A configuration-free edge water meter water quantity identification and data quality control method

Abstract

The present application relates to the technical field of water meter data collection, and in particular to a configuration-free edge water meter water quantity identification and data quality control method, which collects the flow information records of N edge water meters in the water meter community to be controlled and the dynamic change characteristics of the water use status in the water meter community to be controlled; screens and defines the flow information record of the j-th edge water meter as the target user water meter information, and calculates the data quality anomaly coefficient of the j-th edge water meter based on the difference records and inputs it into a network model optimized in advance for data quality confidence identification, and cyclically outputs the different data quality confidences of all edge water meters; analyzes the distribution status of edge water meters with different data quality confidences in the water meter community to be controlled, generates corresponding monitoring plans for edge water meters with different data quality confidences, and transmits them to the corresponding edge water meters in sequence. The present application can effectively identify the edge water meter data quality of residential users, adopt corresponding monitoring plans, and efficiently manage the water use of the community.

Description

Technical Field

[0001] The present application relates to the technical field of water meter data collection, and in particular to a configuration-free edge water meter water volume identification and data quality control method. Background Art

[0002] The increasing popularity of electronic edge water meters, while eliminating the hassle of manual meter reading, has led to a decrease in residents' awareness of their household water usage, leaving many residents completely unaware of their water usage. Many residents, for example, are unable to read meter readings or are unwilling to estimate their monthly water usage.

[0003] Therefore, in order to facilitate residents to check their water usage and carry out targeted water-saving operations, it is urgent to develop a configuration-free edge water meter water volume identification and data quality control solution. At the same time, the water meter water volume information is detailed to each type of household water terminal, which is convenient for relevant staff to read the meter and clearly query the water usage of each type of household water terminal, so that more targeted water-saving measures can be taken. Summary of the Invention

[0004] To achieve the above objectives, this application provides the following technical solutions:

[0005] According to a first aspect of the present invention, the present invention claims a configuration-free edge water meter water quantity identification and data quality control method, the method comprising:

[0006] S1: Collect flow information records of N edge water meters in the water meter community to be controlled, and based on the flow information records of N edge water meters, collect dynamic change characteristics of water consumption status in the water meter community to be controlled;

[0007] S2: Filter and obtain the flow information record of the jth edge water meter, and define the flow information record of the jth edge water meter as the target user water meter information, distinguish and compare the dynamic change characteristics of the water use status with the target user water meter information to collect the distinguished records of the jth edge water meter, and calculate the data quality anomaly coefficient of the jth edge water meter based on the distinguished records;

[0008] S3: Input the data quality anomaly coefficient of the j-th edge water meter into the network model optimized in advance for data quality confidence identification to identify the data quality confidence of the j-th edge water meter, and set j=j+1, and return to step S2;

[0009] S4: Repeat steps S2 to S3 until j=N, and output different data quality confidence levels of all edge water meters;

[0010] S5: Analyze the distribution status of edge water meters with different data quality confidence levels in the water meter community to be controlled, generate corresponding monitoring plans for edge water meters with different data quality confidence levels according to the distribution status, and transmit the monitoring plans to the corresponding edge water meters in sequence.

[0011] Furthermore, the flow information record contains five fields, which are the monthly average water flow, instantaneous water flow rate, peak and valley water use cycle, maximum value number and minimum value number;

[0012] The dynamic change characteristics of water usage status within the water meter community to be controlled are collected, including:

[0013] a1: Filter the jth field in the traffic information record and analyze all field values ​​of the jth field;

[0014] a2: Divide all field values ​​of the j-th field by interval segmentation to collect P divided intervals;

[0015] a3: Prioritize the P partitions in order of information size. Define the partition with the highest priority as a high-priority cluster. Calculate the mean of all data in the high-priority cluster and output the high-priority value of the jth field.

[0016] a4: Repeat steps a1 to a3 until j=5, then end the recursion and output the high priority value of the field; define the high priority value of the field as a dynamic change feature of the water usage status.

[0017] Furthermore, the step of distinguishing and comparing the dynamic change characteristics of water usage status with the target user's water meter information includes:

[0018] b1: Filter and obtain the field value of the wth field in the target user's water meter information, and filter and obtain the high priority quantity of the same field in the dynamic change characteristics of water usage status, define the field value of the wth field as the field value to be identified, and define the high priority quantity of the same field as the reference field value;

[0019] b2: Calculate the distance between the value of the field to be identified and the value of the reference field, and determine whether the distance between the value of the field to be identified and the value of the reference field is within a preset range. If so, set w = w + 1 and return to step b1; if not, define the distance between the value of the field to be identified and the value of the reference field as the deviation ratio of the wth field, define the wth field as the distinguishing field, set w = w + 1, and return to step b1;

[0020] b3: Repeat steps b1 to b2 until w = 5, then end the recursion and output K distinguishing fields and the deviation ratio of each distinguishing field. The K distinguishing fields and the deviation ratio of each distinguishing field are defined as the distinguishing records of the j-th edge water meter.

[0021] Furthermore, the calculation of the data quality anomaly coefficient of the j-th edge water meter based on the distinguished records includes:

[0022] Filter and obtain the deviation ratio of each difference field in the difference record of the jth edge water meter;

[0023] The deviation ratio of each distinguishing field is input into a preconfigured quality anomaly analysis model, and the data quality anomaly coefficient of the j-th edge water meter is output; wherein the formula of the quality anomaly analysis model is as follows: Where: R is the data quality anomaly coefficient of the jth edge water meter, D g is the deviation ratio of the g-th distinguishing field.

[0024] Furthermore, the optimization steps of the network model for data quality confidence identification are as follows:

[0025] Collect historical data quality confidence sample information, and divide the historical data quality confidence sample information into a data quality confidence sample set and a data quality confidence to-be-identified data set; the historical data quality confidence sample information includes data quality anomaly coefficients of multiple edge water meters and corresponding data quality confidence setting confidence scenarios;

[0026] The data quality confidence setting confidence scenarios include abnormally low confidence scenarios, abnormally medium confidence scenarios, and abnormally high confidence scenarios;

[0027] Configure the quality listener, define the data quality anomaly coefficient in the data quality confidence sample set as the input data of the quality listener, and define the setting confidence scenario in the data quality confidence sample set as the output data of the quality listener, optimize the quality listener, and output the initial monitoring network;

[0028] The initial monitoring network is model verified using the data quality confidence dataset to be identified, and the corresponding initial monitoring network with an output value greater than or equal to a preset accuracy threshold is defined as the network model for data quality confidence identification.

[0029] Furthermore, the generation logic of the confidence scenario set in the historical data quality confidence sample information is as follows:

[0030] Setting a data quality anomaly coefficient threshold value, wherein the data quality anomaly coefficient threshold value includes a data quality anomaly coefficient threshold value Lim1 and a data quality anomaly coefficient threshold value Lim2, Lim1>Lim2;

[0031] Compare the data quality anomaly coefficient R with the data quality anomaly coefficient threshold;

[0032] If R≥Lim1, the edge water meter corresponding to the data quality anomaly coefficient is set to the data quality confidence of the abnormally low confidence scenario;

[0033] If R<Lim1 and R>Lim2, the edge water meter corresponding to the data quality anomaly coefficient is set to the data quality confidence of the abnormal medium confidence scenario;

[0034] If R≤Lim2, the edge water meter corresponding to the data quality anomaly coefficient is set to the data quality confidence of the abnormally high confidence scenario.

[0035] Furthermore, the generation of corresponding monitoring solutions for edge water meters with different data quality confidence levels includes:

[0036] Collect the W buildings in the water meter community to be controlled and the building ID of each building;

[0037] The number of water meters at the edge of each building with abnormally low confidence, the number of water meters at the edge of each building with abnormally medium confidence, and the number of water meters at the edge of each building with abnormally high confidence are collected in sequence;

[0038] Define the building with the highest priority for the number of edge water meters in the abnormally low confidence scenario as a high-consumption building, filter out the building IDs of the high-consumption buildings, and define the building IDs of the high-consumption buildings as the monitoring plan for edge water meters in the abnormally low confidence scenario;

[0039] Define the building with the highest priority for the number of edge water meters in the abnormal medium confidence scenario as a medium-consumption building, filter out the building IDs of the medium-consumption buildings, and define the building IDs of the medium-consumption buildings as the monitoring plan for the edge water meters in the abnormal medium confidence scenario;

[0040] The building with the highest priority in the number of edge water meters in the abnormally high confidence scenario is defined as a low-consumption building, and the building IDs of the low-consumption buildings are screened and defined as the monitoring plan for the edge water meters in the abnormally high confidence scenario.

[0041] The present application relates to the technical field of water meter data collection, and in particular to a configuration-free edge water meter water quantity identification and data quality control method, which collects the flow information records of N edge water meters in the water meter community to be controlled and the dynamic change characteristics of the water use status in the water meter community to be controlled; screens and defines the flow information record of the j-th edge water meter as the target user water meter information, and calculates the data quality anomaly coefficient of the j-th edge water meter based on the difference records and inputs it into a network model optimized in advance for data quality confidence identification, and cyclically outputs the different data quality confidences of all edge water meters; analyzes the distribution status of edge water meters with different data quality confidences in the water meter community to be controlled, generates corresponding monitoring plans for edge water meters with different data quality confidences, and transmits them to the corresponding edge water meters in sequence. The present application can effectively identify the edge water meter data quality of residential users, adopt corresponding monitoring plans, and efficiently manage the water use of the community. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a workflow diagram of a configuration-free edge water meter water volume identification and data quality control method claimed in an embodiment of the present application. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0044] The terms "first", "second" and "third" in this application are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, a feature defined as "first", "second" and "third" may explicitly or implicitly include at least one of such features. In the description of this application, "multiple" means at least two, for example, two, three, etc., unless otherwise clearly and specifically defined. All directional indications in the embodiments of this application (such as up, down, left, right, front, back...) are only used to explain the relative positional relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally also include steps or units that are not listed, or may optionally also include other steps or units inherent to these processes, methods, products or devices.

[0045] References to "embodiments" herein mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0046] See also Figure 1 As shown, this embodiment discloses a configuration-free edge water meter water volume identification and data quality control method, the method comprising:

[0047] S1: Collect flow information records of N edge water meters in the water meter community to be controlled, and based on the flow information records of N edge water meters, collect dynamic change characteristics of water consumption status in the water meter community to be controlled;

[0048] It should be noted that the water meter community to be controlled is selected based on actual conditions, by selecting high-flow water use scenarios in the urban pipeline network where water pipe accidents or water shortages often occur during peak hours;

[0049] Specifically, the flow information record contains five fields, namely, monthly average water flow, instantaneous water flow rate, peak and valley water use cycle, maximum value number and minimum value number;

[0050] It should be noted that the monthly average water flow, instantaneous water flow rate, peak and valley water use period, maximum and minimum water use times in the flow information record are collected by sensors or output by monitors installed in the water meter community to be controlled;

[0051] During implementation, the dynamic change characteristics of water usage status within the community of water meters to be controlled are collected, including:

[0052] a1: Filter the jth field in the traffic information record and analyze all field values ​​of the jth field;

[0053] a2: Divide all field values ​​of the j-th field by interval segmentation to collect P divided intervals;

[0054] a3: Prioritize the P partitions in order of information size. Define the partition with the highest priority as a high-priority cluster. Calculate the mean of all data in the high-priority cluster and output the high-priority value of the jth field.

[0055] a4: Repeat steps a1 to a3 until j=5, then end the recursion and output the high priority value of the field; define the high priority value of the field as a dynamic change feature of the water usage status;

[0056] For example, assume that there are 5 edge water meters in the water meter community to be controlled, that is, N=5, which are X1, X2, X3, X4 and X5, where the monthly average water flow of X1 (i.e., the field value of the cubic meter feature) is 9.0, the monthly average water flow of X2 is 8.8, the monthly average water flow of X3 is 6.5, the monthly average water flow of X4 is 11.5, and the monthly average water flow of X5 is 3.0. Assume that after the field value of the cubic meter field is divided, three division intervals are output, namely Y1, Y2 and Y3, where Y1 contains X1, X2 and X3. 3 cubic meters, Y2 contains the field value of the X4 cubic meters field, and Y3 contains the field value of the X5 cubic meters field. Among them, Y1 is the partition interval with the first priority configuration. In this case, Y1 is defined as the high-priority cluster. The mean of all data in high-priority cluster Y1 is calculated, and the output is 8.1. 8.1 is defined as the high-priority quantity of the cubic meter field. Similarly, the collection logic of high-priority quantities of other fields is the same. For details, refer to the above description. Finally, the high-priority quantities of all fields are output, that is, the dynamic change characteristics of water use status.

[0057] It should be understood that the division interval with the first priority configuration often contains the most common patterns or behaviors in the data, that is, it represents most of the characteristic behaviors of water use status in the water meter community to be controlled, and reflects the relatively stable state of water use status (especially in high-flow water use scenarios); by collecting the characteristic quantities of the vast majority of data characteristic behaviors of water use status and defining them as reference benchmarks, the present invention is conducive to providing important data support for the subsequent determination of data quality confidence of different edge water meters in the current time and space.

[0058] S2: Filter and obtain the flow information record of the jth edge water meter, and define the flow information record of the jth edge water meter as the target user water meter information, distinguish and compare the dynamic change characteristics of the water use status with the target user water meter information to collect the distinguished records of the jth edge water meter, and calculate the data quality anomaly coefficient of the jth edge water meter based on the distinguished records;

[0059] In implementation, the dynamic change characteristics of water usage status and target user water meter information are distinguished and compared, including:

[0060] b1: Filter and obtain the field value of the wth field in the target user's water meter information, and filter and obtain the high priority quantity of the same field in the dynamic change characteristics of water usage status, define the field value of the wth field as the field value to be identified, and define the high priority quantity of the same field as the reference field value;

[0061] For example, if the wth field is a cubic meter field (i.e., the average monthly water flow), and the field value of the cubic meter field is 8.8, then when the same field is obtained by screening, the high priority value of the consumption field in the dynamic change characteristics of water use status is obtained by screening. If the high priority value of the cubic meter field is 8.1, then 8.8 is the field value to be identified, and 8.1 is the reference field value;

[0062] b2: Calculate the distance between the value of the field to be identified and the value of the reference field, and determine whether the distance between the value of the field to be identified and the value of the reference field is within a preset range. If so, set w = w + 1 and return to step b1; if not, define the distance between the value of the field to be identified and the value of the reference field as the deviation ratio of the wth field, define the wth field as the distinguishing field, set w = w + 1, and return to step b1;

[0063] b3: Repeat steps b1 to b2 until w = 5, then end the recursion and output K distinguishing fields and the deviation ratio of each distinguishing field. These K distinguishing fields and the deviation ratio of each distinguishing field are defined as the distinguishing record of the j-th edge water meter.

[0064] In implementation, the calculation of the data quality anomaly coefficient of the j-th edge water meter based on the distinguished records includes:

[0065] Filter and obtain the deviation ratio of each difference field in the difference record of the jth edge water meter;

[0066] The deviation ratio of each distinguishing field is input into a preconfigured quality anomaly analysis model, and the data quality anomaly coefficient of the j-th edge water meter is output; wherein the formula of the quality anomaly analysis model is as follows: Where: R is the data quality anomaly coefficient of the jth edge water meter, D g is the deviation ratio of the g-th distinguishing field.

[0067] S3: Input the data quality anomaly coefficient of the j-th edge water meter into the network model optimized in advance for data quality confidence identification to identify the data quality confidence of the j-th edge water meter, and set j=j+1, and return to step S2;

[0068] Specifically, the optimization steps of the network model for data quality confidence identification are as follows:

[0069] Collect historical data quality confidence sample information, and divide the historical data quality confidence sample information into a data quality confidence sample set and a data quality confidence to-be-identified data set; the historical data quality confidence sample information includes data quality anomaly coefficients of multiple edge water meters and corresponding data quality confidence setting confidence scenarios;

[0070] The data quality confidence setting confidence scenarios include abnormally low confidence scenarios, abnormally medium confidence scenarios, and abnormally high confidence scenarios;

[0071] It should be noted that the data quality anomaly coefficient of the edge water meter in the historical data quality confidence sample information is output after distinguishing and comparing the flow information records of each edge water meter and analyzing the quality anomaly. For details, please refer to the above description and will not be repeated here.

[0072] The generation logic of the confidence scenario set in the historical data quality confidence sample information is as follows:

[0073] Setting a data quality anomaly coefficient threshold value, wherein the data quality anomaly coefficient threshold value includes a data quality anomaly coefficient threshold value Lim1 and a data quality anomaly coefficient threshold value Lim2, Lim1>Lim2;

[0074] Compare the data quality anomaly coefficient R with the data quality anomaly coefficient threshold;

[0075] If R≥Lim1, the edge water meter corresponding to the data quality anomaly coefficient is set to the data quality confidence of the abnormally low confidence scenario;

[0076] If R<Lim1 and R>Lim2, the edge water meter corresponding to the data quality anomaly coefficient is set to the data quality confidence of the abnormal medium confidence scenario;

[0077] If R≤Lim2, the edge water meter corresponding to the data quality anomaly coefficient is set to the data quality confidence of the abnormally high confidence scenario.

[0078] It can be understood that: the data quality confidence level in the abnormally low confidence scenario indicates that the current data quality behavior of the household owner of the corresponding edge water meter is too aggressive, tending to be higher than the monthly average water flow monitoring; the data quality confidence level in the abnormally medium confidence scenario indicates that the current data quality behavior of the household owner of the corresponding edge water meter remains within the speed limit, with a moderate cubic meter, tending to be monitored based on the monthly average water flow; and the data quality confidence level in the abnormally high confidence scenario indicates that the current data quality behavior of the household owner of the corresponding edge water meter is relatively slow, tending to be lower than the monthly average water flow monitoring;

[0079] Configure the quality listener, define the data quality anomaly coefficient in the data quality confidence sample set as the input data of the quality listener, and define the setting confidence scenario in the data quality confidence sample set as the output data of the quality listener, optimize the quality listener, and output the initial monitoring network;

[0080] The initial monitoring network is model-verified using the data quality confidence dataset to be identified, and the corresponding initial monitoring network with an output value greater than or equal to a preset accuracy threshold is defined as the network model for data quality confidence identification;

[0081] S4: Repeat steps S2 to S3 until j=N, and output different data quality confidence levels of all edge water meters;

[0082] It can be understood that: by distinguishing and comparing each edge water meter and the data quality anomaly coefficient, and finally inputting the data quality anomaly coefficient corresponding to each edge water meter into the network model optimized in advance for data quality confidence identification, the data quality confidence of each edge water meter and household in the water meter community to be controlled can be qualitatively determined, which is conducive to providing important data support for subsequent water diversion.

[0083] S5: Analyze the distribution status of edge water meters with different data quality confidence levels in the community of water meters to be controlled, generate corresponding monitoring plans for edge water meters with different data quality confidence levels according to the distribution status, and transmit the monitoring plans to the corresponding edge water meters in sequence;

[0084] In implementation, the generation of corresponding monitoring plans for edge water meters with different data quality confidence levels includes:

[0085] Collect the W buildings in the water meter community to be controlled and the building ID of each building;

[0086] The number of water meters at the edge of each building with abnormally low confidence, the number of water meters at the edge of each building with abnormally medium confidence, and the number of water meters at the edge of each building with abnormally high confidence are collected in sequence;

[0087] Define the building with the highest priority for the number of edge water meters in the abnormally low confidence scenario as a high-consumption building, filter out the building IDs of the high-consumption buildings, and define the building IDs of the high-consumption buildings as the monitoring plan for edge water meters in the abnormally low confidence scenario;

[0088] Define the building with the highest priority for the number of edge water meters in the abnormal medium confidence scenario as a medium-consumption building, filter out the building IDs of the medium-consumption buildings, and define the building IDs of the medium-consumption buildings as the monitoring plan for the edge water meters in the abnormal medium confidence scenario;

[0089] Define the building with the highest priority for the number of edge water meters in the abnormally high confidence scenario as a low-consumption building, filter out the building IDs of the low-consumption buildings, and define the building IDs of the low-consumption buildings as the monitoring plan for the edge water meters in the abnormally high confidence scenario;

[0090] For example, it is assumed that there are 4 buildings in the water meter community to be controlled, that is, W=4, and the building IDs of the 4 buildings are T1 (first from the left), T2 (second from the left), T3 (first from the right), and T4 (second from the right) in sequence. It is further assumed that there are 20 edge water meters in the water meter community to be controlled, and there are 8 edge water meters with abnormally low confidence scenarios in T2 (second from the left) (the edge water meters with abnormally low confidence scenarios account for the largest proportion), and there are 5 edge water meters with abnormally medium confidence scenarios in T3 (first from the right) (the edge water meters with abnormally medium confidence scenarios account for the largest proportion), and there are 4 edge water meters with abnormally high confidence scenarios in T4 (second from the right) (the edge water meters with abnormally high confidence scenarios account for the largest proportion). Therefore, T2 (second from the left) is defined as the monitoring scheme for the edge water meter with abnormally low confidence scenarios, T3 (first from the right) is defined as the monitoring scheme for the edge water meter with abnormally medium confidence scenarios, and T4 (second from the right) is defined as the monitoring scheme for the edge water meter with abnormally high confidence scenarios;

[0091] By evaluating the data quality anomaly coefficients of different edge water meters, determining the data quality confidence of different edge water meters based on the data quality anomaly coefficients, and finally providing monitoring solutions for edge water meters with different data quality confidence levels, the present invention can accurately evaluate the data quality confidence levels of different edge water meters and data quality personnel in the current time and space, and the evaluation is more objective. Furthermore, by providing different data quality solutions for edge water meters with different data quality confidence levels, the present invention can indirectly intervene in or control the water use status, which is beneficial to alleviating the water shortage status in high-flow water use scenarios, ensuring the stability of water use status, and improving the smoothness of water use status in high-flow water use scenarios.

[0092] Since the electronic device introduced in this embodiment is an electronic device used to implement the configuration-free edge water meter water quantity identification and data quality control method in the embodiment of this application, based on the configuration-free edge water meter water quantity identification and data quality control method introduced in the embodiment of this application, those skilled in the art can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application will not be introduced in detail here. As long as those skilled in the art implement the electronic device used by the configuration-free edge water meter water quantity identification and data quality control method in the embodiment of this application, they are all within the scope of protection to be provided by this application.

[0093] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0094] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. The above is only an implementation method of the present application and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made through the content of the description and drawings of this application, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of this application.

[0095] The above detailed description of the specific embodiments of the invention is intended to be illustrative only, and the present application is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications or substitutions of the invention are also within the scope of the present application. Therefore, equivalent changes, modifications, and improvements made without departing from the spirit and scope of the present application should be included within the scope of the present application.

Claims

1. A configuration-free edge water meter water volume identification and data quality control method, characterized in that: The method comprises: S1: Collect flow information records of N edge water meters in the water meter community to be controlled, and based on the flow information records of N edge water meters, collect dynamic change characteristics of water consumption status in the water meter community to be controlled; S2: Filter and obtain the flow information record of the jth edge water meter, and define the flow information record of the jth edge water meter as the target user water meter information, distinguish and compare the dynamic change characteristics of the water use status with the target user water meter information to collect the distinguished records of the jth edge water meter, and calculate the data quality anomaly coefficient of the jth edge water meter based on the distinguished records; S3: Input the data quality anomaly coefficient of the j-th edge water meter into the network model optimized in advance for data quality confidence identification to identify the data quality confidence of the j-th edge water meter, and set j=j+1, and return to step S2; S4: Repeat the above steps S2 to S3 until j=N, and output the different data quality confidence levels of all edge water meters; S5: Analyze the distribution status of edge water meters with different data quality confidence levels in the water meter community to be controlled, generate corresponding monitoring plans for edge water meters with different data quality confidence levels according to the distribution status, and transmit the monitoring plans to the corresponding edge water meters in sequence.

2. The configuration-free edge water meter water volume identification and data quality control method according to claim 1, characterized in that: The flow information record contains five fields, which are the monthly average water flow, instantaneous water flow rate, peak and valley water use period, maximum value number and minimum value number; The dynamic change characteristics of water usage status within the water meter community to be controlled are collected, including: a1: Filter the jth field in the traffic information record and analyze all field values ​​of the jth field; a2: Divide all field values ​​of the j-th field by interval segmentation to collect P divided intervals; a3: Prioritize the P partitions in order of information size. Define the partition with the highest priority as a high-priority cluster. Calculate the mean of all data in the high-priority cluster and output the high-priority value of the jth field. a4: Repeat steps a1 to a3 until j=5, then end the recursion and output the high priority value of the field; define the high priority value of the field as a dynamic change feature of the water usage status.

3. The configuration-free edge water meter water volume identification and data quality control method according to claim 2, characterized in that: The process of distinguishing and comparing the dynamic change characteristics of water usage status with target user water meter information includes: b1: Filter and obtain the field value of the wth field in the target user's water meter information, and filter and obtain the high priority quantity of the same field in the dynamic change characteristics of water usage status, define the field value of the wth field as the field value to be identified, and define the high priority quantity of the same field as the reference field value; b2: Calculate the distance between the value of the field to be identified and the value of the reference field, and determine whether the distance between the value of the field to be identified and the value of the reference field is within a preset range. If so, set w = w + 1 and return to step b1; if not, define the distance between the value of the field to be identified and the value of the reference field as the deviation ratio of the wth field, define the wth field as the distinguishing field, set w = w + 1, and return to step b1; b3: Repeat steps b1 to b2 until w = 5, then end the recursion and output K distinguishing fields and the deviation ratio of each distinguishing field. The K distinguishing fields and the deviation ratio of each distinguishing field are defined as the distinguishing records of the j-th edge water meter.

4. The configuration-free edge water meter water volume identification and data quality control method according to claim 3, characterized in that: The calculation of the data quality anomaly coefficient of the j-th edge water meter based on the distinguished records includes: Filter and obtain the deviation ratio of each difference field in the difference record of the jth edge water meter; The deviation ratio of each distinguishing field is input into a preconfigured quality anomaly analysis model, and the data quality anomaly coefficient of the j-th edge water meter is output; wherein the formula of the quality anomaly analysis model is as follows: Where: R is the data quality anomaly coefficient of the jth edge water meter, D g is the deviation ratio of the g-th distinguishing field.

5. The configuration-free edge water meter water volume identification and data quality control method according to claim 4, characterized in that: The optimization steps of the network model for data quality confidence identification are as follows: Collect historical data quality confidence sample information, and divide the historical data quality confidence sample information into a data quality confidence sample set and a data quality confidence to-be-identified data set; the historical data quality confidence sample information includes data quality anomaly coefficients of multiple edge water meters and corresponding data quality confidence setting confidence scenarios; The data quality confidence setting confidence scenarios include abnormally low confidence scenarios, abnormally medium confidence scenarios, and abnormally high confidence scenarios; Configure the quality listener, define the data quality anomaly coefficient in the data quality confidence sample set as the input data of the quality listener, and define the setting confidence scenario in the data quality confidence sample set as the output data of the quality listener, optimize the quality listener, and output the initial monitoring network; The initial monitoring network is model verified using the data quality confidence dataset to be identified, and the corresponding initial monitoring network with an output value greater than or equal to a preset accuracy threshold is defined as the network model for data quality confidence identification.

6. The configuration-free edge water meter water volume identification and data quality control method according to claim 5, characterized in that: The generation logic of setting the confidence scenario in the historical data quality confidence sample information is as follows: Setting a data quality anomaly coefficient threshold value, wherein the data quality anomaly coefficient threshold value includes a data quality anomaly coefficient threshold value Lim1 and a data quality anomaly coefficient threshold value Lim2, Lim1>Lim2; Compare the data quality anomaly coefficient R with the data quality anomaly coefficient threshold; If R≥Lim1, the edge water meter corresponding to the data quality anomaly coefficient is set to the data quality confidence of the abnormally low confidence scenario; If R<Lim1 and R>Lim2, the edge water meter corresponding to the data quality anomaly coefficient is set to the data quality confidence of the abnormal medium confidence scenario; If R≤Lim2, the edge water meter corresponding to the data quality anomaly coefficient is set to the data quality confidence of the abnormally high confidence scenario.

7. The configuration-free edge water meter water volume identification and data quality control method according to claim 6, characterized in that: The generation of corresponding monitoring solutions for edge water meters with different data quality confidence levels includes: Collect the W buildings in the water meter community to be controlled and the building ID of each building; The number of water meters at the edge of each building with abnormally low confidence, the number of water meters at the edge of each building with abnormally medium confidence, and the number of water meters at the edge of each building with abnormally high confidence are collected in sequence; Define the building with the highest priority for the number of edge water meters in the abnormally low confidence scenario as a high-consumption building, filter out the building IDs of the high-consumption buildings, and define the building IDs of the high-consumption buildings as the monitoring plan for edge water meters in the abnormally low confidence scenario; Define the building with the highest priority for the number of edge water meters in the abnormal medium confidence scenario as a medium-consumption building, filter out the building IDs of the medium-consumption buildings, and define the building IDs of the medium-consumption buildings as the monitoring plan for the edge water meters in the abnormal medium confidence scenario; The building with the highest priority in the number of edge water meters in the abnormally high confidence scenario is defined as a low-consumption building, and the building IDs of the low-consumption buildings are screened and defined as the monitoring plan for the edge water meters in the abnormally high confidence scenario.

Images