CN116402351A - Method, device, equipment and storage medium for early warning of alarm situation in protective place - Google Patents
Method, device, equipment and storage medium for early warning of alarm situation in protective placeDownload PDFInfo
- Publication number
- CN116402351A CN116402351ACN202310403167.1ACN202310403167ACN116402351ACN 116402351 ACN116402351 ACN 116402351ACN 202310403167 ACN202310403167 ACN 202310403167ACN 116402351 ACN116402351 ACN 116402351A
- Authority
- CN
- China
- Prior art keywords
- information
- label
- spatial
- units
- model
- 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
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; 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
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本申请涉及风险预警的技术领域，尤其是涉及一种防护场所警情预警方法、装置、设备及存储介质。The present application relates to the technical field of risk early warning, and in particular to a method, device, equipment and storage medium for early warning of alarm conditions in protected places.
背景技术Background technique
对于一些对防火、防水或者防漏电等警情有防护需求的重要防护场所，例如数据机房、设备机房等，为了保障重要防护场所的安全，需要及时对场所内的警情进行排除。For some important protection places that require protection against fire, water, or electric leakage, such as data computer rooms, equipment rooms, etc., in order to ensure the safety of important protection places, it is necessary to eliminate the police situations in the place in time.
现有技术中对场所内警情进行排除的过程主要依赖人工定时巡检，以及利用温度传感器、湿度传感器等物联感知单元对场所内部进行实时监测。In the prior art, the process of eliminating the police situation in the place mainly relies on manual regular inspections, and real-time monitoring of the inside of the place by using IoT sensing units such as temperature sensors and humidity sensors.
然而，人工定时巡检的方式难免存在巡检空白期，而利用物联感知单元进行监测的方式则存在误报警的情况，导致重点防护场所内部的警情排除效果较差。However, the method of manual scheduled inspection inevitably has a blank period of inspection, while the method of monitoring using the IoT sensing unit has false alarms, resulting in poor alarm elimination effect in key protection places.
发明内容Contents of the invention
为了有助于提升重点防护场所内部的警情排除效果，本申请提供的一种防护场所警情预警方法、装置、设备及存储介质。In order to help improve the effect of eliminating alarms in key protection places, the application provides a method, device, equipment and storage medium for warning warnings of polices in a protection place.
第一方面，本申请提供一种防护场所警情预警方法，采用如下的技术方案：所述方法包括：In the first aspect, the present application provides a method for early warning of police situations in protected places, and adopts the following technical solution: the method includes:
获取防护场所的空间信息，所述空间信息包括与防护场所对应的尺寸信息及位置信息；Obtaining the spatial information of the protected place, the spatial information including size information and location information corresponding to the protected place;
根据所述尺寸信息构建所述防护场所的立体空间模型，根据预设的划分规则对所述立体空间模型进行划分得到若干空间单元；Constructing a three-dimensional space model of the protective site according to the size information, and dividing the three-dimensional space model according to preset division rules to obtain several space units;
获取与防护场所对应的人员履职信息以及防护场所内的物联感知单元的分布信息；Obtain the personnel performance information corresponding to the protective place and the distribution information of the IoT sensing units in the protective place;
分别根据所述位置信息、人员履职信息以及物联感知单元的分布信息确定若干所述空间单元的模型样本因子；Determining model sample factors of several spatial units according to the location information, personnel performance information and distribution information of IoT sensing units respectively;
以所述模型样本因子为输入样本，利用XGBoost方法构建多标签分类模型；Taking the model sample factor as an input sample, using the XGBoost method to construct a multi-label classification model;
根据所述多标签分类模型对应获取并输出与若干所述空间单元对应的多标签风险概率。According to the multi-label classification model, multi-label risk probabilities corresponding to several spatial units are correspondingly acquired and output.
在一个具体的可实施方案中，所述模型样本因子包括地理信息因子、气象条件因子、履职行为因子、风险触发因子以及位置点习惯因子；In a specific implementation, the model sample factors include geographic information factors, weather condition factors, performance behavior factors, risk trigger factors and location point habit factors;
所述根据所述位置信息，人员履职信息以及物联感知单元的分布信息确定若干所述空间单元的模型样本因子包括：The determining of the model sample factors of several spatial units based on the location information, personnel performance information and distribution information of IoT sensing units includes:
基于所述位置信息确定所述地理信息因子；determining the geographic information factor based on the location information;
基于所述位置信息对应查询与所述位置信息对应的天气信息，将所述天气信息设置为气象条件因子；Querying weather information corresponding to the location information based on the location information, and setting the weather information as a meteorological condition factor;
基于所述人员履职信息中的履职完成情况确定所述履职行为因子；Determining the duty performance factor based on the performance completion status in the personnel performance information;
基于所述物联感知单元的分布信息对应确定所述空间单元内的风险触发因子及位置点习惯因子。Based on the distribution information of the sensing unit of the Internet of Things, the risk trigger factor and the location point habit factor in the space unit are correspondingly determined.
在一个具体的可实施方案中，所述天气信息包括当前日期对应的实际天气状况以及预设时间内的预计天气状况。In a specific implementation, the weather information includes actual weather conditions corresponding to the current date and forecast weather conditions within a preset time.
在一个具体的可实施方案中，所述以所述模型样本因子为输入样本，利用XGBoost方法构建多标签分类模型包括：In a specific implementation, the use of the model sample factor as an input sample, using the XGBoost method to construct a multi-label classification model includes:
根据预设的标注规则对符合标注规则的输入样本进行标注获得已标注样本；According to the preset labeling rules, the input samples conforming to the labeling rules are marked to obtain the marked samples;
根据已标注样本利用XGBoost方法对未标注样本进行训练；Use the XGBoost method to train unlabeled samples based on labeled samples;
根据训练结果以及所述已标注样本构建多标签分类模型。A multi-label classification model is constructed according to the training results and the labeled samples.
在一个具体的可实施方案中，所述方法还包括：In a specific embodiment, the method also includes:
在获取到用户反馈的标注信息时，将所述用户反馈的标注信息与所述标注规则对应的标注信息进行比对；When acquiring the annotation information fed back by the user, comparing the annotation information fed back by the user with the annotation information corresponding to the annotation rule;
若所述标注规则对应的标注信息不包含所述用户反馈的标注信息，则将用户反馈的标注信息添加到所述标注规则内。If the labeling information corresponding to the labeling rule does not include the labeling information fed back by the user, the labeling information fed back by the user is added to the labeling rule.
在一个具体的可实施方案中，所述根据所述多标签分类模型对应获取并输出与若干所述空间单元对应的多标签风险概率包括：In a specific implementable implementation, the correspondingly obtaining and outputting the multi-label risk probabilities corresponding to several of the spatial units according to the multi-label classification model includes:
根据所述多标签分类模型对应获取与若干所述空间单元对应的多标签风险概率；Correspondingly obtaining multi-label risk probabilities corresponding to several of the spatial units according to the multi-label classification model;
查询用户预设定的输出喜好格式，所述输出喜好格式包括空间单元格式以及立体空间格式；Querying the output preference format preset by the user, the output preference format includes a spatial unit format and a three-dimensional spatial format;
若所述输出喜好格式为空间单元格式，则输出与若干所述空间单元对应的多标签风险概率；If the output preference format is a spatial unit format, then output multi-label risk probabilities corresponding to several of the spatial units;
若所述输出喜好格式为立体空间格式，则计算若干所述空间单元对应的多标签风险概率的平均值；输出所述多标签风险概率的平均值。If the output preference format is a three-dimensional space format, then calculate the average value of the multi-label risk probabilities corresponding to several spatial units; and output the average value of the multi-label risk probabilities.
在一个具体的可实施方案中，所述计算若干所述空间单元对应的多标签风险概率的平均值包括：In a specific implementation, the calculation of the average value of the multi-label risk probability corresponding to several spatial units includes:
剔除位于预设合理范围之外的多标签风险概率，计算剔除后剩余的若干所述空间单元对应的多标签风险概率的平均值。Eliminate the multi-label risk probabilities that are outside the preset reasonable range, and calculate the average value of the multi-label risk probabilities corresponding to the remaining several spatial units after elimination.
第二方面，本申请提供一种防护场所警情预警装置，采用如下技术方案：所述装置包括：In the second aspect, the present application provides a warning device for warning situations in a protective place, which adopts the following technical solution: the device includes:
空间信息获取模块，用于获取防护场所的空间信息，所述空间信息包括与场所空间对应的尺寸信息及位置信息；The spatial information acquisition module is used to obtain the spatial information of the protective site, and the spatial information includes size information and position information corresponding to the site space;
空间单元划分模块，用于根据所述尺寸信息构建所述防护场所的立体空间模型，根据预设的划分规则对所述立体空间模型进行划分得到若干空间单元；A space unit division module, configured to construct a three-dimensional space model of the protective site according to the size information, and divide the three-dimensional space model according to preset division rules to obtain several space units;
分布信息获取模块，用于获取与防护场所对应的人员履职信息以及防护场所内的物联感知单元的分布信息；The distribution information acquisition module is used to obtain the personnel performance information corresponding to the protection place and the distribution information of the IoT sensing units in the protection place;
样本因子确定模块，用于分别根据所述位置信息，人员履职信息以及物联感知单元的分布信息确定若干所述空间单元的模型样本因子；The sample factor determination module is used to determine the model sample factors of several spatial units according to the location information, personnel performance information and distribution information of IoT sensing units respectively;
标签模型构建模块，用于以所述模型样本因子为输入样本，利用XGBoost方法构建多标签分类模型；Label model construction module, for taking described model sample factor as input sample, utilize XGBoost method to construct multi-label classification model;
风险概率输出模块，用于根据所述多标签分类模型对应获取并输出与若干所述空间单元对应的多标签风险概率。A risk probability output module, configured to obtain and output multi-label risk probabilities corresponding to several spatial units according to the multi-label classification model.
第三方面，本申请提供一种计算机设备，采用如下技术方案：包括存储器和处理器，所述存储器上存储有能够被处理器加载并执行如上述任一种防护场所警情预警方法的计算机程序。In the third aspect, the present application provides a computer device, which adopts the following technical solution: it includes a memory and a processor, and the memory stores a computer program that can be loaded by the processor and execute any one of the above-mentioned warning methods for protected places .
第四方面，本申请提供一种计算机可读存储介质，采用如下技术方案：存储有能够被处理器加载并执行上述任一种防护场所警情预警方法的计算机程序。In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: storing a computer program that can be loaded by a processor and execute any one of the above-mentioned warning methods for protected places.
综上所述，本申请具有以下有益技术效果：In summary, the application has the following beneficial technical effects:
利用构建多标签分类模型的方式，实时检测并计算防护场所内不同空间单元的风险概率，也即防护场所内不同位置的风险概率；使得用户可以实时直观的根据需要了解到防护场所内部整体的风险概率或者防护场所内每个空间单元对应的风险概率；同时，在对防护空间内部的风险概率进行计算的过程中，综合考虑了防护空间内不同物联感知单元所处的位置，防护场所所处的地理位置，防护场所近期的天气状况以及当前防护场所内人员巡检履职的完成情况等多方面的因素，使得用户可以参照防护空间对应的多标签等闲概率准确的获知当前防护场所内存在的风险情况，减少了单纯依靠温度传感器、湿度传感器等物联感知单元对防护场所内部进行监测时，容易出现误报警情况的可能；从而提升了重点防护场所内部的警情排除效果。Using the method of building a multi-label classification model, real-time detection and calculation of the risk probability of different spatial units in the protective field, that is, the risk probability of different positions in the protective field; so that users can understand the overall risk inside the protective field in real time and intuitively as needed probability or the risk probability corresponding to each space unit in the protected space; at the same time, in the process of calculating the risk probability inside the protected space, the positions of different IoT sensing units in the protected space, the location of the protected The geographic location of the protection site, the recent weather conditions of the protection site, and the completion of the inspection and performance of personnel in the current protection site allow users to accurately know the existence of the current protection site by referring to the multi-label probability corresponding to the protection space. The risk situation reduces the possibility of false alarms that are likely to occur when simply relying on temperature sensors, humidity sensors and other IoT sensing units to monitor the interior of the protection site; thus improving the effectiveness of alarm elimination in key protection sites.
附图说明Description of drawings
图1是本申请实施例总机房安全监测中心的系统架构示意图。Fig. 1 is a schematic diagram of the system architecture of the main computer room safety monitoring center of the embodiment of the present application.
图2是本申请实施例中防护场所警情预警方法的流程图。Fig. 2 is a flow chart of the method for early warning of alarm conditions in protected places in the embodiment of the present application.
图3是本申请实施例中多标签分类模型的构建及输出示意图。Fig. 3 is a schematic diagram of the construction and output of the multi-label classification model in the embodiment of the present application.
图4是本申请实施例中防护场所警情预警装置的结构框图。Fig. 4 is a structural block diagram of an alarm warning device for a protected place in an embodiment of the present application.
图5是本申请另一实施例中防护场所警情预警装置的结构框图。Fig. 5 is a structural block diagram of an alarm warning device for a protected place in another embodiment of the present application.
附图标记：401、空间信息获取模块；402、空间单元划分模块；403、分布信息获取模块；404、样本因子确定模块；405、标签模型构建模块；406、风险概率输出模块；407、标注规则更新模块。Reference numerals: 401, spatial information acquisition module; 402, spatial unit division module; 403, distribution information acquisition module; 404, sample factor determination module; 405, label model building module; 406, risk probability output module; 407, labeling rules Update modules.
具体实施方式Detailed ways
以下结合附图1-5对本申请作进一步详细说明。The present application will be described in further detail below in conjunction with accompanying drawings 1-5.
本申请实施例公开一种防护场所警情预警方法，如图1所示，该方法应用于机房安全监测中心，机房内部的温度传感器、湿度传感器、烟雾报警器等物联感知单元的检测信息实时回传至机房安全监测中心；机房的管理人员可以通过手机或电脑等智能终端与机房安全监测中心建立链接，机房安全监测中心可以实时将机房内部的警情分析结果传输至管理人员的智能终端；同时，管理人员也可以通过智能终端对机房安全监测中心的监测数据进行设定及调整。The embodiment of the present application discloses a method for early warning of alarm conditions in a protective place. As shown in Figure 1, the method is applied to the safety monitoring center of the computer room, and the detection information of the temperature sensor, humidity sensor, smoke alarm and other IoT sensing units inside the computer room is real-time. Send back to the computer room safety monitoring center; the management personnel of the computer room can establish a link with the computer room safety monitoring center through smart terminals such as mobile phones or computers, and the computer room safety monitoring center can transmit the alarm analysis results inside the computer room to the management personnel's smart terminal in real time; At the same time, management personnel can also set and adjust the monitoring data of the computer room safety monitoring center through the smart terminal.
如图2所示，该方法具体包括以下步骤：As shown in Figure 2, the method specifically includes the following steps:
S10，获取防护场所的空间信息。S10, acquiring spatial information of the protected place.
其中，空间信息包括与防护场所对应的尺寸信息及位置信息；具体来说，尺寸信息即机房空间内部的长宽高；位置信息即为机房所处的地理位置；尺寸信息和位置信息可以由管理人员利用智能终端进行输入。Among them, the spatial information includes the size information and location information corresponding to the protective place; specifically, the size information is the length, width and height of the computer room space; the location information is the geographical location of the computer room; the size information and location information can be managed by Personnel use smart terminals for input.
S20，根据空间信息构建立体空间模型。S20, constructing a three-dimensional space model according to the space information.
具体来说，机房安全监测中心在接收到用户通过智能终端输入的空间信息时，首先根据空间信息中的尺寸信息构建与防护空间对应的立体空间模型，继而根据预设的划分规则对立体空间模型进行划分后得到若干空间单元Pos；其中，预设的划分规则由管理人员预先进行设定；例如，按照从左至右、从上至下的顺序将立体空间模型划分为N个大小一致的空间单元，空间单元的大小一般不超过一立方米。Specifically, when the computer room safety monitoring center receives the spatial information input by the user through the smart terminal, it first constructs a three-dimensional space model corresponding to the protective space according to the size information in the spatial information, and then analyzes the three-dimensional space model according to the preset division rules. After division, a number of space units Pos are obtained; among them, the preset division rules are pre-set by the manager; for example, the three-dimensional space model is divided into N spaces of the same size according to the order from left to right and from top to bottom Unit, the size of a space unit generally does not exceed one cubic meter.
S30，获取与防护场所对应的人员履职信息及物联感知单元的分布信息。S30. Obtain the duty performance information of the personnel corresponding to the protection place and the distribution information of the sensing units of the Internet of Things.
其中，人员履职信息是指机房巡检人员在机房内的巡检履职情况；具体来说，机房的管理人员会预先设定机房内部需要巡检的项目形成履职表，巡检人员按照履职表对机房内部进行巡视和排查，并将巡视和排查的情况如实反馈至管理人员，继而管理人员可以根据巡查人员履职表的完成情况得到该机房对应的人员履职信息，并利用智能终端将人员履职信息录入至机房安全监测中心；物联感知单元的分布信息也即机房内部各个传感器所处的具体位置，由管理人员根据物联感知单元的实际分布情况将该信息录入机房安全监测中心。Among them, the personnel performance information refers to the inspection performance of the inspection personnel in the computer room. The duty performance form inspects and checks the interior of the computer room, and truthfully feeds back the results of the inspection and inspection to the management personnel, and then the management personnel can obtain the performance information of the corresponding personnel in the computer room according to the completion of the inspection personnel's performance form, and use the intelligent The terminal enters the personnel performance information into the computer room safety monitoring center; the distribution information of the IoT sensing unit is the specific location of each sensor in the computer room, and the manager enters this information into the computer room security system according to the actual distribution of the IoT sensing unit. monitoring center.
S40，确定若干空间单元的模型样本因子。S40. Determine model sample factors for several spatial units.
具体来说，机房安全监测中心根据防护场所对应的位置信息，人员履职信息以及物联感知单元的分布信息确定若干空间单元对应的模型样本因子。Specifically, the computer room safety monitoring center determines the model sample factors corresponding to several spatial units based on the location information corresponding to the protection site, personnel performance information, and the distribution information of IoT sensing units.
在一个实施例中，模型样本因子具体包括地理信息因子G、气象条件因子Q、履职行为因子E、风险触发因子W以及位置点习惯因子H。In one embodiment, the model sample factors specifically include geographic information factor G, weather condition factor Q, duty performance factor E, risk trigger factor W, and location point habit factor H.
具体来说，根据防护场所对应的位置信息可以确定地理信息因子G，地理信息因子为当前地理位置对应的气候特征，例如，干燥、潮湿、温差较大等等；气象条件因子Q为与当前地理位置对应的天气信息，根据防护场所所在的位置信息，可以确定防护场所的地理位置，继而联网查询该地理位置对应的天气信息，天气信息即为天气预报所给出的天气信息；例如，降水、降雪、降温、升温、台风等等；并将查询到的天气情况设置为气象条件因子Q；进一步的，查询的天气信息可以包括当前日期对应的实际天气状况以及预设时间内的预计天气状况，例如当前及后续10天内的天气情况；履职行为因子E则基于管理人员录入的履职完成情况，分别对应确定每个空间单元对应的履职行为因子；具体来说，也即每个空间单元对应的履职完成情况，履职完成即为达标，履职未完成则为未达标；风险触发因子W以及位置点习惯因子H则根据物联感知单元的具体分布信息进行确定，风险触发因子W包括温度，湿度，水浸，门磁，地磁，市电状态，电线温度等，也即与物联感知单元对应的检测属性；位置点习惯因子H则由空间单元所处的具体位置进行确定，包括易积水、怕积水、怕地震、怕断电、怕台风、怕强降温等；通常情况下，物联感知单元所在的位置即说明了该位置对应的位置点习惯因子；例如设置有温度传感器的位置通常为怕高温的位置。Specifically, the geographic information factor G can be determined according to the location information corresponding to the protection site. The geographic information factor is the climate characteristic corresponding to the current geographic location, such as dryness, humidity, and large temperature difference, etc.; the meteorological condition factor Q is the The weather information corresponding to the location, according to the location information of the protective place, can determine the geographical location of the protective place, and then query the weather information corresponding to the geographical location online. The weather information is the weather information given by the weather forecast; for example, precipitation, Snowfall, temperature drop, temperature rise, typhoon, etc.; and the weather conditions queried are set as the meteorological condition factor Q; further, the queried weather information can include the actual weather conditions corresponding to the current date and the expected weather conditions within the preset time, For example, the weather conditions in the current and subsequent 10 days; the duty performance factor E is based on the completion of the duties entered by the managers, and respectively determines the duty performance factors corresponding to each spatial unit; specifically, each spatial unit The corresponding completion of duty performance, the completion of duty performance means reaching the standard, and the incomplete performance of duty means not reaching the standard; the risk trigger factor W and the location point habit factor H are determined according to the specific distribution information of the sensing unit of the IoT, and the risk trigger factor W Including temperature, humidity, water immersion, door magnetism, geomagnetism, mains power status, wire temperature, etc., that is, the detection attributes corresponding to the IoT sensing unit; the location point habit factor H is determined by the specific location of the space unit, Including easy accumulation of water, fear of accumulation of water, fear of earthquakes, fear of power outages, fear of typhoons, fear of strong cooling, etc.; usually, the location of the sensing unit of the IoT indicates the location point habit factor corresponding to the location; for example, setting The position of the temperature sensor is usually a position that is afraid of high temperature.
S50，以模型样本因子为输入样本构建多标签分类模型。S50, constructing a multi-label classification model by using the model sample factors as input samples.
具体来说，机房安全监测中心在确定若干空间单元的模型样本因子之后，以确定的模型样本因子为输入样本，利用XGBoost方法构建多标签分类模型；也即输入样本X＝(Pos，Q，G，E，W，H)。Specifically, after determining the model sample factors of several spatial units, the computer room safety monitoring center takes the determined model sample factors as input samples and uses the XGBoost method to construct a multi-label classification model; that is, the input sample X = (Pos, Q, G , E, W, H).
在一个实施例中，结合图3，利用XGBoost方法构建多标签分类模型的步骤可以被具体执行为：In one embodiment, with reference to FIG. 3, the steps of constructing a multi-label classification model using the XGBoost method can be specifically performed as follows:
机房安全监测中心首先根据预设的标注规则对符合标注规则的输入样本进行标注以获得已标注样本；其中，预设的标注规则由管理人员预先通过智能终端录入到机房安全监测中心；继而机房安全监测中心根据已标注的样本利用XGBoost方法对未标注样本进行训练，之后综合训练后得到的训练结果以及已标注样本构建出多标签分类模型。多标签分类模型的得出过程，一部分根据标注规则进行自行标注，另一部分根据已标注样本进行训练后得出，提升了多标签分类模型的客观度以及可靠程度。The computer room safety monitoring center first marks the input samples that meet the labeling rules according to the preset labeling rules to obtain the labeled samples; among them, the preset labeling rules are entered into the computer room security monitoring center by the management personnel through the smart terminal in advance; then the computer room security The monitoring center uses the XGBoost method to train the unlabeled samples based on the labeled samples, and then builds a multi-label classification model based on the training results obtained after the training and the labeled samples. In the derivation process of the multi-label classification model, one part is self-labeled according to the labeling rules, and the other part is obtained after training based on the labeled samples, which improves the objectivity and reliability of the multi-label classification model.
S60，根据多标签分类模型对应获取并输出与若干空间单元对应的多标签风险概率。S60. Correspondingly acquire and output multi-label risk probabilities corresponding to several spatial units according to the multi-label classification model.
具体来说，机房安全监测中心根据构建的多标签分类模型可以对应获取到与若干空间单元对应的多标签风险概率；继而机房安全检测中心会根据管理人员预设定的输出喜好格式对获取到的多标签风险概率进行输出。Specifically, the computer room security monitoring center can obtain the multi-label risk probabilities corresponding to several spatial units according to the constructed multi-label classification model; Multi-label risk probabilities are output.
在一个实施例中，输出喜好格式包括空间单元格式以及立体空间格式；输出喜好形式由管理人员根据需要通过智能终端进行预设定；根据多标签分类模型对应获取并输出与若干空间单元对应的多标签风险概率的步骤可以被具体执行为：In one embodiment, the output preference format includes a spatial unit format and a three-dimensional spatial format; the output preference format is preset by the manager through the smart terminal according to needs; The step of labeling risk probability can be specifically performed as:
机房安全监测中心首先根据多标签分类模型对应获取与若干空间单元对应的多标签风险概率，继而查询管理人员预设定的输出喜好格式；若预设定的输出喜好格式为空间单元格式，则直接输出与若干空间单元对应的多标签风险概率至管理人员的智能终端，以便于管理人员可以获知每个空间单元对应的风险概率情况；若预设定的输出喜好格式为立体空间格式，则计算若干空间单元对应的多标签风险概率的平均值，继而将计算得到的平均值作为整体立体空间的风险概率输出至管理人员的智能终端，以便于管理人员可以整体获知机房内部的风险概率情况。The computer room safety monitoring center first obtains the multi-label risk probability corresponding to several spatial units according to the multi-label classification model, and then queries the output preference format preset by the management personnel; if the preset output preference format is the spatial unit format, directly Output the multi-label risk probability corresponding to several spatial units to the smart terminal of the manager, so that the manager can know the risk probability corresponding to each spatial unit; if the preset output preference format is a three-dimensional spatial format, calculate a number of The average value of the multi-label risk probability corresponding to the space unit, and then output the calculated average value as the risk probability of the overall three-dimensional space to the smart terminal of the manager, so that the manager can know the risk probability inside the computer room as a whole.
进一步的，在一个实施例中，为了减少异常数据对立体空间风险概率的影响；机房安全监测中心计算若干空间单元对应的多标签风险概率的平均值的步骤可以被具体执行为：Further, in one embodiment, in order to reduce the impact of abnormal data on the three-dimensional space risk probability; the step of calculating the average value of the multi-label risk probability corresponding to several space units by the computer room safety monitoring center can be specifically executed as follows:
机房安全监测中心在获取到若干空间单元对应的多标签风险概率之后，会首先剔除位于预设合理范围之外的多标签风险概率，继而计算剔除后剩余的若干空间单元对应的多标签风险概率的平均值；预设的合理范围可以为0-100％，从而达到了在计算立体空间的风险概率时剔除异常数据的效果，提升了立体空间风险概率的可靠性及准确度。After obtaining the multi-label risk probabilities corresponding to several spatial units, the computer room safety monitoring center will first eliminate the multi-label risk probabilities that are outside the preset reasonable range, and then calculate the multi-label risk probabilities corresponding to the remaining spatial units after elimination. Average value; the preset reasonable range can be 0-100%, so as to achieve the effect of eliminating abnormal data when calculating the risk probability of the three-dimensional space, and improve the reliability and accuracy of the risk probability of the three-dimensional space.
防护场所警情预警方法利用构建多标签分类模型的方式，实时检测并计算防护场所内不同空间单元的风险概率，也即防护场所内不同位置的风险概率；使得用户可以实时直观的根据需要了解到防护场所内部整体的风险概率或者防护场所内每个空间单元对应的风险概率；同时，在对防护空间内部的风险概率进行计算的过程中，综合考虑了防护空间内不同物联感知单元所处的位置，防护场所所处的地理位置，防护场所近期的天气状况以及当前防护场所内人员巡检履职的完成情况等多方面的因素，使得管理人员可以参照防护空间对应的多标签风险概率准确的获知当前防护场所内存在的风险情况，减少了单纯依靠温度传感器、湿度传感器等物联感知单元对防护场所内部进行监测时，容易出现误报警情况的可能；从而提升了重点防护场所内部的警情排除效果。The method of early warning of police situation in the protective field uses the method of building a multi-label classification model to detect and calculate the risk probability of different spatial units in the protective field in real time, that is, the risk probability of different positions in the protective field; so that users can understand it in real time and intuitively as needed The overall risk probability inside the protected area or the risk probability corresponding to each space unit in the protected area; at the same time, in the process of calculating the risk probability inside the protected space, the location of different IoT sensing units in the protected space is comprehensively considered. The location, the geographical location of the protective site, the recent weather conditions of the protective site, and the completion of the personnel inspection and performance of the current personnel in the protective site, etc., enable managers to refer to the multi-label risk probability corresponding to the protective space. Knowing the risks existing in the current protection site reduces the possibility of false alarms when relying solely on temperature sensors, humidity sensors and other IoT sensing units to monitor the inside of the protection site; thereby improving the alarm situation in key protection sites exclusion effect.
需要说明的是：现有技术中利用物联感知单元进行监测的方式存在误报警情况的原因在于，单个传感器的检测结果异常有时难以直接体现出异常情况发生的原因；例如，机房内出现漏水的情况时，湿度传感器会由于机房漏水而检测到机房内部的湿度异常，但是根据湿度传感器检测到的湿度异常这一现象，并无法唯一推导出湿度异常的原因是由于机房内部出现漏水情况而引发的，继而导致根据物联感知单元给出的风险预警与实际的风险情况之间存在出入，也即湿度传感器反馈出的风险为湿度异常，而实际的风险在于漏水；而本申请的技术方案，在给出机房内部的风险概率情况时，综合考虑防护空间内不同物联感知单元所处的位置，防护场所所处的地理位置，防护场所近期的天气状况以及当前防护场所内人员巡检履职的完成情况等多方面的因素，减少了单纯依靠温度传感器、湿度传感器等物联感知单元对防护场所内部进行监测时，容易出现误报警情况的可能；从而提升了重点防护场所内部的警情排除效果。It should be noted that the reason for false alarms in the monitoring method using IoT sensing units in the prior art is that sometimes it is difficult to directly reflect the cause of the abnormality when the detection result of a single sensor is abnormal; In some cases, the humidity sensor will detect abnormal humidity inside the computer room due to water leakage in the computer room. However, based on the phenomenon of abnormal humidity detected by the humidity sensor, it cannot be deduced that the cause of the abnormal humidity is due to water leakage inside the computer room. , which in turn leads to discrepancies between the risk warning given by the IoT sensing unit and the actual risk situation, that is, the risk fed back by the humidity sensor is abnormal humidity, while the actual risk lies in water leakage; and the technical solution of this application, in When giving the risk probability situation inside the computer room, comprehensively consider the location of different IoT sensing units in the protective space, the geographical location of the protective site, the recent weather conditions of the protective site, and the current inspection performance of personnel in the protective site. Various factors such as the completion status reduce the possibility of false alarms when relying solely on temperature sensors, humidity sensors and other IoT sensing units to monitor the interior of the protection site; thus improving the effectiveness of alarm elimination in key protection sites .
在一个实施例中，为了及时对预设的标注信息进行更新；防护场所警情预警方法还可以包括以下执行步骤：In one embodiment, in order to update the preset labeling information in time; the method for early warning of alarm conditions in protected places may also include the following execution steps:
管理人员可以根据实际情况利用智能终端向机房安全监测中心反馈具体的标注信息，机房安全监测中心在接收到管理人员反馈的标注信息时，会首先将接收到的标注信息与预设标注规则内对应的标注信息进行比对，若标注规则内对应的标注信息包含用户反馈的标注信息，则不对反馈的标注信息进行处理；若标注规则内对应的标注信息不包含用户反馈的标注信息，则将用户反馈的标注信息添加到预设的标注规则内，从而实现对标注规则的更新，以便于标注规则可以随着不断使用与当前机房的实际情况更加适配。Managers can use the smart terminal to feed back specific labeling information to the computer room security monitoring center according to the actual situation. When the computer room security monitoring center receives the labeling information fed back by the management personnel, it will first match the received labeling information with the preset labeling rules. If the corresponding labeling information in the labeling rule contains the labeling information fed back by the user, the feedback labeling information will not be processed; if the corresponding labeling information in the labeling rule does not contain the labeling information fed back by the user, the user The feedback labeling information is added to the preset labeling rules, so as to update the labeling rules, so that the labeling rules can be more adapted to the actual situation of the current computer room with continuous use.
图2为一个实施例中防护场所警情预警方法的流程示意图。应该理解的是，虽然图2的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行；除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行；并且图2中的至少一部分步骤可以包括多个子步骤或者多个阶段，这些子步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些子步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤的子步骤或者阶段的至少一部分轮流或者交替地执行。Fig. 2 is a schematic flow chart of an early warning method for a protected place in an embodiment. It should be understood that although the various steps in the flow chart of FIG. 2 are displayed sequentially according to the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows; Strict order restriction, these steps can be carried out in other orders; And at least a part of steps in Fig. 2 can comprise multiple sub-steps or multiple stages, these sub-steps or stages are not necessarily executed at the same moment to complete, but can Executed at different times, the execution order of these sub-steps or stages is not necessarily sequential, but may be performed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.
基于上述方法，本申请实施例还公开一种防护场所警情预警装置。Based on the above method, the embodiment of the present application also discloses an alarm warning device for a protective place.
如图4所示，该装置包括以下模块：As shown in Figure 4, the device includes the following modules:
空间信息获取模块401，用于获取防护场所的空间信息，空间信息包括与场所空间对应的尺寸信息及位置信息；The space
空间单元划分模块402，用于根据尺寸信息构建防护场所的立体空间模型，根据预设的划分规则对立体空间模型进行划分得到若干空间单元；The space
分布信息获取模块403，用于获取与防护场所对应的人员履职信息以及防护场所内的物联感知单元的分布信息；The distribution
样本因子确定模块404，用于分别根据位置信息，人员履职信息以及物联感知单元的分布信息确定若干空间单元的模型样本因子；The sample
标签模型构建模块405，用于以模型样本因子为输入样本，利用XGBoost方法构建多标签分类模型；The label
风险概率输出模块406，用于根据多标签分类模型对应获取并输出与若干空间单元对应的多标签风险概率。The risk
在一个实施例中，模型样本因子包括地理信息因子、气象条件因子、履职行为因子、风险触发因子以及位置点习惯因子；空间信息获取模块401具体用于基于位置信息确定地理信息因子；基于位置信息对应查询与位置信息对应的天气信息，将天气信息设置为气象条件因子；基于人员履职信息中的履职完成情况确定履职行为因子；基于物联感知单元的分布信息对应确定空间单元内的风险触发因子及位置点习惯因子。In one embodiment, the model sample factors include geographic information factors, meteorological condition factors, duty performance factors, risk trigger factors, and location point habit factors; the spatial
在一个实施例中，天气信息包括当前日期对应的实际天气状况以及预设时间内的预计天气状况。In one embodiment, the weather information includes actual weather conditions corresponding to the current date and forecast weather conditions within a preset time.
在一个实施例中，标签模型构建模块405，具体用于根据预设的标注规则对符合标注规则的输入样本进行标注获得已标注样本；根据已标注样本利用XGBoost方法对未标注样本进行训练；根据训练结果以及已标注样本构建多标签分类模型。In one embodiment, the label
在一个实施例中，结合图5，防护场所警情预警装置还包括标注规则更新模块407，用于在获取到用户反馈的标注信息时，将用户反馈的标注信息与标注规则对应的标注信息进行比对；若标注规则内对应的标注信息不包含用户反馈的标注信息，则将用户反馈的标注信息添加到标注规则内。In one embodiment, referring to FIG. 5 , the alarm warning device for protected places further includes a labeling
在一个实施例中，风险概率输出模块406，具体用于根据多标签分类模型对应获取与若干空间单元对应的多标签风险概率；查询预设定的输出喜好格式，输出喜好格式包括空间单元格式以及立体空间格式；若输出喜好格式为空间单元格式，则输出与若干空间单元对应的多标签风险概率；若输出喜好格式为立体空间格式，则计算若干空间单元对应的多标签风险概率的平均值；输出多标签风险概率的平均值。In one embodiment, the risk
在一个实施例中，风险概率输出模块406，还用于剔除位于预设合理范围之外的多标签风险概率，计算剔除后剩余的若干空间单元对应的多标签风险概率的平均值。In one embodiment, the risk
本申请实施例还公开一种计算机设备。The embodiment of the present application also discloses a computer device.
具体来说，该计算机设备包括存储器和处理器，存储器上存储有能够被处理器加载并执行上述防护场所警情预警方法的计算机程序。Specifically, the computer device includes a memory and a processor, and the memory stores a computer program that can be loaded by the processor and execute the above-mentioned method for warning and early warning of a protected place.
本申请实施例还公开一种计算机可读存储介质。The embodiment of the present application also discloses a computer-readable storage medium.
具体来说，该计算机可读存储介质，其存储有能够被处理器加载并执行如上述防护场所警情预警方法的计算机程序，该计算机可读存储介质例如包括：U盘、移动硬盘、只读存储器(Read-OnlyMemory，ROM)、随机存取存储器(RandomAccessMemory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。Specifically, the computer-readable storage medium stores a computer program that can be loaded by a processor and executes the above-mentioned warning method for a protected place. The computer-readable storage medium includes, for example: U disk, mobile hard disk, read-only Various media capable of storing program codes such as a memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk.
本具体实施例仅仅是对本发明的解释，其并不是对本发明的限制，本领域技术人员在阅读完本说明书后可以根据需要对本实施例做出没有创造性贡献的修改，但只要在本发明的权利要求范围内都受到专利法的保护。This specific embodiment is only an explanation of the present invention, and it is not a limitation of the present invention. Those skilled in the art can make modifications to this embodiment without creative contribution as required after reading this specification, but as long as they are within the rights of the present invention All claims are protected by patent law.
Claims (10)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310403167.1ACN116402351A (en) | 2023-04-14 | 2023-04-14 | Method, device, equipment and storage medium for early warning of alarm situation in protective place |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310403167.1ACN116402351A (en) | 2023-04-14 | 2023-04-14 | Method, device, equipment and storage medium for early warning of alarm situation in protective place |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116402351Atrue CN116402351A (en) | 2023-07-07 |
Family
ID=87010207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310403167.1APendingCN116402351A (en) | 2023-04-14 | 2023-04-14 | Method, device, equipment and storage medium for early warning of alarm situation in protective 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
- 2023-04-14CNCN202310403167.1Apatent/CN116402351A/enactivePending
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 |
|---|---|---|
| CN113450545B (en) | Natural disaster early warning system and method, cloud platform and storable medium | |
| CN109800961A (en) | A kind of fire rescue decision-making technique, device, storage medium and terminal device | |
| CN113192283A (en) | Wireless fire early warning system with multi-sensor information fusion | |
| CN109872491A (en) | Fire monitoring method, device, electronic equipment and system | |
| CN114254879B (en) | Multi-sensor information fusion type power equipment safety diagnosis method and device | |
| CN110750413B (en) | Multi-machine room temperature alarm method and device and storage medium | |
| CN112884199A (en) | Method and device for predicting faults of hydropower station equipment, computer equipment and storage medium | |
| CN113671886B (en) | Fire safety monitoring method and system based on 5G | |
| CN115393566A (en) | Fault identification and early warning method, device, storage medium, and equipment for power equipment | |
| CN117495804A (en) | Charging station safety monitoring method, charging station safety monitoring device, computer equipment and storage medium | |
| CN112149770A (en) | Data radio frequency identification display system, method and device of intelligent cable | |
| CN113959477A (en) | Environmental control monitoring reminding method and system based on Internet of things | |
| CN116050930A (en) | Monitoring disc system, monitoring disc method, storage medium and electronic equipment | |
| US20160275407A1 (en) | Diagnostic device, estimation method, non-transitory computer readable medium, and diagnostic system | |
| CN114444776A (en) | A method and device for hazard analysis based on neural network | |
| CN116402351A (en) | Method, device, equipment and storage medium for early warning of alarm situation in protective place | |
| CN112598025A (en) | Processing method, device, equipment and medium for target information of power equipment | |
| CN111898823A (en) | Frost prediction method, device, equipment and computer readable storage medium | |
| CN117558116A (en) | Fire control early warning system based on big data | |
| CN111465045A (en) | AP monitoring method, monitoring server and monitoring system | |
| CN114387391A (en) | Safety monitoring method, device, computer equipment and medium for substation equipment | |
| CN117421551A (en) | Sensor detection method, device, computer equipment and storage medium | |
| CN116484428B (en) | Data security detection system, method and device and related equipment | |
| CN118500471A (en) | Power plant safety detection method and device, computer equipment and storage medium | |
| CN119132026B (en) | Equipment early warning method and related devices |
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 | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20230707 |