| CPC H02J 13/00001 (2020.01) [H02J 3/003 (2020.01); H02J 2203/20 (2020.01)] | 5 Claims |
|
1. A power demand side speech interaction method, comprising:
obtaining original demand information by a processor, the original demand information comprising user's basic information, user demand information, and a user demand time;
converting the original demand information into first information in text format by the processor;
performing text statistical analysis based on an industry term on the first information in text format by the processor, to obtain second information;
searching for corresponding user's actual information from a database according to the second information by the processor, the database storing the user's basic information, user status information, the industry term, and policy information; and
outputting the user's actual information by the processor;
wherein the method further comprising:
searching for a corresponding forecasting model from the database, according to the second information and the user's basic information by the processor, the corresponding forecasting model represents a change trend of electric power data of the user as the second information changes;
calculating, according to a policy limit value of latest policy information in the database, a policy limit time for which the forecasting model corresponding to the user's basic information reaches the policy limit value by the processor; and
transmitting an early warning message based on the user's basic information and the policy limit time by the processor; wherein industrial enterprises mobilizes to take time off or reduce production based on the early warning message;
wherein the database stores a historical dataset, the historical dataset comprises the user's basic information, electricity consumption items, user status information, the industry term, and policy information; the forecasting model associated with the user's basic information and a preset item is calculated, according to the historical dataset and in combination with a neural network model; and the latest policy information is policy information of a region found by a location in the user's basic information;
wherein the obtaining original demand information comprises:
obtaining basic speech information transmitted by a user client in a communication connection; and
splitting the basic speech information according to a preset rule to obtain speech segments, and correlating the speech segments from the same basic speech information, to obtain the original demand information;
wherein the preset rule comprises:
setting a first labeling signal for the basic speech information every preset duration, and in a case that the first labeling signal is located at a keyword in the basic speech information, setting a second labeling signal in front of the keyword at the first labeling signal; and
taking the first labeling signal and the second labeling signal as a boundary, a priority of the second labeling signal being higher than a priority of the first labeling signal, and splitting the basic speech information to obtain the speech segments comprising the keyword;
wherein the keyword is preset;
wherein the converting the original demand information into first information in text format comprises:
performing speech-to-text conversion on each speech segment in the original demand information, to obtain a text segment; and grouping the text segments of the speech segments from the same original demand information as the first information;
wherein the performing text statistical analysis based on an industry term on the first information in text format, to obtain second information comprises:
using the industry term as a feature word, selecting text segments with the same feature word from all of the first information as the second information, and counting a number; and
determining, according to the number corresponding to each feature word, a priority corresponding to the feature word;
the priority being configured for an execution order of searching for corresponding user's actual information according to each piece of second information from the database.
|