CN110929565B - Risk monitoring method and device based on machine learning, storage medium and electronic equipment - Google Patents
Risk monitoring method and device based on machine learning, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN110929565B CN110929565B CN201910979638.7A CN201910979638A CN110929565B CN 110929565 B CN110929565 B CN 110929565B CN 201910979638 A CN201910979638 A CN 201910979638A CN 110929565 B CN110929565 B CN 110929565B
- Authority
- CN
- China
- Prior art keywords
- building
- monitoring
- inclination
- periodic
- crack
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 287
- 238000010801 machine learning Methods 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000000737 periodic effect Effects 0.000 claims abstract description 148
- 238000012549 training Methods 0.000 claims description 12
- 238000012806 monitoring device Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 abstract 1
- 238000012545 processing Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Alarm Systems (AREA)
Abstract
The application relates to a risk monitoring method and device based on machine learning, a storage medium and electronic equipment, belonging to the technical field of building monitoring, wherein the method comprises the following steps: acquiring an inclination monitoring image of the building, and periodically acquiring a crack monitoring image of the building; acquiring a periodic gradient according to the gradient monitoring image, and acquiring periodic crack element data according to the crack monitoring image; generating a plurality of input data streams from the periodic fracture element data associated with each periodic inclination; generating a base data stream according to all the periodic inclinations and all the periodic crack element data; and acquiring a preset number of input data streams in the plurality of input data streams to form an attack stream, and inputting the attack stream into a machine learning model to obtain the risk value of the building. According to the method, the device and the system, the risk value of the building is efficiently and accurately monitored through the machine learning model based on the construction inclination of the building monitoring image and the attacked flow generated by the crack data.
Description
Technical Field
The application relates to the technical field of building monitoring, in particular to a risk monitoring method and device based on machine learning, a storage medium and electronic equipment.
Background
The cracking and deformation of the building structure are common technical problems at home and abroad, the building structure is inclined and deformed to cause the building to collapse unstably, particularly the building with poor integrity or damaged building is damaged, and once the deformation limit is reached, the building structure can cause great loss at all times.
At present, manual methods or sensor arrangement are adopted for detection in building monitoring, detection and observation are performed manually, the period is long, the error is large, and collection of dynamic data for analysis cannot be realized, so that the house safety is difficult to be effectively ensured. When monitoring a building by adopting a method such as an inclination sensor, the problem of difficult arrangement of the sensor exists, and the deformation of the crack building is not detected in place. In the prior art, the problem that the safety monitoring accuracy of the building is not high and more human resources are consumed simultaneously exists.
It should be noted that the information disclosed in the foregoing background section is only for enhancing understanding of the background of the present application and thus may include information that does not form the prior art that is already known to those of ordinary skill in the art.
Disclosure of Invention
The purpose of the application is to provide a real-time monitoring scheme of building, and then based on the attacked stream generated according to the building gradient and the crack data of building monitoring images at least to a certain extent, the risk value of the building is efficiently and accurately monitored through a machine learning model.
According to one aspect of the present application, there is provided a risk monitoring method based on machine learning, including:
the method comprises the steps that an inclined image acquisition device preset at a plurality of inclined monitoring positions of a building is used for periodically acquiring inclined monitoring images of the building, and a crack image acquisition device preset at a plurality of crack monitoring positions of the building is used for periodically acquiring crack monitoring images of the building;
acquiring periodic inclinations of the plurality of inclined monitoring positions according to the inclined monitoring images, and acquiring periodic crack element data of the plurality of crack monitoring positions according to the crack monitoring images;
generating a plurality of input data streams from periodic crack element data for each of the periodic inclinations at a crack monitoring location associated with an inclination monitoring location from which each of the periodic inclinations originated;
generating a base data stream according to all the periodic inclinations and all the periodic crack element data;
And obtaining a preset number of input data streams in the plurality of input data streams to form an attack stream, merging the attack stream with the base data stream to obtain an attacked data stream, and inputting the attacked data stream into a pre-trained machine learning model to obtain the risk value of the building.
In an exemplary embodiment of the present application, the training method of the machine learning model is:
acquiring a sample set of the attacked data stream, wherein each sample is calibrated with a risk value of a corresponding building in advance;
respectively inputting the data of each sample into a machine learning model to obtain a risk value of a building output by the machine learning model;
if the risk value of the building obtained after the data of the sample are input into the machine learning model is inconsistent with the risk value of the building calibrated in advance for the sample, the coefficient of the machine learning model is adjusted until the risk value of the building is consistent with the risk value of the building calibrated in advance for the sample;
and after the data of all the samples are input into the machine learning model, the obtained risk value of the building is consistent with the risk value of the building calibrated in advance for the data samples, and training is finished.
In an exemplary embodiment of the present application, after said generating a base data stream from all of said periodic inclinations and all of said periodic fracture element data, the method further comprises:
Acquiring a plurality of the base data streams of a preset time period;
and inputting a plurality of the base data streams into a pre-trained second machine learning model together to obtain a life prediction value of the building.
In an exemplary embodiment of the present application, after the acquiring the periodic inclinations of the plurality of inclination monitoring positions from the inclination monitoring image and the acquiring the periodic crack element data of the plurality of crack monitoring positions from the crack monitoring image, the method further includes:
acquiring periodic crack element data of a target crack monitoring position associated with the target inclination monitoring position when the periodic inclination of the target inclination monitoring position among the periodic inclinations of the plurality of inclination monitoring positions is monitored to exceed a predetermined threshold;
calculating a first inclination risk value of the target inclination monitoring position on the building and a second inclination risk value of the target crack monitoring position on the building based on a preset building information registry;
and acquiring a risk value of the building according to the regular inclination of the target inclination monitoring position, the regular crack element data of the target crack monitoring position, the first inclination risk value and the second inclination risk value.
In an exemplary embodiment of the present application, the acquiring the risk value of the building according to the periodic inclination of the target inclination monitoring location, the periodic crack element data of the target crack monitoring location, the first inclination risk value and the second inclination risk value includes:
according to the formula w= (X S + Y T) o+p And acquiring a risk value of the building, wherein W is the risk value of the building, X is a weight corresponding to the periodic inclination, S is the periodic inclination, Y is a weight corresponding to the data of one attribute in the periodic crack element data, O is a first inclination risk value, and P is a second inclination risk value.
In an exemplary embodiment of the present application, the calculating, based on a preset building information registry, a first inclination risk value of the target inclination monitoring position on the building and a second inclination risk value of the target crack monitoring position on the building includes:
acquiring weather data of the building site by positioning the building site;
acquiring first inclination risk data of the target inclination monitoring position from a preset building information registry;
Acquiring the first inclination risk value through the weather data and the first inclination risk data;
acquiring second inclination risk data of the target crack monitoring position from a preset building information registry;
and acquiring the second inclination risk value through the weather data and the second inclination risk data.
In an exemplary embodiment of the present application, the acquiring the periodic crack element data of the target crack monitoring position associated with the target inclination monitoring position when the periodic inclination of the target inclination monitoring position among the periodic inclinations of the plurality of inclination monitoring positions is monitored to exceed a predetermined threshold value includes:
when the regular inclination of the target inclination monitoring position in the regular inclinations of the plurality of inclination monitoring positions exceeds a preset threshold value, acquiring all target crack monitoring positions related to the target inclination monitoring position from a preset monitoring position association relation table;
periodic fracture element data of the plurality of target fracture monitoring locations is obtained.
According to one aspect of the present application, there is provided a risk monitoring apparatus based on machine learning, including:
The acquisition module is used for periodically acquiring the inclination monitoring images of the building through inclination image acquisition equipment preset at a plurality of inclination monitoring positions of the building, and periodically acquiring the crack monitoring images of the building through crack image acquisition equipment preset at a plurality of crack monitoring positions of the building;
the acquisition module is used for acquiring the periodic inclinations of the plurality of inclined monitoring positions according to the inclined monitoring images and acquiring periodic crack element data of the plurality of crack monitoring positions according to the crack monitoring images;
a first generation module for generating a plurality of input data streams from periodic crack element data of a crack monitoring location associated with each of the periodic inclinations and an inclination monitoring location from which each of the periodic inclinations originated;
the second generation module is used for generating a base data stream according to all the periodic inclination and all the periodic crack element data;
the prediction module is used for acquiring a preset number of input data streams in the plurality of input data streams to form an attack stream, merging the attack stream with the base data stream to obtain an attacked data stream, and inputting the attacked data stream into a pre-trained machine learning model to obtain the risk value of the building.
According to one aspect of the present application, there is provided a computer readable storage medium having stored thereon a real-time monitoring program for a building, characterized in that the real-time monitoring program for a building, when executed by a processor, implements the method of any of the above.
According to an aspect of the present application, there is provided an electronic apparatus, including:
a processor; and
the memory is used for storing a real-time monitoring program of the building of the processor; wherein the processor is configured to perform the method of any of the above via execution of a real-time monitoring program of the building.
Firstly, periodically acquiring inclination monitoring images of a building through inclination image acquisition equipment preset at a plurality of inclination monitoring positions of the building, and periodically acquiring crack monitoring images of the building through crack image acquisition equipment preset at a plurality of crack monitoring positions of the building; therefore, the inclination monitoring images and the crack monitoring images of all positions of the building can be rapidly and accurately acquired as required, and the inclination monitoring images and the crack monitoring images are used for accurately acquiring building risk values and risk sources in the follow-up process. Further, after periodic inclinations of the plurality of inclination monitoring positions are obtained according to the inclination monitoring images, periodic crack element data of the plurality of crack monitoring positions are obtained according to the crack monitoring images, a plurality of input data streams are generated according to the periodic crack element data of the crack monitoring positions, wherein each periodic inclination is associated with the inclination monitoring position from which each periodic inclination originates; the input data stream accurately representing the correlation of each periodic gradient and the associated periodic crack element data is obtained, and can be used for efficiently and accurately calculating and analyzing the building risk in the subsequent steps.
Then, generating a base data stream according to all the periodic inclinations and all the periodic crack element data; in this way, a clear representation of the relationship between the monitoring data at the various locations of the building and the base data stream of the correspondence to the building can be obtained, in clear contrast to each of the input data streams. And finally, acquiring a preset number of input data streams in the plurality of input data streams to form an attack stream, merging the attack stream with the base data stream to obtain an attacked data stream, and inputting the attacked data stream into a pre-trained machine learning model to obtain the risk value of the building. Therefore, based on the attacked flow which is generated according to the building gradient and the crack data of the building monitoring image and can clearly represent the opposite relation between the risk element data of each associated position of the building and the integral building data, the risk value of the building can be efficiently and accurately monitored through the machine learning model.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application. It is apparent that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
Fig. 1 schematically shows a flow chart of a risk monitoring method based on machine learning.
Fig. 2 schematically shows an example diagram of an application scenario of a risk monitoring method based on machine learning.
Fig. 3 schematically shows a flow chart of a method of acquiring a risk value for a building.
Fig. 4 schematically shows a block diagram of a machine learning based risk monitoring device.
Fig. 5 schematically shows an example block diagram of an electronic device for implementing the machine learning based risk monitoring method described above.
Fig. 6 schematically illustrates a computer readable storage medium for implementing the machine learning based risk monitoring method described above.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the present application. One skilled in the relevant art will recognize, however, that the aspects of the application may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known aspects have not been shown or described in detail to avoid obscuring aspects of the present application.
Furthermore, the drawings are only schematic illustrations of the present application and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor devices and/or microcontroller devices.
In this exemplary embodiment, a risk monitoring method based on machine learning is provided first, where the risk monitoring method based on machine learning may be executed on a server, or may be executed on a server cluster or a cloud server, or the like, and of course, those skilled in the art may execute the method of the present invention on other platforms according to requirements, which is not limited in particular in this exemplary embodiment. Referring to fig. 1, the risk monitoring method based on machine learning may include the steps of:
step S110, periodically acquiring inclination monitoring images of a building through inclination image acquisition equipment preset at a plurality of inclination monitoring positions of the building, and periodically acquiring crack monitoring images of the building through crack image acquisition equipment preset at a plurality of crack monitoring positions of the building;
Step S120, acquiring the periodic inclinations of the plurality of inclined monitoring positions according to the inclined monitoring images, and acquiring periodic crack element data of the plurality of crack monitoring positions according to the crack monitoring images;
step S130, generating a plurality of input data streams according to the periodic crack element data of the crack monitoring position related to the inclination monitoring position of each periodic inclination source;
step S140, generating a base data stream according to all the periodic inclinations and all the periodic crack element data;
step S150, obtaining a preset number of input data streams in the input data streams to form an attack stream, merging the attack stream with the base data stream to obtain an attacked data stream, and inputting the attacked data stream into a pre-trained machine learning model to obtain the risk value of the building.
In the risk monitoring method based on machine learning, firstly, the inclination monitoring images of the building are periodically acquired through inclination image acquisition equipment preset at a plurality of inclination monitoring positions of the building, and the crack monitoring images of the building are periodically acquired through crack image acquisition equipment preset at a plurality of crack monitoring positions of the building; therefore, the inclination monitoring images and the crack monitoring images of all positions of the building can be rapidly and accurately acquired as required, and the inclination monitoring images and the crack monitoring images are used for accurately acquiring building risk values and risk sources in the follow-up process. Further, after periodic inclinations of the plurality of inclination monitoring positions are obtained according to the inclination monitoring images, periodic crack element data of the plurality of crack monitoring positions are obtained according to the crack monitoring images, a plurality of input data streams are generated according to the periodic crack element data of the crack monitoring positions, wherein each periodic inclination is associated with the inclination monitoring position from which each periodic inclination originates; the input data stream accurately representing the correlation of each periodic gradient and the associated periodic crack element data is obtained, and can be used for efficiently and accurately calculating and analyzing the building risk in the subsequent steps. Then, generating a base data stream according to all the periodic inclinations and all the periodic crack element data; in this way, a clear representation of the relationship between the monitoring data at the various locations of the building and the base data stream of the correspondence to the building can be obtained, in clear contrast to each of the input data streams. And finally, acquiring a preset number of input data streams in the plurality of input data streams to form an attack stream, merging the attack stream with the base data stream to obtain an attacked data stream, and inputting the attacked data stream into a pre-trained machine learning model to obtain the risk value of the building. Therefore, based on the attacked flow which is generated according to the building gradient and the crack data of the building monitoring image and can clearly represent the opposite relation between the risk element data of each associated position of the building and the integral building data, the risk value of the building can be efficiently and accurately monitored through the machine learning model.
Next, each step in the above-described risk monitoring method based on machine learning in the present exemplary embodiment will be explained and described in detail with reference to the accompanying drawings.
In step S110, tilt monitoring images of a building are periodically acquired by tilt image acquisition apparatuses preset at a plurality of tilt monitoring positions of the building, and crack monitoring images of the building are periodically acquired by crack image acquisition apparatuses preset at a plurality of crack monitoring positions of the building.
In the embodiment of the present example, referring to fig. 2, a server 201 periodically acquires tilt monitoring images of a building through tilt image acquisition apparatuses 202 preset at a plurality of tilt monitoring positions of the building, and periodically acquires crack monitoring images of the building through crack image acquisition apparatuses 203 preset at a plurality of crack monitoring positions of the building. This allows the building to be monitored in real time by the server 201 in a subsequent step based on the inclination monitoring image and the crack monitoring image. The server 201 may be any device with processing capability, for example, a computer, a microprocessor, etc., and the oblique image capturing device 202 and the crack image capturing device 203 may be any device with an image capturing function, for example, a camera, a mobile phone, etc., which are not limited in particular herein.
The plurality of tilt monitoring positions of the building are positions where tilt is likely to occur, which are determined by an expert, around the target building, such as the side or back of a certain building, etc. By the provided tilt image capturing apparatus such as a camera for a plurality of tilt monitoring positions of a building, tilt monitoring images of a predetermined position of the building can be periodically captured by photographing.
The plurality of crack monitoring positions of the building are positions where building cracks are easy to occur, such as the top of the center of a longitudinal wall, a bottom windowsill and the like, and the crack monitoring images of the preset positions of the building can be acquired periodically through crack image acquisition equipment such as a camera and the like preset at the plurality of crack monitoring positions of the building. The method comprises the steps of setting a monitoring position association relation table, wherein a plurality of inclination monitoring positions and a plurality of crack monitoring positions of a building have a preset association relation, and storing the preset association relation in the monitoring position association relation table. For example, the correlation is that the inclination of a certain inclination monitoring position easily causes cracks to appear in a certain crack monitoring position, and the inclination monitoring position and the crack monitoring position have the correlation.
In step S120, periodic inclinations of the plurality of inclination monitoring positions are acquired according to the inclination monitoring image, and periodic crack element data of the plurality of crack monitoring positions are acquired according to the crack monitoring image.
In the embodiment of the present example, from the periodically acquired inclination monitoring image, inclination data such as the inclination angle and the inclination direction of the wall with respect to the ground can be accurately acquired by locating, for example, the contour line of the wall and the ground, and then based on the angle of the contour line of the wall and the ground.
From the periodically acquired crack monitoring images, the edge profile of the crack can be detected by the existing image detection, then, the inclined direction line of the crack can be obtained by positioning and fitting the points on the crack profile, for example, the connecting line between two points with the farthest distance among the points on the crack profile, further, the periodic inclined direction of the crack is calculated according to the inclined direction line, and the periodic crack element data such as the area of the crack, the length of the crack and the like are calculated according to the area surrounded by the profile line of the crack. In this way, the risk of the building can be accurately analyzed in a subsequent step by means of the inclination and crack element data. In one embodiment, acquiring the inclination of the plurality of inclination monitoring positions from the inclination monitoring image and acquiring the crack element data of the plurality of crack monitoring positions from the crack monitoring image includes: extracting the contour line of the building and the contour line of the preset perpendicularity reference element from the inclination monitoring image, and acquiring the inclination of the building based on the included angle between the contour line of the building and the contour line of the preset perpendicularity reference element; and extracting the contour lines of the cracks and the contour lines of the preset perpendicularity reference elements from the crack monitoring images, and obtaining the inclined directions of the cracks at the plurality of crack monitoring positions by locating points on the crack contour and fitting to obtain the included angles between the inclined direction lines of the cracks and the contour lines of the perpendicularity reference elements. Wherein the perpendicularity reference element is a reference element obtained by hanging a heavy ball on a vertical line, for example.
In step S130, a plurality of input data streams are generated from the periodic crack element data of the crack monitoring position associated with each of the periodic inclinations and the inclination monitoring position from which the periodic inclination originates.
In the embodiment of the present example, a plurality of crack monitoring positions are associated in advance with each tilt monitoring position, and the building is tilted in a certain direction due to subsidence of the ground or the like, and then, the building can drive a plurality of positions on the building associated with the tilt direction to generate cracks when tilted, and as the tilt is larger, the cracks of the building are increased, and finally, the building is destroyed.
Generating a plurality of input data streams according to the periodic crack element data of the crack monitoring position, which is related to the inclination monitoring position of each periodic inclination source, namely processing the data of each periodic inclination and the periodic crack element data of the corresponding related crack monitoring position into data streams, and in one embodiment, forming a data matrix after adding the position and the type of the data source into each data to obtain the input data streams; in another embodiment, after each data is added with a tag of a data source position and type, the data are sequentially connected in series to form a data string, so as to obtain an input data stream. The periodic crack element data of the target crack monitoring position related to the target inclination monitoring position is obtained, which positions of the building are at risk can be accurately analyzed by combining the inclination of the target inclination monitoring position and the related crack element data in the subsequent steps, and the input data stream accurately representing the correlation of each periodic inclination and the related periodic crack element data can be used for efficiently and accurately calculating and analyzing the building risk in the subsequent steps.
In step S140, a base data stream is generated from all the periodic inclinations and all the periodic fracture element data.
In this exemplary embodiment, the base data stream is a data stream containing monitoring data for all buildings. In one embodiment, a base data stream is generated according to all the periodic inclinations and all the periodic crack element data, that is, each periodic inclination data and each periodic crack element data are added to coordinates of corresponding positions of a plurality of two-dimensional structure diagrams of the building, so as to obtain a two-dimensional building monitoring data lattice as the base data stream; in one embodiment, a base data stream is generated according to all the periodic inclinations and all the periodic crack element data, that is, each periodic inclination data and each periodic crack element data are added to coordinates of a corresponding position of a three-dimensional structure diagram of the building, so as to obtain a three-dimensional building monitoring data lattice as the base data stream. Therefore, the relation between the monitoring data of each position of the building and the corresponding relation with the building can be clearly represented through the base data stream, and further, the positions of the building can be effectively analyzed to have risks through comparison after the input data stream is combined, so that the risks of the building can be efficiently and accurately analyzed in the follow-up steps based on the base data stream.
In step S150, a predetermined number of input data streams in the plurality of input data streams are acquired to form an attack stream, and an attacked data stream obtained by combining the attack stream with the base data stream is input into a machine learning model trained in advance to obtain a risk value of the building.
In the present exemplary embodiment, a predetermined number of the plurality of input data streams is acquired, that is, 3 or the like is acquired from 5 data streams, for example. The obtaining mode may be that after the plurality of input data streams are arranged and combined, each combined input data stream is obtained in sequence, so that various combined input data streams can be obtained, and various combined building risk monitoring data can be obtained, and further analysis of various conditions is performed. And then, forming an attack flow, namely, acquiring dynamic data such as weather, earthquake and the like in a preset time period, combining the dynamic data with a preset number of input data flows to obtain an attack flow capable of reflecting the dynamic risk of the building, and analyzing the instability of all the current building inclination data and the instability of the building crack data of the building, namely, the instability of all the current building inclination data and the instability of the building crack data of the building in the current environment, namely, the risk of the building through the attack flow. Therefore, the attack stream can attack the base data stream, and is embodied as an attacked data stream obtained by combining the attack stream and the base data stream, wherein the combining mode can be to directly connect the two data streams in series; the attack stream may be inserted into a predetermined position of the base data stream. And finally, inputting the attacked data stream into a pre-trained machine learning model, so that the risk value of the building can be obtained efficiently and accurately.
In particular, in this way, the data input into the machine learning model is organized, so that the machine learning model can accurately predict risk monitoring sources, namely, risk sources such as inclination or cracks of a certain position which causes risk to the current building, geographical environment and the like.
In one embodiment of the present example, the training method of the machine learning model is:
acquiring a sample set of the attacked data stream, wherein each sample is calibrated with a risk value of a corresponding building in advance;
respectively inputting the data of each sample into a machine learning model to obtain a risk value of a building output by the machine learning model;
if the risk value of the building obtained after the data of the sample are input into the machine learning model is inconsistent with the risk value of the building calibrated in advance for the sample, the coefficient of the machine learning model is adjusted until the risk value of the building is consistent with the risk value of the building calibrated in advance for the sample;
and after the data of all the samples are input into the machine learning model, the obtained risk value of the building is consistent with the risk value of the building calibrated in advance for the data samples, and training is finished.
The attacked data stream sample is the attack data stream sample which corresponds to a large number of buildings in history and is collected respectively. By collecting the sample set of the attacked data stream as the input of the first learning model, each sample is calibrated by an expert in advance to the risk value of the corresponding building as the output of the machine learning model. Then, the coefficient is adjusted so that the risk value of the obtained building is consistent with the risk value of the building calibrated in advance for the sample after the data of all the samples are input into the machine learning model, and training is finished, so that a trained machine learning model is obtained, and training accuracy can be effectively ensured.
In one embodiment of the present example, after said generating a base data stream from all of said periodic inclinations and all of said periodic fracture element data, the method further comprises:
acquiring a plurality of the base data streams of a preset time period;
and inputting a plurality of the base data streams into a pre-trained second machine learning model together to obtain a life prediction value of the building.
In this way, the life of the building, namely the life prediction value of the building, can be efficiently and accurately predicted according to the plurality of basic data streams of the building for a preset time period through the pre-trained second machine learning model.
In one embodiment of the present example, the training method of the second machine learning model is:
acquiring a sample set of a base data stream group, wherein each sample is calibrated with a life prediction value of a corresponding building in advance;
respectively inputting the data of each sample into a machine learning model to obtain the service life of a building output by the machine learning model;
if the life predicted value of the building obtained after the data of the sample are input into the machine learning model is inconsistent with the life of the building calibrated in advance for the sample, the coefficient of the machine learning model is adjusted until the life predicted value of the building is consistent with the life of the building calibrated in advance for the sample;
And after the data of all the samples are input into a machine learning model, the obtained life prediction value of the building is consistent with the life of the building calibrated in advance for the data samples, and training is finished.
A base data stream group sample is a sample of a plurality of base data streams historically corresponding to a predetermined period of time acquired by a large number of buildings, respectively. By collecting a sample set of the base data stream group as input of the first learning model, each sample is calibrated in advance by an expert as output of the machine learning model. Then, after the data of all the samples are input into the machine learning model, the obtained life prediction value of the building is consistent with the life of the building calibrated in advance for the samples, and training is finished, so that a trained machine learning model is obtained, and training accuracy can be effectively ensured.
In one embodiment of the present example, referring to fig. 3, after the acquiring the periodic inclinations of the plurality of inclination monitoring positions according to the inclination monitoring image and the acquiring the periodic crack element data of the plurality of crack monitoring positions according to the crack monitoring image, the method further includes:
step S310, when the periodic inclination of a target inclination monitoring position in the periodic inclinations of the plurality of inclination monitoring positions exceeds a preset threshold value, periodic crack element data of the target crack monitoring position related to the target inclination monitoring position is obtained;
Step S320, calculating a first inclination risk value of the target inclination monitoring position on the building and a second inclination risk value of the target crack monitoring position on the building based on a preset building information registry;
step S330, obtaining a risk value of the building according to the periodic inclination of the target inclination monitoring position, the periodic crack element data of the target crack monitoring position, the first inclination risk value and the second inclination risk value.
By acquiring the predetermined threshold value of the inclination early warning at each inclination monitoring position of the target building by calculation in advance by an expert, it is possible to monitor in real time whether or not the inclination of the target inclination monitoring position among the inclinations of the plurality of inclination monitoring positions exceeds the predetermined threshold value. When the inclination of the target inclination monitoring position exceeds a preset threshold value, the inclination condition of the target inclination position is indicated to reach the limit of early warning. The building is inclined in a certain direction due to the collapse of the ground, and then cracks appear at a plurality of positions on the building which are related to the inclined direction when the building is inclined, and as the inclination is larger, the cracks of the building are increased, and finally the building is destroyed. Then by acquiring crack element data of the target crack monitoring position associated with the target inclination monitoring position, the risk value of the building can be accurately calculated in a subsequent step in combination with the inclination of the target inclination monitoring position and the associated crack element data.
The inclination risk value of the target inclination monitoring position on the building is the inclination risk value caused by the geology of the target inclination monitoring position or the target crack monitoring position on the building site, the bearing condition, the current weather condition and the like. The geology of the place where the building is located and the bearing data of the target inclination monitoring position on the building can be accurately obtained from a preset building information registry, meanwhile, the weather condition of the place where the building is located can be obtained in real time through building positioning, and then the first inclination risk value can be accurately calculated by calculating the weighted sum according to the data and the weight of each risk element. Meanwhile, the stress data and the weight thereof of the target crack monitoring position on the building can be accurately obtained from a preset building information registry, and further, the second inclination risk value can be accurately calculated by calculating the weighted sum. In this way, in the subsequent step, the real-time risk value of the building can be accurately obtained by combining the gradient of the target gradient monitoring position, the crack element data of the target crack monitoring position, the first gradient risk value and the second gradient risk value.
The risk value of the building is the risk value of collapse or dumping of the building under the current condition, and the building can be accurately and timely subjected to measures such as personnel evacuation according to the risk value by monitoring the risk value of the building in real time.
According to the gradient of the target gradient monitoring position, the crack element data of the target crack monitoring position, the first gradient risk value and the second gradient risk value, the risk value of the building is obtained by taking each data as a variable of a preset algorithm, and the risk value of the building can be automatically and accurately obtained.
In one embodiment of the present example, the acquiring the risk value of the building according to the periodic inclination of the target inclination monitoring location, the periodic crack element data of the target crack monitoring location, the first inclination risk value and the second inclination risk value includes:
according to the formula w= (X S + Y1T 1+ Yn Tn o+p And acquiring a risk value of the building, wherein W is the risk value of the building, X is a weight corresponding to the periodic inclination, S is the periodic inclination, yn is a weight corresponding to the data of one attribute in the periodic crack element data, O is a first inclination risk value, and P is a second inclination risk value.
In the above empirical formula, x+y1+t1.+ yn+tn can obtain a weighted sum of building risk factor data, and then the sum of o+p is used as an index, so that the influence of the weighted sum can be effectively amplified, and the risk value W of the building can be calculated.
In one embodiment of the present example, the calculating, based on a preset building information registry, a first inclination risk value of the target inclination monitoring position on the building and a second inclination risk value of the target crack monitoring position on the building includes:
acquiring weather data of the building site by positioning the building site;
acquiring first inclination risk data of the target inclination monitoring position from a preset building information registry;
acquiring the first inclination risk value through the weather data and the first inclination risk data;
acquiring second inclination risk data of the target crack monitoring position from a preset building information registry;
and acquiring the second inclination risk value through the weather data and the second inclination risk data.
The weather data of the building site is such data as rainfall and wind power; the first inclination risk data such as geology of the building site and bearing data of the target inclination monitoring position on the building can be accurately obtained from a preset building information registry, meanwhile, weather conditions of the building site can be obtained in real time through building positioning, and then the first inclination risk value can be accurately calculated through weighting sum according to the data and the weight of each risk element. Meanwhile, second inclination risk data such as stress data and weight of the target crack monitoring position on the building can be accurately obtained from a preset building information registry, and further, a second inclination risk value can be accurately calculated by weighting and summing the weather data and the second inclination risk data.
In one embodiment of the present example, the acquiring the periodic crack element data of the target crack monitoring position associated with the target inclination monitoring position when it is monitored that the periodic inclination of the target inclination monitoring position exceeds a predetermined threshold value, includes:
when the regular inclination of the target inclination monitoring position in the regular inclinations of the plurality of inclination monitoring positions exceeds a preset threshold value, acquiring all target crack monitoring positions related to the target inclination monitoring position from a preset monitoring position association relation table;
periodic fracture element data of the plurality of target fracture monitoring locations is obtained.
The method has the advantages that the calculation accuracy can be effectively ensured by acquiring the periodic crack element data of the plurality of target crack monitoring positions at the positions where a plurality of inclination risks possibly occur simultaneously on the building, and the accuracy of building monitoring is further ensured.
The application also provides a risk monitoring device based on machine learning. Referring to fig. 4, the machine learning-based risk monitoring apparatus may include an acquisition module 410, an acquisition module 420, a first generation module 430, a second generation module 440, and a prediction module 450. Wherein:
The acquisition module 410 may be configured to periodically acquire tilt monitoring images of a building through tilt image acquisition devices preset at a plurality of tilt monitoring positions of the building, and periodically acquire crack monitoring images of the building through crack image acquisition devices preset at a plurality of crack monitoring positions of the building;
the acquiring module 420 may be configured to acquire the periodic inclinations of the plurality of inclination monitoring positions according to the inclination monitoring image, and acquire periodic crack element data of the plurality of crack monitoring positions according to the crack monitoring image;
the first generation module 430 may be configured to generate a plurality of input data streams according to the periodic crack element data of the crack monitoring location associated with each of the periodic inclinations and the inclination monitoring location from which the periodic inclination originates;
the second generation module 440 may generate a base data stream from all of the periodic inclinations and all of the periodic fracture element data;
the prediction module 450 may be configured to obtain a predetermined number of input data streams from the plurality of input data streams to form an attack stream, and input an attacked data stream obtained by combining the attack stream with the base data stream into a pre-trained machine learning model to obtain a risk value of the building.
The specific details of each module in the above risk monitoring device based on machine learning have been described in detail in the corresponding risk monitoring method based on machine learning, so that they will not be described herein.
It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit, in accordance with embodiments of the present application. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
Furthermore, although the various steps of the methods herein are depicted in the accompanying drawings in a particular order, this is not required to either suggest that the steps must be performed in that particular order, or that all of the illustrated steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform, etc.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, a mobile terminal, or a network device, etc.) to perform the method according to the embodiments of the present application.
In an exemplary embodiment of the present application, an electronic device capable of implementing the above method is also provided.
Those skilled in the art will appreciate that the various aspects of the invention may be implemented as a system, method, or program product. Accordingly, aspects of the invention may be embodied in the following forms, namely: an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects may be referred to herein as a "circuit," module "or" system.
An electronic device 500 according to such an embodiment of the invention is described below with reference to fig. 5. The electronic device 500 shown in fig. 5 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 5, the electronic device 500 is embodied in the form of a general purpose computing device. The components of electronic device 500 may include, but are not limited to: the at least one processing unit 510, the at least one memory unit 520, and a bus 530 connecting the various system components, including the memory unit 520 and the processing unit 510.
Wherein the storage unit stores program code that is executable by the processing unit 510 such that the processing unit 510 performs steps according to various exemplary embodiments of the present invention described in the above section of the "exemplary method" of the present specification. For example, the processing unit 510 may perform step S110 as shown in fig. 1: the method comprises the steps that an inclined image acquisition device preset at a plurality of inclined monitoring positions of a building is used for periodically acquiring inclined monitoring images of the building, and a crack image acquisition device preset at a plurality of crack monitoring positions of the building is used for periodically acquiring crack monitoring images of the building; s120: acquiring periodic inclinations of the plurality of inclined monitoring positions according to the inclined monitoring images, and acquiring periodic crack element data of the plurality of crack monitoring positions according to the crack monitoring images; step S130: generating a plurality of input data streams from periodic crack element data for each of the periodic inclinations at a crack monitoring location associated with an inclination monitoring location from which each of the periodic inclinations originated; step S140: generating a base data stream according to all the periodic inclinations and all the periodic crack element data; step S150: and obtaining a preset number of input data streams in the plurality of input data streams to form an attack stream, merging the attack stream with the base data stream to obtain an attacked data stream, and inputting the attacked data stream into a pre-trained machine learning model to obtain the risk value of the building.
The storage unit 520 may include readable media in the form of volatile storage units, such as Random Access Memory (RAM) 5201 and/or cache memory unit 5202, and may further include Read Only Memory (ROM) 5203.
The storage unit 520 may also include a program/utility 5204 having a set (at least one) of program modules 5205, such program modules 5205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
Bus 530 may be one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
The electronic device 500 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a client to interact with the electronic device 500, and/or any device (e.g., router, modem, etc.) that enables the electronic device 500 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 550. Also, electronic device 500 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 560. As shown, network adapter 560 communicates with other modules of electronic device 500 over bus 530. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 500, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a usb disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the embodiments of the present application.
In an exemplary embodiment of the present application, a computer readable storage medium is also provided, on which a program product capable of implementing the method described in the present specification is stored. In some possible embodiments, the various aspects of the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the invention as described in the "exemplary methods" section of this specification, when said program product is run on the terminal device.
Referring to fig. 6, a program product 600 for implementing the above-described method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the client computing device, partly on the client device, as a stand-alone software package, partly on the client computing device and partly on a remote computing device or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the client computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
Furthermore, the above-described drawings are only schematic illustrations of processes included in the method according to the exemplary embodiment of the present invention, and are not intended to be limiting. It will be readily appreciated that the processes shown in the above figures do not indicate or limit the temporal order of these processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, for example, among a plurality of modules.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
Claims (8)
1. A risk monitoring method based on machine learning, comprising:
the method comprises the steps that an inclined image acquisition device preset at a plurality of inclined monitoring positions of a building is used for periodically acquiring inclined monitoring images of the building, and a crack image acquisition device preset at a plurality of crack monitoring positions of the building is used for periodically acquiring crack monitoring images of the building;
Acquiring periodic inclinations of the plurality of inclined monitoring positions according to the inclined monitoring images, and acquiring periodic crack element data of the plurality of crack monitoring positions according to the crack monitoring images;
generating a plurality of input data streams from periodic crack element data for each of the periodic inclinations at a crack monitoring location associated with an inclination monitoring location from which each of the periodic inclinations originated;
acquiring periodic crack element data of a target crack monitoring position associated with the target inclination monitoring position when the periodic inclination of the target inclination monitoring position among the periodic inclinations of the plurality of inclination monitoring positions is monitored to exceed a predetermined threshold;
calculating a first inclination risk value of the target inclination monitoring position on the building and a second inclination risk value of the target crack monitoring position on the building based on a preset building information registry;
according to the formula w= (x.s+y.t) o+p Acquiring a risk value of the building, wherein W is the risk value of the building, X is a weight corresponding to the periodic inclination, S is the periodic inclination, Y is a weight corresponding to the data of one attribute in the periodic crack element data, o is a first inclined risk value, and p is a second inclined risk value;
Generating a base data stream according to all the periodic inclinations and all the periodic crack element data;
and obtaining a preset number of input data streams in the plurality of input data streams to form an attack stream, merging the attack stream with the base data stream to obtain an attacked data stream, and inputting the attacked data stream into a pre-trained machine learning model to obtain the risk value of the building.
2. The method of claim 1, wherein the training method of the machine learning model is:
acquiring a sample set of the attacked data stream, wherein each sample is calibrated with a risk value of a corresponding building in advance;
respectively inputting the data of each sample into a machine learning model to obtain a risk value of a building output by the machine learning model;
if the risk value of the building obtained after the data of the sample are input into the machine learning model is inconsistent with the risk value of the building calibrated in advance for the sample, the coefficient of the machine learning model is adjusted until the risk value of the building is consistent with the risk value of the building calibrated in advance for the sample;
after the data of all the samples are input into the machine learning model, the obtained risk value of the building is consistent with the risk value of the building calibrated in advance for the samples, and training is finished.
3. The method of claim 1, wherein after said generating a base data stream from all of said periodic inclinations and all of said periodic fracture element data, the method further comprises:
acquiring a plurality of the base data streams of a preset time period;
and inputting a plurality of the base data streams into a pre-trained second machine learning model together to obtain a life prediction value of the building.
4. The method of claim 1, wherein calculating a first risk of tilting of the target tilt monitoring location on the building and a second risk of tilting of the target crack monitoring location on the building based on a preset building information registry comprises:
acquiring weather data of the building site by positioning the building site;
acquiring first inclination risk data of the target inclination monitoring position from a preset building information registry;
acquiring the first inclination risk value through the weather data and the first inclination risk data;
acquiring second inclination risk data of the target crack monitoring position from a preset building information registry;
And acquiring the second inclination risk value through the weather data and the second inclination risk data.
5. The method of claim 1, wherein the acquiring periodic crack element data of a target crack monitoring location associated with the target tilt monitoring location when the periodic tilt of the target tilt monitoring location among the periodic tilts of the plurality of tilt monitoring locations is monitored to exceed a predetermined threshold comprises:
when the regular inclination of the target inclination monitoring position in the regular inclinations of the plurality of inclination monitoring positions exceeds a preset threshold value, acquiring all target crack monitoring positions related to the target inclination monitoring position from a preset monitoring position association relation table;
periodic fracture element data of the plurality of target fracture monitoring locations is obtained.
6. A risk monitoring device based on machine learning, comprising:
the acquisition module is used for periodically acquiring the inclination monitoring images of the building through inclination image acquisition equipment preset at a plurality of inclination monitoring positions of the building, and periodically acquiring the crack monitoring images of the building through crack image acquisition equipment preset at a plurality of crack monitoring positions of the building;
The acquisition module is used for acquiring the periodic inclinations of the plurality of inclined monitoring positions according to the inclined monitoring images and acquiring periodic crack element data of the plurality of crack monitoring positions according to the crack monitoring images;
a first generation module for generating a plurality of input data streams from periodic crack element data of a crack monitoring location associated with each of the periodic inclinations and an inclination monitoring location from which each of the periodic inclinations originated; acquiring periodic crack element data of a target crack monitoring position associated with the target inclination monitoring position when the periodic inclination of the target inclination monitoring position among the periodic inclinations of the plurality of inclination monitoring positions is monitored to exceed a predetermined threshold; calculating a first inclination risk value of the target inclination monitoring position on the building and a second inclination risk value of the target crack monitoring position on the building based on a preset building information registry; according to the formula w= (x.s+y.t) o+p Acquiring a risk value of the building, wherein W is the risk value of the building, X is a weight corresponding to the periodic inclination, S is the periodic inclination, Y is a weight corresponding to the data of one attribute in the periodic crack element data, o is a first inclined risk value, and p is a second inclined risk value;
The second generation module is used for generating a base data stream according to all the periodic inclination and all the periodic crack element data;
the prediction module is used for acquiring a preset number of input data streams in the plurality of input data streams to form an attack stream, merging the attack stream with the base data stream to obtain an attacked data stream, and inputting the attacked data stream into a pre-trained machine learning model to obtain the risk value of the building.
7. A computer readable storage medium having stored thereon a real time monitoring program of a building, characterized in that the real time monitoring program of a building, when executed by a processor, implements the method of any of claims 1-5.
8. An electronic device, comprising:
a processor; and
the memory is used for storing a real-time monitoring program of the building of the processor; wherein the processor is configured to perform the method of any of claims 1-5 via execution of a real-time monitoring program of the building.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910979638.7A CN110929565B (en) | 2019-10-15 | 2019-10-15 | Risk monitoring method and device based on machine learning, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910979638.7A CN110929565B (en) | 2019-10-15 | 2019-10-15 | Risk monitoring method and device based on machine learning, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110929565A CN110929565A (en) | 2020-03-27 |
| CN110929565B true CN110929565B (en) | 2023-12-22 |
Family
ID=69848991
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910979638.7A Active CN110929565B (en) | 2019-10-15 | 2019-10-15 | Risk monitoring method and device based on machine learning, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110929565B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111457854A (en) * | 2020-04-16 | 2020-07-28 | 福建汇川物联网技术科技股份有限公司 | Deformation monitoring method and device based on building |
| DE102020209509A1 (en) * | 2020-07-28 | 2022-02-03 | Sivantos Pte. Ltd. | Method for error detection in a hearing aid and system |
| CN117162104B (en) * | 2023-11-02 | 2024-01-30 | 泓浒(苏州)半导体科技有限公司 | Transfer mechanical arm installation machine control early warning system and method in ultra-clean environment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104392224A (en) * | 2014-12-04 | 2015-03-04 | 西南交通大学 | Crack detection method for road surface |
| CN106203351A (en) * | 2016-07-13 | 2016-12-07 | 南京工大建设工程技术有限公司 | The method of crack Intelligent Recognition classification |
| CN109726936A (en) * | 2019-01-24 | 2019-05-07 | 辽宁工业大学 | A kind of monitoring method rectified a deviation for tilting ancient masonry pagoda |
| CN110163842A (en) * | 2019-04-15 | 2019-08-23 | 深圳高速工程检测有限公司 | Building cracks detection method, device, computer equipment and storage medium |
| CN110222609A (en) * | 2019-05-24 | 2019-09-10 | 江西理工大学 | A kind of wall body slit intelligent identification Method based on image procossing |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10552914B2 (en) * | 2016-05-05 | 2020-02-04 | Sensormatic Electronics, LLC | Method and apparatus for evaluating risk based on sensor monitoring |
-
2019
- 2019-10-15 CN CN201910979638.7A patent/CN110929565B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104392224A (en) * | 2014-12-04 | 2015-03-04 | 西南交通大学 | Crack detection method for road surface |
| CN106203351A (en) * | 2016-07-13 | 2016-12-07 | 南京工大建设工程技术有限公司 | The method of crack Intelligent Recognition classification |
| CN109726936A (en) * | 2019-01-24 | 2019-05-07 | 辽宁工业大学 | A kind of monitoring method rectified a deviation for tilting ancient masonry pagoda |
| CN110163842A (en) * | 2019-04-15 | 2019-08-23 | 深圳高速工程检测有限公司 | Building cracks detection method, device, computer equipment and storage medium |
| CN110222609A (en) * | 2019-05-24 | 2019-09-10 | 江西理工大学 | A kind of wall body slit intelligent identification Method based on image procossing |
Non-Patent Citations (1)
| Title |
|---|
| 基于机器学习与智能建模的大数据建筑火灾风险预测;曾明杰;;现代物业(中旬刊)(第01期);第45页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110929565A (en) | 2020-03-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110929565B (en) | Risk monitoring method and device based on machine learning, storage medium and electronic equipment | |
| US11555921B2 (en) | Method and apparatus for predicting severe convection weather | |
| CN108830837B (en) | Method and device for detecting steel ladle corrosion defect | |
| CN109118542B (en) | Calibration method, device, equipment and storage medium between laser radar and camera | |
| US11893538B1 (en) | Intelligent system and method for assessing structural damage using aerial imagery | |
| KR101984778B1 (en) | Method for multiple image cooperation on diagnosis exterior wall of structure and apparatus for performing the method | |
| Wang | Automatic checks from 3D point cloud data for safety regulation compliance for scaffold work platforms | |
| US20230005176A1 (en) | Throwing position acquisition method and apparatus, computer device and storage medium | |
| JP7065477B2 (en) | Disaster situation judgment system and disaster judgment flight system | |
| CN113205037B (en) | Event detection method, event detection device, electronic equipment and readable storage medium | |
| CN110705759A (en) | Water level early warning monitoring method and device, storage medium and electronic equipment | |
| CN111914667A (en) | Smoking detection method and device | |
| CN111708687B (en) | Equipment abnormality index determination method, device, equipment and storage medium | |
| KR101910892B1 (en) | IoT based Mobile Smart Solar Power Generation Management System | |
| US11044855B2 (en) | Environmental scanning and tree cutting guidance | |
| CN116597604A (en) | Assembly type intelligent construction site safety early warning system, method, equipment and medium | |
| CN114459531A (en) | Station building structure safety monitoring method and device based on meteorological information and electronic equipment | |
| CN114758296A (en) | Power grid equipment remote monitoring method and system based on VR technology | |
| CN116311770A (en) | House safety early warning system, method and terminal based on Internet of things edge computing gateway | |
| US11900470B1 (en) | Systems and methods for acquiring insurance related informatics | |
| CN114460599A (en) | Station building structure safety monitoring method and device based on laser radar and electronic equipment | |
| CN112665730B (en) | Pre-earthquake temperature anomaly detection method, pre-earthquake temperature anomaly detection device, pre-earthquake temperature anomaly detection equipment and storage medium | |
| CN114821806A (en) | Method and device for determining behavior of operator, electronic equipment and storage medium | |
| CN114418945A (en) | Photovoltaic module hot spot detection method and device | |
| CN114187245A (en) | Video contamination detection method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |