Intelligent water meter data truth value discrimination method and system, electronic equipment and storage medium

Abstract

The invention relates to the field of intelligent water meter data processing, and discloses an intelligent water meter data truth value judgment method and system, electronic equipment and a storage medium. The method comprises the steps of collecting and preprocessing multi-dimensional data of the intelligent water meter, extracting and selecting features, training a multi-dimensional shrinkage data model, judging a new data truth value by using the model, and presenting a result in a visual mode. The method can comprehensively consider historical reading, water usage rules, user habits, industry characteristics and other information, effectively improves the accuracy and efficiency of data truth value discrimination, provides a customized solution, is easy to deploy and maintain, enhances the model generalization ability, improves the user experience, provides reliable data support for water resource management, water saving and emission reduction, and is suitable for popularization and application. The method can be widely applied to resident life, industrial production and other scenes where intelligent water meter data needs to be accurately distinguished.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent water meter data processing, and in particular to an intelligent water meter data true value determination method, system, electronic equipment and storage medium. Background Art

[0002] In the context of the widespread application of smart water meter data, although existing technologies have made progress in data true value identification, there are still many problems. Early manual inspections and simple statistical analysis have limited efficiency and accuracy. Although intelligent algorithms based on multi-dimensional data have become mainstream, some algorithms are complex, require large computing resources, and take a long time. Some algorithms are too simple and lack accuracy, and there is a lack of customized solutions for specific industries or users. Summary of the invention

[0003] The present invention aims to provide a method, system, electronic device and storage medium for determining the true value of smart water meter data, which comprehensively considers multi-dimensional information such as historical readings of the water meter for half a year or even longer, historical water use patterns, historical average water consumption, user water use habits, minimum flow at night, industry water use properties and patterns, etc., and improves the accuracy and efficiency of data true value determination through a training algorithm based on a multi-dimensional contraction data model, thereby providing more reliable data support for water resource management and water conservation and emission reduction.

[0004] The complete technical solution provided by the present invention

[0005] Data collection and preprocessing (data acquisition module)

[0006] Collect data such as historical readings, historical water usage patterns, and historical average water consumption of smart water meters, and obtain auxiliary information such as user water usage habits, minimum nighttime flow, and industry water usage characteristics. For example, historical readings can be obtained from past records of water meters, user water usage habits can be determined by analyzing water consumption in different time periods, and industry water usage characteristics can be determined based on the industry category of the user.

[0007] The collected data is cleaned to remove erroneous data; denoised to eliminate interfering data; and standardized to give the data a unified format and magnitude to ensure data quality and consistency.

[0008] Feature extraction and selection (feature extraction module)

[0009] After preprocessing the collected data, features are extracted to form feature vectors for model training, such as calculating the change rate of historical readings, analyzing the periodic characteristics of water consumption (such as the change pattern of water consumption on working days and non-working days), and extracting the characteristics of user water consumption habits (such as the characteristics of water consumption during peak hours in the morning and evening).

[0010] Use feature selection algorithms to select the feature subset that has the greatest impact on the discrimination results. For example, use algorithms such as information gain and chi-square test to determine key features such as the rate of change of historical readings and water consumption in a specific time period.

[0011] Multi-dimensional shrinkage data model training (model training module)

[0012] Based on the multi-dimensional shrinkage data model training algorithm, the extracted feature vectors are used for model training. During the training process, the model parameters, such as weight coefficients, are continuously adjusted, and the algorithm is optimized, such as selecting a suitable gradient descent algorithm, to improve the model's discrimination accuracy and generalization ability.

[0013] Based on the selected feature subsets, a multi-dimensional shrinkage data model is constructed. This model can comprehensively consider multi-dimensional information, optimize model parameters through historical data training, and enable it to accurately determine the true value of data.

[0014] Data truth value determination (data truth value determination module)

[0015] Input the smart water meter data to be identified into the trained model.

[0016] Based on the input data and feature subsets, the model outputs the judgment result of the true value of the data, such as whether the data is true and whether there are anomalies (such as whether the data deviates too much from historical rules).

[0017] System implementation and deployment (result output module)

[0018] The identification results are presented to users or water supply companies in an intuitive manner, such as displaying the water meter data identification status of each household in the community in real time through an electronic display screen, or pushing abnormal data notifications through a mobile phone APP.

[0019] The above method is integrated into the smart water meter data true value judgment system to ensure that all modules of the system work together.

[0020] The system is deployed on electronic devices (such as servers, computers, etc.) and provides a friendly user interface and interactive mode to facilitate user operation and viewing of results.

[0021] Store system-related algorithms, models, and parameters in storage media (such as hard disks, solid-state drives, etc.) for subsequent use and maintenance. Data and model parameters can be updated regularly to adapt to new situations.

[0022] Beneficial effects of the present invention:

[0023] 1. Improve the accuracy of judgment: By comprehensively considering information from multiple dimensions, the present invention can more accurately judge the authenticity of smart water meter data and reduce misjudgment and missed judgment.

[0024] 2. Improve the efficiency of discrimination: Based on the training algorithm of the multi-dimensional shrinkage data model, the present invention can quickly discriminate a large amount of data and improve the discrimination efficiency.

[0025] 3. Customized solutions: The present invention can provide customized solutions according to the needs of different industries or users to meet the needs in different scenarios.

[0026] 4. Easy to deploy and maintain: The system implementation scheme provided by the present invention is simple and clear, and easy to deploy and maintain on electronic equipment.

[0027] 5. Enhance the generalization ability of the model: By adopting a multi-dimensional shrinkage data model training algorithm, the present invention can make full use of the rules and features in historical data, improve the generalization ability of the model, and adapt to the needs of data truth value discrimination in different scenarios.

[0028] Improve user experience: Through an intuitive result output method, the present invention can facilitate users or water supply companies to view the judgment results, thereby improving user experience and satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the present invention or 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 in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 A schematic diagram of a method for determining the true value of data according to an embodiment of the present invention;

[0031] Figure 2 Schematic diagram of the data truth value determination process according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0033] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0034] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0035] Example 1

[0036] See also Figure 1 to Figure 2

[0037] 1. Data collection and preprocessing (data acquisition module):

[0038] 1. Used to collect data such as historical readings, historical water usage patterns, historical average water usage of smart water meters, as well as auxiliary information such as user water usage habits, minimum flow at night, and industry water usage characteristics.

[0039] 2. Clean, denoise and standardize the data to ensure data quality and consistency.

[0040] 2. Feature extraction and selection (feature extraction module):

[0041] 1. Preprocess and extract features of the collected data to form feature vectors for model training. Feature vectors include multiple dimensions, such as the rate of change of historical readings, periodic characteristics of water consumption, and user water usage habits.

[0042] 2. Through the feature selection algorithm, filter out the feature subset that has the greatest impact on the discrimination results.

[0043] 3. Multi-dimensional shrinkage data model training (model training module):

[0044] Based on the multi-dimensional shrinkage data model training algorithm, the extracted feature vectors are used for model training. During the model training process, the model parameters are adjusted and the algorithm is optimized to improve the model's discrimination accuracy and generalization ability.

[0045] 1. Based on the selected feature subset, build a multi-dimensional shrinkage data model.

[0046] 2. Use historical data to train the model, optimize model parameters, and improve the model's discrimination ability.

[0047] 4. Data truth value determination (data truth value determination module):

[0048] The trained model is used to perform true value discrimination on the newly collected smart water meter data. The discrimination results include whether the data is true and whether there are anomalies.

[0049] 1. Input the smart water meter data to be identified into the trained model.

[0050] 2. The model outputs the judgment result of the true value of the data based on the input data and feature subset.

[0051] 5. System implementation and deployment (result output module):

[0052] The identification results are presented to users or water supply companies in an intuitive manner, such as through electronic display screens, mobile phone apps, etc.

[0053] 1. Integrate the above method into the smart water meter data true value judgment system.

[0054] 2. Deploy the system on electronic devices and provide a friendly user interface and interaction method.

[0055] Store system-related algorithms, models, parameters, etc. in storage media for subsequent use and maintenance.

[0056] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0057] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for determining the true value of smart water meter data, characterized in that: The following steps are involved: Data collection and preprocessing steps: collect historical readings of smart water meters, historical water use patterns, historical average water consumption data, as well as user water use habits, minimum nighttime flow, and auxiliary information on industry water use characteristics, and clean, denoise, and standardize the data; Feature extraction and selection step: extracting features from the preprocessed data to form a feature vector, the feature vector includes the historical reading change rate, the periodicity characteristics of water consumption, and the user's water use habit characteristics, and then filtering out the feature subset that has the greatest impact on the discrimination result through a feature selection algorithm; Multi-dimensional shrinkage data model training step: based on the multi-dimensional shrinkage data model training algorithm, using the feature subset to build a multi-dimensional shrinkage data model, and using historical data to train the model, adjusting model parameters and optimizing algorithms during the training process to improve the discrimination accuracy and generalization ability of the model; Data true value judgment step: Input the smart water meter data to be judged into the trained model, and the model outputs the judgment result of the data true value based on the input data and feature subset.

2. The method for determining true value of smart water meter data according to claim 1, characterized in that: In the data collection and preprocessing steps, historical readings are obtained from past records of the water meter, user water usage habits are determined by analyzing water consumption in different time periods, and the nature of industry water use is determined based on the industry category of the user.

3. The method for determining true value of smart water meter data according to claim 1, characterized in that: In the feature extraction and selection step, the feature selection algorithm includes an information gain algorithm or a chi-square test algorithm.

4. The method for determining true value of smart water meter data according to claim 1, characterized in that: In the multi-dimensional shrinkage data model training step, the optimization algorithm includes a gradient descent algorithm.

5. A smart water meter data true value determination system, characterized in that: include: A data acquisition module, used to perform the data collection and preprocessing steps in claim 1; A feature extraction module, used to perform the feature extraction and selection steps in claim 1; A model training module, used to perform the multi-dimensional shrinkage data model training step in claim 1; A data truth value determination module, used to perform the data truth value determination step in claim 1; The result output module is used to present the judgment result to the user or water supply enterprise in an intuitive manner, and integrate the true value judgment method of the smart water meter data into the system, deploy the system on the electronic device and provide a user interface and interaction method, and store the system-related algorithms, models and parameters in the storage medium.

6. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the true value determination method of smart water meter data according to any one of claims 1 to 4 when executing the program.

7. A storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method for determining the true value of smart water meter data according to any one of claims 1 to 4 is implemented.

Images