System and method for monitoring abnormal metering data of intelligent water meter

Abstract

The invention relates to the technical field of intelligent monitoring, and particularly discloses an intelligent water meter metering data abnormity monitoring system and method.Metered data of an intelligent water meter is sent to a remote monitoring center through a built-in communication module of the intelligent water meter, and meanwhile a data processing algorithm is deployed in the remote monitoring center; the method comprises the following steps: segmenting intelligent water meter measurement data into continuous time sequence fragments according to a preset time step length, taking a measurement data fragment at the tail end as a verification reference, and carrying out secondary stacking time sequence coding on the intelligent water meter measurement data fragments in a historical period so as to capture deep time sequence characteristics of the intelligent water meter measurement data; and performing water meter measurement data reasoning under the current time step, and further realizing abnormality judgment on the measurement data based on comparison between a reasoning result and a verification reference. The method can effectively reduce dependence on preset rules, dynamically adapt to diversified water use scenes, and reduce misinformation and missed detection risks.

Description

Technical Field

[0001] The present application relates to the field of intelligent monitoring technology, and more specifically, to a system and method for monitoring abnormal measurement data of an intelligent water meter. Background Art

[0002] In modern smart water systems, smart water meters are key terminal devices for water supply data collection. The accuracy of their metering data is crucial to ensuring the efficient operation of the water supply system, reasonable billing, and timely detection of pipe network leakage and other problems. In this regard, the invention patent with publication number CN118211160A proposes a water meter metering data anomaly monitoring method, which breaks down the original water meter metering data into fine-grained units, and comprehensively characterizes water use behavior by mining its stage metering state element vector (short-term features) and period metering state element vector (long-term features). At the same time, the knowledge embedding technology is introduced to convert the preset anomaly monitoring rules (such as time period thresholds, seasonal water use patterns) into computable embedding vectors, and establish a deep association between data patterns and rules. Finally, a comprehensive decision vector is generated by integrating the above short-term stage characteristics, long-term cycle characteristics and rule characteristics to quantitatively evaluate the deviation of water use status and identify data anomalies.

[0003] In the prior art, the anomaly monitoring rule characteristics refer to a series of predefined rules or standards used when monitoring data anomalies, which describe the patterns or behaviors that data should follow under normal circumstances. When the actual data does not match the rule characteristics, it may be identified as an anomaly. However, the anomaly monitoring rules are constructed based on historical data and expert knowledge to describe and identify common abnormal behavior patterns in water meter data. The rigid nature of this preset rule limits its ability to identify new abnormal behaviors and makes it difficult to cope with complex and changing water use scenarios. For example, sudden water use events, the introduction of new water use equipment, or changes in regional water use behaviors may cause the preset rules to fail, resulting in false alarms or missed detections.

[0004] Therefore, an optimized smart water meter measurement data abnormality monitoring system and method are expected. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a smart water meter metering data anomaly monitoring system and method, which uses the built-in communication module of the smart water meter to send the smart water meter metering data to the remote monitoring center, and deploys a data processing algorithm in the remote monitoring center to divide the smart water meter metering data into continuous time series segments according to a predetermined time step, and uses the terminal metering data segment as a verification benchmark, and performs secondary stacking time series encoding on the smart water meter metering data segments of the historical period, that is, extracting the short-term time series fluctuation features within the segment and mining the long-term time series correlation features between the segments, so as to capture the deep time series characteristics of the smart water meter metering data, and based on this, the water meter metering data inference at the current time step is performed, and then based on the comparison between the inference result and the verification benchmark, the abnormal judgment of the metering data is realized. This method can effectively reduce the dependence on preset rules, dynamically adapt to diverse water use scenarios, and reduce the risk of false alarms and missed detections.

[0006] According to one aspect of the present application, a method for monitoring abnormal measurement data of a smart water meter is provided, which includes: Use the built-in communication module of the smart water meter to send the smart water meter measurement data to the remote monitoring center; At the remote monitoring center, data segmentation is performed on the smart water meter measurement data based on a fixed time step to obtain a sequence distribution of the smart water meter measurement time step data; Extracting the last time step of the smart water meter metering time step data from the sequence distribution of the smart water meter metering time step data as the smart water meter metering self-supervision verification data; Performing metering data temporal secondary stacking coding on the smart water meter metering time step data in the sequence distribution of the smart water meter metering time step data except the smart water meter metering self-supervision verification data to obtain a smart water meter metering temporal context coding vector; Performing smart water meter measurement reasoning based on the smart water meter measurement time series context coding vector to obtain smart water meter measurement reasoning time step data; Based on the comparison between the smart water meter measurement reasoning time step data and the smart water meter measurement self-supervision verification data, it is determined whether there is data anomaly.

[0007] According to another aspect of the present application, a smart water meter measurement data abnormality monitoring system is provided, which includes: A water meter measurement data transmission module, used to send the smart water meter measurement data to a remote monitoring center using the built-in communication module of the smart water meter; A water meter measurement data segmentation module is used to perform data segmentation on the smart water meter measurement data based on a fixed time step in the remote monitoring center to obtain a sequence distribution of the smart water meter measurement time step data; A verification data extraction module is used to extract the last time step of the smart water meter measurement time step data from the sequence distribution of the smart water meter measurement time step data as the smart water meter measurement self-supervision verification data; A time series stacking coding module is used to perform metering data time series secondary stacking coding on the smart water meter metering time step data in the sequence distribution of the smart water meter metering time step data except the smart water meter metering self-supervision verification data to obtain a smart water meter metering time series context coding vector; A metering reasoning module, used for performing metering reasoning of the smart water meter based on the smart water meter metering time series context coding vector to obtain metering reasoning time step data of the smart water meter; The anomaly detection module is used to determine whether there is a data anomaly based on the comparison between the intelligent water meter measurement reasoning time step data and the intelligent water meter measurement self-supervision verification data.

[0008] Compared with the prior art, the smart water meter metering data anomaly monitoring system and method provided by the present application utilizes the built-in communication module of the smart water meter to send the smart water meter metering data to the remote monitoring center, and deploys the data processing algorithm in the remote monitoring center to divide the smart water meter metering data into continuous time series segments according to the predetermined time step, and uses the terminal metering data segment as the verification benchmark, and performs secondary stacking time series coding on the smart water meter metering data segments of the historical period, that is, extracting the short-term time series fluctuation features within the segments and mining the long-term time series correlation features between the segments, so as to capture the deep time series characteristics of the smart water meter metering data, and perform water meter metering data inference at the current time step based on this, and then realize the abnormal judgment of the metering data based on the comparison between the inference result and the verification benchmark. This method can effectively reduce the dependence on preset rules, dynamically adapt to various water use scenarios, and reduce the risk of false alarms and missed detections. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0010] Figure 1 The present invention is a flowchart of a method for monitoring abnormal measurement data of a smart water meter according to an embodiment of the present application.

[0011] Figure 2 Schematic diagram of data flow of a method for monitoring abnormal measurement data of a smart water meter according to an embodiment of the present application.

[0012] Figure 3This is a flowchart of sub-step S4 of the method for monitoring abnormal measurement data of a smart water meter according to an embodiment of the present application.

[0013] Figure 4 This is a flowchart of sub-step S43 of the method for monitoring abnormal measurement data of a smart water meter according to an embodiment of the present application.

[0014] Figure 5 This is a flowchart of sub-step S432 of the method for monitoring abnormal measurement data of a smart water meter according to an embodiment of the present application.

[0015] Figure 6 This is a flowchart of sub-step S6 of the method for monitoring abnormal measurement data of a smart water meter according to an embodiment of the present application.

[0016] Figure 7 4 is a block diagram of a smart water meter measurement data anomaly monitoring system according to an embodiment of the present application. DETAILED DESCRIPTION

[0017] As shown in this application, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular, but also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list, and the method or device may also include other steps or elements.

[0018] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0019] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0020] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0021] It is worth noting that in this application, all actions to obtain data are carried out in compliance with the relevant data protection laws and policies of the country where the data is located, and with the authorization given by the owner of the corresponding device.

[0022] In response to the above technical problems, this application proposes a method for monitoring abnormal metering data of smart water meters, which uses the built-in communication module of the smart water meter to send the metering data of the smart water meter to the remote monitoring center, and deploys a data processing algorithm in the remote monitoring center to divide the metering data of the smart water meter into continuous time series segments according to a predetermined time step, and uses the metering data segment at the end as the verification benchmark. The metering data segments of the smart water meters in the historical period are subjected to secondary stacking time series encoding, that is, the short-term time series fluctuation feature extraction within the segment and the long-term time series correlation feature mining between the segments, so as to capture the deep time series characteristics of the metering data of the smart water meter, and perform water metering data inference at the current time step based on this, and then realize the abnormal judgment of the metering data based on the comparison between the inference result and the verification benchmark. This method can effectively reduce the dependence on preset rules, dynamically adapt to diverse water use scenarios, and reduce the risk of false alarms and missed detections.

[0023] Figure 1 The present invention is a flowchart of a method for monitoring abnormal measurement data of a smart water meter according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of the method for monitoring abnormal measurement data of smart water meters according to an embodiment of the present application. Figure 1 and Figure 2 As shown, the method for monitoring abnormal metering data of smart water meters includes the following steps: S1, using the built-in communication module of the smart water meter to send the metering data of the smart water meter to a remote monitoring center; S2, at the remote monitoring center, data segmenting the metering data of the smart water meter based on a fixed time step to obtain a sequence distribution of metering time step data of the smart water meter; S3, extracting the metering time step data of the last time step from the sequence distribution of the metering time step data of the smart water meter as the metering self-supervisory verification data of the smart water meter; S4, performing metering data time series secondary stacking coding on the metering time step data of the smart water meter except the metering self-supervisory verification data in the sequence distribution of the metering time step data of the smart water meter to obtain a metering time series context coding vector of the smart water meter; S5, performing metering reasoning of the smart water meter based on the metering time series context coding vector of the smart water meter to obtain metering reasoning time step data of the smart water meter; S6, determining whether there is data abnormality based on the comparison between the metering reasoning time step data of the smart water meter and the metering self-supervisory verification data of the smart water meter.

[0024] In the above-mentioned smart water meter measurement data abnormality monitoring method, the step S1 uses the built-in communication module of the smart water meter to send the smart water meter measurement data to the remote monitoring center. It should be understood that since smart water meters are widely distributed and numerous, in order to achieve centralized data management, this application uses the built-in communication module of the smart water meter to perform remote data transmission, so as to utilize the efficient data processing capabilities of the remote monitoring center to perform centralized data management and abnormality monitoring. In a specific example of the present application, the built-in communication module is an NB-IoT module or a LoRaWAN module.

[0025] Specifically, for the NB-IoT module, it can provide deep coverage based on the existing cellular network, so that even in the basement or indoor environment with weak signals, it can maintain a good connection. In addition, NB-IoT supports the simultaneous access of large-scale devices, which is especially important for cities that deploy a large number of smart water meters. By using narrowband technology, NB-IoT can effectively reduce energy consumption, extend battery life, and reduce maintenance costs. Therefore, in urban environments, NB-IoT is an ideal choice, especially for smart water meters that require long-term stable operation and are not easy to replace batteries.

[0026] On the other hand, the LoRaWAN module uses unlicensed frequency bands for long-distance data transmission, which is particularly suitable for those located in remote areas or places that cannot rely on traditional cellular network coverage. LoRaWAN not only supports long-distance data transmission, but also has low power consumption, which makes it a reliable choice for smart water meters in complex geographical environments. At the same time, because LoRaWAN adopts a star topology, that is, all nodes communicate directly with the gateway, it simplifies the network architecture and reduces deployment costs. This feature makes LoRaWAN show unparalleled advantages in some special application scenarios, such as water meter monitoring in rural areas.

[0027] After selecting the communication modules, the next step is to configure them. The configuration process involves multiple levels, including but not limited to network parameter settings, security policy formulation, etc. First of all, it is necessary to ensure that each smart water meter can correctly identify and connect to the designated remote monitoring center. This requires the communication module to have good compatibility and stability. Secondly, in order to ensure the security of data, the built-in communication module needs to take a series of encryption measures, such as using SSL / TLS protocol to protect the security of data during transmission and prevent information leakage. In addition, strict access control mechanisms can be implemented to limit access to the data of smart water meters to only authenticated users.

[0028] After the initial configuration is completed, the smart water meter starts collecting metering data at predetermined intervals and prepares to send it out. During this process, the built-in communication module is responsible for managing the entire data transmission process, from establishing the initial connection to maintaining stable communication, and handling any error conditions that may occur. For example, in the event of data loss or corruption, the communication module should be able to automatically detect these problems and initiate a retransmission mechanism to ensure data integrity. An effective error handling mechanism is essential to ensure the reliability of data transmission. It is worth noting that in addition to basic data transmission functions, the built-in communication module must also support advanced functions such as firmware updates. With the development of technology and the continuous change of security threats, it is becoming increasingly important to regularly update the software version of the communication module. Through the over-the-air download (OTA) technology, remote firmware upgrades can be achieved without affecting the normal operation of the smart water meter, thereby enhancing the security and performance of the system.

[0029] In the above-mentioned smart water meter metering data abnormality monitoring method, the step S2, in the remote monitoring center, performs data segmentation on the smart water meter metering data based on a fixed time step to obtain a sequence distribution of the smart water meter metering time step data. It should be understood that the smart water meter metering data is essentially a continuous time series. Considering that directly processing the complete data stream may result in low computational efficiency due to the long time span, and it is difficult to capture local abnormal fluctuations in the metering data. Therefore, the present application adopts a data segmentation strategy based on a predetermined time step. By segmenting the data according to a fixed time step (such as 7 days), the smart water meter metering data can be converted from continuous data to discrete serialized fragments, each fragment represents an independent time unit, which is helpful for the subsequent hierarchical modeling of short-term fluctuations in metering data within each independent time unit (such as instantaneous water consumption mutations) and long-term associations between each independent time unit (such as daily water use pattern changes).

[0030] In a specific embodiment, 7 days is selected as a time step, which can not only cover the common changes in water use patterns in daily life, but also ensure the computational efficiency of data processing. Of course, the fixed time step can also be adjusted according to actual conditions, and this embodiment is not restrictive. In this way, the originally huge data stream spanning a long period of time can be converted into discrete serialized fragments that are easy to manage and analyze. Each fragment represents the water use status in a specific time period, which not only helps to capture the short-term fluctuation characteristics in the metering data, such as sudden changes in instantaneous water consumption, but also can mine the long-term correlation between each independent time unit, such as the changing trend of water use patterns between different days.

[0031] In the specific implementation process, all the raw metering data collected from the smart water meter needs to be preprocessed to ensure the quality and consistency of the data. After that, the data is segmented according to the selected 7-day time step. At this stage, it is important to ensure that the selection of segmentation points does not break any meaningful data patterns or events. Therefore, in actual applications, the segmentation strategy may be adjusted according to specific water use habits and known peak water use periods, so that each time step data segment can reflect the user's water use behavior characteristics during that period as completely as possible.

[0032] In addition, since the smart water meter measurement data is essentially a continuous time series, directly processing the entire data stream may result in excessive computational burden due to the large time span, and it is difficult to accurately capture local abnormal fluctuations. The method of splitting the data by fixed time steps (such as 7 days) can not only alleviate the above problems, but also deeply explore the short-term time series fluctuation characteristics within each time step, and explore the long-term time series correlation characteristics between different time steps, which helps to build a more detailed and comprehensive data model, thereby more accurately reflecting the user's water use behavior pattern and its changing rules over time.

[0033] In the above-mentioned smart water meter metering data anomaly monitoring method, the step S3 extracts the smart water meter metering time step data of the last time step from the sequence distribution of the smart water meter metering time step data as the smart water meter metering self-supervisory verification data. It should be understood that the traditional anomaly monitoring method relies on preset rules, but the rules are easy to become outdated in dynamic water use scenarios, which limits the model's ability to generalize new abnormal patterns. In order to overcome this defect, the present application adopts a self-supervised learning strategy, that is, using unlabeled smart water meter metering data for self-verification. Here, the smart water meter metering time step data (the latest data fragment) at the end represents the current water use status. By using it as a verification benchmark, historical data can be used to predict the current status and construct a self-supervised learning framework, thereby reducing dependence on expert rules and dynamically adapting to changes in water use behavior.

[0034] In the above-mentioned smart water meter metering data anomaly monitoring method, the step S4 performs metering data time series secondary stacking encoding on the smart water meter metering time step data in the sequence distribution of the smart water meter metering time step data except the smart water meter metering self-supervision verification data to obtain the smart water meter metering time series context encoding vector. It should be understood that since the smart water meter metering data has significant time series correlation, the time series pattern and dynamic change trend of water use behavior can be mined through time series modeling and learning of smart water meter metering data in historical periods, thereby providing a basis for the prediction of current water use status and abnormal judgment. Here, in order to avoid the verification data interfering with the model's autonomous learning of historical time series patterns, the verification data needs to be removed from the sequence distribution of the smart water meter metering time step data, and only the remaining historical data is subjected to time series feature learning to ensure that the time series reasoning process is not affected by the current state. Among them, Figure 3 FIG. 4 is a flowchart of sub-step S4 of the method for monitoring abnormal measurement data of a smart water meter according to an embodiment of the present application. Figure 3 As shown, the step S4 includes the steps of: S41, defining the smart water meter metering time step data in the sequence distribution of the smart water meter metering time step data except the smart water meter metering self-supervision verification data as the smart water meter metering historical time step data to obtain the time series of the smart water meter metering historical time step data; S42, performing the first-level time series encoding based on the forward LSTM model on each smart water meter metering historical time step data in the time series of the smart water meter metering historical time step data to obtain the time series of the first-level time series associated feature vector of the smart water meter metering data; S43, performing the second-level time series context encoding based on the multi-dimensional constraint optimization mechanism on the time series of the first-level time series associated feature vector of the smart water meter metering data to obtain the smart water meter metering time series context encoding vector.

[0035] Specifically, in step S41, the smart water meter metering time step data except the smart water meter metering self-supervised verification data in the sequence distribution of the smart water meter metering time step data is defined as the smart water meter metering historical time step data to obtain the time series of the smart water meter metering historical time step data. That is, by explicitly defining all time step data except the self-supervised verification data as historical time step data, the boundary between training and verification data is structuredly divided, providing a clear input range for subsequent time series modeling.

[0036] Specifically, in step S42, each smart water meter metering historical time step data in the time series of the smart water meter metering historical time step data is respectively encoded by the first-level time series based on the forward LSTM model to obtain the time series of the first-level time series associated feature vector of the smart water meter metering data. It should be understood that since the water meter metering data has strong time series dependence (such as the water use pattern during the day and night), in order to capture the local time series fluctuations of the smart water meter metering data in the historical period, the present application adopts the forward LSTM model with excellent performance in the time series processing task to extract the short-term time series fluctuation features of each smart water meter metering historical time step data. Specifically, the LSTM model (Long Short-Term Memory, long short-term memory network) has a memory unit and a gating mechanism inside. When processing the smart water meter metering historical time step data, it can selectively memorize the key historical state and filter the noise, effectively learn the time series dependency in the data, so as to capture the time series fluctuation characteristics of the water consumption in each independent time unit, such as the daily or weekly water consumption peak and trough, and then generate the time series of the first-level time series associated feature vector of the smart water meter metering data. In addition, the “forward LSTM” is chosen here instead of the bidirectional model because water meter anomaly detection focuses more on the unidirectional causal chain from history to the present, and does not require reverse time series information.

[0037] Specifically, in step S43, the time series of the first-level time series correlation feature vector of the smart water meter measurement data is subjected to second-level time series context coding based on a multi-dimensional constraint optimization mechanism to obtain the smart water meter measurement time series context coding vector. Specifically, since the above-mentioned first-level time series coding only captures the short-term time series fluctuation characteristics within each independent time unit, it is unable to capture the long-term correlation across time steps (such as monthly or seasonal water use pattern changes), which may cause the model to lack a global perspective in prediction and anomaly judgment. Therefore, in order to fully reflect the time series characteristics of the smart water meter measurement data, the present application further performs second-level time series context coding on the time series of the first-level time series correlation feature vector of the smart water meter measurement data to realize the mining of long-term time series correlation characteristics of water consumption. In particular, considering that traditional sequence models (such as standard Transformer) may introduce redundant associations when performing sequence feature association fusion, causing key patterns to be submerged by noise. In this regard, the present application introduces an independence constraint mechanism. In the dynamic propagation process of the time series of the first-level time series associated feature vector of the smart water meter measurement data, by dynamically adjusting the information interaction intensity between time nodes, while retaining the cross-time step dependency, the coupling of irrelevant features is suppressed, thereby effectively avoiding the interference of redundant information on the model prediction ability, and generating a smart water meter measurement time series context encoding vector that integrates the global time series context information. Among them, Figure 4 FIG. 4 is a flowchart of sub-step S43 of the method for monitoring abnormal measurement data of a smart water meter according to an embodiment of the present application. Figure 4 As shown, the step S43 includes the steps of: S431, anchoring the tail constraint of the message transmission space and the axis constraint of the time series of the first-level time series correlation feature vector of the smart water meter metering data to obtain the tail constraint anchor coding vector of the first-level time series correlation message transmission space of the smart water meter metering data and the axis constraint anchor coding vector of the first-level time series correlation message transmission space of the smart water meter metering data; S432, using the tail constraint anchor coding vector of the first-level time series correlation message transmission space of the smart water meter metering data and the axis constraint anchor coding vector of the first-level time series correlation message transmission space of the smart water meter metering data as constraint conditions, calculating the message transmission constraint factor of each first-level time series correlation feature vector of the smart water meter metering data in the time series of the first-level time series correlation feature vector of the smart water meter metering data to obtain the time series of the first-level time series correlation feature message transmission constraint factor of the smart water meter metering data; S433, based on the time series of the first-level time series correlation feature message transmission constraint factor of the smart water meter metering data, dynamically constrain the time series of the first-level time series correlation feature vector of the smart water meter metering data to obtain the smart water metering time series context coding vector.

[0038] More specifically, the step S431 includes: first, extracting the last first-level time series correlation feature vector of the smart water meter metering data from the time series of the first-level time series correlation feature vector of the smart water meter metering data as the tail-end constraint anchor coding vector of the first-level time series correlation message transmission space of the smart water meter metering data, which is expressed by the formula:

[0039] in, represents the time series of the first-level time series correlation feature vector of the smart water meter measurement data, , , and They respectively represent the first, second, and third time series of the first-level time series correlation feature vector of the smart water meter measurement data. and The first-level time series correlation feature vector of smart water meter measurement data, is the number of primary time series correlation feature vectors of the smart water meter measurement data, The tail constraint anchor encoding vector of the first-level temporal correlation message transmission space of smart water meter measurement data is constructed.

[0040] Here, the self-supervision verification capability of the model is enhanced by constructing a dynamic anchoring mechanism for time series features. It should be understood that by converting the last first-level time series correlation feature vector of smart water meter metering data into the tail-end constraint anchor coding vector of the first-level time series correlation message transmission space of smart water meter metering data, the terminal state information of the time series is retained, and the dynamic propagation process is effectively guided by the feature independence constraint. The tail-end constraint anchor coding vector of the first-level time series correlation message transmission space of smart water meter metering data generated by this anchor coding method can set boundary conditions in the feature distribution sequence, thereby ensuring that the subsequent message transmission process focuses on the most recent local fluctuation characteristics.

[0041] Then, cluster analysis is performed on the time series of the first-level time series correlation feature vector of the smart water meter measurement data to obtain the first-level time series correlation message transmission space axis constraint anchor coding vector of the smart water meter measurement data, which is expressed as follows:

[0042] in, represents the cluster analysis function, and They represent the maximum and minimum functions respectively. It is a preset hyperparameter used to adjust the sensitivity of cluster analysis. express The feature importance factor of represents the normalized exponential function, express The clustering weight coefficient is Represents the spatial axis constraint anchor coding vector of the first-level temporal correlation message transmission of smart water meter measurement data.

[0043] That is, by skeletonizing the time series of the first-level time-series correlation feature vector of the smart water meter metering data through cluster analysis, the extreme boundary features represented by it can be automatically extracted, and combined with the vector mapping mechanism, the original discrete time series fluctuations can be converted into a compact representation in the continuous probability distribution space, thereby revealing the potential structure of the data manifold through the normalization operation of the softmax function without explicitly defining rules. Through this cluster analysis method, the axis constraint anchor coding vector of the first-level time-series correlation message transmission space of the smart water meter metering data generated can reveal the time-series dominant change mode of the water meter metering data, which helps to limit the distortion amplitude of the feature space in the subsequent message transmission process, reduce local noise interference, and improve the accuracy of metering data anomaly detection.

[0044] Figure 5 FIG. 4 is a flowchart of sub-step S432 of the method for monitoring abnormal measurement data of a smart water meter according to an embodiment of the present application. Figure 5As shown, the step S432 includes the steps of: S4321, calculating the tail message transmission constraint factor of each first-level time series associated feature vector of the smart water meter metering data in the time series of the first-level time series associated feature vector of the smart water meter metering data relative to the tail constraint anchor coding vector of the first-level time series associated message transmission space of the smart water meter metering data; S4322, calculating the axis message transmission constraint factor of each first-level time series associated feature vector of the smart water meter metering data in the time series of the first-level time series associated feature vector of the smart water meter metering data relative to the axis constraint anchor coding vector of the first-level time series associated message transmission space of the smart water meter metering data; S4323, based on the tail message transmission constraint factor and the axis message transmission constraint factor of each first-level time series associated feature vector of the smart water meter metering data in the time series of the first-level time series associated feature vector of the smart water meter metering data, calculating the message transmission constraint factor of each first-level time series associated feature vector of the smart water meter metering data to obtain the time series of the first-level time series associated feature message transmission constraint factor of the smart water meter metering data.

[0045] In a specific example of the present application, the step S4321 is expressed by the formula:

[0046] in, Indicates The first level time series correlation feature vector of the smart water meter measurement data Position feature value, The first one represents the tail constraint anchor coding vector of the first-level temporal correlation message transmission space of smart water meter measurement data. Position feature value, represents the logarithmic function with base 2, Indicates taking the absolute value, express The tail end message delivery constraint factor.

[0047] That is, by measuring the interactive response strength of the first-level time series associated feature vector of the smart water meter metering data and the tail constraint anchor coding vector of the first-level time series associated message transmission space of the smart water meter metering data, a local constraint weight system of conditional probability distribution is constructed, so as to dynamically adjust the importance of different features in the message transmission process. When a feature vector is highly matched with the tail benchmark coding, its constraint weight increases, indicating that the feature carries key time series information compatible with the verification benchmark, otherwise the weight decreases, suggesting potential abnormal disturbances. Through this adaptive attention mechanism, the generated tail message transmission constraint factor enables the model to effectively focus on the core features of maintaining time series coherence and suppress noise interference.

[0048] In a specific example of the present application, step S4322 is expressed by the formula:

[0049] in, represents the square of the norm of a vector, represents the inverse hyperbolic cosine function, express The axis message passing constraint factor.

[0050] That is, similar to the calculation of the tail-end message transmission constraint factor, the present application introduces the axis message transmission constraint factor to impose regularization constraints in the feature space, and compresses the originally unbounded time series of the first-level time series correlation feature vector of the smart water meter metering data onto a multidimensional sphere with a clear semantic boundary. Specifically, the axis message transmission constraint factor measures the Poincare distance between the first-level time series correlation feature vector of the smart water meter metering data and the axis reference code (i.e., the axis constraint anchor code vector of the first-level time series correlation message transmission space of the smart water meter metering data), thereby achieving fine-grained regulation of feature importance. When the first-level time series correlation feature vector of the smart water meter metering data is close to the axis reference code, it indicates that the feature occupies a dominant position in the time series evolution process, and its axis message transmission constraint factor increases, otherwise it decreases, thereby enhancing the model's ability to recognize the dominant time series features, and further improving the accuracy and robustness of metering data anomaly detection.

[0051] In particular, in a preferred example of the present application, the step S4323 includes: first, performing message transmission collaborative constraint optimization on the tail end message transmission constraint factor and the axis message transmission constraint factor of the first-level time series correlation feature vector of the smart water meter measurement data to obtain the optimized tail end message transmission constraint factor and the optimized axis message transmission constraint factor, which are expressed as follows:

[0052] in, and Respectively The covariant unified tail message passing constraint factor and the covariant unified axis message passing constraint factor, represents the transpose of a matrix, and Respectively The optimized tail-end message passing constraint factor and the optimized axis message passing constraint factor.

[0053] That is, considering that the local mutation (tail constraint) of water metering data and the global trend (axis constraint) may conflict in message transmission, the present application further balances the two constraints by constructing a message transmission collaborative constraint optimization mechanism to ensure the consistency and stability of the time series features during the transmission process. Specifically, first, through the horizontally closed covariant mechanism of the message transmission field, the standard space constraint matrix is ​​applied to the tail message transmission constraint factor and the axis message transmission constraint factor, forcing them to establish a unified transmission paradigm in the global topological structure. At the same time, the component rotation matrix of the reversible space metric is used to impose a spinor closure constraint on the covariant representation, so that the optimized tail message transmission constraint factor and the optimized axis message transmission constraint factor can maintain the elasticity of the horizontal feature propagation and meet the continuity of the vertical time series evolution. Through this collaborative optimization method, the metric parameters of the feature space are dynamically adjusted to balance short-term sensitivity and long-term memory. It should be understandable that the lateral tight covariance eliminates the gradient vanishing problem on the feature propagation path, ensures the complete transmission of abnormal signals at different time scales, and avoids the local disturbance from being diluted or amplified prematurely, while the spinor tight constraint maps the originally separated long-term and short-term constraints to the same geometric space. The generated optimized tail message transmission constraint factor and optimized axis message transmission constraint factor significantly reduce the risk of overfitting.

[0054] Then, the optimized tail end message transmission constraint factor and the optimized axis message transmission constraint factor of the first-level time series correlation feature vector of the smart water meter measurement data are weighted and fused, and then input into the Sigmoid function for normalization processing to obtain the first-level time series correlation feature message transmission constraint factor of the smart water meter measurement data, which is expressed by the formula:

[0055] in, and Represent different weight coefficients, is the sigmoid function, for The first-level time series correlation feature message transmission constraint factor of smart water meter measurement data.

[0056] It should be understood that at the feature expression level, the weighted fusion of the first-level time series correlation feature message transmission constraint factor of the smart water meter measurement data not only combines the advantages of the tail message transmission constraint factor and the axis message transmission constraint factor, but also through the normalization processing of the sigmoid function, the first-level time series correlation feature message transmission constraint factor of the smart water meter measurement data is mapped to between 0 and 1, realizing the smooth regulation of feature importance. This processing method not only enhances the model's sensitivity and recognition ability to feature importance, but also improves the stability and reliability of anomaly detection results.

[0057] More specifically, the step S433 is expressed by the formula:

[0058] in, Represents the smart water meter measurement timing context encoding vector.

[0059] That is, through the dynamic weighted pooling operation, the time series of the first-level time series correlation feature vector of the smart water meter measurement data is compressed into the smart water meter measurement time series context encoding vector. By assigning differentiated weight coefficients to the features of different time steps, the model's ability to capture complex abnormal patterns is significantly enhanced, and its adaptability to new abnormal scenarios is significantly improved.

[0060] In the above-mentioned smart water meter metering data anomaly monitoring method, the step S5 performs smart water meter metering reasoning based on the smart water meter metering timing context coding vector to obtain the smart water meter metering reasoning time step data. In a specific example of the present application, the step S5 includes: decoding the smart water meter metering timing context coding vector based on the RNN model to obtain the smart water meter metering reasoning time step data. It should be understood that after obtaining the smart water meter metering timing context coding vector that integrates the global timing context information, it is necessary to further map it back to the original data space to predict the metering data of the smart water meter at the next time step. Here, the present application adopts the RNN model (Recurrent Neural Network) to perform the timing feature decoding of the smart water meter metering timing context coding vector. Specifically, the smart water meter metering time series context encoding vector is used as the input of the RNN model, and the global time series context information of the metering data contained in the encoding vector is learned through the hidden layer state transfer mechanism of the RNN model. Based on the learned metering data time series context evolution information, the predicted metering data of the smart water meter at the next time step is gradually derived, thereby generating the smart water meter metering reasoning time step data.

[0061] In the above-mentioned smart water meter metering data anomaly monitoring method, the step S6 determines whether there is a data anomaly based on the comparison between the smart water meter metering reasoning time step data and the smart water meter metering self-supervised verification data. It should be understood that the smart water meter metering reasoning time step data is the current state predicted by the self-supervised learning framework based on the historical smart water meter metering data, while the smart water meter metering self-supervised verification data is the current state actually observed. By comparing the deviation between the actual data and the expected pattern, it can be intuitively determined whether the current smart water meter metering data is abnormal. Among them, Figure 6 FIG. 6 is a flowchart of sub-step S6 of the method for monitoring abnormal measurement data of a smart water meter according to an embodiment of the present application. Figure 6As shown, the step S6 includes the steps of: S61, calculating the cosine function value between the smart water meter measurement reasoning time step data and the smart water meter measurement self-supervision verification data as the measurement data time series consistency operator; S62, determining whether there is a data anomaly based on the comparison between the measurement data time series consistency operator and a preset threshold.

[0062] Specifically, the step S61 calculates the cosine function value between the smart water meter metering reasoning time step data and the smart water meter metering self-supervision verification data as the metering data time series consistency operator. It should be understood that the cosine function value is an indicator for measuring the similarity of the directions of two vectors, and its value range is between [-1,1]. When the directions of the two vectors are exactly the same, the cosine function value is 1; when the directions are completely opposite, the cosine function value is -1; when the directions are vertical, the cosine function value is 0. Therefore, by calculating the cosine function value between the smart water meter metering reasoning time step data and the smart water meter metering self-supervision verification data, the similarity in direction between the predicted data and the actual observed data can be quantitatively evaluated, thereby reflecting the consistency of the metering data time series.

[0063] Specifically, step S62 determines whether there is a data anomaly based on the comparison between the metering data time series consistency operator and the preset threshold. That is, if the metering data time series consistency operator is greater than or equal to the preset threshold, the metering data of the smart water meter is judged to be normal, indicating that the current metering state of the smart water meter meets the expected mode and no further intervention is required; conversely, if the metering data time series consistency operator is less than the preset threshold, it is judged that the metering data of the smart water meter is abnormal, indicating that the smart water meter needs to be inspected or maintained to avoid potential water resource waste or metering error problems. This smart water meter anomaly detection method based on self-supervised learning not only improves the accuracy and efficiency of anomaly detection, but also provides strong support for remote monitoring and maintenance of smart water meters.

[0064] In summary, the method for monitoring abnormal metering data of smart water meters based on the embodiment of the present application is explained, which uses the built-in communication module of the smart water meter to send the metering data of the smart water meter to the remote monitoring center, and deploys the data processing algorithm in the remote monitoring center to divide the metering data of the smart water meter into continuous time series segments according to the predetermined time step, and uses the metering data segment at the end as the verification benchmark, and performs secondary stacking time series encoding on the metering data segments of the smart water meters in the historical period, that is, extracting the short-term time series fluctuation features within the segments and mining the long-term time series correlation features between the segments, so as to capture the deep time series characteristics of the metering data of the smart water meter, and perform water metering data inference at the current time step based on this, and then realize the abnormal judgment of the metering data based on the comparison between the inference result and the verification benchmark. This method can effectively reduce the dependence on preset rules, dynamically adapt to various water use scenarios, and reduce the risk of false alarms and missed detections.

[0065] Furthermore, a smart water meter measurement data abnormality monitoring system is also provided.

[0066] Figure 7 FIG. 1 is a block diagram of a smart water meter measurement data abnormality monitoring system according to an embodiment of the present application. Figure 7 As shown, according to the embodiment of the present application, the smart water meter measurement data abnormality monitoring system 100 includes: a water meter measurement data transmission module 110, which is used to send the smart water meter measurement data to the remote monitoring center by using the built-in communication module of the smart water meter; a water meter measurement data segmentation module 120, which is used to perform data segmentation on the smart water meter measurement data based on a fixed time step in the remote monitoring center to obtain a sequence distribution of the smart water meter measurement time step data; a verification data extraction module 130, which is used to extract the smart water meter measurement time step data of the last time step from the sequence distribution of the smart water meter measurement time step data as the smart water meter measurement self-supervision verification data; a time series stacking coding module 140, which is used to perform time series secondary stacking coding of the smart water meter metering time step data in the sequence distribution of the smart water meter metering time step data except the smart water meter metering self-supervisory verification data to obtain a smart water meter metering time series context coding vector; a metering reasoning module 150, which is used to perform smart water meter metering reasoning based on the smart water meter metering time series context coding vector to obtain smart water meter metering reasoning time step data; an anomaly detection module 160, which is used to determine whether there is a data anomaly based on the comparison between the smart water meter metering reasoning time step data and the smart water meter metering self-supervisory verification data.

[0067] Here, those skilled in the art can understand that the specific operations of each module in the above-mentioned smart water meter measurement data abnormality monitoring system have been referred to above. Figures 1 to 6 The description of the smart water meter metering data abnormality monitoring method has been introduced in detail, and therefore, its repeated description will be omitted.

[0068] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0069] In the above embodiments, the description of each embodiment has its own emphasis. For the parts that are not described or recorded in detail in a certain embodiment, please refer to the relevant description of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiment described above is only schematic. For example, the unit division is only a logical function division, and there may be other division methods in actual implementation. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0070] It is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, the embodiments should be considered as exemplary and non-restrictive in all respects.

[0071] Finally, it should be noted that the above description has been given for the purpose of illustration and description. In addition, the above embodiments are only used to illustrate the technical solution of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for monitoring abnormal measurement data of a smart water meter, characterized in that: include: Use the built-in communication module of the smart water meter to send the smart water meter measurement data to the remote monitoring center; At the remote monitoring center, data segmentation is performed on the smart water meter measurement data based on a fixed time step to obtain a sequence distribution of the smart water meter measurement time step data; Extracting the last time step of the smart water meter metering time step data from the sequence distribution of the smart water meter metering time step data as the smart water meter metering self-supervision verification data; Performing metering data temporal secondary stacking coding on the smart water meter metering time step data in the sequence distribution of the smart water meter metering time step data except the smart water meter metering self-supervision verification data to obtain a smart water meter metering temporal context coding vector; Performing smart water meter measurement reasoning based on the smart water meter measurement time series context coding vector to obtain smart water meter measurement reasoning time step data; Based on the comparison between the smart water meter measurement reasoning time step data and the smart water meter measurement self-supervision verification data, it is determined whether there is data anomaly.

2. The method for monitoring abnormal measurement data of smart water meters according to claim 1, characterized in that: The built-in communication module is a NB-IoT module or a LoRaWAN module.

3. The method for monitoring abnormal measurement data of smart water meters according to claim 1, characterized in that: Performing metering data temporal secondary stacking coding on the smart water meter metering time step data except the smart water meter metering self-supervision verification data in the sequence distribution of the smart water meter metering time step data to obtain a smart water meter metering temporal context coding vector, including: The smart water meter measurement time step data except the smart water meter measurement self-supervision verification data in the sequence distribution of the smart water meter measurement time step data are defined as the smart water meter measurement historical time step data to obtain the time series of the smart water meter measurement historical time step data; Performing primary time series encoding based on a forward LSTM model on each smart water meter measurement historical time step data in the time series of the smart water meter measurement historical time step data to obtain a time series of primary time series correlation feature vectors of the smart water meter measurement data; The time series of the primary time series correlation feature vector of the smart water meter measurement data is subjected to secondary time series context coding based on a multi-dimensional constraint optimization mechanism to obtain the smart water meter measurement time series context coding vector.

4. The method for monitoring abnormal measurement data of smart water meters according to claim 3 is characterized in that: The time series of the primary time series correlation feature vector of the smart water meter measurement data is subjected to secondary time series context coding based on a multi-dimensional constraint optimization mechanism to obtain the smart water meter measurement time series context coding vector, including: Perform message transfer space tail constraint anchoring and axis constraint anchoring on the time series of the first-level time series correlation feature vector of the smart water meter measurement data to obtain a smart water meter measurement data first-level time series correlation message transfer space tail constraint anchoring coding vector and a smart water meter measurement data first-level time series correlation message transfer space axis constraint anchoring coding vector; Taking the tail constraint anchor coding vector of the first-level time series associated message transmission space of the smart water meter metering data and the axis constraint anchor coding vector of the first-level time series associated message transmission space of the smart water meter metering data as constraint conditions, calculating the message transmission constraint factor of each first-level time series associated feature vector of the smart water meter metering data in the time series of the first-level time series associated feature vector of the smart water meter metering data to obtain the time series of the first-level time series associated feature message transmission constraint factor of the smart water meter metering data; Based on the time series of the first-level timing correlation feature message transmission constraint factor of the smart water meter measurement data, the time series of the first-level timing correlation feature vector of the smart water meter measurement data is dynamically constrained to be transmitted and encoded to obtain the smart water meter measurement timing context encoding vector.

5. The method for monitoring abnormal measurement data of smart water meters according to claim 4 is characterized in that: The time series of the first-level time series correlation feature vector of the smart water meter measurement data is anchored by the tail constraint of the message transmission space and the axis constraint to obtain the first-level time series correlation message transmission space tail constraint anchor coding vector of the smart water meter measurement data and the first-level time series correlation message transmission space axis constraint anchor coding vector of the smart water meter measurement data, including: Extract the last first-level time series correlation feature vector of the smart water meter metering data from the time series of the first-level time series correlation feature vector of the smart water meter metering data as the tail-end constraint anchor coding vector of the first-level time series correlation message transmission space of the smart water meter metering data; A cluster analysis is performed on the time series of the first-level time series correlation feature vector of the smart water meter measurement data to obtain the first-level time series correlation message transmission space axis constraint anchor coding vector of the smart water meter measurement data.

6. The method for monitoring abnormal measurement data of smart water meters according to claim 5, characterized in that: Taking the tail constraint anchor coding vector of the first-level time series associated message transmission space of the smart water meter metering data and the axis constraint anchor coding vector of the first-level time series associated message transmission space of the smart water meter metering data as constraint conditions, calculating the message transmission constraint factor of each first-level time series associated feature vector of the smart water meter metering data in the time series of the first-level time series associated feature vector of the smart water meter metering data to obtain the time series of the first-level time series associated feature message transmission constraint factor of the smart water meter metering data, including: Calculate the tail end message transmission constraint factor of each first-level time series correlation feature vector of the smart water meter metering data in the time series of the first-level time series correlation feature vector of the smart water meter metering data relative to the tail end constraint anchor coding vector of the first-level time series correlation message transmission space of the smart water meter metering data; Calculate the axis message transmission constraint factor of each first-level time series correlation feature vector of the smart water meter metering data in the time series of the first-level time series correlation feature vector of the smart water meter metering data relative to the axis constraint anchor coding vector of the first-level time series correlation message transmission space of the smart water meter metering data; Based on the tail message transmission constraint factor and the axis message transmission constraint factor of each first-level time series correlation feature vector of the smart water meter metering data in the time series of the first-level time series correlation feature vector of the smart water meter metering data, the message transmission constraint factor of each first-level time series correlation feature vector of the smart water meter metering data is calculated to obtain the time series of the first-level time series correlation feature message transmission constraint factor of the smart water meter metering data.

7. The method for monitoring abnormal measurement data of smart water meters according to claim 6, characterized in that: Based on the tail message transmission constraint factor and the axis message transmission constraint factor of each first-level time series correlation feature vector of the smart water meter metering data in the time series of the first-level time series correlation feature vector of the smart water meter metering data, the message transmission constraint factor of each first-level time series correlation feature vector of the smart water meter metering data is calculated to obtain the time series of the first-level time series correlation feature message transmission constraint factor of the smart water meter metering data, including: Perform message transmission collaborative constraint optimization on the tail end message transmission constraint factor and the axis line message transmission constraint factor of the first-level time series correlation feature vector of the smart water meter measurement data to obtain an optimized tail end message transmission constraint factor and an optimized axis line message transmission constraint factor; The optimized tail end message transmission constraint factor and the optimized axis message transmission constraint factor of the first-level time series correlation feature vector of the smart water meter measurement data are weighted and fused, and then input into the Sigmoid function for normalization processing to obtain the first-level time series correlation feature message transmission constraint factor of the smart water meter measurement data.

8. The method for monitoring abnormal measurement data of smart water meters according to claim 6, characterized in that: Performing smart water meter metering reasoning based on the smart water meter metering time series context coding vector to obtain smart water meter metering reasoning time step data includes: The smart water meter measurement time series context encoding vector is decoded based on the time series feature of the RNN model to obtain the smart water meter measurement reasoning time step data.

9. The method for monitoring abnormal measurement data of smart water meters according to claim 8, characterized in that: Based on the comparison between the smart water meter measurement reasoning time step data and the smart water meter measurement self-supervision verification data, determining whether there is data anomaly includes: Calculate the cosine function value between the smart water meter measurement reasoning time step data and the smart water meter measurement self-supervision verification data as a measurement data time series consistency operator; Based on the comparison between the measurement data time series consistency operator and a preset threshold, it is determined whether there is data anomaly.

10. A smart water meter measurement data abnormality monitoring system, characterized in that: include: A water meter measurement data transmission module, used to send the smart water meter measurement data to a remote monitoring center using the built-in communication module of the smart water meter; A water meter measurement data segmentation module is used to perform data segmentation on the smart water meter measurement data based on a fixed time step in the remote monitoring center to obtain a sequence distribution of the smart water meter measurement time step data; A verification data extraction module is used to extract the last time step of the smart water meter measurement time step data from the sequence distribution of the smart water meter measurement time step data as the smart water meter measurement self-supervision verification data; A time series stacking coding module is used to perform metering data time series secondary stacking coding on the smart water meter metering time step data in the sequence distribution of the smart water meter metering time step data except the smart water meter metering self-supervision verification data to obtain a smart water meter metering time series context coding vector; A metering reasoning module, used for performing metering reasoning of the smart water meter based on the smart water meter metering time series context coding vector to obtain metering reasoning time step data of the smart water meter; The anomaly detection module is used to determine whether there is a data anomaly based on the comparison between the intelligent water meter measurement reasoning time step data and the intelligent water meter measurement self-supervision verification data.

Images