring historical penetration rate, historical power consumption data, and historical driving data in a target area; based on the historical penetration rate, using a composite prediction model to predict the future penetration rate of electric vehicles corresponding to multiple market types, obtaining penetration rate prediction results; based on the historical power consumption data, historical driving data, and penetration rate prediction results, using an exponential decay convergence model and a weighted regression model to predict energy consumption prediction results; based on the penetration rate prediction results and energy consumption prediction results, predicting the boundary condition parameters of charging facilities corresponding to multiple scenarios; and based on the boundary condition parameters of charging facilities corresponding to multiple scenarios, determining the boundary condition trend sequence. This invention solves the technical problems of single-dimensional prediction of key boundary conditions for electric vehicles participating in vehicle-to-grid interaction, insufficient scenario segmentation, and lack of dynamic evolution mechanisms.

The invention discloses a business increment prediction model construction method, a business increment prediction method and a business increment prediction device, and relates to the technical field of computers. One specific embodiment of the construction method of the business increment prediction model comprises the following steps: determining customer information features; constructing a line order quantity matrix and a penetration order quantity matrix of historical customers according to the historical business information, and further determining historical coupon issuing characteristics, order quantity estimation results and penetration rate estimation results; training an estimated order increment model and an estimated permeability increment model based on the customer information feature, the historical coupon issuing feature, the order estimation result and the permeability estimation result of each historical customer and the business increment label set, and further constructing a business increment prediction model; and the accuracy of the business increment prediction result is improved. A specific embodiment of the business increment prediction method comprises the following steps: inputting a plurality of input features of a target customer into a business increment prediction model to obtain a business increment prediction result; and the conversion rate of right putting is increased.