Intelligent meter reading method and system based on NBIoT

Abstract

The present application relates to the technical field of meter reading technology, and discloses a method and system for meter reading of intelligent meter collectors based on NBIoT, which includes connecting metering equipment with meter collectors using NBIoT technology, generating user characteristics and data characteristics, performing data verification and fault analysis. The system corresponds to the method. The present application, by generating user characteristics and data characteristics respectively, and then performing data verification on real-time metering data based on these characteristics and conducting fault analysis on metering equipment, realizes the elimination of the limitations of traditional manual meter reading methods in the field of energy metering, improves the automation of metering data collection, enhances the ability to evaluate data accuracy, and can timely and effectively determine whether there are faults in metering equipment, ensure reliable acquisition of metering data and stable and efficient operation of the entire energy usage metering system, and provide strong support for scientific billing and reasonable management of energy supply enterprises and users' accurate grasp of their own energy usage.

Description

Technical Field

[0001] The present application relates to the technical field of meter reading technology, and specifically to a meter reading method and system of an intelligent meter collector based on NBIoT. Background Art

[0002] In the modern energy management system, accurate metering data collection and equipment fault monitoring are crucial. Traditional meter reading methods mainly rely on manual operations, which have many disadvantages. Manual meter reading not only consumes a lot of manpower and time costs, but is also prone to data recording errors and omissions due to human negligence, making it difficult to ensure data accuracy.

[0003] At the same time, the detection of metering equipment failures is often delayed. Usually, equipment failures can only be discovered when users notice abnormalities and give feedback, or during regular inspections, and real-time monitoring and timely processing are impossible. This may cause metering data to be distorted for a long time, affecting the billing accuracy and resource coordination rationality of energy supply companies, and is not conducive to providing users with stable and reliable energy services.

[0004] In addition, the traditional meter reading model makes it difficult to conduct in-depth mining and analysis of large amounts of metering data, and cannot effectively use data patterns to predict equipment status or data anomalies in advance.

[0005] With the development of smart devices and IoT technology, this inefficient, high-error, and lack of foresighted meter reading method can no longer meet the development needs of refined and intelligent energy management. Narrow Band Internet of Things (Narrow Band Internet of Things) is based on the 3GPP Evolved Universal Terrestrial Radio Access (E-UTRA) technology, using a 180kHz carrier transmission bandwidth to support cellular data connections of low-power devices in the wide area network, also known as Low Power Wide Area Network (LPWAN). This technology can provide a technical basis for effectively solving the above technical problems.

[0006] The Chinese patent application with application number CN201911174318.0 discloses a remote meter reading system for electric energy meters based on NB-IoT, but the invention performs poorly in improving data accuracy and the timeliness and intelligence level of equipment fault monitoring.

[0007] In summary, a new NBIoT-based intelligent meter reading technology is urgently needed to improve data accuracy and the timeliness and intelligence of equipment fault monitoring. Summary of the invention

[0008] The purpose of this application is to provide a smart meter reading method and system based on NBIoT to solve the technical problems raised in the above background technology.

[0009] To achieve the above objectives, this application discloses the following technical solutions:

[0010] In a first aspect, the present application discloses a method for reading meters using an intelligent meter collector based on NBIoT, the method comprising:

[0011] The metering device is connected to the meter collector using NBIoT technology; wherein the metering device is used to collect metering data, and the metering data is used to characterize the user's energy usage;

[0012] Extracting features from the historical metering data to generate user features and data features; wherein the user features are used to characterize the energy usage of the user, and the data features are used to characterize the data form in which the metering data has faults;

[0013] Performing data verification on the real-time metering data based on the user characteristics, wherein the data verification is used to evaluate the accuracy of the metering data;

[0014] Based on the data features, a fault analysis is performed on the metering device corresponding to the real-time metering data, and the fault analysis is used to determine whether there is a fault in the metering device.

[0015] Preferably, the metering equipment includes at least a water meter, and the meter collector is connected to all water meters through a two-wire M-BUS communication bus, and the data uplink and downlink protocols adopt the MODBUS standard protocol.

[0016] Preferably, the process of generating the user characteristics includes:

[0017] The metering data under different time dimensions are counted based on time series, and the time dimensions at least include metering data of the same metering cycle and metering data of the same season;

[0018] Under the dimension of the data collection cycle, the statistics of the metering data in each cycle are calculated, and the statistics at least include the mean and the variance;

[0019] Under the seasonal dimension, the measurement data of the same season for multiple years are summarized and their data distribution characteristics are determined;

[0020] The statistics and data distribution characteristics of the measurement data obtained in different time dimensions are defined as user features and output.

[0021] Preferably, the process of generating the data features includes:

[0022] Extracting features from the data form of the metering data in the history of communication failure to obtain communication failure features;

[0023] Extracting features from the data form of the metering data in the history of interface failure to obtain interface failure features;

[0024] Extracting features from the data form of the metering data in the history of power failure to obtain power failure features;

[0025] The communication fault feature, the interface fault feature and the power fault feature are defined as the data features and output.

[0026] Preferably, the data verification is specifically as follows:

[0027] Calculating predicted metering data using the user characteristics, the predicted metering data being used to characterize predicted values ​​of the metering data of the user obtained based on the user characteristics;

[0028] The deviation value between the predicted metering data and the metering data is calculated, and the accuracy of the metering data is checked based on the deviation value and a preset deviation threshold.

[0029] Preferably, the calculation process of the predicted metering data includes:

[0030] The predicted metering data is calculated using a predicted metering data calculation formula, wherein the predicted metering data calculation formula is specifically:

[0031]

[0032] in, For the The user's metering data obtained in a collection cycle, For the The user's metering data obtained in the first collection cycle and the The absolute value of the difference between the user's metering data obtained in the collection cycle, For the The average value of the user's metering data for the quarter corresponding to the collection cycle, The calculated forecast measurement data.

[0033] Preferably, the calculation process of the deviation value includes:

[0034]

[0035] in, For the The real metering data of users obtained in each collection cycle, The average value of the deviation adjustment allowed when calculating the historical deviation value. is the calculated deviation value; when When The accuracy of the user's actual metering data obtained in each meter reading cycle does not meet the standards.

[0036] Preferably, the fault analysis is specifically as follows:

[0037] Feature extraction corresponding to the data feature is performed on the real-time metering data to obtain real-time data features. When the real-time data features meet any one or more of the communication fault features, the interface fault features and the power supply fault features, it is determined that a corresponding fault exists in the metering equipment corresponding to the real-time metering data.

[0038] Preferably, when a fault occurs, the deviation value is recalculated based on a preset fault deviation amplification factor, and the previous The average accuracy of the predicted metering data in a collection cycle. When the average accuracy meets the preset average accuracy, the predicted metering data is allowed to be used as filling data to complete the data when there is a fault.

[0039] In a second aspect, the present application discloses a smart meter reading system based on NBIoT, which is applicable to the smart meter reading method based on NBIoT as described above, and includes a hardware construction module, a feature extraction module, a data verification module and a fault analysis module which are sequentially connected in communication;

[0040] The hardware building module is configured to connect the metering device to the meter collector using NBIoT technology; wherein the metering device is used to collect metering data, and the metering data is used to characterize the user's energy usage;

[0041] The feature extraction module is configured to: extract features from the historical metering data to generate user features and data features; wherein the user features are used to characterize the energy usage of the user, and the data features are used to characterize the data form in which the metering data has faults;

[0042] The data checking module is configured to: perform data checking on the real-time metering data based on the user characteristics, and the data checking is used to evaluate the accuracy of the metering data;

[0043] The fault analysis module is configured to perform a fault analysis on the metering device corresponding to the real-time metering data based on the data characteristics, and the fault analysis is used to determine whether the metering device has a fault.

[0044] Beneficial effect: The NBIoT-based intelligent meter reading method and system of the present application utilizes NBIoT technology to connect the metering equipment with the metering equipment, and extracts features from historical metering data to generate user features and data features respectively, and then performs data verification on real-time metering data based on these features and conducts fault analysis on the metering equipment, thereby breaking away from the limitations of traditional manual meter reading methods in the field of energy metering, improving the degree of automation in metering data collection, and enhancing the ability to assess data accuracy. It can also timely and effectively determine whether the metering equipment has faults, thereby ensuring the reliable acquisition of metering data and the stable and efficient operation of the entire energy usage metering system, and providing strong support for scientific billing and reasonable management of energy supply companies and for users to accurately grasp their own energy usage. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 A flowchart of a method for reading meters using an intelligent meter collector based on NBIoT provided in an embodiment of the present application;

[0047] Figure 2 This is a structural block diagram of the NBIoT-based intelligent meter reading system provided in the embodiment of the present application. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present application are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0049] In this article, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprising..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0050] The first aspect of this embodiment discloses Figure 1A method for reading meters using an intelligent meter collector based on NBIoT is shown, the method comprising:

[0051] S1: Use NBIoT technology to connect the metering device with the meter collector; the metering device is used to collect metering data, and the metering data is used to characterize the user's energy usage;

[0052] S2: Extract features from historical metering data to generate user features and data features; user features are used to characterize the user's energy usage, and data features are used to characterize the data form of metering data failures;

[0053] S3: Performing data verification on real-time metering data based on user characteristics, which is used to evaluate the accuracy of metering data;

[0054] S4: Performing a fault analysis on the metering equipment corresponding to the real-time metering data based on the data characteristics, and the fault analysis is used to determine whether the metering equipment has a fault.

[0055] Based on the above, this embodiment uses NBIoT technology to connect the metering equipment with the meter collector, and generates user characteristics and data characteristics by extracting features from historical metering data, and then performs data verification on real-time metering data based on these features and conducts fault analysis on the metering equipment. It has achieved the goal of breaking away from the limitations of traditional manual meter reading methods in the field of energy metering, improving the degree of automation of metering data collection, and enhancing the ability to assess data accuracy. It can also timely and effectively determine whether there are faults in the metering equipment, ensure the reliable acquisition of metering data and the stable and efficient operation of the entire energy usage metering system, and provide strong support for scientific billing and reasonable management of energy supply companies and users to accurately grasp their own energy usage.

[0056] Specifically, the metering equipment includes at least a water meter, and the meter collector is connected to all water meters through a two-wire M-BUS communication bus, and the data uplink and downlink protocols adopt the MODBUS standard protocol.

[0057] Through the above, this embodiment realizes stable and standardized data interaction between the water meter and the meter collector, avoids data transmission errors or instability caused by messy communication methods, inconsistent protocols, etc., improves the accuracy and completeness of metering data collection, and ensures that data can be transmitted upstream and downstream in an orderly manner between the water meter and the meter collector, laying a good foundation for subsequent feature extraction, data verification, and fault analysis based on these data, ensuring that the entire NBIoT-based smart meter collector meter reading process can proceed smoothly.

[0058] Specifically, the process of generating user features includes:

[0059] Based on time series statistics, the metering data under different time dimensions are collected. The time dimension at least includes metering data of the same collection period and metering data of the same season.

[0060] Under the dimension of the data collection cycle, the statistics of the metering data in each cycle are calculated, and the statistics include at least the mean and variance;

[0061] Under the seasonal dimension, the measurement data of the same season for multiple years are summarized and their data distribution characteristics are determined;

[0062] The statistics and data distribution characteristics of the measurement data obtained in different time dimensions are defined as user features and output.

[0063] Based on the above, this embodiment uses statistics on metering data in different time dimensions (including meter reading cycles, seasons, etc.) based on time series, calculates corresponding statistics and determines data distribution characteristics to generate user characteristics, thereby accurately grasping the user's energy usage patterns and characteristics from multiple angles and levels, so that the generated user characteristics can comprehensively and accurately reflect the user's actual energy usage. When the real-time metering data is subsequently checked based on the user characteristics, the data accuracy can be evaluated more scientifically and effectively, and the possible abnormal deviations in the data can be accurately discovered, thereby improving the reliability and precision of data quality control in the entire meter reading process.

[0064] Specifically, the process of generating data features includes:

[0065] Extract features from the data form of historical metering data with communication failures to obtain communication failure features;

[0066] Extract features from the data form of historical metering data of interface failures to obtain interface failure features;

[0067] Extract features from the data form of historical metering data of power failures to obtain power failure features;

[0068] The communication fault characteristics, interface fault characteristics and power supply fault characteristics are defined as data characteristics and output.

[0069] Based on the above, this embodiment uses the data forms of metering data when communication failures, interface failures, and power failures occur in the past to perform feature extraction respectively, and generates corresponding fault features as data features, thereby achieving effective induction and quantification of different types of fault data manifestations. When faced with real-time metering data, it is possible to quickly and accurately perform feature matching based on these data features, accurately determine whether the metering equipment has corresponding faults, and change the previous situation where it was difficult to accurately judge faults in advance, making fault analysis more targeted and timely, thereby ensuring that the metering equipment can maintain a good operating state and reducing adverse effects such as data distortion caused by faults.

[0070] Specifically, data verification is as follows:

[0071] Calculating predicted metering data using user characteristics, where the predicted metering data is used to represent predicted values ​​of metering data of the user obtained based on the user characteristics;

[0072] The deviation value between the predicted metering data and the metering data is calculated, and the accuracy of the metering data is checked based on the deviation value and a preset deviation threshold.

[0073] Based on the above, this embodiment uses user characteristics to calculate the predicted metering data, and verifies the data accuracy by calculating the deviation value between the predicted metering data and the real metering data and combining the preset deviation threshold, thereby realizing a quantitative and scientific metering data accuracy evaluation mechanism. It no longer judges whether the data is accurate based on subjective experience, but predicts a reasonable data range based on user characteristics extracted from historical data rules. When the deviation exceeds the threshold, the anomaly can be discovered in time, thereby improving the objectivity and accuracy of metering data quality monitoring, ensuring that the metering data used can truly reflect the user's energy usage, and providing a reliable data basis for subsequent reasonable billing, energy management and other links.

[0074] Specifically, the calculation process of forecasting measurement data includes:

[0075] The predicted measurement data calculation formula is used to calculate the predicted measurement data, wherein the predicted measurement data calculation formula is specifically as follows:

[0076]

[0077] in, For the The user's metering data obtained in a collection cycle, For the The user's metering data obtained in the first collection cycle and the The absolute value of the difference between the user's metering data obtained in the collection cycle, For the The average value of the user's metering data for the quarter corresponding to the collection cycle, The calculated forecast measurement data.

[0078] Based on the above, this embodiment uses the predicted metering data calculation formula to fully combine the metering data in different collection and reading periods and the corresponding quarterly average and other factors to calculate the predicted metering data, thereby integrating the changing patterns and seasonal characteristics of historical data into the prediction of future metering data, making the prediction results more in line with the actual energy usage trends of users, improving the scientificity and accuracy of the prediction, and then more accurately discovering data deviations when comparing and verifying with the actual metering data, better assisting in judging the accuracy of the metering data, and ensuring that the entire NBIoT-based smart meter reading system plays a more effective role in data control and improves overall operating efficiency.

[0079] Specifically, the calculation process of the deviation value includes:

[0080]

[0081] in, For the The real metering data of users obtained in each collection cycle, The average value of the deviation adjustment allowed when calculating the historical deviation value. is the calculated deviation value; when When The accuracy of the user's actual metering data obtained in each meter reading cycle does not meet the standards.

[0082] Based on the above, this embodiment uses the deviation value calculation process, considers factors such as the deviation adjustment average value allowed by the historical deviation value to measure the accuracy of the real measurement data, and sets corresponding judgment standards, so as to achieve a more realistic and rigorous judgment of the accuracy of the measurement data. It not only considers the difference between the current data and the predicted data, but also takes into account the past deviations to avoid misjudgment due to accidental factors. At the same time, it clarifies the judgment conditions for non-compliance with the accuracy standard, making the data verification work more operational and standardized, thereby accurately screening out problematic data, providing an accurate basis for subsequent possible troubleshooting and data correction operations, and ensuring the stable operation of the system.

[0083] Specifically, the fault analysis is as follows:

[0084] Feature extraction corresponding to the data feature is performed on the real-time metering data to obtain the real-time data feature. When the real-time data feature satisfies any one or more of the communication fault feature, the interface fault feature and the power supply fault feature, it is determined that the metering device corresponding to the real-time metering data has a corresponding fault.

[0085] Based on the above, this embodiment utilizes the method of extracting real-time data features from real-time metering data and matching and judging with existing communication fault features, interface fault features, and power supply fault features to achieve real-time and accurate monitoring and analysis of metering equipment failure conditions, and to detect corresponding metering equipment failures as soon as abnormal features appear in the data, and take corresponding measures in time to repair or adjust them, thereby reducing data loss, errors, and other problems caused by equipment failures, ensuring that metering equipment continuously and stably collects accurate metering data, ensuring that the entire meter reading system operates efficiently and reliably, and maintaining the normal order of energy metering work.

[0086] Specifically, when a fault occurs, the deviation value is recalculated based on the preset fault deviation amplification factor, and the previous The average accuracy of the predicted metering data in a collection cycle. When the average accuracy meets the preset average accuracy, the predicted metering data is allowed to be used as filling data to complete the data when there is a fault.

[0087] It should be noted that the fault deviation amplification factor of the present embodiment is an empirical value known to those skilled in the art based on historical settings of actual fault processing.

[0088] Based on the above, this embodiment uses a preset fault deviation amplification factor to recalculate the deviation value, and combines the average accuracy of the predicted metering data in the previous several collection cycles to determine whether the predicted metering data can be used as filling data to complete the data at the time of the fault. This ensures that in the face of missing or unreliable data caused by a metering equipment failure, the data can be supplemented and improved scientifically and reasonably, taking into account the impact of the failure on the data and the accuracy of the previous predicted data, ensuring that the supplemented data can reflect the actual energy usage to a certain extent, maintain the consistency and availability of the data, and ensure that subsequent energy billing, management and other tasks can be carried out smoothly based on relatively complete data.

[0089] The second aspect of this embodiment discloses Figure 2 A smart meter reading system based on NBIoT is shown, which is applicable to the smart meter reading method based on NBIoT, and the system includes a hardware construction module, a feature extraction module, a data verification module and a fault analysis module which are sequentially connected in communication;

[0090] The hardware building module is configured to connect the metering device with the meter collector using NBIoT technology; wherein the metering device is used to collect metering data, and the metering data is used to characterize the user's energy usage;

[0091] The feature extraction module is configured to: extract features from historical metering data to generate user features and data features; wherein the user features are used to characterize the energy usage of the user, and the data features are used to characterize the data form of the metering data having faults;

[0092] The data checking module is configured to: perform data checking on real-time metering data based on user characteristics, and the data checking is used to evaluate the accuracy of the metering data;

[0093] The fault analysis module is configured to perform fault analysis on the metering equipment corresponding to the real-time metering data based on data characteristics, and the fault analysis is used to determine whether there is a fault in the metering equipment.

[0094] It should be noted that the NBIoT-based smart meter reading system of the present embodiment corresponds to the aforementioned NBIoT-based smart meter reading method. Therefore, the contents not specifically described in the NBIoT-based smart meter reading system of the present embodiment may include but are not limited to function definitions, working principles, and technical effects, etc., and may refer to the records of the aforementioned NBIoT-based smart meter reading method, which will not be elaborated in this text.

[0095] In summary, the NBIoT-based smart meter reading method and system of this embodiment uses NBIoT technology to connect the metering equipment with the metering equipment, and extracts features from historical metering data to generate user features and data features respectively, and then based on these features, performs data verification on real-time metering data and conducts fault analysis on the metering equipment, thereby breaking away from the limitations of traditional manual meter reading methods in the field of energy metering, improving the degree of automation of metering data collection, and enhancing the ability to assess data accuracy. It can also timely and effectively determine whether the metering equipment has faults, ensure the reliable acquisition of metering data and the stable and efficient operation of the entire energy usage metering system, and provide strong support for scientific billing and reasonable management of energy supply companies and users' accurate grasp of their own energy usage.

[0096] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code, or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a processor, a controller, a microcontroller, a microprocessor, other electronic units designed to implement the functions described herein, or a combination thereof. For software implementation, part or all of the processes of the embodiment can be completed by instructing the relevant hardware through a computer program. When implemented, the above program can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein the communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The storage medium can be any available medium that can be accessed by a computer. Computer-readable storage media can include, but are not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer.

[0097] Finally, it should be noted that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A smart meter reading method based on NBIoT, characterized in that: The method includes: The metering device is connected to the meter collector using NBIoT technology; wherein the metering device is used to collect metering data, and the metering data is used to characterize the user's energy usage; Extracting features from the historical metering data to generate user features and data features; wherein the user features are used to characterize the energy usage of the user, and the data features are used to characterize the data form in which the metering data has faults; Performing data verification on the real-time metering data based on the user characteristics, wherein the data verification is used to evaluate the accuracy of the metering data; Performing a fault analysis on the metering device corresponding to the real-time metering data based on the data characteristics, wherein the fault analysis is used to determine whether the metering device has a fault; The process of generating the user features includes: The metering data under different time dimensions are counted based on time series, and the time dimensions at least include metering data of the same metering cycle and metering data of the same season; Under the dimension of the data collection cycle, the statistics of the metering data in each cycle are calculated, and the statistics at least include the mean and the variance; Under the seasonal dimension, the measurement data of the same season for multiple years are summarized and their data distribution characteristics are determined; The statistics and data distribution characteristics of the measurement data obtained in different time dimensions are defined as user features and outputted; The data verification is specifically as follows: Calculating predicted metering data using the user characteristics, the predicted metering data being used to characterize predicted values ​​of the metering data of the user obtained based on the user characteristics; Calculating a deviation value between the predicted metering data and the metering data, and checking the accuracy of the metering data based on the deviation value and a preset deviation threshold; The calculation process of the predicted measurement data includes: The predicted metering data is calculated using a predicted metering data calculation formula, wherein the predicted metering data calculation formula is specifically: ； in, For the The user's metering data obtained in a collection cycle, For the The user's metering data obtained in the first collection cycle and the The absolute value of the difference between the user's metering data obtained in the collection cycle, For the The average value of the user's metering data for the quarter corresponding to the collection cycle, The calculated forecast measurement data.

2. The NBIoT-based intelligent meter reading method according to claim 1 is characterized in that: The metering equipment at least includes a water meter, and the meter collector is connected to all water meters through a two-wire M-BUS communication bus, and the data uplink and downlink protocols adopt the MODBUS standard protocol.

3. The NBIoT-based intelligent meter reading method according to claim 1 is characterized in that: The process of generating the data features includes: Extracting features from the data form of the metering data in the history of communication failure to obtain communication failure features; Extracting features from the data form of the metering data in the history of interface failure to obtain interface failure features; Extracting features from the data form of the metering data in the history of power failure to obtain power failure features; The communication fault feature, the interface fault feature and the power fault feature are defined as the data features and output.

4. The NBIoT-based intelligent meter reading method according to claim 1 is characterized in that: The calculation process of the deviation value includes: ； in, For the The real metering data of users obtained in each collection cycle, The average value of the deviation adjustment allowed when calculating the historical deviation value. is the calculated deviation value; when When The accuracy of the user's actual metering data obtained in each meter reading cycle does not meet the standards.

5. The NBIoT-based intelligent meter reading method according to claim 3 is characterized in that: The fault analysis is specifically as follows: Feature extraction corresponding to the data feature is performed on the real-time metering data to obtain real-time data features. When the real-time data features meet any one or more of the communication fault features, the interface fault features and the power supply fault features, it is determined that a corresponding fault exists in the metering equipment corresponding to the real-time metering data.

6. The NBIoT-based intelligent meter reading method according to claim 4 is characterized in that: When a fault occurs, the deviation value is recalculated based on the preset fault deviation amplification factor, and the previous The average accuracy of the predicted metering data in a collection cycle. When the average accuracy meets the preset average accuracy, the predicted metering data is allowed to be used as filling data to complete the data when there is a fault.

7. A smart meter reading system based on NBIoT, the system is applicable to the smart meter reading method based on NBIoT as claimed in any one of claims 1 to 6, characterized in that: The system includes a hardware construction module, a feature extraction module, a data checking module and a fault analysis module which are sequentially connected in communication; The hardware building module is configured to connect the metering device to the meter collector using NBIoT technology; wherein the metering device is used to collect metering data, and the metering data is used to characterize the user's energy usage; The feature extraction module is configured to: extract features from the historical metering data to generate user features and data features; wherein the user features are used to characterize the energy usage of the user, and the data features are used to characterize the data form in which the metering data has faults; The data checking module is configured to: perform data checking on the real-time metering data based on the user characteristics, and the data checking is used to evaluate the accuracy of the metering data; The fault analysis module is configured to perform a fault analysis on the metering device corresponding to the real-time metering data based on the data characteristics, and the fault analysis is used to determine whether the metering device has a fault.

Images