Intelligent gas abnormal data analysis method, internet of things system and device, and medium

Abstract

This specification provides a method, IoT system, device, and medium for analyzing abnormal gas data. The method is based on the smart gas equipment management platform of the smart gas IoT system. The method includes: acquiring user characteristics and pipeline transportation characteristics of multiple gas users; clustering the gas users according to the user characteristics and pipeline transportation characteristics to obtain a first clustering result and a second clustering result, each of which includes one or more gas user clusters; for a gas user cluster: identifying potential abnormal gas users based on the equipment usage data and / or gas metering data of the gas users in the gas user cluster; identifying target abnormal users based on the abnormal gas users; and sending early warning information to the target abnormal users.

Description

Technical Field

[0001] This specification relates to the field of gas data processing technology, and in particular to a smart gas anomaly data analysis method, Internet of Things system and device and medium. Background Technology

[0002] The widespread use of natural gas has brought great convenience to social production and people's lives. However, some gas users engage in abnormal behaviors such as stealing or misusing gas. This not only causes economic losses to gas companies but may also affect the user experience of other gas users and pose a potential threat to social safety.

[0003] Therefore, there is a need to provide a smart gas anomaly data analysis method, IoT system and device and medium to quickly and accurately identify abnormal users and provide timely early warnings. Summary of the Invention

[0004] One embodiment of this specification provides a method for analyzing abnormal gas data. The method is executed based on the intelligent gas equipment management platform of an intelligent gas IoT system, and includes: acquiring user characteristics and pipeline transportation characteristics of multiple gas users; clustering the gas users according to the user characteristics and pipeline transportation characteristics to obtain a first clustering result and a second clustering result, each including one or more gas user clusters; for any gas user cluster: identifying potential abnormal gas users based on the equipment usage data and / or gas metering data of the gas users in the cluster; wherein the equipment usage data includes gas equipment and its gas consumption, and the gas metering data includes cumulative gas consumption values ​​at multiple times; the potential abnormal gas users include a first abnormal user and a second abnormal user; determining a target abnormal user based on the first abnormal user and the second abnormal user, wherein the first abnormal user is the potential abnormal gas user determined based on the first clustering result, and the second abnormal user is the potential abnormal gas user determined based on the second clustering result; and sending a warning message to the target abnormal user.

[0005] One embodiment of this specification provides a smart gas IoT system for analyzing gas anomaly data. The system includes a smart gas equipment management platform configured to execute a smart gas anomaly data analysis method.

[0006] One embodiment of this specification provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes a smart gas anomaly data analysis method.

[0007] One embodiment of this specification provides an apparatus for analyzing gas anomaly data, including a processor for executing a smart gas anomaly data analysis method. Attached Figure Description

[0008] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0009] Figure 1 This is an exemplary platform structure diagram of a smart gas IoT system according to some embodiments of this specification;

[0010] Figure 2 This is an exemplary flowchart of a smart gas anomaly data analysis method according to some embodiments of this specification;

[0011] Figure 3 This is an exemplary schematic diagram illustrating the determination of a first abnormal user according to some embodiments of this specification;

[0012] Figure 4 This is an exemplary schematic diagram illustrating the distribution of outlier users according to some embodiments of this specification;

[0013] Figure 5 This is an exemplary schematic diagram illustrating the determination of a second abnormal user according to some embodiments of this specification;

[0014] Figure 6 This is an exemplary schematic diagram illustrating the determination of a target abnormal user according to some embodiments of this specification. Detailed Implementation

[0015] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0016] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0017] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0018] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0019] Figure 1 This is an exemplary platform structure diagram of a smart gas IoT system according to some embodiments of this specification. Figure 1 As shown, the gas anomaly data analysis system based on the smart gas Internet of Things can include a smart gas user platform, a smart gas service platform, a smart gas equipment management platform, a smart gas sensor network platform, and a smart gas object platform connected in sequence.

[0020] A smart gas user platform is a platform for interacting with users. In some embodiments, the smart gas user platform can be configured as a terminal device.

[0021] In some embodiments, the smart gas user platform may include a gas user sub-platform, a government user sub-platform, and a regulatory user sub-platform.

[0022] The gas user sub-platform provides gas users with data related to gas usage and solutions to gas-related problems. Gas users can be industrial gas users, commercial gas users, or general gas users.

[0023] In some embodiments, the smart gas user platform can send warning information to gas users based on the gas user sub-platform. For more information on warning information, please refer to [link / reference]. Figure 2 And related explanations.

[0024] The government user sub-platform is a platform that provides gas operation-related data to government users. Government users can be personnel from government statistics, urban operation management, and other departments.

[0025] The supervisory user sub-platform is a platform for supervisory users to monitor the operation of the entire IoT system. Supervisory users can include personnel from security management departments, etc.

[0026] A smart gas service platform is a platform used to receive and transmit data and / or information.

[0027] In some embodiments, the smart gas service platform may include a smart gas consumption service sub-platform, a smart operation service sub-platform, and a smart supervision service sub-platform.

[0028] The Smart Gas Service Sub-Platform is a platform that provides gas users with information related to gas equipment.

[0029] The Smart Operation Service Sub-Platform is a platform that provides gas operation-related information to government users.

[0030] The intelligent supervision service sub-platform is a platform that provides safety supervision-related information to regulatory users.

[0031] In some embodiments, the various sub-platforms of the smart gas service platform can interact with the various sub-platforms of the smart gas user platform.

[0032] A smart gas equipment management platform refers to a platform that coordinates and integrates the connections and collaborations between various functional platforms.

[0033] In some embodiments, the smart gas equipment management platform may include a smart gas indoor equipment parameter management sub-platform, a smart gas pipeline equipment parameter management sub-platform, and a smart gas data center.

[0034] A smart gas data center is used to store and manage operational information. In some embodiments, the smart gas data center can be configured as a storage device for storing and managing user characteristics and pipeline transportation characteristics, etc. For more information on user characteristics and pipeline transportation characteristics, please refer to [link to relevant documentation]. Figure 2 And related explanations.

[0035] The Smart Gas Indoor Equipment Management Sub-Platform is a platform used to process information related to indoor equipment.

[0036] The intelligent gas pipeline network equipment management sub-platform is a platform used to process information related to pipeline network equipment.

[0037] In some embodiments, the smart gas indoor equipment management sub-platform and the smart gas pipeline equipment management sub-platform include, but are not limited to, an equipment operation parameter monitoring and early warning module and an equipment parameter remote management module.

[0038] The equipment operation parameter monitoring and early warning module is used to monitor and issue early warnings for equipment operation parameters. In some embodiments, the smart gas indoor equipment management sub-platform and the smart gas pipeline equipment management sub-platform can respectively analyze and process the data output by the equipment operation parameter monitoring and early warning module.

[0039] The equipment parameter remote management module is a module for remotely managing the relevant parameters of gas equipment. In some embodiments, the smart gas indoor equipment management sub-platform and the smart gas pipeline equipment management sub-platform can respectively use the equipment parameter remote management module to remotely set, adjust, and authorize user characteristics and pipeline transportation characteristics.

[0040] The intelligent gas sensor network platform is a functional platform for managing sensor communication. In some embodiments, the intelligent gas sensor network platform can be configured as a communication network and a gateway.

[0041] In some embodiments, the smart gas sensor network platform may include a smart gas indoor equipment sensor network sub-platform and a smart gas pipeline equipment sensor network sub-platform.

[0042] The smart gas indoor equipment sensor network sub-platform is used to obtain the operating information of gas indoor equipment and can interact with the smart gas indoor equipment object sub-platform.

[0043] The intelligent gas pipeline network equipment sensor network sub-platform is used to obtain the operation information of gas pipeline network equipment and can interact with the intelligent gas pipeline network equipment object sub-platform.

[0044] In some embodiments, each sub-platform of the smart gas sensor network platform can interact with each sub-platform of the smart gas object platform.

[0045] A smart gas object platform refers to a functional platform used to acquire sensing information. In some embodiments, the smart gas object platform can be configured as various types of devices, including gas equipment (such as indoor equipment and pipeline equipment) and other equipment (such as monitoring equipment).

[0046] In some embodiments, the smart gas object platform may include, but is not limited to, a smart gas indoor equipment object sub-platform and a smart gas pipeline equipment object sub-platform.

[0047] In some embodiments, the gas indoor equipment object sub-platform can be configured as various gas indoor equipment of gas users, such as gas meters of gas users.

[0048] In some embodiments, the gas pipeline equipment object sub-platform can be configured to include various types of pipeline equipment and monitoring equipment. Pipeline equipment may include gas gate compressors, gas flow meters, valve control devices, etc. Monitoring equipment may include temperature sensors, pressure sensors, etc.

[0049] In some embodiments, the smart gas service platform can interact with the smart gas user platform. For example, the smart gas service platform can send warning messages to the smart gas user platform.

[0050] In some embodiments, the smart gas equipment management platform can interact with the smart gas service platform and the smart gas sensor network platform through a smart gas data center. For example, the smart gas data center can send early warning information to the smart gas service platform. As another example, the smart gas data center can send instructions to the smart gas sensor network platform to obtain user characteristics and pipeline transportation characteristics.

[0051] In some embodiments, the smart gas sensor network platform can interact with the smart gas object platform. For example, the smart gas sensor network platform can send instructions to the smart gas object platform to obtain user characteristics and pipeline transportation characteristics, and then upload these characteristics to the smart gas data center.

[0052] For detailed explanations of the above content, please refer to other parts of this instruction manual, such as... Figures 2 to 6 The description.

[0053] It should be noted that the above description of the system and its components is for convenience only and should not limit this specification to the scope of the embodiments described.

[0054] Figure 2 This is an exemplary flowchart of a smart gas anomaly data analysis method according to some embodiments of this specification. In some embodiments, process 200 can be executed by a smart gas equipment management platform. Figure 2 As shown, process 200 includes the following steps:

[0055] Step 210: Obtain user characteristics and pipeline transportation characteristics of multiple gas users.

[0056] User characteristics refer to features that reflect the user level. For example, user characteristics may include gas appliance type, user type, monthly usage, etc. In some embodiments, the smart gas appliance management platform can obtain user characteristics through the smart gas user platform.

[0057] Pipeline transportation characteristics refer to the features related to gas transportation within a gas pipeline network. For example, pipeline transportation characteristics may include the complexity of the pipelines and whether the pipelines belong to the same branch. In some embodiments, the intelligent gas equipment management platform can obtain pipeline transportation characteristics through the intelligent gas object platform.

[0058] Step 220: Based on user characteristics and pipeline transportation characteristics, gas users are clustered to obtain the first clustering result and the second clustering result.

[0059] In some embodiments, the intelligent gas equipment management platform can construct corresponding vectors for gas users based on user characteristics and pipeline transportation characteristics, use vector distance to measure the similarity of corresponding features, and group them based on similarity. This ensures that gas users in the same group have high similarity in their user characteristics or pipeline transportation characteristics, while gas users in different groups have low similarity in their user characteristics or pipeline transportation characteristics. Then, through clustering based on user characteristics and clustering based on pipeline transportation characteristics, respectively, a first clustering result and a second clustering result are obtained. The first clustering result and the second clustering result each include one or more gas user clusters.

[0060] A gas user cluster refers to a group of gas users. A gas user cluster includes one or more gas users.

[0061] The first clustering result refers to one or more gas user clusters obtained by clustering gas users based on user characteristics.

[0062] The second clustering result refers to one or more gas user clusters obtained by clustering gas users based on pipeline transportation characteristics.

[0063] Step 230: For any gas user cluster: Identify potential abnormal gas users based on the equipment usage data and / or gas metering data of the gas users in the gas user cluster.

[0064] Equipment usage data refers to data related to the gas usage of equipment. For example, equipment usage data may include the type of gas equipment and its gas consumption. In some embodiments, the smart gas equipment management platform can obtain equipment usage data through a smart gas object platform.

[0065] Gas metering data refers to data related to gas usage. For example, gas metering data may include cumulative gas usage values ​​at multiple points in time.

[0066] Potential gas users with abnormal gas usage are those with a high probability of experiencing gas malfunctions. Smart gas equipment management platforms can identify potential gas users with abnormal usage through various methods. For example, based on historical data, the platform can determine standard equipment usage data and / or standard gas metering data. Gas users whose equipment usage data and / or gas metering data differ from the standard equipment usage data and / or standard gas metering data by a significant margin are identified as potential gas users with abnormal usage.

[0067] In some embodiments, potential abnormal gas users include a first abnormal user and a second abnormal user.

[0068] The first anomalous user is a potential anomalous gas user identified based on the first clustering result. The intelligent gas equipment management platform can determine the first anomalous user in various ways. For example, the intelligent gas equipment management platform can preset the standard user characteristics corresponding to each gas user cluster in the first clustering result, and determine the gas users in each gas user cluster whose user characteristics differ from their corresponding standard user characteristics by more than a feature threshold as the first anomalous user.

[0069] In some embodiments, the intelligent gas equipment management platform can determine the first abnormal user based on histogram distribution. For further explanation on how to determine the first abnormal user, see [link to documentation]. Figure 3 And its related descriptions.

[0070] The second abnormal user is a potential abnormal gas user identified based on the results of the second clustering. The intelligent gas equipment management platform can identify the second abnormal user in a similar way to identifying the first abnormal user.

[0071] In some embodiments, the intelligent gas equipment management platform can also identify the first abnormal user based on a reference correlation coefficient. For further explanation on how to identify the second abnormal user, please refer to [link to relevant documentation]. Figure 5 And its related descriptions.

[0072] Step 240: Determine the target abnormal user based on the first abnormal user and the second abnormal user.

[0073] A target abnormal user refers to a user who has been identified as experiencing an abnormality. The intelligent gas equipment management platform can identify target abnormal users in various ways. In some embodiments, the platform can identify a gas user who is simultaneously a first abnormal user and a second abnormal user as a target abnormal user. For more information on identifying target abnormal users, please refer to [link to relevant documentation]. Figure 6 .

[0074] Step 250: Send a warning message to the target abnormal user.

[0075] Warning information refers to alerts issued based on anomalies. In some embodiments, warning information can be predetermined.

[0076] In some embodiments, the intelligent gas equipment management platform can send warning information to the terminal of the target abnormal user through text, voice, or other means.

[0077] Some embodiments in this specification, through the analysis of equipment usage data and / or gas metering data of clustered gas users, can screen out potential abnormal gas users by combining data from a large number of gas users, thereby identifying target abnormal users and sending early warning information to them in a timely manner to avoid potential safety risks and gas leaks, thus improving the efficiency and safety of gas management.

[0078] It should be noted that the above description of the process is for illustrative purposes only and does not limit the scope of this specification. Those skilled in the art can make various modifications and changes to the process under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0079] Figure 3 This is an exemplary schematic diagram illustrating the determination of a first abnormal user according to some embodiments of this specification.

[0080] In some embodiments, the intelligent gas equipment management platform can generate multiple histogram distributions 330 for one or more gas user clusters in the first clustering result 310 based on multiple preset gas usage characteristics 320; for any histogram distribution 330, identify one or more outlier users 340 in the histogram distribution 330; count the number 350 times each gas user in the first clustering result 310 is identified as an outlier user 340 in the multiple histogram distributions 330; and based on at least the number 350, identify the first abnormal user 360 in the gas user cluster.

[0081] In some embodiments, the clustering parameters corresponding to the first clustering result 310 include at least one of gas equipment type, user type, and monthly usage.

[0082] Gas appliance type refers to the category of gas appliances used by a user. In some embodiments, the smart gas appliance management platform can obtain the gas appliance type through the smart gas user platform.

[0083] User type refers to the classification of gas user usage patterns. For example, user types can include residential gas users, commercial gas users, and industrial gas users. In some embodiments, the smart gas equipment management platform can obtain user types through the smart gas user platform.

[0084] Monthly usage refers to the total amount of gas used by a gas user within a month. In some embodiments, the smart gas equipment management platform can obtain the monthly usage through the smart gas object platform.

[0085] In some embodiments of this specification, the clustering parameters corresponding to the first clustering result include at least one of gas equipment type, user type, and monthly usage, which can more comprehensively analyze the needs and behavior patterns of gas users, making the first clustering result more accurate and representative.

[0086] Preset gas usage characteristics 320 refer to characteristics at the gas usage level. For example, preset gas usage characteristics 320 may include average daily gas consumption, average hourly gas consumption, peak usage range, gas ignition frequency, etc. In some embodiments, the smart gas equipment management platform can obtain preset gas usage characteristics 320 through the smart gas object platform.

[0087] The histogram distribution 330 refers to the frequency distribution of preset gas usage characteristics taking different values ​​within a certain range. This frequency distribution can be determined based on the historical gas usage data of gas users.

[0088] In some embodiments, the histogram distribution 330 can be generated based on a preset gas usage characteristic 320 for each gas user in a gas user cluster. For example, a histogram distribution 330 can be generated for a preset gas usage characteristic 320 for multiple gas users in a gas user cluster.

[0089] Outlier user 340 refers to a user who differs significantly from other gas users. In some embodiments, the intelligent gas equipment management platform can identify gas users whose data points in the histogram distribution are abnormally far from other gas users as outlier user 340. For example, the outlier value of each gas user can be determined based on the histogram distribution, and gas users whose outlier value exceeds a distance threshold can be identified as outlier user 340. For example, the outlier value can be obtained based on Mahalanobis distance.

[0090] In some embodiments, the intelligent gas equipment management platform can count the number of times each gas user is identified as an outlier 340 in multiple histogram distributions 330 in the first clustering result 310.

[0091] In some embodiments, the intelligent gas equipment management platform can identify the gas user who is identified as an outlier 340 the most times in each gas user cluster as the first abnormal user 360 in that gas user cluster.

[0092] In some embodiments, the intelligent gas equipment management platform can identify gas users who meet the preset number of conditions 350 times as the first abnormal user 360, and determine the first abnormal probability of the first abnormal user 360.

[0093] In some embodiments, the preset frequency condition includes an outlier threshold. For example, the preset frequency condition could be that the number of times user 340 is identified as an outlier (350) is greater than the outlier threshold. In some embodiments, the outlier threshold can be preset.

[0094] In some embodiments, the outlier threshold is related to the degree of outlier a gas user is identified as outlier user 340. For example, the lower the degree of outlier, the higher the outlier threshold.

[0095] Outlier degree can represent the distance of outlier users from the interval with the most concentrated distribution in a histogram. In some embodiments, outlier degree can be represented based on outlier values ​​or by equivalent substitution.

[0096] In some embodiments, the degree of outlier a gas user is identified as an outlier (hereinafter referred to as the gas user's overall outlier) can be determined based on multiple histogram distributions corresponding to when the gas user is identified as an outlier. For example, the gas user's overall outlier can be the sum of the outlier values ​​of the gas user in the multiple histogram distributions corresponding to when the gas user is identified as an outlier.

[0097] In some embodiments, the intelligent gas equipment management platform can perform weighted processing on the outlier degree of a gas user when it is identified as an outlier user 340 multiple times in multiple histogram distributions 330, and use the weighted value as the outlier degree of the gas user when it is identified as an outlier user, that is, the comprehensive outlier degree of the gas user.

[0098] For example, the overall outlier degree of a gas user can also be the sum of the weights of the outlier values ​​of the gas user in the multiple histogram distributions 330 corresponding to the gas user being identified as an outlier user 340.

[0099] In some embodiments, the weights in the weighted processing are related to preset gas usage characteristics. For example, the smart gas equipment management platform can preset the weights corresponding to each preset gas usage characteristic, and then the weight values ​​corresponding to outliers determined based on the preset gas usage characteristics corresponding to the histogram distribution can be determined.

[0100] In some embodiments of this specification, by using the weighted value as the degree of outlier when a gas user is identified as an outlier, the degree of outlierness can more accurately reflect user behavior.

[0101] Some embodiments in this specification include preset frequency conditions, including outlier thresholds, which can comprehensively analyze users' gas usage behavior and more accurately identify outlier users.

[0102] The first anomalous probability of the first anomalous user 360 refers to the probability that the first anomalous user 360 is the target anomalous gas user. In some embodiments, the first anomalous probability can be determined based on the number of times the first anomalous user 360 is identified as an outlier and an outlier threshold. For example, the first anomalous probability can be calculated using formula (1):

[0103]

[0104] Where A represents the first anomaly probability, x is the number of times a user is identified as an outlier, and x0 is the outlier threshold.

[0105] In some embodiments of this specification, by identifying the gas user whose number of occurrences meets a preset number of conditions as the first abnormal user, the accuracy of identifying the first abnormal user can be improved, and the sensitivity of the judgment can be controlled by adjusting the preset number of occurrences conditions.

[0106] In some embodiments, the intelligent gas equipment management platform may determine the first abnormal user 360 based at least on the number 350 using a predictive model.

[0107] The predictive model can be a machine learning model. For example, the predictive model can be a deep neural network (DNN) model, a convolutional neural network (CNN) model, or any combination thereof.

[0108] In some embodiments, the input to the prediction model may include the histogram distribution 330 of various preset gas usage characteristics and the outlier user distribution, and the output may be the first abnormal user 360 and its first abnormal probability.

[0109] Outlier distribution refers to the distribution of the number of times each gas user is identified as an outlier. In some embodiments, outlier distribution can be represented using an outlier distribution graph. For further explanation of outlier distribution graphs, see [link to documentation]. Figure 4 And related content.

[0110] In some embodiments, the prediction model can be trained using first training samples with a first label. Multiple first training samples with the first label can be input into the initial prediction model. A loss function is constructed using the first label and the output of the initial prediction model. The parameters of the initial prediction model are then iteratively updated based on the loss function. Model training is complete when the loss function of the initial prediction model satisfies a preset condition, resulting in a trained prediction model. The preset condition may be loss function convergence, the number of iterations reaching a threshold, etc.

[0111] The first training sample may include the histogram distribution of the pre-defined gas usage characteristics of the sample and the distribution of outlier users. The first label can be obtained by labeling historically identified outlier users (1) and non-outlier users (0) in the sample users corresponding to the outlier distribution. The first training sample and the first label can be obtained based on historical data.

[0112] Some embodiments in this specification process the histogram distribution and outlier user distribution of preset gas usage characteristics through a prediction model. By utilizing the self-learning capability of the machine learning model, patterns can be found from a large number of preset gas usage characteristics, and the correlation between the first abnormal user and the preset gas usage characteristics can be obtained, thereby improving the accuracy and efficiency of identifying the first abnormal user.

[0113] Some embodiments in this specification generate multiple histogram distributions for each gas user cluster based on multiple preset gas usage characteristics, identify outliers, and determine the first abnormal user based on the number of occurrences. This approach can more comprehensively discover potential first abnormal users and improve the coverage and reliability of anomaly detection.

[0114] Figure 4 This is an exemplary schematic diagram illustrating the distribution of outlier users according to some embodiments of this specification.

[0115] In some embodiments, the input to the prediction model includes a map of outlier user distributions.

[0116] An outlier distribution graph is a graph that reflects the distribution of outliers. In some embodiments, the outlier distribution graph may include nodes and node characteristics, edges and edge characteristics, etc.

[0117] The node corresponds to a gas user identified as an outlier. For example, Figure 4 The circles in the graph can represent nodes in the outlier user distribution map.

[0118] In some embodiments, node characteristics may include the number of times a gas user has been identified as an outlier, the environment in which the gas user resides, and historical maintenance data of the gas user's gas metering equipment. For more information on the number of times a user has been identified as an outlier, please refer to [link to relevant documentation]. Figure 3 And related explanations.

[0119] The environment in which a gas user is located refers to the specific environmental conditions and circumstances in which the gas user is located. For example, the environment in which a gas user is located may include geographical environment (such as location, weather, climate, etc.) and social environment (such as population density, residents' lifestyles, etc.).

[0120] Historical maintenance data for gas metering equipment refers to maintenance-related data generated during past maintenance of the equipment. For example, historical maintenance data for gas metering equipment may include maintenance records, maintenance time, maintenance location, and maintenance duration.

[0121] The edges correspond to the gas pipelines between gas users. For example, Figure 4 Line segments between nodes can represent edges in an outlier user distribution graph.

[0122] In some embodiments, edge features may include the distance between gas users. For example, the edge feature of the edge between node A and node B may be the pipe length corresponding to the edge between node A and node B.

[0123] In some embodiments, by inputting an outlier user distribution map into the prediction model, the intrinsic correlation between the number of times each user is identified as an outlier and the probability of anomaly can be analyzed, thereby improving the accuracy of identifying potential abnormal gas users.

[0124] Figure 5 This is an exemplary schematic diagram illustrating the determination of a second abnormal user according to some embodiments of this specification.

[0125] In some embodiments, the intelligent gas equipment management platform can, for a gas user cluster in the second clustering result 510: calculate a reference correlation coefficient 530 for any two gas users in the gas user cluster based on the gas metering data 520 of historical gas users; determine at least one associated user 540 for each gas user in the gas user cluster based on the reference correlation coefficient 530; and determine whether the gas user is a second abnormal user 560 based on the equipment usage data 550 of the gas user and its associated user 540 and the gas metering data 520.

[0126] In some embodiments, the clustering parameters corresponding to the second clustering result 510 include at least one of the following: the complexity of the pipeline where the gas user is located, and whether the pipeline where the gas user is located belongs to the same branch. For further explanation of the clustering parameters, refer to the explanation of the clustering parameters in the first clustering result.

[0127] The complexity of a pipeline refers to the complexity of its structure. For example, the complexity of a pipeline can be related to the types and quantities of its components, its shape, etc. In some embodiments, the intelligent gas equipment management platform can obtain the complexity of the pipeline through the intelligent gas object platform.

[0128] Whether a pipeline belongs to the same branch refers to whether the pipeline where the gas user is located belongs to / is located on the same pipeline branch. In some embodiments, the smart gas equipment management platform can obtain whether the pipeline belongs to the same branch through the smart gas object platform.

[0129] In some embodiments of this specification, the clustering parameters corresponding to the second clustering result include the complexity of the pipeline and whether the pipeline belongs to at least one of the same branch. This allows for a more comprehensive analysis of the transportation situation of gas pipelines, making the second clustering result more accurate and representative.

[0130] For more information regarding gas metering data 520, please see [link / reference]. Figure 2 And its related descriptions.

[0131] The reference correlation coefficient 530 is a parameter determined based on historical gas data of gas users, representing the degree of correlation between two gas users. In some embodiments, the intelligent gas equipment management platform can calculate the reference correlation coefficient 530 between two gas users based on the gas metering data of any two historical gas users. For example, the reference correlation coefficient 530 between gas user A and gas user B can be obtained based on formula (2):

[0132]

[0133] Where R is the reference correlation coefficient (530) between gas user A and gas user B, cov is the covariance of historical gas metering data for gas user A and gas user B, and y std z is the standard deviation of gas user A's historical gas metering data. std It is the standard deviation of the historical gas metering data of gas user B.

[0134] Associated user 540 refers to other gas users whose gas metering data is highly correlated with that of the gas user. In some embodiments, the smart gas equipment management platform can identify gas users in a gas user cluster whose reference correlation coefficient with a certain gas user is greater than a coefficient threshold as associated users 540 of that gas user in that gas user cluster, and thus identify all associated users 540 of that gas user.

[0135] In some embodiments, the smart gas equipment management platform can identify the second abnormal user 560 based on various methods. For example, the smart gas equipment management platform can use time series analysis to predict future equipment usage data and gas metering data based on the historical equipment usage data and gas metering data of gas users and their associated users 540, and identify gas users whose equipment usage data 550 and gas metering data 520 differ from the predicted values ​​beyond the usage threshold as the second abnormal user.

[0136] In some embodiments, the intelligent gas equipment management platform may, for a gas user,: obtain the actual correlation coefficient between the gas user and an associated user 540; determine the sub-difference between the actual correlation coefficient and its corresponding reference correlation coefficient 53; perform weighted processing on the multiple sub-differences of the gas user to obtain a comprehensive difference; and, in response to the comprehensive difference satisfying a preset difference condition, determine the gas user as a second abnormal user 560 and calculate the second abnormal probability of the second abnormal user 560.

[0137] The actual correlation coefficient is a parameter determined based on the gas user's current gas data, representing the degree of correlation between the gas user and its associated users (540). In some embodiments, the smart gas equipment management platform can calculate the actual correlation coefficient based on the gas user's current gas metering data and that of its associated users (540). The specific calculation method can refer to the aforementioned method for calculating the reference correlation coefficient.

[0138] Sub-difference refers to the difference between the actual correlation coefficient and the reference correlation coefficient between a gas user and an associated user 540. In some embodiments, sub-difference can be determined by subtracting the actual correlation coefficient from its corresponding reference correlation coefficient 530.

[0139] The overall difference can represent the degree of difference between the gas user and all associated users 540. In some embodiments, the overall difference can be determined by weighting multiple sub-differences between the gas user and multiple associated users 540.

[0140] In some embodiments, during the weighted processing, the weight of a sub-difference is positively correlated with the value of a reference correlation coefficient 530. For example, the larger the value of a reference correlation coefficient 530, the larger the weight of the sub-difference determined based on that reference correlation coefficient 530.

[0141] In some embodiments of this specification, the weight of sub-differences is positively correlated with the value of the reference correlation coefficient. The larger the reference correlation coefficient, the more attention will be paid to the differences between gas users, and the more accurately the overall differences can be assessed.

[0142] In some embodiments, during the weighted processing, the weights of the sub-differences are related to the first clustering result of the gas user and associated user 540.

[0143] For example, if gas user A and associated user B belong to the same gas user cluster in the first clustering result, then the sub-difference weight corresponding to associated user B is larger.

[0144] In some embodiments of this specification, the weight of sub-differences is related to the first clustering results of gas users and associated users. Differences between gas users belonging to the same gas user cluster are given higher importance, and the overall differences can be evaluated more accurately.

[0145] The preset difference condition refers to the conditions that the gas user identified as the second abnormal user 560 must meet in terms of overall difference. In some embodiments, the preset difference condition may include a difference threshold. For example, the preset difference condition may be that the overall difference is greater than the difference threshold. The difference threshold can be manually set and determined.

[0146] The second abnormal probability of the second abnormal user 560 refers to the probability that the second abnormal user is the target abnormal gas user. In some embodiments, the second abnormal probability can be determined based on a comprehensive difference and a difference threshold. For example, the second abnormal probability can be calculated using formula (3):

[0147]

[0148] Where B represents the second anomaly probability, t is the overall difference, and t0 is the difference threshold.

[0149] In some embodiments of this specification, the comprehensive difference is calculated by combining the actual correlation coefficient and the corresponding reference correlation coefficient, which can be used to refer to the current usage of the associated user in order to improve the accuracy of identifying the second abnormal user.

[0150] Some embodiments of this specification identify at least one associated user based on correlation coefficients, and determine whether a gas user is the second abnormal user based on the equipment usage data of the gas user and its associated users, as well as gas metering data. This better identifies potential second abnormal users based on the correlation between users, improving the coverage and reliability of anomaly detection.

[0151] Figure 5 This is an exemplary schematic diagram illustrating the determination of a target abnormal user according to some embodiments of this specification.

[0152] In some embodiments, the intelligent gas equipment management platform can identify a first abnormal user 360 and a second abnormal user 560 as a candidate abnormal user 620; based on the candidate abnormal user 620, a target abnormal user 640 is determined, and the first abnormal probability 610 and the second abnormal probability 630 of the target abnormal user 640 satisfy a preset probability condition.

[0153] Candidate abnormal user 620 refers to the gas user to be confirmed as target abnormal user 640. (Smart Gas Equipment Management Platform)

[0154] Preset probability conditions refer to the conditions that must be met to be identified as a target abnormal user.

[0155] In some embodiments, the preset probability condition includes a first preset probability. For example, the preset probability condition includes at least one of a first abnormal probability 610 and a second abnormal probability 630 being greater than the first preset probability. The first preset probability can be preset.

[0156] In some embodiments, the first preset probability is correlated with at least one of an outlier threshold and a difference threshold. For example, the first preset probability is negatively correlated with both the outlier threshold and the difference threshold. For further explanation of the outlier threshold, see [link to relevant documentation]. Figure 3 And its related description. For more information on difference thresholds, see [link to relevant documentation / description]. Figure 5And its related descriptions.

[0157] In some embodiments of this specification, the larger the outlier threshold and the difference threshold, the more lenient the monitoring of anomalies. In this case, the first preset probability can be appropriately reduced to increase the monitoring intensity of anomalies, making the selection of target abnormal gas users more reasonable.

[0158] In some embodiments, the preset probability condition includes a probability summation value greater than a first preset probability.

[0159] The probability summation value is a weighted sum of the first anomaly probability 610 and the second anomaly probability 620. In some embodiments, the weights of the weighted summation can be preset.

[0160] In some embodiments of this specification, the preset probability condition includes a probability summation value greater than a first preset probability, which can fully consider the situation where the first abnormal user and the second abnormal user occur simultaneously, and more accurately determine the target abnormal user.

[0161] In some embodiments, the intelligent gas equipment management platform can identify the candidate abnormal users whose first abnormal probability and second abnormal probability satisfy the aforementioned preset probability conditions as target abnormal users.

[0162] Some embodiments of this specification provide a computer-readable storage medium that stores computer instructions, which, when executed by a computer, implement the intelligent gas anomaly data analysis method described in any one of the embodiments of this specification.

[0163] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0164] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0165] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0166] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0167] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0168] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0169] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method for analyzing abnormal gas data, executed on the intelligent gas equipment management platform of an intelligent gas IoT system, characterized in that, include: Obtain user characteristics and pipeline transportation characteristics of multiple gas users; The pipeline transportation characteristics include the complexity of the pipeline where the gas user is located and whether the pipeline where the gas user is located belongs to the same branch; Based on the user characteristics, the gas users are clustered to obtain a first clustering result. The clustering parameters corresponding to the first clustering result include at least one of gas equipment type, user type, and monthly usage. Based on the pipeline transportation characteristics, the gas users are clustered to obtain a second clustering result. The clustering parameters corresponding to the second clustering result include at least one of the following: the complexity of the pipeline where the gas user is located, and whether the pipeline where the gas user is located belongs to the same branch. The first clustering result and the second clustering result each include one or more gas user clusters. For any one of the gas user clusters: Based on the equipment usage data and / or gas metering data of the gas users in the gas user cluster, potential abnormal gas users are identified; wherein, the equipment usage data includes gas equipment and its gas consumption, and the gas metering data includes the cumulative gas consumption values ​​at multiple times; the potential abnormal gas users include a first abnormal user and a second abnormal user; Target abnormal users are determined based on the first abnormal user and the second abnormal user, where the first abnormal user is the potential abnormal gas user determined based on the first clustering result, and the second abnormal user is the potential abnormal gas user determined based on the second clustering result. Send warning information to the target abnormal user; The step of identifying potential abnormal gas users based on the equipment usage data and / or gas metering data of the gas users in the gas user cluster includes: For one of the gas user clusters in the second clustering result: Based on historical gas metering data of gas users, a reference correlation coefficient is calculated for any two gas users in the gas user cluster. Based on the reference correlation coefficient, at least one associated user of each gas user in the gas user cluster is determined; Based on the equipment usage data and gas metering data of the gas user and its associated users, it is determined whether the gas user is the second abnormal user.

2. The method according to claim 1, characterized in that, The step of identifying potential abnormal gas users based on the equipment usage data and / or gas metering data of the gas users in the gas user cluster includes: For one or more gas user clusters in the first clustering result, multiple histogram distributions are generated based on multiple preset gas usage characteristics. For any given histogram distribution, identify one or more outlier users within the histogram distribution; The number of times each gas user is identified as an outlier in the multiple histogram distributions in the first clustering result is counted. Based at least on the number of occurrences, the first abnormal user in the gas user cluster is identified.

3. The method according to claim 2, characterized in that, The determination of the first abnormal user in the gas user cluster based at least on the number of times includes: The gas user whose number of occurrences meets the preset number of conditions is identified as the first abnormal user, and the first abnormal probability of the first abnormal user is determined.

4. The method according to claim 2, characterized in that, The determination of the first abnormal user in the gas user cluster based at least on the number of times includes: Based at least on the number of occurrences, the first abnormal user is identified using a prediction model, which is a machine learning model.

5. The method according to claim 1, characterized in that, The step of determining the target abnormal user based on the first abnormal user and the second abnormal user includes: Identify users who belong to both the first and second abnormal users as candidate abnormal users; Based on the candidate abnormal users, the target abnormal user is determined, and the first abnormal probability and the second abnormal probability of the target abnormal user satisfy a preset probability condition.

6. A smart gas IoT system for analyzing abnormal gas data, characterized in that, The system includes a smart gas equipment management platform, which is configured to perform the following operations: Obtain user characteristics and pipeline transportation characteristics of multiple gas users; The pipeline transportation characteristics include the complexity of the pipeline where the gas user is located and whether the pipeline where the gas user is located belongs to the same branch; Based on the user characteristics, the gas users are clustered to obtain a first clustering result. The clustering parameters corresponding to the first clustering result include at least one of gas equipment type, user type, and monthly usage. Based on the pipeline transportation characteristics, the gas users are clustered to obtain a second clustering result. The clustering parameters corresponding to the second clustering result include at least one of the following: the complexity of the pipeline where the gas user is located, and whether the pipeline where the gas user is located belongs to the same branch. The first clustering result and the second clustering result each include one or more gas user clusters. For one of the aforementioned gas user clusters: Based on the equipment usage data and / or gas metering data of the gas users in the gas user cluster, potential abnormal gas users are identified; wherein, the equipment usage data includes gas equipment and its gas consumption, and the gas metering data includes the cumulative gas consumption values ​​at multiple times; the potential abnormal gas users include a first abnormal user and a second abnormal user; Target abnormal users are determined based on the first abnormal user and the second abnormal user, where the first abnormal user is the potential abnormal gas user determined based on the first clustering result, and the second abnormal user is the potential abnormal gas user determined based on the second clustering result. Send warning information to the target abnormal user; The step of identifying potential abnormal gas users based on the equipment usage data and / or gas metering data of the gas users in the gas user cluster includes: For one of the gas user clusters in the second clustering result: Based on historical gas metering data of gas users, a reference correlation coefficient is calculated for any two gas users in the gas user cluster. Based on the reference correlation coefficient, at least one associated user of each gas user in the gas user cluster is determined; Based on the equipment usage data and gas metering data of the gas user and its associated users, it is determined whether the gas user is the second abnormal user.

7. The system according to claim 6, characterized in that, The smart gas IoT system includes a smart gas user platform, a smart gas service platform, a smart gas equipment management platform, a smart gas sensor network platform, and a smart gas object platform that interact sequentially. The smart gas service platform is used to send the early warning information to the smart gas user platform; The smart gas object platform is used to acquire gas user characteristics, gas pipeline transportation characteristics, equipment usage data and gas metering data, and transmit them to the smart gas equipment management platform through the smart gas sensor network platform. The smart gas user platform includes a gas user sub-platform, a government user sub-platform, and a regulatory user sub-platform. The smart gas service platform includes a smart gas consumption service sub-platform, a smart operation service sub-platform, and a smart supervision service sub-platform. The intelligent gas equipment management platform includes an intelligent gas indoor equipment parameter management sub-platform, an intelligent gas pipeline equipment parameter management sub-platform, and an intelligent gas data center. The intelligent gas indoor equipment parameter management sub-platform includes an equipment operation parameter monitoring and early warning module and an equipment parameter remote management module. The intelligent gas pipeline equipment parameter management sub-platform includes an equipment operation parameter monitoring and early warning module and an equipment parameter remote management module. The intelligent gas sensing network platform includes an intelligent gas indoor equipment sensing network sub-platform and an intelligent gas pipeline equipment sensing network sub-platform. The smart gas platform includes a smart gas indoor equipment platform and a smart gas pipeline equipment platform.

8. A computer-readable storage medium storing computer instructions, wherein when a computer reads the computer instructions in the storage medium, the computer executes the intelligent gas anomaly data analysis method as described in any one of claims 1-5.

9. An apparatus for analyzing abnormal gas flow data, comprising a processor, characterized in that, The processor is used to execute the intelligent gas anomaly data analysis method as described in any one of claims 1-5.

Images