Abnormal environment detection method, device and equipment and computer storage medium

Abstract

The invention discloses an abnormal environment detection method, device and equipment and a computer storage medium, and relates to the technical field of fire safety monitoring. The method comprises the following steps: acquiring to-be-detected people flow data, to-be-detected environment data and to-be-detected environment types; determining a target preset busy degree membership degree corresponding to the to-be-detected visitor flow rate data according to a relationship between the visitor flow rate data and a preset busy degree membership degree; determining a target preset busy degree membership degree and a target fluctuation index of the to-be-detected environment corresponding to the target preset output value according to the preset busy degree membership degree, a preset output value corresponding to the preset busy degree and the fluctuation index; determining a corresponding target detection threshold according to the to-be-detected environment type and the target fluctuation index; and when the to-be-detected environment data exceed the target detection threshold, judging that the to-be-detected environment is an abnormal environment. According to the embodiment of the invention, by dynamically setting the target detection threshold value of the environment to be detected, the accuracy of abnormal environment detection is improved.

Description

Technical Field

[0001] This application belongs to the field of fire safety monitoring technology, and in particular relates to a method, device, equipment and computer storage medium for abnormal environment detection. Background Technology

[0002] With economic development, the number of large shopping malls and street-front shops in cities is constantly increasing. Since these malls and shops are often shared with various other locations such as production facilities, businesses, and guesthouses, they pose numerous fire hazards, impacting people's safety and well-being.

[0003] In existing technologies, abnormal environment detection often relies on sensor devices to detect environmental data such as temperature and smoke concentration, and sets data detection thresholds to determine the abnormal environment. However, environmental data such as temperature and smoke concentration are constantly changing in different scenarios and at different times. The fixed detection thresholds set in existing technologies are not suitable for environments where environmental data changes in real time, resulting in low accuracy in abnormal environment detection. Summary of the Invention

[0004] This application provides a method, apparatus, device, and computer storage medium for abnormal environment detection, in order to solve the problem that the fixed detection threshold set in existing methods and technologies is not suitable for environments where environmental data changes in real time, resulting in low accuracy of abnormal environment detection.

[0005] In a first aspect, embodiments of this application provide a method for detecting abnormal environments, the method comprising:

[0006] Acquire information about the environment to be tested, including pedestrian flow data, environmental data, and the type of environment to be tested.

[0007] Based on the relationship between pedestrian flow data and preset busyness membership, determine the target preset busyness membership corresponding to the pedestrian flow data to be detected;

[0008] Based on the relationship between the preset busyness membership degree, the preset output value corresponding to the preset busyness degree and the fluctuation index, the target fluctuation index of the environment to be detected corresponding to the target preset busyness membership degree and the target preset output value is determined, and the target preset output value is the preset output value corresponding to the target preset busyness degree.

[0009] Determine the corresponding target detection threshold based on the type of environment to be detected and the target fluctuation index;

[0010] If the data of the environment to be detected exceeds the target detection threshold, the environment to be detected is determined to be an abnormal environment.

[0011] Secondly, embodiments of this application provide an apparatus for detecting abnormal environments, the apparatus comprising:

[0012] The acquisition module is used to acquire information about the environment to be detected, including the pedestrian flow data, the environmental data to be detected, and the type of the environment to be detected.

[0013] The determination module is used to determine the target preset busyness membership degree corresponding to the pedestrian flow data to be detected based on the relationship between pedestrian flow data and preset busyness membership degree;

[0014] The determination module is also used to determine the target fluctuation index of the environment to be detected corresponding to the target preset busy level membership and the target preset output value based on the relationship between the preset busy level membership, the preset output value corresponding to the preset busy level and the fluctuation index. The target preset output value is the preset output value corresponding to the target preset busy level.

[0015] The determination module is also used to determine the corresponding target detection threshold based on the type of environment to be detected and the target fluctuation index;

[0016] The judgment module is used to determine that the environment to be detected is an abnormal environment when the data of the environment to be detected exceeds the target detection threshold.

[0017] Thirdly, embodiments of this application provide a terminal device, the device including: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the abnormal environment detection method as described in the first aspect.

[0018] Fourthly, embodiments of this application provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement the abnormal environment detection method as described in the first aspect.

[0019] Fifthly, embodiments of this application provide a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform an abnormal environment detection method as described in the first aspect.

[0020] This application provides a method, apparatus, device, and computer storage medium for detecting abnormal environments. The method first acquires pedestrian traffic data, environmental data, and environmental type to be detected, providing a data foundation for subsequent analysis. Based on the relationship between pedestrian traffic data and preset busyness levels, fuzzification processing is performed to determine the target preset busyness level membership degree corresponding to the pedestrian traffic data; the precise input values ​​are simplified into set membership relationships, assessing the importance of pedestrian traffic data at each preset busyness level, reducing the impact of noise and outliers. Based on the relationship between the preset busyness level membership degree, the preset output value corresponding to the preset busyness level, and the fluctuation index, a target fluctuation index for the environment to be detected is determined; based on the busyness level membership degree and the preset output value, defuzzification is performed to quantify the busyness of the environment to be detected into a specific fluctuation index, enabling the system to dynamically adjust its sensitivity according to different busyness levels. Based on the environmental type and the target fluctuation index, a corresponding target detection threshold is determined; the detection threshold for detecting anomalies is adaptively adjusted according to the environmental type, enabling the monitoring system to adapt to the characteristics of different environments. If the data of the environment to be detected exceeds the target detection threshold, the environment is determined to be an abnormal environment. By comparing the data of the environment to be detected with the target detection threshold, the system can automatically determine whether the environment is abnormal, improving response speed and processing efficiency. By dynamically setting the target fluctuation index and target detection threshold of the environment to be detected, the system can automatically adjust the abnormal environment judgment criteria according to changes in environmental data, improving the accuracy of abnormal environment detection. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating the abnormal environment detection method provided in the embodiments of this application;

[0023] Figure 2 This is a flowchart illustrating one implementation method for determining the target detection threshold provided in an embodiment of this application;

[0024] Figure 3 This is a flowchart illustrating one implementation method of abnormal environment analysis provided in an embodiment of this application;

[0025] Figure 4 This is a schematic diagram of the abnormal environment detection device provided in the embodiments of this application;

[0026] Figure 5 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application. Detailed Implementation

[0027] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0028] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0029] Existing fire detection solutions primarily rely on sensors such as cameras, smoke detectors, and gas detectors to collect video and concentration data, which is then sent to a monitoring module. The monitoring module processes the received data based on preset threshold values; when the detected data exceeds these thresholds, the module determines an abnormal event has occurred. However, because environmental factors such as temperature and smoke concentration vary across different scenarios, while the threshold values ​​remain constant, excessively high thresholds can lead to missed detections, while excessively low thresholds can result in false alarms.

[0030] To address the shortcomings of existing technologies, this application provides a method, apparatus, device, and computer storage medium for detecting abnormal environments. The method first acquires pedestrian traffic data, environmental data, and environmental type to be detected, providing a data foundation for subsequent analysis. Based on the relationship between pedestrian traffic data and preset busyness levels, fuzzification processing is performed to determine the target preset busyness level membership degree corresponding to the pedestrian traffic data. Precise input values ​​are simplified to set membership relationships, assessing the importance of pedestrian traffic data at each preset busyness level, reducing the impact of noise and outliers. Based on the relationship between the preset busyness level membership degree, the preset output value corresponding to the preset busyness level, and the fluctuation index, a target fluctuation index for the environment to be detected is determined. Defuzzification is performed based on the busyness level membership degree and the preset output value, quantifying the busyness of the environment to be detected into a specific fluctuation index, enabling the system to dynamically adjust its sensitivity according to different busyness levels. Based on the environmental type and the target fluctuation index, a corresponding target detection threshold is determined. The detection threshold for detecting anomalies is adaptively adjusted according to the environmental type, enabling the monitoring system to adapt to the characteristics of different environments. If the data of the environment to be detected exceeds the target detection threshold, the environment is determined to be an abnormal environment. By comparing the data of the environment to be detected with the target detection threshold, the system can automatically determine whether the environment is abnormal, improving response speed and processing efficiency. By dynamically setting the target fluctuation index and target detection threshold of the environment to be detected, the system can automatically adjust the abnormal environment judgment criteria according to changes in environmental data, improving the accuracy of abnormal environment detection.

[0031] The following section first introduces the method for detecting abnormal environments provided in the embodiments of this application.

[0032] Figure 1 A flowchart illustrating an abnormal environment detection method according to an embodiment of this application is shown. Figure 1 As shown, the method may include the following steps: S101 to S105.

[0033] S101, Obtain the information of the environment to be detected, which includes the pedestrian flow data, the environmental data, and the type of the environment to be detected.

[0034] In some embodiments, the environmental data to be detected is a time series and may include data such as temperature, smoke density, and carbon monoxide density.

[0035] The environmental data to be tested can include activity-sensitive locations and activity-insensitive locations.

[0036] Among them, activity-sensitive venues are those where environmental data changes significantly with changes in the density of people in the environment, such as kitchens. During peak dining hours, the temperature is higher than at other times due to the increased use of electricity and fire in the kitchen, and environmental data such as temperature and smoke density are also higher than at other times. During non-dining hours, the temperature and smoke density of the kitchen are lower.

[0037] Activity-insensitive locations are those where environmental data changes little with variations in pedestrian density. For example, supermarkets have air conditioning to regulate temperature, resulting in stable temperatures with minimal fluctuations, and smoke density also remains relatively constant.

[0038] In some embodiments, the pedestrian flow data to be detected is collected and analyzed in real time through a camera, and the environmental data to be detected is collected through devices such as sensors, and the type of the environment to be detected is preset.

[0039] By acquiring information about the environment to be tested, necessary input data is provided for subsequent testing processes.

[0040] S102, Based on the relationship between the pedestrian flow data and the preset busyness membership degree, determine the target preset busyness membership degree corresponding to the pedestrian flow data to be detected.

[0041] In some embodiments, the level of busyness may include three levels: idle, busy, and very busy.

[0042] Among them, the preset busyness level membership degree is the degree to which the traffic flow data belongs to the preset busyness level set.

[0043] The amount of pedestrian traffic data affects the level of congestion and potential risks in the environment. Determining the degree of busyness corresponding to pedestrian traffic data is to map specific data to fuzzy concepts, which facilitates subsequent processing and decision-making.

[0044] In some embodiments, the relationship between pedestrian traffic data and preset busyness membership can include triangular membership functions, trapezoidal membership functions, Gaussian membership functions, or sigmoid membership functions.

[0045] By associating pedestrian traffic data with preset busy levels and determining the membership degree of the target preset busy level corresponding to the pedestrian traffic data to be detected, the busy level of the environment to be detected can be determined.

[0046] S103, based on the relationship between the preset busyness membership degree, the preset output value corresponding to the preset busyness degree and the fluctuation index, determine the target fluctuation index of the environment to be detected corresponding to the target preset busyness membership degree and the target preset output value, and the target preset output value is the preset output value corresponding to the target preset busyness degree.

[0047] In some embodiments, the preset output value corresponding to the preset busy level may include 0, 0.5 and 1. When the preset busy level is idle, the corresponding preset output value is 0; when the preset busy level is busy, the corresponding preset output value is 0.5; and when the preset busy level is very busy, the corresponding preset output value is 1.

[0048] Among them, the volatility index represents the degree of volatility or change in environmental data.

[0049] By defining a volatility index, the degree of fluctuation in environmental data can be quantified, providing a basis for subsequent threshold setting and anomaly detection. This helps to adjust monitoring strategies in a timely manner and improve the response speed and accuracy of the monitoring system.

[0050] S104. Determine the corresponding target detection threshold based on the type of environment to be detected and the target fluctuation index.

[0051] Different environmental types have varying sensitivities to different environmental data. By setting different detection thresholds based on different environmental types and fluctuation indices, we can adapt to the monitoring needs of different environments, which helps to improve the accuracy and efficiency of detection and reduce false alarms and missed alarms.

[0052] S105, if the data of the environment to be detected exceeds the target detection threshold, the environment to be detected is determined to be an abnormal environment.

[0053] By comparing the data of the environment to be detected with the target detection threshold, it is possible to quickly determine whether the environment is abnormal, which helps to take timely countermeasures.

[0054] First, the system acquires the pedestrian flow data, environmental data, and environmental type to be detected, providing a data foundation for subsequent analysis. Based on the relationship between pedestrian flow data and preset busyness levels, fuzzification is performed to determine the target preset busyness level membership degree corresponding to the pedestrian flow data. This simplifies precise input values ​​into set membership relationships, assessing the importance of pedestrian flow data at each preset busyness level and reducing the impact of noise and outliers. Based on the relationship between the preset busyness level membership degree, the preset output value corresponding to the preset busyness level, and the fluctuation index, the target fluctuation index for the environment to be detected is determined. Defuzzification is then performed based on the busyness level membership degree and the preset output value, quantifying the busyness of the environment to be detected into a specific fluctuation index, enabling the system to dynamically adjust its sensitivity according to different busyness levels. Based on the environmental type and the target fluctuation index, the corresponding target detection threshold is determined. The detection threshold for anomaly detection is adaptively adjusted according to the environmental type, allowing the monitoring system to adapt to the characteristics of different environments. If the environmental data exceeds the target detection threshold, the environment is determined to be an abnormal environment. By comparing the environmental data and the target detection threshold, the system can automatically determine whether the environment is abnormal, improving response speed and processing efficiency. By dynamically setting the target fluctuation index and target detection threshold of the environment to be detected, the system can automatically adjust the judgment criteria for abnormal environments based on changes in environmental data, thereby improving the accuracy of abnormal environment detection.

[0055] In some embodiments, the relationship between pedestrian traffic data and the membership degree of busy preset level can be:

[0056]

[0057] Where μ(x) is the preset busyness membership degree, x is the pedestrian flow data to be detected, a is the preset slope, and c is the preset center.

[0058] Using the Sigmoid membership function to fuzzify the input has a smoothing effect, making the changes in the membership degree of the preset busy level more continuous and gradual. This helps to reduce abrupt changes and discontinuities, better fits the actual data, and makes the output more stable and reliable.

[0059] In some embodiments, the relationship between pedestrian traffic data and the membership degree of busy preset level can also be:

[0060]

[0061] Where μ(x) is the preset busyness membership degree, x is the pedestrian flow data to be detected, a is the preset slope, and c is the preset center.

[0062] In some embodiments, the relationship between the preset busyness membership degree, the preset output value corresponding to the preset busyness degree, and the fluctuation index can be:

[0063]

[0064] Where ε is the fluctuation index, x is the pedestrian flow data to be detected, μ(x) is the membership degree of the preset busy level, and β is the preset output value corresponding to the preset busy level.

[0065] The volatility index combines the preset busyness membership degree and the corresponding preset output value. It calculates the volatility index by weighting the membership degree and the output value, taking into account the influence of both, and more comprehensively reflecting the volatility of the system.

[0066] In some embodiments, before determining the target fluctuation index of the environment to be detected corresponding to the target preset busyness membership degree and the target preset output value, the method may further include:

[0067] Obtain the preset fuzzy rule library, which includes the preset busy level and the preset output value corresponding to the preset busy level.

[0068] The pre-defined fuzzy rule base includes a series of rules, each describing the input or corresponding output under different conditions. This allows the system to quickly find the corresponding preset output value based on the input pedestrian traffic data and convert it into a preset busyness membership degree. Furthermore, when encountering abnormal or unforeseen pedestrian traffic data, the system can make reasonable decisions based on the pre-defined rule base, rather than relying entirely on real-time calculations or model predictions. This enhances the system's robustness to uncertainty and abnormal situations.

[0069] In one example, the preset fuzzy rule base is shown in Table 1, where the input quantity is the preset busy level.

[0070] Table 1 Preset Fuzzy Rule Base

[0071] Input Output idle 0 busy 0.5 Very busy 1

[0072] In some embodiments, such as Figure 2 As shown, the corresponding target detection threshold is determined based on the type of environment to be detected and the target fluctuation index, and may include:

[0073] S201, when the environment type to be detected is a preset environment type, obtain the maximum value and average value of the target abnormal environment data within a preset number of days.

[0074] S202, based on the relationship between the fluctuation index, the maximum and average values ​​of the abnormal environment data, and the detection threshold, determine the target detection threshold corresponding to the target fluctuation index, the maximum and average values ​​of the target abnormal environment data.

[0075] In some embodiments, the preset environment type can be an activity-sensitive location.

[0076] When the type of place to be detected is an activity-sensitive location, the real-time changes in environmental data are significant. By obtaining the maximum and average values ​​of the target data with no abnormal environment within a preset number of days, the target detection threshold can be determined based on the actual environmental conditions. Taking into account both data fluctuations and environmental anomalies, the threshold setting becomes more specific and reasonable.

[0077] In some embodiments, the relationship between the volatility index, the maximum and average values ​​of abnormal environment data, and the detection threshold can be:

[0078]

[0079] Where THD is the detection threshold and ε is the volatility index. Let x be the average value of the target abnormal environment data within a preset number of days from time t. max (t) represents the maximum value of the target abnormal environment data within the preset number of days at time t.

[0080] By calculating the average and maximum values ​​of abnormal environment data and weighting them using a fluctuation index, the detection threshold can be dynamically adjusted according to data fluctuations. Furthermore, because both the maximum and average values ​​are considered, it exhibits robustness to extreme values ​​in the data, preventing the detection threshold from deviating from its normal value due to anomalies in individual data points.

[0081] In some embodiments, if the type of environment to be detected is not a preset environment type, a preset detection threshold is used as the target detection threshold.

[0082] When the environment type to be tested is not the preset environment type, the environmental data of the environment to be tested is relatively stable and changes little. Using a preset threshold can effectively reduce the consumption of system resources and improve the overall performance of the system.

[0083] In some embodiments, such as Figure 3 As shown, the method may further include:

[0084] S301, Input the environmental data to be detected into the pre-trained abnormal environment analysis model;

[0085] S302, determine the weighted sum of the environmental data to be detected based on the preset node weights of the neural network in the abnormal environment analysis model, and use it as the probability of the abnormal environment corresponding to the abnormal environment analysis model;

[0086] S303, if the probability of an abnormal environment exceeds a set threshold, determine that the environment to be detected is an abnormal environment corresponding to an abnormal environment probability exceeding the set threshold.

[0087] By using a pre-trained abnormal environment analysis model and quickly analyzing and judging the data of the environment to be detected based on preset node weights, it is possible to quickly judge and respond to real-time data, help to promptly detect and handle abnormal situations, and improve detection efficiency.

[0088] In some embodiments, the abnormal environment analysis model is a radial basis function (RBF) neural network, including an input layer, a hidden layer, and an output layer. The hidden layer consists of multiple RBF units. The input is the environmental data to be detected, and the output is the probability of the abnormal environment, such as the probability of a fire or a gas leak.

[0089] In some embodiments, the weighted sum of the environmental data to be detected is determined based on the preset node weights of the neural network in the abnormal environment analysis model. The formula can be:

[0090]

[0091] Among them, y j w represents the value of the j-th output node of the neural network. ij To represent the weight connecting the i-th RBF unit and the j-th output node, x p Let c be the p-th input vector. i Let be the center vector of the i-th RBF unit, δ be the preset variance parameter, m be the number of RBF units, and n be the number of output nodes.

[0092] Figure 4 An embodiment of this application illustrates an abnormal environment detection device 400, which may include:

[0093] The acquisition module 401 is used to acquire information about the environment to be detected, including the pedestrian flow data, the environment data to be detected, and the type of the environment to be detected.

[0094] The determining module 402 is used to determine the target preset busyness membership degree corresponding to the pedestrian flow data to be detected based on the relationship between the pedestrian flow data and the preset busyness membership degree;

[0095] The determining module 402 is further configured to determine the target fluctuation index of the environment to be detected corresponding to the target preset busyness membership degree and the target preset output value based on the relationship between the preset busyness membership degree, the preset output value corresponding to the preset busyness degree and the fluctuation index, wherein the target preset output value is the preset output value corresponding to the target preset busyness degree.

[0096] The determining module 402 is further configured to determine the corresponding target detection threshold based on the type of environment to be detected and the target fluctuation index;

[0097] The judgment module 403 is used to determine that the environment to be detected is an abnormal environment when the data of the environment to be detected exceeds the target detection threshold.

[0098] In some embodiments, the relationship between the pedestrian flow data and the membership degree of the busy preset level in the determining module 402 can be:

[0099]

[0100] Where μ(x) is the preset busyness membership degree, x is the pedestrian flow data to be detected, a is the preset slope, and c is the preset center.

[0101] In some embodiments, the relationship between the preset busyness membership degree, the preset output value corresponding to the preset busyness, and the fluctuation index in the determining module 402 can be:

[0102]

[0103] Where ε is the fluctuation index, x is the pedestrian flow data to be detected, μ(x) is the membership degree of the preset busy level, and β is the preset output value corresponding to the preset busy level.

[0104] In some embodiments, the acquisition module 401 is further configured to acquire a preset fuzzy rule base, the preset fuzzy rule base including the preset busy level and the preset output value corresponding to the preset busy level.

[0105] In some embodiments, the acquisition module 401 is further configured to acquire the maximum value and average value of the target abnormal environment data within a preset number of days when the environment type to be detected is a preset environment type.

[0106] The determination module 402 is further configured to determine the target detection threshold corresponding to the target fluctuation index, the maximum value and the average value of the target abnormal environment data, based on the relationship between the fluctuation index, the maximum value and the average value of the abnormal environment data, and the detection threshold.

[0107] In some embodiments, in the determining module 402, the relationship between the fluctuation index, the maximum value and the average value of the abnormal environment data, and the detection threshold is as follows:

[0108]

[0109] Where THD is the detection threshold and ε is the volatility index. Let x be the average value of the target abnormal environment data within a preset number of days from time t.max (t) represents the maximum value of the target abnormal environment data within the preset number of days at time t.

[0110] In some embodiments, the determination module 403 is further configured to use a preset detection threshold as the target detection threshold when the type of the environment to be detected is not a preset environment type.

[0111] In some embodiments, the abnormal environment detection device 400 may further include:

[0112] The input module is used to input the environmental data to be detected into a pre-trained abnormal environment analysis model;

[0113] The determining module 402 is further configured to determine the weighted sum of the environmental data to be detected based on the preset node weights of the neural network in the abnormal environment analysis model, as the probability of the abnormal environment corresponding to the abnormal environment analysis model;

[0114] The judgment module 403 is further configured to determine, when the probability of the abnormal environment exceeds a set threshold, that the environment to be detected is an abnormal environment corresponding to an abnormal environment probability exceeding the set threshold.

[0115] Figure 4 The various modules in the illustrated device can achieve Figure 1 The various steps involved, and the corresponding technical effects achieved, will not be elaborated upon here for the sake of brevity.

[0116] Figure 5 A schematic diagram of the hardware structure of the terminal device provided in an embodiment of this application is shown.

[0117] The terminal device may include a processor 501 and a memory 502 storing computer program instructions.

[0118] Specifically, the processor 501 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0119] Memory 502 may include mass storage for data or instructions. For example, and not limitingly, memory 502 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. In one instance, memory 502 may include removable or non-removable (or fixed) media, or memory 502 may be non-volatile solid-state storage. Memory 502 may be internal or external to the integrated gateway disaster recovery device.

[0120] In one example, memory 502 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Thus, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method of abnormal environment detection according to this disclosure.

[0121] The processor 501 reads and executes computer program instructions stored in the memory 502 to achieve... Figure 1 The method for detecting abnormal environments in the illustrated embodiment.

[0122] In one example, the terminal device may also include a communication interface 503 and a bus 504. Wherein, for example... Figure 5 As shown, the processor 501, memory 502, and communication interface 503 are connected through bus 504 and complete communication with each other.

[0123] The communication interface 503 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0124] Bus 504 includes hardware, software, or both, that couples components of an end device together. For example, and not as a limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 504 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0125] Furthermore, in conjunction with the abnormal environment detection methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the abnormal environment detection methods in the above embodiments.

[0126] This application also provides a computer program product, including a computer program, which, when executed, implements any of the abnormal environment detection methods described in the above embodiments.

[0127] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0128] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or text segments used to perform the required tasks. Programs or text segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memory (ROM), flash memory, erasable read-only memory (EROM), floppy disks, compact disc read-only memory (CD-ROM), optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Text segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0129] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0130] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0131] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for detecting abnormal environments, characterized in that, include: Acquire information about the environment to be detected, including pedestrian flow data, environmental data, and environment type. Based on the relationship between pedestrian flow data and preset busyness membership, the target preset busyness membership corresponding to the pedestrian flow data to be detected is determined; Based on the relationship between the preset busyness membership degree, the preset output value corresponding to the preset busyness degree and the fluctuation index, the target fluctuation index of the environment to be detected corresponding to the target preset busyness membership degree and the target preset output value is determined, and the target preset output value is the preset output value corresponding to the target preset busyness degree. Based on the type of environment to be detected and the target fluctuation index, determine the corresponding target detection threshold; If the data of the environment to be detected exceeds the target detection threshold, the environment to be detected is determined to be an abnormal environment.

2. The method for detecting abnormal environments according to claim 1, characterized in that, The relationship between the pedestrian flow data and the membership degree of the preset busy level is as follows: Where μ(x) is the preset busyness membership degree, x is the pedestrian flow data to be detected, a is the preset slope, and c is the preset center.

3. The method for detecting abnormal environments according to claim 1, characterized in that, The relationship between the preset busyness membership degree, the preset output value corresponding to the preset busyness degree, and the fluctuation index is as follows: Where ε is the fluctuation index, x is the pedestrian flow data to be detected, μ(x) is the membership degree of the preset busy level, and β is the preset output value corresponding to the preset busy level.

4. The method for detecting abnormal environments according to claim 1, characterized in that, Before determining the target fluctuation index of the environment to be detected corresponding to the target preset busyness membership degree and the target preset output value, the method further includes: Obtain a preset fuzzy rule library, which includes the preset busy level and the preset output value corresponding to the preset busy level.

5. The method for detecting abnormal environments according to claim 1, characterized in that, Based on the type of environment to be detected and the target fluctuation index, the corresponding target detection threshold is determined, including: When the environment type to be detected is a preset environment type, obtain the maximum value and average value of the target abnormal environment data within a preset number of days; Based on the relationship between the volatility index, the maximum and average values ​​of the abnormal environment data, and the detection threshold, the target detection threshold corresponding to the target volatility index, the maximum and average values ​​of the target abnormal environment data are determined.

6. The method for detecting abnormal environments according to claim 5, characterized in that, The relationship between the fluctuation index, the maximum and average values ​​of the abnormal environment data, and the detection threshold is as follows: Where THD is the detection threshold and ε is the volatility index. Let x be the average value of the target abnormal environment data within a preset number of days from time t. max (t) represents the maximum value of the target abnormal environment data within the preset number of days at time t.

7. The method for detecting abnormal environments according to claim 5, characterized in that, The method further includes: If the type of environment to be detected is not a preset environment type, the preset detection threshold will be used as the target detection threshold.

8. The method for detecting abnormal environments according to claim 1, characterized in that, The method further includes: The environmental data to be detected is input into a pre-trained abnormal environment analysis model; The weighted sum of the environmental data to be detected is determined based on the preset node weights of the neural network in the abnormal environment analysis model, and is used as the probability of the abnormal environment corresponding to the abnormal environment analysis model. If the probability of an abnormal environment exceeds a set threshold, the environment to be detected is determined to be an abnormal environment corresponding to an abnormal environment probability exceeding the set threshold.

9. A device for detecting abnormal environments, characterized in that, The device includes: The acquisition module is used to acquire information about the environment to be detected, including pedestrian flow data, environmental data, and environmental type. The determination module is used to determine the target preset busyness membership degree corresponding to the pedestrian flow data to be detected based on the relationship between pedestrian flow data and preset busyness membership degree; The determination module is also used to determine the target fluctuation index of the environment to be detected corresponding to the target preset busyness membership degree and the target preset output value based on the relationship between the preset busyness membership degree, the preset output value corresponding to the preset busyness degree and the fluctuation index, wherein the target preset output value is the preset output value corresponding to the target preset busyness degree. The determination module is also used to determine the corresponding target detection threshold based on the type of environment to be detected and the target fluctuation index; The judgment module is used to determine that the environment to be detected is an abnormal environment when the data of the environment to be detected exceeds the target detection threshold.

10. A terminal device, characterized in that, The device includes: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the abnormal environment detection method as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the abnormal environment detection method as described in any one of claims 1-8.

12. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs the abnormal environment detection method as described in any one of claims 1-8.

Images