CN-121997159-A - Method, device, equipment and computer storage medium for detecting abnormal environment

CN121997159ACN 121997159 ACN121997159 ACN 121997159ACN-121997159-A

Abstract

The application discloses a method, a device, equipment and a computer storage medium for detecting abnormal environments, and relates to the technical field of fire safety monitoring. The method comprises the steps of obtaining to-be-detected people flow data, to-be-detected environment data and to-be-detected environment types, determining target preset busy degree membership degrees corresponding to the to-be-detected people flow data according to the relationship between the people flow data and preset busy degree membership degrees, determining target fluctuation indexes of to-be-detected environments corresponding to the target preset busy degree membership degrees and the target preset output values according to the relationship between the preset busy degree membership degrees, the preset output values corresponding to the preset busy degrees and the fluctuation indexes, determining corresponding target detection threshold values according to the to-be-detected environment types and the target fluctuation indexes, and judging that the to-be-detected environments are abnormal environments under the condition that the to-be-detected environment data exceeds the target detection threshold values. According to the embodiment of the application, the detection accuracy of the abnormal environment is improved by dynamically setting the detection threshold of the environmental target to be detected.

Inventors

LI SHUXIAN
FANG WENMIN
ZHOU CHUANKAI
CHEN FANG
JIAO JUNPENG

Assignees

中移（杭州）信息技术有限公司
中国移动通信集团有限公司

Dates

Publication Date: 20260508
Application Date: 20241105

Claims (12)

1. A method of abnormal environment detection, comprising: acquiring environment information to be detected, wherein the environment information to be detected comprises people flow data to be detected, environment data to be detected and environment type to be detected; determining a target preset busyness degree membership degree corresponding to the to-be-detected people flow data according to the relationship between the people flow data and the preset busyness degree membership degree; Determining a target fluctuation index of an environment to be detected corresponding to the target preset busyness degree membership degree and the target preset output value according to the relation among the preset busyness degree membership degree, the preset output value corresponding to the preset busyness degree and the fluctuation index, wherein the target preset output value is the preset output value corresponding to the target preset busyness degree; determining a corresponding target detection threshold according to the environment type to be detected and the target fluctuation index; And judging the environment to be detected as an abnormal environment under the condition that the environment to be detected exceeds the target detection threshold value.
2. The method for detecting abnormal environments according to claim 1, wherein the relationship between the people flow data and the busyness preset degree membership is: Wherein mu (x) is a preset busyness degree membership degree, x is the data of the flow of people to be detected, a is a preset slope, and c is a preset center.
3. The method for detecting abnormal environments according to claim 1, wherein the relationship among the preset busyness membership, the preset output value corresponding to the preset busyness, and the fluctuation index is: Wherein epsilon is a fluctuation index, x is the flow data of the people to be detected, mu (x) is a preset busyness degree membership degree, and beta is a preset output value corresponding to the preset busyness degree.
4. The method for detecting an abnormal environment according to claim 1, wherein before determining the target fluctuation index of the environment to be detected corresponding to the target preset busyness degree membership degree and the target preset output value, the method further comprises: and acquiring a preset fuzzy rule base, wherein the preset fuzzy rule base comprises the preset busyness and a preset output value corresponding to the preset busyness.
5. The method of abnormal environment detection according to claim 1, wherein determining a corresponding target detection threshold according to the type of environment to be detected and a target fluctuation index comprises: under the condition that the environment type to be detected is a preset environment type, obtaining the maximum value and the average value of target abnormal environment data of abnormal environment in a preset day; and determining a target detection threshold corresponding to the maximum value and the average value of the target fluctuation index and the target abnormal-environment-free data according to the relation between the maximum value and the average value of the fluctuation index and the abnormal-environment-free data and the detection threshold.
6. The method of abnormal environment detection according to claim 5, wherein the relationship between the maximum value and the average value of the fluctuation index, the abnormal environment-free data and the detection threshold is: Wherein THD is a detection threshold, ε is a fluctuation index, And x max (t) is the maximum value of the target abnormal environment-free data of the abnormal environment-free in the preset days at the t moment.
7. The method of abnormal environment detection according to claim 5, further comprising: And taking the preset detection threshold value as a target detection threshold value under the condition that the environment type to be detected is not the preset environment type.
8. The method of abnormal environment detection according to claim 1, further comprising: inputting the environmental data to be detected into a pre-trained abnormal environment analysis model; determining a weighted sum value of the environmental data to be detected according to the preset node weight of the neural network in the abnormal environment analysis model, and taking the weighted sum value as the abnormal environment probability corresponding to the abnormal environment analysis model; and judging the environment to be detected as an abnormal environment corresponding to the abnormal environment probability exceeding the set threshold value under the condition that the abnormal environment probability exceeds the set threshold value.
9. An apparatus for abnormal environment detection, the apparatus comprising: The system comprises an acquisition module, a detection module and a detection module, wherein the acquisition module is used for acquiring environmental information to be detected, and the environmental information to be detected comprises people flow data to be detected, environmental data to be detected and environmental types to be detected; the determining module is used for determining the target preset busyness degree membership degree corresponding to the to-be-detected traffic data according to the relationship between the traffic data and the preset busyness degree membership degree; The determining module is further used for determining a target fluctuation index of the environment to be detected, which corresponds to the target preset busy degree membership degree and the target preset output value, according to the relation among the preset busy degree membership degree, the preset output value corresponding to the preset busy degree and the fluctuation index, wherein the target preset output value is the preset output value corresponding to the target preset busy degree; The determining module is further used for determining a corresponding target detection threshold according to the environment type to be detected and the target fluctuation index; The judging module is used for judging that the environment to be detected is an abnormal environment under the condition that the environment to be detected data exceeds the target detection threshold value.
10. A terminal device, characterized in that the device comprises a processor and a memory storing computer program instructions, which when executed by the processor implement the method of abnormal environment detection according to any of claims 1-8.
11. A computer readable storage medium, having stored thereon computer program instructions, which when executed by a processor, implement a method of abnormal environment detection according to any of claims 1-8.
12. A computer program product, characterized in that instructions in the computer program product, when executed by a processor of an electronic device, cause the electronic device to perform the method of abnormal environment detection according to any of claims 1-8.

Description

Method, device, equipment and computer storage medium for detecting abnormal environment Technical Field The application belongs to the technical field of fire safety monitoring, and particularly relates to a method, a device, equipment and a computer storage medium for detecting abnormal environments. Background With the development of economy, the number of urban mass shops and street-oriented shops is continuously increasing. As the malls and the malls along the street are commonly rented with various places such as production, operation, civilian destination and the like, the fire hazard is more, and the life safety of people is affected. In the prior art, when detecting an abnormal environment, environmental data such as temperature, smoke concentration and the like are often detected based on sensor equipment, and a data detection threshold is set to judge the abnormal environment. However, under different scenes and time, environmental data such as temperature, smoke concentration and the like are continuously changed, the fixed detection threshold set in the prior art is not suitable for an environment with the environmental data changed in real time, and the detection accuracy of abnormal environments is low. Disclosure of Invention The embodiment of the application provides a method, a device, equipment and a computer storage medium for detecting an abnormal environment, which are used for solving the problems that a fixed detection threshold set in the prior art of the prior method is not suitable for an environment with environmental data changing in real time and the accuracy rate of detecting the abnormal environment is low. In a first aspect, an embodiment of the present application provides a method for detecting an abnormal environment, where the method includes: acquiring environment information to be detected, wherein the environment information to be detected comprises people flow data to be detected, environment data to be detected and environment types to be detected; according to the relationship between the people flow data and the preset busyness degree membership degree, determining a target preset busyness degree membership degree corresponding to the people flow data to be detected; determining a target preset busyness membership degree and a target fluctuation index of an environment to be detected corresponding to the target preset busyness according to the relation among the preset busyness membership degree, the preset output value corresponding to the preset busyness and the fluctuation index, wherein the target preset output value is a preset output value corresponding to the target preset busyness; Determining a corresponding target detection threshold according to the type of the environment to be detected and the target fluctuation index; and under the condition that the environment data to be detected exceeds the target detection threshold value, judging that the environment to be detected is an abnormal environment. In a second aspect, an embodiment of the present application provides an apparatus for detecting an abnormal environment, including: the acquisition module is used for acquiring environment information to be detected, wherein the environment information to be detected comprises people flow data to be detected, environment data to be detected and environment type to be detected; The determining module is used for determining a target preset busyness degree membership degree corresponding to the to-be-detected people flow data according to the relationship between the people flow data and the preset busyness degree membership degree; The determining module is further used for determining a target fluctuation index of the environment to be detected corresponding to the target preset busy degree membership degree and the target preset output value according to the relation among the preset busy degree membership degree, the preset output value corresponding to the preset busy degree and the fluctuation index, wherein the target preset output value is the preset output value corresponding to the target preset busy degree; The determining module is also used for determining a corresponding target detection threshold according to the type of the environment to be detected and the target fluctuation index; the judging module is used for judging that the environment to be detected is an abnormal environment under the condition that the environment to be detected exceeds the target detection threshold value. In a third aspect, an embodiment of the present application provides a terminal device, where the device includes a processor and a memory storing computer program instructions, and where the processor executes the computer program instructions to implement a method for detecting an abnormal environment as in the first aspect. In a fourth aspect, embodiments of the present application provide a computer storage medium having stored thereon computer program instru