Meter reading rate analysis method, device and equipment of automatic meter reading system and medium

Abstract

The invention discloses a meter reading rate analysis method, device and equipment of an automatic meter reading system and a medium. The method comprises the following steps: acquiring to-be-analyzed meter reading data; inputting the to-be-analyzed meter reading data into a meter reading rate analysis model to enable the meter reading rate analysis model to extract feature data in the to-be-analyzed meter reading data, and then determining the meter reading rate of the to-be-analyzed meter reading data according to the number of the feature data; wherein the feature data comprises meter reading time, a meter reading equipment type, a geographic position where the meter reading equipment is located and a weather condition of the position where the meter reading equipment is located.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power metering, and in particular to a meter reading rate analysis method, device, equipment and medium of an automatic meter reading system. Background Art

[0002] In the public utilities such as electricity, water, and gas, meter reading is an important part of ensuring service charges. Traditional meter reading methods mainly rely on manual work, which is not only inefficient, but also may cause errors due to various factors. With the development of technology, automated meter reading systems are gradually being widely used.

[0003] In existing meter reading technologies, an automated system is usually used to collect and monitor data; however, the existing automated meter reading system usually directly obtains meter reading data without detecting whether the meter reading data is missing, and determines the meter reading rate based on the directly obtained meter reading data, resulting in the final meter reading rate being greater than the actual meter reading rate. Summary of the invention

[0004] The embodiments of the present invention provide a meter reading rate analysis method, device, equipment and medium for an automated meter reading system, which can improve the accuracy of meter reading rate analysis.

[0005] An embodiment of the present invention provides a meter reading rate analysis method of an automatic meter reading system, comprising:

[0006] Obtain meter reading data to be analyzed;

[0007] The meter reading data to be analyzed is input into a meter reading rate analysis model so that the meter reading rate analysis model extracts characteristic data from the meter reading data to be analyzed, and then determines the meter reading rate of the meter reading data to be analyzed according to the quantity of the characteristic data; wherein the characteristic data includes: meter reading time, meter reading device type, geographical location of the meter reading device, and weather conditions at the location of the meter reading device.

[0008] Furthermore, the meter reading rate analysis model is constructed in the following manner:

[0009] Acquire a training sample set; wherein the training sample set includes a number of meter reading data samples and corresponding sample meter reading rates; the sample meter reading rate corresponding to each meter reading data sample is determined according to the number of feature data in the meter reading data sample;

[0010] An initial decision tree model is constructed, and the initial decision tree model is trained with the training sample set until the initial decision tree model reaches a preset convergence condition, and a meter reading rate analysis model is generated; wherein, during the training process, the initial decision tree model extracts feature data of each meter reading data sample, and determines the meter reading rate according to the number of extracted feature data.

[0011] Furthermore, after obtaining the training sample set, the method further includes:

[0012] The training sample set is subjected to data preprocessing to obtain a preprocessed training sample set; wherein the data preprocessing includes: data cleaning, data standardization processing and data normalization processing.

[0013] Furthermore, after obtaining the training sample set, the method further includes:

[0014] The meter reading data samples in the training sample set are divided according to the meter reading time, the type of meter reading equipment, the geographical location of the meter reading equipment, and the weather conditions at the location of the meter reading equipment;

[0015] Determine the first relationship between the meter reading data sample and the meter reading rate in the time dimension;

[0016] Determine a second relationship between the meter reading data sample and the meter reading rate in the device dimension;

[0017] Determine the third relationship between the meter reading data sample and the meter reading rate in the location dimension;

[0018] Determine the fourth relationship between meter reading data samples and meter reading rate under the weather dimension;

[0019] The first relationship, the second relationship, the third relationship and the fourth relationship are added to the training sample set.

[0020] Furthermore, during the training process, the initial decision tree model extracts feature data of each meter reading data sample, and determines the meter reading rate according to the amount of the extracted feature data, including:

[0021] During the training process, the initial decision tree model extracts the quantity of feature data of each meter reading data sample, and determines the meter reading rate in combination with the first relationship, the second relationship, the third relationship and the fourth relationship.

[0022] Furthermore, after the meter reading rate analysis model is generated, the method further includes:

[0023] The relationship between each meter reading data sample, the first relationship, the second relationship, the third relationship, the fourth relationship and the meter reading rate is displayed in a visual chart; wherein the visual chart includes: a tree chart, a layered pie chart and a bar chart.

[0024] Based on the above method embodiment, the present invention provides a corresponding device embodiment;

[0025] An embodiment of the present invention provides a meter reading rate analysis device for an automated meter reading system, including: a data acquisition module and a meter reading rate analysis module;

[0026] The data acquisition module is used to acquire the meter reading data to be analyzed;

[0027] The meter reading rate analysis module is used to input the meter reading data to be analyzed into the meter reading rate analysis model, so that the meter reading rate analysis model extracts characteristic data from the meter reading data to be analyzed, and then determines the meter reading rate of the meter reading data to be analyzed through the characteristic data; wherein the characteristic data includes: meter reading time, meter reading device type, geographical location of the meter reading device, and weather conditions at the location of the meter reading device.

[0028] Furthermore, the meter reading rate analysis model is constructed in the following manner:

[0029] Acquire a training sample set; wherein the training sample set includes a number of meter reading data samples and corresponding sample meter reading rates; the sample meter reading rate corresponding to each meter reading data sample is determined according to the number of feature data in the meter reading data sample;

[0030] An initial decision tree model is constructed, and the initial decision tree model is trained with the training sample set until the initial decision tree model reaches a preset convergence condition, and a meter reading rate analysis model is generated; wherein, during the training process, the initial decision tree model extracts feature data of each meter reading data sample, and determines the meter reading rate according to the number of extracted feature data.

[0031] Another embodiment of the present invention provides a device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the meter reading rate analysis method of the automatic meter reading system described in the above embodiment of the invention is implemented.

[0032] Another embodiment of the present invention provides a medium, wherein the medium includes a stored computer program, wherein when the computer program is executed, the device where the medium is located is controlled to execute the meter reading rate analysis method of an automatic meter reading system described in the above embodiment of the invention.

[0033] The following beneficial effects are achieved by implementing the present invention:

[0034] The present invention provides a meter reading rate analysis method, device, equipment and medium of an automatic meter reading system. The meter reading rate analysis method obtains meter reading data to be analyzed, inputs the meter reading data to be analyzed into a meter reading rate analysis model, and enables the meter reading rate analysis model to extract characteristic data of meter reading time, meter reading device type, geographical location of the meter reading device and weather conditions at the location of the meter reading device in the meter reading data to be analyzed, and then analyzes the quantity of these characteristic data to determine the meter reading rate of the meter reading data to be analyzed; by analyzing factors such as meter reading time, meter reading device type, geographical location of the meter reading device and weather conditions at the location of the meter reading device, it is determined whether there is missing characteristic data in the meter reading data to be analyzed, and then the meter reading rate is determined according to the quantity of characteristic data, thereby improving the accuracy of meter reading rate analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 The present invention is a flowchart of a meter reading rate analysis method of an automatic meter reading system provided by an embodiment of the present invention.

[0036] Figure 2 The present invention is a schematic diagram of the structure of a meter reading rate analysis device of an automatic meter reading system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0040] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0041] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0042] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0043] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0044] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0045] like Figure 1 As shown, a meter reading rate analysis method of an automatic meter reading system provided by an embodiment of the present invention includes:

[0046] Step S1: Obtain meter reading data to be analyzed;

[0047] Step S2: inputting the meter reading data to be analyzed into a meter reading rate analysis model, so that the meter reading rate analysis model extracts characteristic data from the meter reading data to be analyzed, and then determines the meter reading rate of the meter reading data to be analyzed according to the quantity of the characteristic data; wherein the characteristic data includes: meter reading time, meter reading device type, geographical location of the meter reading device, and weather conditions at the location of the meter reading device.

[0048] For step S1, the meter reading data to be analyzed is obtained through the automated meter reading system, and the meter reading data includes but is not limited to the electric energy meter data, the water meter data and the gas meter data. For each set of meter reading data to be analyzed, it needs to include the meter reading time, the type of meter reading device, the geographical location of the meter reading device and the weather condition information of the location of the meter reading device. When any one of the data is missing, the meter reading data is still incomplete, and the meter reading rate corresponding to the meter reading data is determined according to the integrity of the meter reading data.

[0049] When using the automated meter reading system to obtain the meter reading data or meter reading data samples to be analyzed, it is necessary to select suitable meter reading equipment according to different meter reading requirements; for example, for electric energy meters, electronic multifunctional electric energy meters can be selected, which can measure parameters such as electric energy, voltage, current, and power; for water meters, smart water meters can be selected, which can measure the flow and cumulative flow of water; for gas meters, smart gas meters can be selected, which can measure the flow and cumulative flow of gas. After selecting a suitable meter reading equipment, connect the selected meter reading equipment to the automated meter reading system by wire or wireless means; for example, use wired means such as RS485 bus or CAN bus to connect, or use wireless means such as Bluetooth and ZigBee to connect. Configure the parameters of the meter reading equipment in the automated meter reading system, such as equipment address, measurement range, measurement unit, etc. According to the meter reading requirements, develop suitable meter reading system software, which needs to be able to communicate with the meter reading equipment, read the meter reading data, and save the meter reading data to a database or other storage medium. After the automatic meter reading system software is written, it is tested and debugged to ensure that the automatic meter reading system can work properly and accurately read the meter reading data. The meter reading system is installed in the actual environment, and necessary adjustments and modifications are made according to the actual situation. The meter reading system is regularly maintained and updated to ensure the stability and accuracy of the system. By deploying the above-mentioned automatic meter reading system, when the meter reading data is needed in the future, the required meter reading data can be obtained through the database or storage medium.

[0050] For step S2, the meter reading data to be analyzed is input into the meter reading rate analysis model, so that the meter reading rate analysis model extracts characteristic data such as meter reading time, meter reading device type, geographical location of the meter reading device, and weather conditions at the location of the meter reading device from the meter reading data to be analyzed, and determines the meter reading rate corresponding to the meter reading data to be analyzed based on the extracted characteristic data. It should be noted that for a group of meter reading data to be analyzed, when any characteristic data extracted lacks, the meter reading rate is less than 100%, and the meter reading rate is determined according to the number of characteristic data extracted from the meter reading data to be analyzed, and its interval is between 1-100%. When any one of the above characteristic data is missing, the meter reading rate is reduced by 25%. When the meter reading rate of the system is analyzed as a whole for multiple groups of meter reading data to be analyzed, if there is a missing characteristic data in any group of meter reading data to be analyzed, the meter reading data with missing data is regarded as failed meter reading data, and then the overall meter reading rate of the system is determined based on the successful meter reading data and the total meter reading data.

[0051] In a preferred embodiment, the meter reading rate analysis model is constructed in the following manner: a training sample set is obtained; wherein the training sample set includes a number of meter reading data samples and corresponding sample meter reading rates; the sample meter reading rate corresponding to each meter reading data sample is determined according to the number of feature data in the meter reading data sample; an initial decision tree model is constructed, and the initial decision tree model is trained with the training sample set until the initial decision tree model reaches a preset convergence condition, thereby generating a meter reading rate analysis model; wherein, during the training process, the initial decision tree model extracts feature data of each meter reading data sample, and determines the meter reading rate according to the number of extracted feature data.

[0052] In a preferred embodiment, after obtaining the training sample set, it also includes: performing data preprocessing on the training sample set to obtain a preprocessed training sample set; wherein the data preprocessing includes: data cleaning, data standardization processing and data normalization processing.

[0053] Specifically, after reacquiring the training sample set from the automated meter reading system, the acquired training sample set is cleaned to remove invalid and erroneous data; the dimensions of the data are standardized to make data of different dimensions comparable; the data are normalized to make the distribution of the data closer to the standard normal distribution, which is convenient for model training.

[0054] In a preferred embodiment, after obtaining the training sample set, it also includes: dividing the meter reading data samples in the training sample set according to the meter reading time, the type of meter reading equipment, the geographical location of the meter reading equipment, and the weather conditions at the location of the meter reading equipment; determining a first relationship between the meter reading data samples and the meter reading rate in the time dimension; determining a second relationship between the meter reading data samples and the meter reading rate in the equipment dimension; determining a third relationship between the meter reading data samples and the meter reading rate in the location dimension; determining a fourth relationship between the meter reading data samples and the meter reading rate in the weather dimension; and adding the first relationship, the second relationship, the third relationship, and the fourth relationship to the training sample set.

[0055] Specifically, the meter reading data samples in the preprocessed training sample set are divided according to the meter reading time, the type of meter reading equipment, the geographical location of the meter reading equipment, and the weather conditions at the location of the meter reading equipment to obtain meter reading data samples under the time dimension, meter reading data samples under the equipment dimension, meter reading data samples under the location dimension, and meter reading data samples under the weather dimension; then, a first relationship between the meter reading data samples and the meter reading rate under the time dimension is determined according to the meter reading data samples under the time dimension and the corresponding meter reading rate, a second relationship between the meter reading data samples and the meter reading rate under the equipment dimension is determined according to the meter reading data samples under the equipment dimension and the corresponding meter reading rate, a third relationship between the meter reading data samples and the meter reading rate under the location dimension is determined according to the meter reading data samples under the location dimension and the corresponding meter reading rate, and a fourth relationship between the meter reading data samples and the meter reading rate under the weather dimension is determined according to the meter reading data samples under the weather dimension and the corresponding meter reading rate. It can be understood that the first relationship, the second relationship, the third relationship and the fourth relationship respectively represent the mapping relationship between the meter reading data samples statistically analyzed under different dimensions and the meter reading rate under the corresponding dimension, that is, for a set of meter reading data to be analyzed, it can be determined whether the feature data under the corresponding mapping relationship is missing in the meter reading data to be analyzed according to the above-determined mapping relationship and the meter reading data to be analyzed. The first relationship, the second relationship, the third relationship and the fourth relationship are added to the training sample set, so that when the initial decision tree model is trained by the training sample set, the initial decision tree model can learn the above relationships, so as to more accurately analyze the impact of each relationship on the meter reading rate, and improve the comprehensiveness and accuracy of the model's test on whether there is missing after the feature data is extracted.

[0056] Preferably, the above relationship can be expressed by constructing a "star-relation-star" triple structure. Each meter reading data sample can be represented as a star, which contains multiple meter reading records, and each meter reading record contains information related to a meter reading; for example, a meter reading data sample contains at least three meter reading records, namely, meter reading time, meter reading device number, and electric energy meter reading data. By organizing the meter reading data into a star, all meter reading records can be unified into a framework, which is convenient for subsequent processing and analysis. The meter reading records under different meter reading sample data are related to each other through relationships such as time, equipment, location, and weather, and then different meter reading sample data can be analyzed under the time dimension, equipment dimension, location dimension, and weather dimension, and different meter reading sample data can be unified into each dimension for comparative analysis. For example, data from different devices at the same time can be compared with each other, and data from the same device at different times can also be compared with each other. These relationships can help users better understand the characteristics and laws of meter reading data, and they can be visualized and provided to users for viewing through the "star-relation-star" triple structure, which can provide support for subsequent data analysis.

[0057] It should be noted that the GBDT (Gradient Boosting Decision Tree) algorithm is an ensemble learning algorithm based on decision trees, which optimizes the performance of the model by continuously adding new decision trees to the existing model and using a gradient boosting strategy. GBDT gradually optimizes the objective function by fitting the residuals, thereby obtaining better performance than a single decision tree. The GBDT algorithm has many advantages, such as being able to process data with different dimensions, being able to process missing values, being able to perform online learning, etc. At the same time, the GBDT algorithm can also be used for classification and regression problems.

[0058] After completing the preparation of the training sample set and the construction of the initial decision tree model, the initial decision tree model is trained using the training sample set. During the training process, the model parameters such as the learning rate, the number of trees, the depth of the tree, etc. are continuously adjusted to optimize the model performance. At the same time, the generalization ability of the model is evaluated by cross-validation and other methods to avoid overfitting of the model. When the initial decision tree model reaches the preset convergence conditions, the meter reading rate analysis model is generated.

[0059] In a preferred embodiment, during the training process, the initial decision tree model extracts feature data of each meter reading data sample, and determines the meter reading rate based on the number of extracted feature data, including: during the training process, the initial decision tree model extracts the number of feature data of each meter reading data sample, and determines the meter reading rate in combination with the first relationship, the second relationship, the third relationship and the fourth relationship.

[0060] Specifically, during the initial decision tree model training process, the initial decision tree model extracts the meter reading time, meter reading device type, geographical location of the meter reading device, and weather conditions at the location of the meter reading device of each meter reading data sample, and determines whether the characteristic data such as meter reading time, meter reading device type, geographical location of the meter reading device, and weather conditions at the location of the meter reading device are missing under the first relationship, the second relationship, the third relationship, and the fourth relationship in combination with the first relationship, the second relationship, the third relationship, and the fourth relationship, and then determines the meter reading rate according to the quantity of these characteristic data.

[0061] In a preferred embodiment, after generating the meter reading rate analysis model, it also includes: displaying the relationship between each meter reading data sample, the first relationship, the second relationship, the third relationship, the fourth relationship and the meter reading rate in the form of a visual chart; wherein the visual chart includes: a tree diagram, a layered pie chart and a bar chart.

[0062] Specifically, the influence coefficient of each feature in each meter reading sample data on the meter reading rate can be determined according to the importance of each feature in the feature data output by the initial decision tree model; the coefficient reflects the contribution of each feature to the meter reading rate, that is, how much influence will be exerted on the meter reading rate if the feature is abnormal or missing. In the present invention, the influence coefficient of each feature data on the meter reading rate is the same. For example: in the meter reading sample data, the meter reading time, the type of meter reading device, the geographical location of the meter reading device, and the weather conditions at the location of the meter reading device should be included. If the weather conditions at the location of the meter reading device are missing at this time, the influence coefficient characterizing the weather conditions at the location of the meter reading device is 0. At this time, it can be determined that the meter reading sample data is abnormal, and the meter reading rate is 75%. Displaying the relationship between the meter reading sample data and the meter reading rate in the form of a visual chart can help users more intuitively understand the influencing factors and the degree of influence of the meter reading rate. Specifically, the hierarchical relationship between the various features in the meter reading data sample can be displayed in the form of a tree diagram or a layered pie chart. For a single meter reading data sample, its various characteristic data can be displayed in the form of a bar graph. For example, each column in the bar graph directly represents the meter reading time, the type of meter reading equipment, the geographical location of the meter reading equipment, and the weather conditions at the location of the meter reading equipment, so that the characteristic data of each record can be displayed intuitively.

[0063] Furthermore, for the meter reading sample data, it can be further analyzed by the method of Top-n key influencing factor analysis. Specifically, based on the above data visualization content, the selected Top-n features are visualized, and the selected Top-n features are subjected to correlation analysis to explore the correlation between these features and the meter reading rate. The degree of association between these features and the meter reading rate can be evaluated by calculating the correlation coefficient and other methods. Regression analysis is performed on the selected Top-n features to establish a regression model of the selected Top-n features and the meter reading rate. The goodness of fit and prediction accuracy of the regression model can be evaluated by linear regression, logistic regression and other methods. According to the results of the regression analysis, the regression model is explained and verified. Specifically, the contribution and mechanism of each selected feature to the meter reading rate can be explained, and the stability and generalization ability of the regression model can be verified by cross-validation and other methods.

[0064] Based on the above method embodiment, the present invention provides a corresponding device embodiment.

[0065] like Figure 2 As shown, an embodiment of the present invention provides a meter reading rate analysis device for an automated meter reading system, comprising: a data acquisition module and a meter reading rate analysis module;

[0066] The data acquisition module is used to acquire the meter reading data to be analyzed;

[0067] The meter reading rate analysis module is used to input the meter reading data to be analyzed into the meter reading rate analysis model, so that the meter reading rate analysis model extracts characteristic data from the meter reading data to be analyzed, and then determines the meter reading rate of the meter reading data to be analyzed according to the quantity of the characteristic data; wherein the characteristic data includes: meter reading time, meter reading device type, geographical location of the meter reading device, and weather conditions at the location of the meter reading device.

[0068] In a preferred embodiment, the meter reading rate analysis model is constructed in the following manner:

[0069] Acquire a training sample set; wherein the training sample set includes a number of meter reading data samples and corresponding sample meter reading rates; the sample meter reading rate corresponding to each meter reading data sample is determined according to the number of feature data in the meter reading data sample;

[0070] An initial decision tree model is constructed, and the initial decision tree model is trained with the training sample set until the initial decision tree model reaches a preset convergence condition, and a meter reading rate analysis model is generated; wherein, during the training process, the initial decision tree model extracts feature data of each meter reading data sample, and determines the meter reading rate according to the number of extracted feature data.

[0071] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0072] Those skilled in the art can clearly understand that for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0073] Based on the above method item embodiments, the present invention provides corresponding terminal device item embodiments.

[0074] An embodiment of the present invention provides a device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the meter reading rate analysis method of the automatic meter reading system described in any one of the present invention is implemented.

[0075] The device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The device may include, but is not limited to, a processor and a memory.

[0076] The processor may be a central processing unit (CPU), or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0077] The memory can be used to store the computer program, and the processor realizes various functions of the terminal device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Med i aCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0078] Based on the above method item embodiments, the present invention provides a corresponding storage medium item embodiment.

[0079] An embodiment of the present invention provides a storage medium, wherein the storage medium includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute a meter reading rate analysis method for an automatic meter reading system as described in any one of the present inventions.

[0080] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium.

[0081] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A meter reading rate analysis method for an automated meter reading system, characterized in that: include: Obtain meter reading data to be analyzed; The meter reading data to be analyzed is input into a meter reading rate analysis model so that the meter reading rate analysis model extracts characteristic data from the meter reading data to be analyzed, and then determines the meter reading rate of the meter reading data to be analyzed according to the quantity of the characteristic data; wherein the characteristic data includes: meter reading time, meter reading device type, geographical location of the meter reading device, and weather conditions at the location of the meter reading device.

2. The meter reading rate analysis method of the automatic meter reading system according to claim 1, characterized in that: The meter reading rate analysis model is constructed in the following way: Acquire a training sample set; wherein the training sample set includes a number of meter reading data samples and corresponding sample meter reading rates; the sample meter reading rate corresponding to each meter reading data sample is determined according to the number of feature data in the meter reading data sample; An initial decision tree model is constructed, and the initial decision tree model is trained with the training sample set until the initial decision tree model reaches a preset convergence condition, and a meter reading rate analysis model is generated; wherein, during the training process, the initial decision tree model extracts feature data of each meter reading data sample, and determines the meter reading rate according to the number of extracted feature data.

3. The meter reading rate analysis method of the automatic meter reading system according to claim 2, characterized in that: After obtaining the training sample set, it also includes: The training sample set is subjected to data preprocessing to obtain a preprocessed training sample set; wherein the data preprocessing includes: data cleaning, data standardization processing and data normalization processing.

4. The meter reading rate analysis method of the automatic meter reading system according to claim 3, characterized in that: After obtaining the training sample set, it also includes: The meter reading data samples in the training sample set are divided according to the meter reading time, the type of meter reading equipment, the geographical location of the meter reading equipment, and the weather conditions at the location of the meter reading equipment; Determine the first relationship between the meter reading data sample and the meter reading rate in the time dimension; Determine a second relationship between the meter reading data sample and the meter reading rate in the device dimension; Determine the third relationship between the meter reading data sample and the meter reading rate in the location dimension; Determine the fourth relationship between meter reading data samples and meter reading rate under the weather dimension; The first relationship, the second relationship, the third relationship and the fourth relationship are added to the training sample set.

5. The meter reading rate analysis method of the automatic meter reading system according to claim 4, characterized in that: During the training process, the initial decision tree model extracts feature data of each meter reading data sample, and determines the meter reading rate according to the number of extracted feature data, including: During the training process, the initial decision tree model extracts the quantity of feature data of each meter reading data sample, and determines the meter reading rate in combination with the first relationship, the second relationship, the third relationship and the fourth relationship.

6. The meter reading rate analysis method of the automatic meter reading system according to claim 5, characterized in that: After generating the meter reading rate analysis model, it also includes: The relationship between each meter reading data sample, the first relationship, the second relationship, the third relationship, the fourth relationship and the meter reading rate is displayed in a visual chart; wherein the visual chart includes: a tree chart, a layered pie chart and a bar chart.

7. A meter reading rate analysis device for an automated meter reading system, characterized in that: include: Data acquisition module and meter reading rate analysis module; The data acquisition module is used to acquire the meter reading data to be analyzed; The meter reading rate analysis module is used to input the meter reading data to be analyzed into the meter reading rate analysis model, so that the meter reading rate analysis model extracts the number of characteristic data in the meter reading data to be analyzed, and then determines the meter reading rate of the meter reading data to be analyzed through the characteristic data; wherein the characteristic data includes: meter reading time, meter reading device type, geographical location of the meter reading device, and weather conditions at the location of the meter reading device.

8. The meter reading rate analysis device of the automatic meter reading system according to claim 7, characterized in that: The meter reading rate analysis model is constructed in the following way: Acquire a training sample set; wherein the training sample set includes a number of meter reading data samples and corresponding sample meter reading rates; the sample meter reading rate corresponding to each meter reading data sample is determined according to the number of feature data in the meter reading data sample; An initial decision tree model is constructed, and the initial decision tree model is trained with the training sample set until the initial decision tree model reaches a preset convergence condition, and a meter reading rate analysis model is generated; wherein, during the training process, the initial decision tree model extracts feature data of each meter reading data sample, and determines the meter reading rate according to the number of extracted feature data.

9. A device, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the meter reading rate analysis method of the automatic meter reading system according to any one of claims 1 to 6 is implemented.

10. A medium, characterized in that The medium includes a stored computer program, wherein when the computer program is executed, the device where the medium is located is controlled to execute the meter reading rate analysis method for an automatic meter reading system according to any one of claims 1 to 6.

Images