Working condition evaluation and business volume prediction method based on multi-modal neural network model

Abstract

The invention discloses a working condition evaluation and business volume prediction method based on a multi-modal neural network model. The evaluation method comprises the following steps: collecting an operation state; constructing a multi-modal neural network; inputting the states of all the modules into a time sequence coding layer in sequence; integrally inputting the states of all the modules into a batch coding layer; performing local transformation and global transformation to obtain an evaluation value; carrying out overall training on the network, wherein the prediction method comprises the following steps: obtaining predicted data; constructing a multi-modal neural network; inputting the states of all the modules into a time sequence coding layer in sequence; inputting the states of all the modules integrally into a batch coding layer; carrying out local transformation and global transformation to obtain a business volume prediction value; and carrying out overall training on the network. The self-service document filling terminal has the beneficial effects that the service efficiency of the self-service document filling terminal can be greatly improved, the utilization efficiency of litigation service disposal resources can be maximized, and litigation service convenience is provided for the masses to the greatest extent.

Description

technical field [0001] The invention relates to the technical field of evaluation and prediction, in particular, to a working condition evaluation and business volume prediction method based on a multimodal neural network model. Background technique [0002] High speed, continuous and high automation are the operating characteristics of equipment in the 21st century. In order to maintain safe and reliable operation of equipment, it is necessary to know the operating status and accuracy of equipment at any time. It is necessary to monitor the status of major equipment and systems, evaluate their working conditions, and maintain them in a timely manner. And a set of scientific management such as online diagnosis and offline repair. For example, patent number CN201210066256.3 discloses a method for evaluating the operating conditions of sulfur hexafluoride transformers, which effectively solves the problem of complicated test procedures, long cycles, slow data updates, and inab...

AI Technical Summary

Problems solved by technology

For example, the patent number CN201210066256.3 discloses a method for evaluating the operating conditions of sulfur hexafluoride transformers, which effectively solves the problem of complicated test procedures, long cycles, slow data updates, and inability to monitor gas composition data in real time in current operating condition evaluations. To evaluate the health status of sulfur hexafluoride transformers, the efficiency is low, consuming manpower, material and financial resources, and cannot meet the problem of evaluating the operating conditions of sulfur hexafluoride transformers, although it can be used for a large number of sulfur hexafluoride transformers The working condition can be analyzed and evaluated automatically in real time, but it cannot predict the operating status of the equipment, so it cannot better meet the needs of the enterprise

Images