Unlock instant, AI-driven research and patent intelligence for your innovation.

Fire risk assessment method and device and server

A risk assessment and fire technology, applied in the field of devices and servers, fire risk assessment methods, can solve the problems of low learning efficiency, complex machine learning model results, slow convergence, etc., achieve simple process and results, improve learning efficiency and convergence rate , the effect of improving the quality

Inactive Publication Date: 2019-04-19
ZDST COMM TECH CO LTD
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the selection of indicators used in recent years is closely related to the creator’s knowledge level, experience, and historical data accumulation of related fire incidents, which is somewhat subjective and may easily lead to redundant data and redundant data in the sample data used for learning. Noise data, resulting in complex results of machine learning models, low learning efficiency, slow convergence, etc.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fire risk assessment method and device and server
  • Fire risk assessment method and device and server
  • Fire risk assessment method and device and server

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Such as figure 1 As shown, this embodiment provides a fire risk assessment method, which can be applied to, for example, intelligent fire warning devices, PCs, tablet computers, servers, and the like. The fire risk assessment method provided by this embodiment includes:

[0052] S101. Obtain more than one set of fire statistics data, wherein each set of fire statistics data includes index scores and fire hazard levels.

[0053] In specific applications, multiple sets of fire statistics data can be obtained from the fire information management system. Each set of fire statistics data can include the index score of the evaluation target within the first preset time period and the statistical data of the fire event, and the fire corresponding to the statistical data of the fire event within the first preset time period is obtained according to the preset analysis method. Taking the index score as the condition attribute and the fire hazard level as the decision attribute...

Embodiment 2

[0070] Such as figure 2 As shown, this embodiment is a further description of the method steps in the first embodiment. In this embodiment, before the step S01, it also includes:

[0071] S107. Develop a fire risk assessment index system according to the assessment objectives.

[0072] In a specific application, the fire risk assessment index system is formulated according to the assessment objectives, wherein the assessment objectives can be specifically set according to the actual situation, for example, the assessment objectives can be urban administrative areas, large urban complexes, etc. The fire risk assessment index system can include multiple indicators, for example, the indicators can include building fire performance, fire protection facility coverage, fire protection facility integrity, etc.

[0073] S108. Acquire fire statistical data, so as to establish a fire hazard level corresponding to the fire statistical data according to a preset analysis method; wherei...

Embodiment 3

[0077] Such as image 3 As shown, this embodiment is a further description of the method steps in the first embodiment. In this embodiment, step S103 includes:

[0078] S1031. Step A. Acquire the cores of the condition attributes, and use the core set as the initial reduction set.

[0079] In a specific application, in step A, the cores of the conditional attributes are obtained, and the set of cores is used as an initial reduction set.

[0080] S1032. Step B. Calculate the importance of the condition attributes, and sort the condition attributes according to a preset sorting method.

[0081] In a specific application, step B, calculating the importance of different indicators (ie, condition attributes) for evaluating fire events, and sorting the condition attributes according to the importance of the condition attributes according to a preset sorting method. Wherein, the preset sorting method includes sorting the condition attributes according to the importance of the cond...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The method is suitable for the technical field of fire-fighting early warning. The invention provides a fire risk assessment method and device and a server. The method comprises the steps that more than one group of fire-fighting statistical data is acquired, each group of fire-fighting statistical data comprises an index score and a fire hazard level, the index score is taken as a condition attribute, the fire hazard level is taken as a decision attribute, a decision table is established, and attribute reduction is carried out on the decision table to obtain an optimal reduction set; a simplified decision table is establishied according to the optimal reduction set; the machine learning model is trained through the simplified decision table to obtain a training machine learning model; Andsampling data is obtained according to the optimal reduction set, and inputting the sampling data into the training machine learning model to obtain an assessment result of the fire risk output by the training machine learning model. According to the invention, the quality of the sample data can be improved, the process of machine learning model becomes simple, and the learning efficiency and theconvergence rate are improved.

Description

technical field [0001] The invention belongs to the technical field of fire early warning, and in particular relates to a fire risk assessment method, device and server. Background technique [0002] With the development of artificial intelligence, machine learning models began to be applied to fire risk assessment. [0003] However, the selection of indicators used in recent years is closely related to the creator’s knowledge level, experience, and historical data accumulation of related fire incidents, which is somewhat subjective and may easily lead to redundant data and redundant data in the sample data used for learning. Noise data, resulting in complex results of machine learning models, low learning efficiency, and slow convergence. At the same time, due to the rapid development of social economy, the factors that cause fires will continue to change over time. Therefore, it is necessary to adjust the machine learning model according to the actual situation in order t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/06G06Q50/26
CPCG06Q10/0635G06Q50/265
Inventor 王元鹏
Owner ZDST COMM TECH CO LTD