CN116402351A - Alert early warning method, device, equipment and storage medium for guard place - Google Patents
Alert early warning method, device, equipment and storage medium for guard place Download PDFInfo
- Publication number
- CN116402351A CN116402351A CN202310403167.1A CN202310403167A CN116402351A CN 116402351 A CN116402351 A CN 116402351A CN 202310403167 A CN202310403167 A CN 202310403167A CN 116402351 A CN116402351 A CN 116402351A
- Authority
- CN
- China
- Prior art keywords
- information
- space
- label
- model
- units
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000013145 classification model Methods 0.000 claims abstract description 37
- 238000002372 labelling Methods 0.000 claims description 49
- 238000004590 computer program Methods 0.000 claims description 6
- 101710154918 Trigger factor Proteins 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 230000006399 behavior Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 9
- 238000007689 inspection Methods 0.000 description 8
- 230000002159 abnormal effect Effects 0.000 description 7
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 102000016550 Complement Factor H Human genes 0.000 description 2
- 108010053085 Complement Factor H Proteins 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007654 immersion Methods 0.000 description 1
- 230000005389 magnetism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Alarm Systems (AREA)
Abstract
The application relates to a guard place warning condition early warning method, a device, equipment and a storage medium, which are applied to the field of risk early warning, wherein the method comprises the following steps: acquiring space information of a protection place; constructing a three-dimensional space model of the protection place according to the size information, and dividing the three-dimensional space model according to a preset dividing rule to obtain a plurality of space units; acquiring personnel role information corresponding to a protection place and distribution information of an Internet of things sensing unit in the protection place; determining model sample factors of a plurality of space units according to the position information, the personnel performance information and the distribution information of the internet of things sensing units; taking a model sample factor as an input sample, and constructing a multi-label classification model by using an XGBoost method; and correspondingly acquiring and outputting multi-label risk probabilities corresponding to the plurality of space units according to the multi-label classification model. The technical effect that this application had is: the police situation eliminating effect in important protection places is improved.
Description
Technical Field
The application relates to the technical field of risk early warning, in particular to a guard place warning condition early warning method, device and equipment and a storage medium.
Background
For some important protection places with protection requirements on fire prevention, water prevention or anti-creeping police, such as a data machine room, an equipment machine room and the like, in order to ensure the safety of the important protection places, the police in the places need to be removed in time.
In the prior art, the process of eliminating the police situation in the place mainly depends on manual timing inspection, and the inside of the place is monitored in real time by utilizing an Internet of things sensing unit such as a temperature sensor, a humidity sensor and the like.
However, the manual timing inspection mode is inevitably free from an inspection blank period, and the mode of monitoring by using the internet of things sensing unit is false alarm, so that the alarm condition in the important protection place is poor in elimination effect.
Disclosure of Invention
In order to help to promote the effect of eliminating the police conditions in important protection places, the method, the device, the equipment and the storage medium for warning the police conditions in the protection places are provided.
In a first aspect, the present application provides a warning method for a guard site, which adopts the following technical scheme: the method comprises the following steps:
acquiring space information of a protection place, wherein the space information comprises size information and position information corresponding to the protection place;
constructing a three-dimensional space model of the protection place according to the size information, and dividing the three-dimensional space model according to a preset dividing rule to obtain a plurality of space units;
acquiring personnel role information corresponding to a protection place and distribution information of an Internet of things sensing unit in the protection place;
determining model sample factors of a plurality of space units according to the position information, the personnel performing information and the distribution information of the internet of things sensing units;
taking the model sample factors as input samples, and constructing a multi-label classification model by using an XGBoost method;
and correspondingly acquiring and outputting multi-label risk probabilities corresponding to a plurality of space units according to the multi-label classification model.
In a specific embodiment, the model sample factors include a geographic information factor, a meteorological condition factor, a performance behavior factor, a risk trigger factor, and a location point habit factor;
the determining model sample factors of a plurality of space units according to the position information, the personnel performing information and the distribution information of the internet of things sensing units comprises:
determining the geographic information factor based on the location information;
inquiring weather information corresponding to the position information based on the position information correspondence, and setting the weather information as a weather condition factor;
determining the performance factor based on the performance completion condition in the personnel performance information;
and correspondingly determining risk triggering factors and position point habit factors in the space unit based on the distribution information of the internet of things sensing unit.
In a specific embodiment, the weather information includes an actual weather condition corresponding to the current date and an expected weather condition within a preset time.
In a specific embodiment, the constructing the multi-label classification model by using the XGBoost method with the model sample factor as an input sample includes:
marking the input samples conforming to the marking rules according to the preset marking rules to obtain marked samples;
training unlabeled samples by using an XGBoost method according to the labeled samples;
and constructing a multi-label classification model according to the training result and the marked sample.
In a specific embodiment, the method further comprises:
when the labeling information fed back by the user is obtained, comparing the labeling information fed back by the user with the labeling information corresponding to the labeling rule;
and if the labeling information corresponding to the labeling rule does not contain the labeling information fed back by the user, adding the labeling information fed back by the user into the labeling rule.
In a specific embodiment, the obtaining and outputting the multi-label risk probabilities corresponding to the plurality of space units according to the multi-label classification model includes:
correspondingly acquiring multi-label risk probabilities corresponding to a plurality of space units according to the multi-label classification model;
inquiring an output preference format preset by a user, wherein the output preference format comprises a space unit format and a stereoscopic space format;
if the output preference format is a space unit format, outputting multi-label risk probabilities corresponding to a plurality of space units;
if the output preference format is a three-dimensional space format, calculating the average value of the multi-label risk probabilities corresponding to a plurality of space units; and outputting an average value of the multi-label risk probabilities.
In a specific embodiment, the calculating the average value of the multi-tag risk probabilities corresponding to the plurality of spatial units includes:
and eliminating the multi-label risk probability outside a preset reasonable range, and calculating the average value of the multi-label risk probabilities corresponding to a plurality of residual space units after elimination.
In a second aspect, the present application provides a warning device for warning conditions in a protected place, which adopts the following technical scheme: the device comprises:
the space information acquisition module is used for acquiring space information of a protection place, wherein the space information comprises size information and position information corresponding to a place space;
the space unit dividing module is used for constructing a three-dimensional space model of the protection place according to the size information, and dividing the three-dimensional space model according to a preset dividing rule to obtain a plurality of space units;
the distribution information acquisition module is used for acquiring personnel role information corresponding to the protection place and distribution information of the Internet of things sensing unit in the protection place;
the sample factor determining module is used for determining model sample factors of a plurality of space units according to the position information, the personnel performance information and the distribution information of the internet of things sensing units;
the label model construction module is used for constructing a multi-label classification model by using the model sample factors as input samples and using an XGBoost method;
and the risk probability output module is used for correspondingly acquiring and outputting multi-label risk probabilities corresponding to the plurality of space units according to the multi-label classification model.
In a third aspect, the present application provides a computer device, which adopts the following technical scheme: the system comprises a memory and a processor, wherein the memory is stored with a computer program which can be loaded by the processor and execute any guard place warning situation early warning method.
In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical solutions: a computer program capable of being loaded by a processor and executing any one of the guard site warning situation early warning methods is stored.
In summary, the present application has the following beneficial technical effects:
detecting and calculating the risk probabilities of different space units in the protected place in real time by utilizing a mode of constructing a multi-label classification model, namely, the risk probabilities of different positions in the protected place; the user can intuitively know the overall risk probability in the protected place or the risk probability corresponding to each space unit in the protected place in real time according to the needs; meanwhile, in the process of calculating the risk probability in the protected space, the positions of different Internet of things sensing units in the protected space and the geographic position of the protected place are comprehensively considered, and the recent weather conditions of the protected place and the completion conditions of personnel inspection track in the current protected place are considered, so that a user can accurately know the risk conditions in the current protected place according to the idle probabilities of multiple labels and the like corresponding to the protected space, and the possibility of false alarm conditions when the inside of the protected place is monitored by only relying on the Internet of things sensing units such as a temperature sensor, a humidity sensor and the like is reduced; thereby improving the police situation eliminating effect in the important protection places.
Drawings
Fig. 1 is a schematic system architecture diagram of a central office security monitoring center according to an embodiment of the present application.
Fig. 2 is a flowchart of a method for warning a warning situation in a protected location in an embodiment of the present application.
Fig. 3 is a schematic diagram of construction and output of a multi-label classification model in an embodiment of the present application.
Fig. 4 is a block diagram of a warning device in a protected place according to an embodiment of the present application.
Fig. 5 is a block diagram of a warning device for a guard site according to another embodiment of the present application.
Reference numerals: 401. a spatial information acquisition module; 402. a space unit dividing module; 403. a distribution information acquisition module; 404. a sample factor determination module; 405. a label model building module; 406. a risk probability output module; 407. and a labeling rule updating module.
Detailed Description
The present application is described in further detail below in conjunction with figures 1-5.
The embodiment of the application discloses a warning condition early warning method for a protected place, which is applied to a machine room safety monitoring center as shown in fig. 1, and detection information of an internet of things sensing unit such as a temperature sensor, a humidity sensor, a smoke alarm and the like in the machine room is transmitted back to the machine room safety monitoring center in real time; a manager of the machine room can establish a link with a machine room safety monitoring center through an intelligent terminal such as a mobile phone or a computer, and the machine room safety monitoring center can transmit an alarm analysis result in the machine room to the intelligent terminal of the manager in real time; meanwhile, the manager can set and adjust the monitoring data of the machine room safety monitoring center through the intelligent terminal.
As shown in fig. 2, the method specifically includes the following steps:
s10, acquiring space information of a protection place.
The space information comprises size information and position information corresponding to the protection place; specifically, the size information is length, width and height of the interior of the machine room space; the position information is the geographic position of the machine room; the size information and the location information may be input by a manager using the smart terminal.
S20, constructing a three-dimensional space model according to the space information.
Specifically, when receiving space information input by a user through an intelligent terminal, a machine room safety monitoring center firstly builds a three-dimensional space model corresponding to a protection space according to size information in the space information, and then divides the three-dimensional space model according to a preset division rule to obtain a plurality of space units Pos; wherein, the preset dividing rule is preset by a manager; for example, the stereoscopic space model is divided into N space units of uniform size in order from left to right and from top to bottom, and the size of the space units is generally not more than one cubic meter.
S30, acquiring personnel role information corresponding to the protection place and distribution information of the Internet of things sensing unit.
The personnel performing information refers to the condition of the machine room patrol personnel in the machine room; specifically, a manager of the machine room can preset an item to be inspected in the machine room to form a staff-carrying table, the inspector inspects and inspects the interior of the machine room according to the staff-carrying table, the inspection and inspection conditions are faithfully fed back to the manager, then the manager can obtain staff-carrying information corresponding to the machine room according to the completion condition of the staff-carrying table of the inspector, and the staff-carrying information is input to a machine room safety monitoring center by utilizing an intelligent terminal; the distribution information of the internet of things sensing unit, namely the specific positions of all sensors in the machine room, is recorded into the machine room safety monitoring center by a manager according to the actual distribution condition of the internet of things sensing unit.
S40, determining model sample factors of a plurality of space units.
Specifically, the machine room safety monitoring center determines model sample factors corresponding to a plurality of space units according to position information corresponding to a protection place, personnel performance information and distribution information of the internet of things sensing units.
In one embodiment, the model sample factors include, in particular, a geographic information factor G, a meteorological condition factor Q, a performance behavior factor E, a risk trigger factor W, and a location point habit factor H.
Specifically, the geographic information factor G may be determined according to the location information corresponding to the protected location, where the geographic information factor is a climate feature corresponding to the current geographic location, such as dryness, wetness, a larger temperature difference, and the like; the weather condition factor Q is weather information corresponding to the current geographic position, the geographic position of the protected place can be determined according to the position information of the protected place, then the weather information corresponding to the geographic position is queried in a networking manner, and the weather information is the weather information given by the weather forecast; for example, precipitation, snowfall, cooling, warming, typhoons, and the like; setting the queried weather condition as a meteorological condition factor Q; further, the queried weather information may include an actual weather condition corresponding to the current date and an expected weather condition within a preset time, for example, weather conditions within 10 days currently and subsequently; the caterpillar action factors E are respectively and correspondingly determined according to the caterpillar completion conditions recorded by the manager; specifically, the completion condition of the caterpillar corresponding to each space unit is that the caterpillar is up to standard, and the completion condition of the caterpillar is that the caterpillar is not up to standard; the risk triggering factors W and the position point habit factors H are determined according to the specific distribution information of the internet of things sensing unit, wherein the risk triggering factors W comprise temperature, humidity, water immersion, door magnetism, geomagnetism, a mains supply state, wire temperature and the like, namely detection attributes corresponding to the internet of things sensing unit; the position point habit factor H is determined by the specific position of the space unit, and comprises easy water accumulation, earthquake, power failure, typhoon, strong cooling and the like; in general, the position of the internet of things sensing unit illustrates the position point habit factors corresponding to the position; for example, the position where the temperature sensor is provided is usually a position where high temperature is feared.
S50, constructing a multi-label classification model by taking the model sample factors as input samples.
Specifically, after model sample factors of a plurality of space units are determined, a machine room safety monitoring center uses the determined model sample factors as input samples, and a multi-label classification model is built by using an XGBoost method; i.e. the input samples x= (Pos, Q, G, E, W, H).
In one embodiment, in connection with fig. 3, the step of constructing a multi-label classification model using the XGBoost method may be specifically performed as:
firstly, marking an input sample conforming to a marking rule according to a preset marking rule by a machine room safety monitoring center to obtain a marked sample; the preset labeling rules are input into a machine room safety monitoring center through an intelligent terminal in advance by a manager; and then the machine room safety monitoring center trains the unlabeled samples by using an XGBoost method according to the labeled samples, and a multi-label classification model is constructed by comprehensively training the training results obtained after the training and the labeled samples. And in the process of obtaining the multi-label classification model, one part of the multi-label classification model is automatically labeled according to the labeling rule, and the other part of the multi-label classification model is obtained after training according to labeled samples, so that the objectivity and the reliability of the multi-label classification model are improved.
S60, correspondingly acquiring and outputting multi-label risk probabilities corresponding to a plurality of space units according to the multi-label classification model.
Specifically, the machine room safety monitoring center can correspondingly acquire multi-label risk probabilities corresponding to a plurality of space units according to the constructed multi-label classification model; and then the machine room safety detection center outputs the acquired multi-label risk probability according to an output preference format preset by a manager.
In one embodiment, the output preference format includes a spatial unit format and a stereoscopic spatial format; the output preference form is preset by a manager through the intelligent terminal according to the need; the step of correspondingly acquiring and outputting the multi-label risk probabilities corresponding to the plurality of spatial units according to the multi-label classification model may be specifically performed as:
firstly, a machine room safety monitoring center correspondingly acquires multi-label risk probabilities corresponding to a plurality of space units according to a multi-label classification model, and then inquires an output preference format preset by a manager; if the preset output preference format is a space unit format, directly outputting the multi-label risk probabilities corresponding to a plurality of space units to the intelligent terminal of the manager so that the manager can know the risk probability condition corresponding to each space unit; if the preset output preference format is a three-dimensional space format, calculating an average value of multi-label risk probabilities corresponding to a plurality of space units, and then outputting the calculated average value to an intelligent terminal of a manager as the risk probability of the whole three-dimensional space so that the manager can integrally learn the risk probability condition in the machine room.
Further, in one embodiment, to reduce the impact of outlier data on the risk probability of the volume; the step of calculating, by the machine room security monitoring center, an average value of multi-label risk probabilities corresponding to the plurality of space units may be specifically performed as:
after the multi-label risk probabilities corresponding to a plurality of space units are obtained, the machine room safety monitoring center firstly eliminates the multi-label risk probabilities outside a preset reasonable range, and then calculates the average value of the multi-label risk probabilities corresponding to the rest space units after elimination; the preset reasonable range can be 0-100%, so that the effect of eliminating abnormal data when the risk probability of the three-dimensional space is calculated is achieved, and the reliability and accuracy of the risk probability of the three-dimensional space are improved.
The warning method for the guard site utilizes a mode of constructing a multi-label classification model to detect and calculate the risk probabilities of different space units in the guard site in real time, namely the risk probabilities of different positions in the guard site; the user can intuitively know the overall risk probability in the protected place or the risk probability corresponding to each space unit in the protected place in real time according to the needs; meanwhile, in the process of calculating the risk probability in the protected space, the positions of different Internet of things sensing units in the protected space and the geographic position of the protected place are comprehensively considered, and the recent weather conditions of the protected place and the completion conditions of personnel inspection track in the current protected place are considered, so that a manager can accurately know the risk conditions in the current protected place according to the multi-label risk probability corresponding to the protected space, and the possibility of false alarm conditions when the inside of the protected place is monitored by simply relying on the Internet of things sensing units such as a temperature sensor, a humidity sensor and the like is reduced; thereby improving the police situation eliminating effect in the important protection places.
It should be noted that: the reason for the false alarm condition in the mode of monitoring by using the internet of things sensing unit in the prior art is that the abnormal detection result of a single sensor is sometimes difficult to directly show the reason for the abnormal condition; for example, when a water leakage condition occurs in the machine room, the humidity sensor detects the abnormal humidity in the machine room due to the water leakage of the machine room, but according to the phenomenon that the humidity sensor detects the abnormal humidity, the reason that the abnormal humidity cannot be deduced uniquely is caused by the water leakage condition occurring in the machine room, and then the risk early warning and the actual risk condition given by the internet of things sensing unit are caused to come in and go out, namely the risk fed back by the humidity sensor is the abnormal humidity, and the actual risk is water leakage; according to the technical scheme, when the risk probability condition of the inside of the machine room is given, the positions of different Internet of things sensing units in the protection space, the geographic position of the protection place, the recent weather condition of the protection place, the completion condition of personnel inspection on the track in the current protection place and other factors are comprehensively considered, so that the possibility of false alarm condition is reduced when the inside of the protection place is monitored by simply relying on the Internet of things sensing units such as a temperature sensor, a humidity sensor and the like; thereby improving the police situation eliminating effect in the important protection places.
In one embodiment, the preset labeling information is updated in time; the warning method for the alert condition of the protected place can further comprise the following execution steps:
the manager can feed back specific labeling information to the machine room safety monitoring center by utilizing the intelligent terminal according to actual conditions, when the machine room safety monitoring center receives the labeling information fed back by the manager, the received labeling information is firstly compared with the labeling information corresponding to the preset labeling rule, and if the labeling information corresponding to the labeling rule contains the labeling information fed back by a user, the fed-back labeling information is not processed; if the corresponding labeling information in the labeling rules does not contain the labeling information fed back by the user, the labeling information fed back by the user is added into the preset labeling rules, so that the labeling rules are updated, and the labeling rules can be more adapted to the actual conditions of the current machine room along with continuous use.
Fig. 2 is a flow chart of a method for warning a warning situation in a protected location according to an embodiment. It should be understood that, although the steps in the flowchart of fig. 2 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows; the steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders; and at least some of the steps in fig. 2 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the other steps or sub-steps of other steps.
Based on the method, the embodiment of the application also discloses a warning device for the warning situation of the protected place.
As shown in fig. 4, the apparatus includes the following modules:
a space information obtaining module 401, configured to obtain space information of a protected place, where the space information includes size information and position information corresponding to a place space;
the space unit dividing module 402 is configured to construct a three-dimensional space model of the protection place according to the size information, and divide the three-dimensional space model according to a preset dividing rule to obtain a plurality of space units;
the distribution information obtaining module 403 is configured to obtain personnel performance information corresponding to the protection place and distribution information of the internet of things sensing unit in the protection place;
the sample factor determining module 404 is configured to determine model sample factors of a plurality of space units according to the location information, the staff performance information and the distribution information of the internet of things sensing units;
the label model building module 405 is configured to build a multi-label classification model by using an XGBoost method with a model sample factor as an input sample;
and the risk probability output module 406 is configured to correspondingly acquire and output multi-label risk probabilities corresponding to the plurality of space units according to the multi-label classification model.
In one embodiment, the model sample factors include a geographic information factor, a meteorological condition factor, a performance factor, a risk trigger factor, and a location point habit factor; the spatial information acquisition module 401 is specifically configured to determine a geographic information factor based on the location information; inquiring weather information corresponding to the position information based on the position information correspondence, and setting the weather information as a weather condition factor; determining a performance factor based on performance completion conditions in the personnel performance information; and correspondingly determining risk triggering factors and position point habit factors in the space units based on the distribution information of the internet of things sensing units.
In one embodiment, the weather information includes the actual weather condition corresponding to the current date and the predicted weather condition for the preset time.
In one embodiment, the label model building module 405 is specifically configured to label an input sample according to a preset labeling rule to obtain a labeled sample; training unlabeled samples by using an XGBoost method according to the labeled samples; and constructing a multi-label classification model according to the training result and the marked sample.
In one embodiment, referring to fig. 5, the alert early warning device in the protected place further includes a labeling rule updating module 407, configured to compare labeling information fed back by the user with labeling information corresponding to the labeling rule when labeling information fed back by the user is obtained; if the corresponding labeling information in the labeling rule does not contain the labeling information fed back by the user, the labeling information fed back by the user is added into the labeling rule.
In one embodiment, the risk probability output module 406 is specifically configured to obtain, according to the multi-tag classification model correspondence, multi-tag risk probabilities corresponding to a plurality of spatial units; inquiring a preset output preference format, wherein the output preference format comprises a space unit format and a three-dimensional space format; if the output preference format is a space unit format, outputting multi-label risk probabilities corresponding to a plurality of space units; if the output preference format is a three-dimensional space format, calculating the average value of the multi-label risk probabilities corresponding to a plurality of space units; and outputting an average value of the risk probabilities of the multiple labels.
In one embodiment, the risk probability output module 406 is further configured to reject multi-tag risk probabilities that are outside a preset reasonable range, and calculate an average value of the multi-tag risk probabilities corresponding to the plurality of spatial units remaining after the rejection.
The embodiment of the application also discloses a computer device.
Specifically, the computer device comprises a memory and a processor, wherein the memory stores a computer program which can be loaded by the processor and execute the guard place warning situation early warning method.
The embodiment of the application also discloses a computer readable storage medium.
Specifically, the computer readable storage medium stores a computer program that can be loaded by a processor and execute the guard place warning situation early warning method as described above, and includes, for example: a U-disk, a removable hard disk, a Read-only memory (ROM), a random access memory (RandomAccessMemory, RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
The present embodiment is only for explanation of the present invention and is not to be construed as limiting the present invention, and modifications to the present embodiment, which may not creatively contribute to the present invention as required by those skilled in the art after reading the present specification, are all protected by patent laws within the scope of claims of the present invention.
Claims (10)
1. The warning method for the warning condition of the protected place is characterized by comprising the following steps:
acquiring space information of a protection place, wherein the space information comprises size information and position information corresponding to the protection place;
constructing a three-dimensional space model of the protection place according to the size information, and dividing the three-dimensional space model according to a preset dividing rule to obtain a plurality of space units;
acquiring personnel role information corresponding to a protection place and distribution information of an Internet of things sensing unit in the protection place;
determining model sample factors of a plurality of space units according to the position information, the personnel performing information and the distribution information of the internet of things sensing units;
taking the model sample factors as input samples, and constructing a multi-label classification model by using an XGBoost method;
and correspondingly acquiring and outputting multi-label risk probabilities corresponding to a plurality of space units according to the multi-label classification model.
2. The method of claim 1, wherein the model sample factors include a geographic information factor, a meteorological condition factor, a performance behavior factor, a risk trigger factor, and a location point habit factor;
the determining model sample factors of a plurality of space units according to the position information, the personnel performing information and the distribution information of the internet of things sensing units comprises:
determining the geographic information factor based on the location information;
inquiring weather information corresponding to the position information based on the position information correspondence, and setting the weather information as a weather condition factor;
determining the performance factor based on the performance completion condition in the personnel performance information;
and correspondingly determining risk triggering factors and position point habit factors in the space unit based on the distribution information of the internet of things sensing unit.
3. The method of claim 2, wherein the weather information includes an actual weather condition corresponding to the current date and an expected weather condition for a preset time.
4. The method of claim 1, wherein constructing the multi-label classification model using XGBoost method using the model sample factor as an input sample comprises:
marking the input samples conforming to the marking rules according to the preset marking rules to obtain marked samples;
training unlabeled samples by using an XGBoost method according to the labeled samples;
and constructing a multi-label classification model according to the training result and the marked sample.
5. The method according to claim 4, wherein the method further comprises:
when the labeling information fed back by the user is obtained, comparing the labeling information fed back by the user with the labeling information corresponding to the labeling rule;
and if the labeling information corresponding to the labeling rule does not contain the labeling information fed back by the user, adding the labeling information fed back by the user into the labeling rule.
6. The method of claim 1, wherein the correspondingly acquiring and outputting multi-tag risk probabilities corresponding to a number of the spatial units according to the multi-tag classification model comprises:
correspondingly acquiring multi-label risk probabilities corresponding to a plurality of space units according to the multi-label classification model;
inquiring an output preference format preset by a user, wherein the output preference format comprises a space unit format and a stereoscopic space format;
if the output preference format is a space unit format, outputting multi-label risk probabilities corresponding to a plurality of space units;
if the output preference format is a three-dimensional space format, calculating the average value of the multi-label risk probabilities corresponding to a plurality of space units; and outputting an average value of the multi-label risk probabilities.
7. The method of claim 6, wherein calculating an average of the multi-tag risk probabilities for the number of spatial units comprises:
and eliminating the multi-label risk probability outside a preset reasonable range, and calculating the average value of the multi-label risk probabilities corresponding to a plurality of residual space units after elimination.
8. A guard site alert warning device, the device comprising:
a space information acquisition module (401) for acquiring space information of a protected place, wherein the space information comprises size information and position information corresponding to a place space;
the space unit dividing module (402) is used for constructing a three-dimensional space model of the protection place according to the size information, and dividing the three-dimensional space model according to a preset dividing rule to obtain a plurality of space units;
the distributed information acquisition module (403) is used for acquiring personnel performance information corresponding to the protection place and distributed information of the internet of things sensing unit in the protection place;
the sample factor determining module (404) is used for determining model sample factors of a plurality of space units according to the position information, the personnel performing information and the distribution information of the internet of things sensing units;
the label model construction module (405) is used for constructing a multi-label classification model by using the model sample factors as input samples and using an XGBoost method;
and the risk probability output module (406) is used for correspondingly acquiring and outputting multi-label risk probabilities corresponding to the plurality of space units according to the multi-label classification model.
9. A computer device comprising a memory and a processor, the memory having stored thereon a computer program capable of being loaded by the processor and performing the method according to any of claims 1 to 7.
10. A computer readable storage medium, characterized in that a computer program is stored which can be loaded by a processor and which performs the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310403167.1A CN116402351A (en) | 2023-04-14 | 2023-04-14 | Alert early warning method, device, equipment and storage medium for guard place |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310403167.1A CN116402351A (en) | 2023-04-14 | 2023-04-14 | Alert early warning method, device, equipment and storage medium for guard place |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116402351A true CN116402351A (en) | 2023-07-07 |
Family
ID=87010207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310403167.1A Pending CN116402351A (en) | 2023-04-14 | 2023-04-14 | Alert early warning method, device, equipment and storage medium for guard place |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116402351A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202472841U (en) * | 2011-12-19 | 2012-10-03 | 南京农业大学 | Forest fire monitoring and early warning system based on IOT |
| WO2019036924A1 (en) * | 2017-08-22 | 2019-02-28 | 深圳企管加企业服务有限公司 | Machine room device fault early-warning system based on internet of things |
| CN111178828A (en) * | 2019-12-18 | 2020-05-19 | 北京明略软件系统有限公司 | Method and system for building fire safety early warning |
| CN113222420A (en) * | 2021-05-18 | 2021-08-06 | 上海城建信息科技有限公司 | Intelligent sensing monitoring and early warning system for operation of underground complex |
| CN113673748A (en) * | 2021-07-26 | 2021-11-19 | 浙江大华技术股份有限公司 | Fire prediction method, XGboost model training method and related equipment |
| CN115531787A (en) * | 2022-10-09 | 2022-12-30 | 江苏蓝盾消防技术服务有限公司 | Wisdom fire extinguishing system based on internet of things |
-
2023
- 2023-04-14 CN CN202310403167.1A patent/CN116402351A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202472841U (en) * | 2011-12-19 | 2012-10-03 | 南京农业大学 | Forest fire monitoring and early warning system based on IOT |
| WO2019036924A1 (en) * | 2017-08-22 | 2019-02-28 | 深圳企管加企业服务有限公司 | Machine room device fault early-warning system based on internet of things |
| CN111178828A (en) * | 2019-12-18 | 2020-05-19 | 北京明略软件系统有限公司 | Method and system for building fire safety early warning |
| CN113222420A (en) * | 2021-05-18 | 2021-08-06 | 上海城建信息科技有限公司 | Intelligent sensing monitoring and early warning system for operation of underground complex |
| CN113673748A (en) * | 2021-07-26 | 2021-11-19 | 浙江大华技术股份有限公司 | Fire prediction method, XGboost model training method and related equipment |
| CN115531787A (en) * | 2022-10-09 | 2022-12-30 | 江苏蓝盾消防技术服务有限公司 | Wisdom fire extinguishing system based on internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112684133B (en) | Water quality monitoring and early warning method and system based on big data platform and storage medium | |
| CN204315055U (en) | Based on the underground cable monitor and early warning system of Internet of Things | |
| CN105513052A (en) | Refrigerator food storage and deterioration information detection system and method | |
| CN113671886B (en) | Fire safety monitoring method and system based on 5G | |
| CN114446020B (en) | Linkage early warning management method, system, storage medium and equipment | |
| CN113192283B (en) | Wireless fire early warning system with multi-sensor information fusion | |
| CN107632132A (en) | A kind of water quality monitoring warning system with forecast function | |
| CN113359637A (en) | Data quality guarantee system and method based on station house operation environment and equipment operation state | |
| CN117458722B (en) | Data monitoring method and system based on electric power energy management system | |
| CN117039850A (en) | Abnormal electricity consumption analysis method and system based on space-time ground feature characteristics | |
| CN116740883A (en) | Security monitoring alarm system based on cloud computing | |
| CN104517422A (en) | Underground cable monitoring pre-alarm system based on Internet of Things | |
| CN108267170B (en) | Environment monitoring method and device | |
| CN212433949U (en) | Electric energy meter with working environment detection function | |
| CN117093943A (en) | Power consumption monitoring and early warning method and device | |
| CN116311829B (en) | Remote alarm method and device for data machine room | |
| CN116402351A (en) | Alert early warning method, device, equipment and storage medium for guard place | |
| CN108241183A (en) | Wind data method and anemometer tower centralized management device are surveyed in centralized management | |
| CN112149770A (en) | Data radio frequency identification display system, method and device of intelligent cable | |
| CN115862296A (en) | Fire risk early warning method, system, equipment and medium for railway construction site | |
| CN101923605B (en) | Wind pre-warning method for railway disaster prevention | |
| US20210372647A1 (en) | Method and system for automatic detection of malfunctions/inefficient household electronic heating device | |
| CN115187880A (en) | Communication optical cable defect detection method and system based on image recognition and storage medium | |
| KR20160026492A (en) | Anomaly detection method using confidence interval estimation based on time series analysis | |
| CN115208053A (en) | Abnormity warning method, abnormity warning device, computer 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 |