Multi-source data operation status diagnosis and early warning method and device for power terminals

Abstract

This application discloses a multi-source data operating status diagnosis and early warning method and device for power terminals. The method and device include obtaining historical electricity usage information of multiple users collected by multiple smart meters; determining an electricity cost-performance index corresponding to each user's electricity usage behavior information based on the historical electricity usage information of the multiple users; filtering multiple target electricity usage behavior information from the multiple users' electricity usage behavior information based on each electricity cost-performance index; determining push electricity usage behavior information for each user based on the multiple target electricity usage behavior information; and pushing the push electricity usage behavior information for each user to each user. This application can improve the accuracy of multi-source data operating status diagnosis and early warning for power terminals.

Description

Technical Field

[0001] The present application relates to the technical field of smart meters, and in particular to a method and device for diagnosing and warning the operating status of multi-source data for power terminals. Background Art

[0002] Smart meters are intelligent terminals in smart grids. In addition to the basic electricity consumption metering functions of traditional energy meters, they also offer intelligent features such as bidirectional multi-rate metering, user-side control, two-way data communication with multiple data transmission modes, and power theft prevention to adapt to smart grids and renewable energy applications. Smart meters represent the future direction of intelligent terminals for energy-saving smart grid end users. Existing technologies fail to utilize the multi-source data collected by power terminals, resulting in low accuracy in operating status diagnosis and early warning for these terminals.

[0003] That is, the existing technology has low accuracy in diagnosing and warning the operating status of multi-source data for power terminals. Summary of the Invention

[0004] The embodiments of the present application provide a method and device for multi-source data operation status diagnosis and early warning for power terminals, which can use the historical electricity consumption information and electricity cost-effectiveness indicators of multiple users collected by the power terminal to accurately push electricity consumption behavior information with better electricity cost-effectiveness indicators to users, thereby improving the accuracy of multi-source data operation status diagnosis and early warning for power terminals.

[0005] In the first aspect, the present application provides a multi-source data operation status diagnosis and early warning method for power terminals, including:

[0006] Obtain historical electricity usage information of multiple users collected by multiple smart meters;

[0007] Determine the electricity cost performance index corresponding to each user's electricity usage behavior information based on the historical electricity usage information of multiple users;

[0008] Filtering multiple target electricity usage behavior information from the electricity usage behavior information of multiple users based on various electricity cost performance indicators;

[0009] Determining the push electricity usage behavior information of each user based on multiple target electricity usage behavior information;

[0010] Push each user's electricity usage behavior information to each user.

[0011] In an optional embodiment, historical electricity usage information includes the user's total electricity costs, total electricity consumption, and usage time periods of various electrical appliances. The electricity usage behavior information includes the user's frequent usage time periods of various electrical appliances. The electricity cost-effectiveness index is the ratio of total electricity costs to total electricity consumption.

[0012] In an optional embodiment, determining the pushed electricity usage behavior information of each user based on multiple target electricity usage behavior information includes:

[0013] Clustering multiple users based on their electricity usage behavior information to obtain multiple user clusters;

[0014] Determine a preset number of electricity usage behavior information items ranked top in descending order of electricity cost performance in the user cluster as a preset number of target electricity usage behavior information items, and obtain multiple target electricity usage behavior information items corresponding to the user cluster clusters;

[0015] The method of determining the pushed electricity usage behavior information of each user based on the plurality of target electricity usage behavior information includes:

[0016] A target electricity usage behavior information is selected from a plurality of target electricity usage behavior information corresponding to the user cluster to which the user belongs as the pushed electricity usage behavior information of the user.

[0017] In an optional embodiment, selecting a target electricity usage behavior information from a plurality of target electricity usage behavior information corresponding to the user cluster to which the user belongs as the pushed electricity usage behavior information of the user includes:

[0018] Allocating target electricity usage behavior information to each user multiple times to obtain multiple electricity usage behavior allocation information after multiple allocations, wherein the electricity usage behavior allocation information includes a target electricity usage behavior information allocated to each user in a single allocation, and each electricity usage behavior allocation information is different.

[0019] Determine a regional power average value of power consumption in a power consumption area over multiple preset periods based on the power consumption behavior distribution information and the power consumption area to which each user belongs;

[0020] Calculating the power capacity ratio of the regional power average value of the power consumption area and the transformer capacity of the power consumption area, and obtaining the ratio variance of the power capacity ratios of multiple power consumption areas;

[0021] determining an allocation evaluation parameter for the electricity consumption behavior allocation information based on the ratio variance, wherein the larger the ratio variance, the smaller the allocation evaluation parameter;

[0022] Determine the electricity consumption behavior allocation information with the largest allocation evaluation parameter as the target allocation information;

[0023] The target electricity usage behavior information corresponding to each user in the target allocation information is used as the user's pushed electricity usage behavior information.

[0024] In an optional embodiment, determining the distribution evaluation parameter of the electricity usage behavior distribution information based on the ratio variance includes:

[0025] Determine the regional power variation coefficient of the power consumption of the power consumption area in multiple preset periods based on the power consumption behavior distribution information and the power consumption area to which each user belongs;

[0026] Performing a weighted average of the regional power variation coefficients of the multiple power consumption areas based on the number of users in the multiple power consumption areas to obtain a weighted average of the variation coefficients;

[0027] The distribution evaluation parameter of the electricity consumption behavior distribution information is determined based on the ratio variance and the weighted average value of the variation coefficient, wherein the larger the ratio variance, the smaller the distribution evaluation parameter, and the larger the weighted average value of the variation coefficient, the smaller the distribution evaluation parameter.

[0028] In an optional embodiment, obtaining electricity usage behavior information of multiple users collected by multiple smart meters includes:

[0029] The usage time of various electrical appliances is collected through the built-in electricity meters of various electrical appliances or the smart sockets of various electrical appliances.

[0030] In the second aspect, the multi-source data operation status diagnosis and early warning device for power terminals provided by this application includes:

[0031] A first acquisition module is used to acquire historical electricity usage information of multiple users collected by multiple smart meters;

[0032] A first determining module is configured to determine an electricity cost performance index corresponding to each user's electricity usage behavior information based on historical electricity usage information of multiple users;

[0033] A screening module, configured to screen out a plurality of target electricity usage behavior information from the electricity usage behavior information of a plurality of users based on various electricity cost performance indicators;

[0034] A second determining module is configured to determine the pushed electricity usage behavior information of each user based on the plurality of target electricity usage behavior information;

[0035] The push module is used to push the power usage behavior information of each user to each user.

[0036] In an optional embodiment, historical electricity usage information includes the user's total electricity costs, total electricity consumption, and usage time periods of various electrical appliances. The electricity usage behavior information includes the user's frequent usage time periods of various electrical appliances. The electricity cost-effectiveness index is the ratio of total electricity costs to total electricity consumption.

[0037] In an optional embodiment, determining the pushed electricity usage behavior information of each user based on multiple target electricity usage behavior information includes:

[0038] Clustering multiple users based on their electricity usage behavior information to obtain multiple user clusters;

[0039] Determine a preset number of electricity usage behavior information items ranked top in descending order of electricity cost performance in the user cluster as a preset number of target electricity usage behavior information items, and obtain multiple target electricity usage behavior information items corresponding to the user cluster clusters;

[0040] The method of determining the pushed electricity usage behavior information of each user based on the plurality of target electricity usage behavior information includes:

[0041] A target electricity usage behavior information is selected from a plurality of target electricity usage behavior information corresponding to the user cluster to which the user belongs as the pushed electricity usage behavior information of the user.

[0042] In an optional embodiment, selecting a target electricity usage behavior information from a plurality of target electricity usage behavior information corresponding to the user cluster to which the user belongs as the pushed electricity usage behavior information of the user includes:

[0043] Allocating target electricity usage behavior information to each user multiple times to obtain multiple electricity usage behavior allocation information after multiple allocations, wherein the electricity usage behavior allocation information includes a target electricity usage behavior information allocated to each user in a single allocation, and each electricity usage behavior allocation information is different.

[0044] Determine a regional power average value of power consumption in a power consumption area over multiple preset periods based on the power consumption behavior distribution information and the power consumption area to which each user belongs;

[0045] Calculating the power capacity ratio of the regional power average value of the power consumption area and the transformer capacity of the power consumption area, and obtaining the ratio variance of the power capacity ratios of multiple power consumption areas;

[0046] determining an allocation evaluation parameter for the electricity consumption behavior allocation information based on the ratio variance, wherein the larger the ratio variance, the smaller the allocation evaluation parameter;

[0047] Determine the electricity consumption behavior allocation information with the largest allocation evaluation parameter as the target allocation information;

[0048] The target electricity usage behavior information corresponding to each user in the target allocation information is used as the user's pushed electricity usage behavior information.

[0049] In an optional embodiment, determining the distribution evaluation parameter of the electricity usage behavior distribution information based on the ratio variance includes:

[0050] Determine the regional power variation coefficient of the power consumption of the power consumption area in multiple preset periods based on the power consumption behavior distribution information and the power consumption area to which each user belongs;

[0051] Performing a weighted average of the regional power variation coefficients of the multiple power consumption areas based on the number of users in the multiple power consumption areas to obtain a weighted average of the variation coefficients;

[0052] The distribution evaluation parameter of the electricity consumption behavior distribution information is determined based on the ratio variance and the weighted average value of the variation coefficient, wherein the larger the ratio variance, the smaller the distribution evaluation parameter, and the larger the weighted average value of the variation coefficient, the smaller the distribution evaluation parameter.

[0053] In an optional embodiment, obtaining electricity usage behavior information of multiple users collected by multiple smart meters includes:

[0054] The usage time of various electrical appliances is collected through the built-in electricity meters of various electrical appliances or the smart sockets of various electrical appliances.

[0055] On the third aspect, the electronic device provided in this application includes a memory and a processor, the memory stores a computer program, and the processor is used to run the computer program in the memory to implement the steps in the multi-source data operation status diagnosis and early warning method for power terminals provided in this application.

[0056] Fourthly, the computer-readable storage medium provided in the present application stores a plurality of instructions, which are suitable for loading by a processor to implement the steps in the multi-source data operation status diagnosis and early warning method for power terminals provided in the present application.

[0057] In the fifth aspect, the computer program product provided in the present application includes a computer program or instructions, which, when executed by a processor, implements the steps in the multi-source data operation status diagnosis and early warning method for power terminals provided in the present application.

[0058] In this application, compared with related technologies, historical electricity usage information of multiple users collected by multiple smart meters is obtained; based on the historical electricity usage information of multiple users, the electricity cost performance index corresponding to the electricity usage behavior information of each user is determined; based on each electricity cost performance index, multiple target electricity usage behavior information is screened out from the electricity usage behavior information of multiple users; based on the multiple target electricity usage behavior information, the pushed electricity usage behavior information of each user is determined; and the pushed electricity usage behavior information of each user is pushed to each user. This application can use the historical electricity usage information and electricity cost performance index of multiple users collected by the power terminal to accurately push electricity usage behavior information with better electricity cost performance index to users, thereby improving the accuracy of multi-source data operation status diagnosis and early warning for the power terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0060] Figure 1This is a schematic diagram of a scenario of a multi-source data operation status diagnosis and early warning system for power terminals provided by an embodiment of the present application;

[0061] Figure 2 This is a flow chart of an embodiment of a multi-source data operation status diagnosis and early warning method for a power terminal provided by an embodiment of the present application;

[0062] Figure 3 This is a structural diagram of an embodiment of a multi-source data operation status diagnosis and early warning device for power terminals provided by an embodiment of the present application;

[0063] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0064] It should be noted that the principles of this application are illustrated by implementing them in an appropriate computing environment. The following description is based on the illustrated specific embodiments of this application and should not be considered as limiting other specific embodiments not described in detail herein.

[0065] In the following description of this application, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.

[0066] In the following description of this application, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0067] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0068] In order to improve the effectiveness of multi-source data operating status diagnosis and early warning for power terminals, embodiments of the present application provide a multi-source data operating status diagnosis and early warning method for power terminals, a multi-source data operating status diagnosis and early warning device for power terminals, an electronic device, a computer-readable storage medium, and a computer program product. The multi-source data operating status diagnosis and early warning method for power terminals can be executed by the multi-source data operating status diagnosis and early warning device for power terminals, or by an electronic device that integrates the multi-source data operating status diagnosis and early warning device for power terminals.

[0069] 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 those skilled in the art without making creative efforts are within the scope of protection of this application.

[0070] Please refer to Figure 1 ,This application also provides a multi-source data operation status diagnosis and early warning system for power terminals, such as Figure 1 As shown, the multi-source data operation status diagnosis and early warning system for power terminals includes an electronic device. The electronic device is integrated with the multi-source data operation status diagnosis and early warning device for power terminals provided by the present application.

[0071] Among them, electronic devices can be any devices equipped with a processor and have processing capabilities, such as mobile electronic devices with processors such as smartphones, tablets, PDAs, laptops, smart speakers, or fixed electronic devices with processors such as desktop computers, televisions, servers, and industrial equipment.

[0072] In addition, if Figure 1 As shown, the multi-source data operation status diagnosis and early warning system for power terminals may also include a memory for storing original data, intermediate data and result data in the audio processing process.

[0073] In the embodiments of the present application, the memory may be a cloud memory. Cloud storage is a new concept extended and developed from the concept of cloud computing. A distributed cloud storage system (hereinafter referred to as the storage system) refers to a storage system that uses cluster applications, grid technology, and distributed storage file systems to bring together a large number of different types of storage devices (storage devices are also called storage nodes) in the network through application software or application interfaces to work together and provide external data storage and business access functions.

[0074] Currently, storage systems utilize a storage method that creates logical volumes. During the creation of a logical volume, physical storage space is allocated for each logical volume. This physical storage space may consist of disks on a specific storage device or several storage devices. When a client stores data on a logical volume, it stores the data on a file system. The file system divides the data into multiple parts, each of which is an object. An object contains not only the data but also additional information such as the data identifier (ID entity). The file system writes each object to the physical storage space of the logical volume and records the storage location of each object. Therefore, when a client requests access to data, the file system can provide access based on the storage location information of each object.

[0075] The storage system allocates physical storage space to logical volumes by pre-dividing the physical storage space into stripes based on the estimated capacity of the objects to be stored in the logical volume (this estimate often has a large margin relative to the actual capacity of the objects to be stored) and the Redundant Array of Independent Disks (RAID) groupings. A logical volume can be understood as a stripe, thereby allocating physical storage space to the logical volume.

[0076] It should be noted that Figure 1 The scenario diagram of the multi-source data operation status diagnosis and early warning system for power terminals shown is only an example. The multi-source data operation status diagnosis and early warning system for power terminals and the scenario described in the embodiment of the present application are for the purpose of more clearly illustrating the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided by the embodiment of the present application. Ordinary technicians in this field can know that with the evolution of the multi-source data operation status diagnosis and early warning system for power terminals and the emergence of new business scenarios, the technical solution provided by the embodiment of the present application is also applicable to similar technical problems.

[0077] It should be noted that the serial numbers of the following embodiments are not intended to limit the preferred order of the embodiments.

[0078] Please refer to Figure 2 , Figure 2 This is a flow chart of an embodiment of the multi-source data operation status diagnosis and early warning method for power terminals provided by the embodiment of the present application, such as Figure 2 As shown, the process of the multi-source data operation status diagnosis and early warning method for power terminals provided by this application is as follows:

[0079] 201. Obtain historical electricity usage information of multiple users collected by multiple smart meters.

[0080] Smart meters are intelligent terminals of smart grids. In addition to the basic electricity consumption metering function of traditional electricity meters, in order to adapt to the use of smart grids and new energy, they also have intelligent functions such as two-way multi-rate metering, user-side control, two-way data communication in multiple data transmission modes, and anti-electricity theft. Smart meters represent the development direction of intelligent terminals for end users of future energy-saving smart grids.

[0081] In an embodiment of the present application, historical electricity usage information of multiple users collected by multiple smart meters within a target time period is obtained. The target time period can be half a month or a month. Each user corresponds to a smart meter.

[0082] In the embodiment of the present application, the multiple users may be users in one city.

[0083] In the embodiment of the present application, the historical electricity usage information includes the user's total electricity cost, total electricity consumption, total electricity usage time, and the usage time periods of various electrical appliances.

[0084] Specifically, the usage time of each appliance is collected through the built-in electricity meter of each appliance or the smart socket of each appliance. For example, user A uses appliance B from 9:00 to 10:00.

[0085] 202. Determine an electricity cost performance index corresponding to each user's electricity usage behavior information based on historical electricity usage information of multiple users.

[0086] In the embodiment of the present application, the electricity usage behavior information includes the time periods when the user uses various electrical appliances. The electricity cost performance index is the ratio of the total electricity cost to the total electricity consumption.

[0087] Specifically, the electricity usage behavior information includes the time periods when users frequently use various electrical appliances.

[0088] Specifically, the user's daily usage time periods for each type of electrical appliance are obtained from the user's historical electricity usage information. Based on the duration and center time of each usage time period, the user's usage time periods for the target type of electrical appliance over multiple days are clustered to obtain at least one time period cluster for the user. The center time period of each time period cluster is determined as the frequently used time period for the user's use of the target type of electrical appliance, thereby obtaining the frequently used time periods for the user's use of each type of electrical appliance.

[0089] 203. Filter out a plurality of target electricity usage behavior information from the electricity usage behavior information of a plurality of users based on the respective electricity cost performance indicators.

[0090] In a specific embodiment, a preset number of electricity usage behavior information items that are ranked highest in order of electricity cost performance are determined as a plurality of target electricity usage behavior information items.

[0091] In another specific embodiment, a plurality of target electricity usage behavior information is screened out from the electricity usage behavior information of a plurality of users based on various electricity cost performance indicators, including:

[0092] (1) Cluster multiple users based on their electricity usage behavior information to obtain multiple user clusters.

[0093] In an embodiment of the present application, the electricity usage behavior information of multiple users is randomly divided into Q electricity usage information sets. The Q electricity usage information sets are clustered respectively, and each electricity usage information set is clustered into N second information clusters. Specifically, the Q electricity usage information sets are clustered respectively by the K-means algorithm, and each electricity usage information set is clustered into N second information. Each second information cluster is determined as a target information cluster, and the information cluster similarity between the target information cluster and the second information clusters in the Q electricity usage information sets is calculated respectively. The second information clusters with the greatest information cluster similarity with the target information cluster in each electricity usage information set are merged to obtain the first information cluster corresponding to the target information cluster, the first information cluster corresponding to each second information cluster is obtained, and N first information clusters corresponding to N second information clusters are obtained. The users corresponding to each electricity usage behavior information of the first information cluster are determined as a user cluster cluster, and N user cluster clusters corresponding to N first information clusters are obtained.

[0094] (2) A preset number of electricity consumption behavior information items ranked top in descending order of electricity cost performance in the user clusters are determined as a preset number of target electricity consumption behavior information items, and a plurality of target electricity consumption behavior information items corresponding to the user clusters are obtained.

[0095] Specifically, a preset number of target electricity usage behavior information is determined for each user cluster to obtain a plurality of target electricity usage behavior information corresponding to the user cluster.

[0096] In another specific embodiment, it is determined whether the user's smart meter is an old meter, and a preset number of electricity usage behavior information of users whose smart meters are not old meters in the user cluster are ranked from large to small in terms of electricity cost performance and are determined as multiple target electricity usage behavior information.

[0097] In another specific embodiment, it is determined whether the user's smart meter is an old meter, and a preset number of electricity usage behavior information of users whose smart meters are not old meters and whose electricity cost performance is ranked from large to small are determined as multiple target electricity usage behavior information.

[0098] In the embodiment of the present application, determining whether the user's smart meter is an old meter includes:

[0099] (1) The target error upper limit value of the smart meter is determined based on the device model of the smart meter. Different device models correspond to different target error upper limits.

[0100] In this embodiment of the present application, a mapping relationship between a preset device model and a target upper error limit is obtained, a rated upper error limit of the smart meter is determined based on the mapping relationship, and a target upper error limit of the smart meter is determined based on the rated upper error limit of the smart meter. For example, the rated upper error limit of device model A is 0.1%, and the rated upper error limit of device model B is 0.15%.

[0101] In a specific embodiment, the rated upper error limit value of the smart meter is determined as the target upper error limit value of the smart meter.

[0102] In another specific embodiment, the average ambient temperature, humidity, and current values ​​of the smart meter over a preset historical period are obtained. A temperature difference, humidity difference, and current difference are determined based on these values ​​and the smart meter's standard operating temperature, standard operating humidity, and standard current. An error weighting coefficient for the smart meter is then determined based on these temperature, humidity, and current differences. The rated upper error limit is weighted based on the error weighting coefficient to obtain a target upper error limit for the smart meter. The larger the temperature difference, the larger the weighting coefficient; the larger the humidity difference, the larger the weighting coefficient; and the larger the current difference, the larger the weighting coefficient. When the ambient temperature, humidity, and operating current deviate significantly from the standard, the error increases. This is a natural phenomenon, and the upper error limit needs to be increased to prevent a normally functioning smart meter from being classified as an obsolete device.

[0103] (2) Smart meters with reading error parameters higher than the target error upper limit are identified as old devices.

[0104] In a specific embodiment, the reading error parameter of the smart meter is obtained through manual measurement.

[0105] In another specific embodiment, a sequence of electricity usage readings from a master meter device in a power consumption area where the smart meter is located and a sequence of electricity usage readings from each smart meter in the power consumption area are obtained. The power consumption area may be a building and include multiple smart meters. An independent power consumption period of the smart meter is obtained. During the independent power consumption period, the ratio of the smart meter's electricity usage reading to the master meter device's electricity usage reading is greater than a preset electricity usage ratio, where the preset electricity usage ratio is 95% or 99%, which can be set according to specific circumstances. Once the independent power consumption period of the smart meter is obtained, the sum of the electricity usage readings of all smart meters in the power consumption area, excluding the smart meter, within the independent power consumption period is obtained. The difference between the master meter device's electricity usage reading and the sum of the electricity usage readings is determined as the actual electricity usage of the smart meter, the difference between the smart meter's electricity usage reading and its actual electricity usage is determined as an error difference, and the ratio of the error difference to the smart meter's electricity usage reading is determined as a reading error parameter for the smart meter. For example, during an independent electricity consumption period, the total meter reading is 1 kWh. The total meter is a calibrated meter used by the utility company, so the error is negligible. Therefore, the total meter reading is the actual electricity consumption. The smart meter reading is 0.95 kWh. Due to the error, the actual electricity consumption is 0.94 kWh. The total electricity consumption readings of the other smart meters is 0.06 kWh. Since this is very small compared to 0.95 kWh, the error is negligible. Therefore, the total actual electricity consumption of the other smart meters is 0.06 kWh. The difference between the total meter reading and the total reading can be determined as the actual electricity consumption of the smart meter, that is, 0.94 kWh.

[0106] Furthermore, there may be a situation where the smart meter does not have an independent power consumption period. In another specific embodiment, the power consumption reading sequence of the main meter device in the power consumption area where the smart meter is located and the power consumption reading sequence of each smart meter in the power consumption area are obtained. The power consumption area can be a building, and the power consumption area includes multiple smart meters. When the independent power consumption period of the smart meter is not obtained, the other smart meters except the smart meter are respectively determined as target devices, and the total power consumption readings of the other smart meters in the power consumption area except the target device during the independent power consumption period are obtained. The difference between the power consumption reading of the main meter device and the total power consumption readings is determined as the actual power consumption of the target device, the difference between the power consumption reading of the target device and the actual power consumption of the target device is determined as the error difference, and the ratio of the error difference to the power consumption reading of the target device is determined as the reading error parameter of the target device. After obtaining the reading error parameters of each target device, obtain the power consumption reading of the total meter device within the target period, obtain the power consumption reading of each target device within the target period, determine the actual power consumption of each target device within the target period based on the reading error parameters of each target device, add them up to obtain the total actual power consumption, determine the difference between the power consumption reading of the total meter device within the target period and the total actual power consumption as the actual power consumption of the smart meter, determine the difference between the power consumption reading of the smart meter and the actual power consumption of the smart meter as the error difference, and determine the ratio of the error difference to the power consumption reading of the smart meter as the reading error parameter of the smart meter.

[0107] Smart meters with reading error parameters higher than the target error upper limit are determined to be old devices.

[0108] 204. Determine the pushed electricity usage behavior information of each user based on the multiple target electricity usage behavior information.

[0109] In the embodiment of the present application, a target electricity usage behavior information is selected from a plurality of target electricity usage behavior information corresponding to the user cluster to which the user belongs as the pushed electricity usage behavior information of the user.

[0110] In the embodiment of the present application, selecting a target electricity usage behavior information from a plurality of target electricity usage behavior information corresponding to the user cluster to which the user belongs as the user's pushed electricity usage behavior information includes:

[0111] (1) Allocating target electricity usage behavior information to each user multiple times to obtain multiple electricity usage behavior allocation information after multiple allocations, wherein the electricity usage behavior allocation information includes a target electricity usage behavior information allocated to each user in a single allocation, and each electricity usage behavior allocation information is different.

[0112] In a specific embodiment, multiple exhaustive electricity usage behavior allocation information are obtained by traversing and enumerating, and the multiple exhaustive electricity usage behavior allocation information are determined as multiple electricity usage behavior allocation information after multiple allocations.

[0113] In another specific embodiment, target electricity usage behavior information is allocated to each user multiple times to obtain multiple electricity usage behavior allocation information after multiple allocations, including:

[0114] Step 1-1, obtain multiple exhaustive electricity usage behavior allocation information by traversing exhaustively.

[0115] The exhaustive electricity usage behavior allocation information includes a target electricity usage behavior information allocated to each user in a single allocation, and each electricity usage behavior allocation information is different.

[0116] Step 1-2: Calculate the information similarity between one target electricity usage behavior information and other target electricity usage behavior information in the exhaustive electricity usage allocation information to obtain multiple information similarities corresponding to the target electricity usage behavior information.

[0117] In a specific embodiment, the target electricity usage behavior information is converted into a vector, and the cosine similarity between the vectors of two target electricity usage behavior information is determined as the information similarity.

[0118] Step 1-3: sort the multiple information similarities corresponding to the target electricity usage behavior information from large to small and calculate the similarity difference between any two adjacent information similarities after sorting to obtain multiple similarity differences corresponding to the target electricity usage behavior information.

[0119] Step 1-4: determining the coefficient of variation of multiple similarity differences corresponding to the target electricity usage behavior information as the uniform quantized value of the target electricity usage behavior information, and obtaining a quantitative average of the uniform quantized values ​​of the multiple target electricity usage behavior information.

[0120] Coefficient of Variation (CV): When comparing the degree of dispersion between two sets of data, if the measurement scales differ significantly or the data dimensions differ, directly using the standard deviation is inappropriate. Instead, the influence of the measurement scale and dimension should be eliminated. The CV can do this. It is the ratio of the standard deviation of the raw data to the mean of the raw data. CV is dimensionless, allowing for objective comparisons. In fact, the CV, like the range, standard deviation, and variance, can be considered an absolute value reflecting the degree of dispersion of the data. Its size is affected not only by the dispersion of the variable values ​​but also by the average level of the variable values.

[0121] Step 1-5, determining the information feature uniformity of the exhaustive power distribution information by taking the quantized average value of the uniformity quantized values ​​of multiple target power consumption behavior information in the exhaustive power distribution information, and obtaining the information feature uniformity of multiple exhaustive power distribution information, wherein the higher the quantized average value, the smaller the information distribution uniformity.

[0122] A smaller coefficient of variation indicates a more uniform difference in the similarity between target electricity usage behavior information. This means the characteristics of each target electricity usage behavior information vary evenly. In this case, lower quantization values ​​for uniformity and lower average values ​​indicate a higher degree of information distribution uniformity. This means that higher information distribution uniformity indicates a more uniform variation in characteristics between target electricity usage behavior information, effectively covering a wide range of electricity usage scenarios and improving distribution accuracy.

[0123] For example, consider four target electricity usage information sets. For one of these sets, the information similarities corresponding to three sets are 0.5, 0.6, and 0.7, respectively, and the similarity differences are 0.1 and 0.1. The coefficient of variation for these similarity differences is 0. A smaller coefficient of variation indicates a lower uniformity quantization value, a lower quantization average, and a higher uniformity of information distribution. This indicates that the information similarity differences between the target electricity usage information sets are relatively uniform, and the characteristics of each set vary evenly.

[0124] Step 1-5: Determine multiple exhaustive electricity usage allocation information with information feature uniformity higher than a preset uniformity value as multiple electricity usage behavior allocation information after multiple allocations.

[0125] The preset uniformity value may be set according to specific circumstances. For example, the preset uniformity value may be the median of uniformities of multiple information features of multiple exhaustive electricity consumption distribution information.

[0126] (2) Based on the electricity consumption behavior distribution information and the electricity consumption area to which each user belongs, determine the regional power average value of the electricity consumption power in the electricity consumption area in multiple preset periods.

[0127] The power consumption area to which the user belongs may be the cell where the user is located. The preset period may be 1 second or 10 seconds, etc., and may be set according to specific circumstances. The power consumption of the power consumption area during the preset period is the total power consumption of all users in the power consumption area during the preset period.

[0128] (3) Calculate the power capacity ratio of the regional power average value of the power consumption area and the transformer capacity of the power consumption area, and obtain the ratio variance of the power capacity ratios of multiple power consumption areas.

[0129] Transformer capacity refers to the maximum apparent power a transformer can transmit under rated operating conditions, typically measured in kilovolt-amperes (kVA) or megavolt-amperes (MVA). Selecting transformer capacity is a comprehensive and integrated technical consideration, requiring consideration of factors such as load type and characteristics, load factor, demand factor, power factor, transformer active and reactive losses, electricity prices, capital investment (including transformer price), service life, transformer depreciation, maintenance costs, and future plans.

[0130] Because different power consumption areas have different transformer capacities, analysis needs to be tailored to the characteristics of each power consumption area. Therefore, the variance of the power capacity ratios across multiple power consumption areas indicates that the power capacity ratios across the areas are consistent, indicating that the distribution of power consumption areas meets the characteristics of the areas.

[0131] (4) Determine the allocation evaluation parameter of the electricity consumption behavior allocation information based on the ratio variance, where the larger the ratio variance, the smaller the allocation evaluation parameter.

[0132] In a specific embodiment, the ratio variance is determined as the allocation evaluation parameter of the electricity usage behavior allocation information.

[0133] (5) The electricity consumption behavior allocation information with the largest allocation evaluation parameter is determined as the target allocation information.

[0134] (6) The target electricity usage behavior information corresponding to each user in the target allocation information is used as the user's pushed electricity usage behavior information.

[0135] Since the target allocation information includes the target electricity usage behavior information of each user, the target electricity usage behavior information corresponding to each user is used as the pushed electricity usage behavior information of the user.

[0136] In the embodiment of the present application, the method of determining the distribution evaluation parameters of the electricity usage behavior distribution information based on the ratio variance includes:

[0137] (1) Based on the electricity consumption behavior distribution information and the electricity consumption area to which each user belongs, the regional power variation coefficient of the electricity consumption in the electricity consumption area in multiple preset periods is determined.

[0138] (2) Based on the number of users in multiple power consumption areas, the regional power variation coefficients of multiple power consumption areas are weighted averaged to obtain the weighted average value of the variation coefficients.

[0139] Specifically, the regional weights of the plurality of power consumption areas are determined based on the number of users in the plurality of power consumption areas, wherein the greater the number of users in the power consumption area, the greater the regional weight of the power consumption area.

[0140] The regional power variation coefficients of the multiple power consumption areas are weighted averaged based on the regional weights of the multiple power consumption areas to obtain a weighted average value of the variation coefficients.

[0141] (3) The distribution evaluation parameter of the electricity consumption behavior distribution information is determined based on the ratio variance and the weighted average value of the coefficient of variation. The larger the ratio variance, the smaller the distribution evaluation parameter, and the larger the weighted average value of the coefficient of variation, the smaller the distribution evaluation parameter.

[0142] In an embodiment of the present application, a distribution evaluation parameter of the electricity consumption behavior distribution information is obtained by weighted averaging the ratio variance and the weighted average of the coefficient of variation based on a preset weight coefficient, wherein the larger the ratio variance, the smaller the distribution evaluation parameter, and the larger the weighted average of the coefficient of variation, the smaller the distribution evaluation parameter.

[0143] Among them, the weight coefficients of the ratio variance and the weighted average of the coefficient of variation can be set according to specific circumstances.

[0144] Furthermore, the historical electricity usage information includes voltage fluctuation information, current variation information, meter operating hours, frequency variation information, and harmonic content. A predicted lifespan of a first smart meter is determined based on the historical electricity usage information, and a predicted lifespan of a target smart meter is determined based on the first predicted lifespan. Specifically, the historical electricity usage information is input into a support vector machine to obtain a predicted lifespan of the first smart meter.

[0145] Furthermore, a thermodynamic temperature measured by the smart meter under operating conditions is obtained, and a second predicted meter lifespan is determined based on the thermodynamic temperature under normal operation and the thermodynamic temperature under operating conditions. A target predicted meter lifespan is determined based on the first predicted meter lifespan and the second predicted meter lifespan. Specifically, the target predicted meter lifespan is determined by taking the average of the first predicted meter lifespan and the second predicted meter lifespan. The thermodynamic temperature measured by the smart meter under operating conditions is the highest temperature of the smart meter under operating conditions.

[0146] The calculation formula for the predicted life of the target meter is as follows:

[0147] ,

[0148] in, represents the target meter predicted life of the smart meter, j represents the Boltzmann parameter, Indicates the energy required to activate the meter. Indicates the thermodynamic temperature of the smart meter under normal operating conditions. Indicates the thermodynamic temperature under operating conditions.

[0149] The distribution evaluation parameters of the electricity consumption behavior distribution information are determined based on the ratio variance, the weighted average of the coefficient of variation, and the predicted life of the target meter. The larger the ratio variance, the smaller the distribution evaluation parameter, and the larger the weighted average of the coefficient of variation, the smaller the distribution evaluation parameter.

[0150] In an embodiment of the present application, based on the preset weight coefficient ratio variance, the weighted average value of the variation coefficient and the weighted average value of the predicted life of the target meter, the distribution evaluation parameter of the electricity consumption behavior distribution information is obtained, wherein, the larger the ratio variance, the smaller the distribution evaluation parameter, the larger the weighted average value of the variation coefficient, the smaller the distribution evaluation parameter, the longer the predicted life of the meter, and the larger the distribution evaluation parameter.

[0151] 205. Push the electricity usage behavior information of each user to each user.

[0152] Compared to related technologies, this application obtains historical electricity usage information of multiple users collected by multiple smart meters; determines the electricity cost-effectiveness index corresponding to each user's electricity usage behavior information based on the historical electricity usage information of the multiple users; filters multiple target electricity usage behavior information from the multiple users' electricity usage behavior information based on the respective electricity cost-effectiveness indexes; determines the pushed electricity usage behavior information of each user based on the multiple target electricity usage behavior information; and pushes the pushed electricity usage behavior information of each user to each user. This application can improve the accuracy of multi-source data operation status diagnosis and early warning for power terminals.

[0153] Furthermore, the similarity between the user's own electricity usage behavior information and the user's pushed electricity usage behavior information is calculated as the push similarity. When the push similarity is less than the first preset push value, a first warning signal is issued, and the user's pushed electricity usage behavior information is pushed to the user. When the push similarity is greater than the first preset push value and less than the second preset push value, the user's pushed electricity usage behavior information is not pushed to the user, and a second warning signal is issued. When the push similarity is greater than the second preset push value, the user's pushed electricity usage behavior information is not pushed to the user, and no warning signal is issued.

[0154] To facilitate better implementation of the multi-source data operating status diagnosis and early warning method for power terminals provided in the embodiments of the present application, the embodiments of the present application also provide a multi-source data operating status diagnosis and early warning device for power terminals based on the multi-source data operating status diagnosis and early warning method for power terminals. The meanings of the terms herein are the same as those in the multi-source data operating status diagnosis and early warning method for power terminals. For specific implementation details, please refer to the description in the above method embodiment.

[0155] Please refer to Figure 3 , Figure 3 70 is a schematic diagram of a structure of an embodiment of a multi-source data operation status diagnosis and early warning device for a power terminal provided in an embodiment of the present application. The multi-source data operation status diagnosis and early warning device for a power terminal may include a first acquisition module 701, a first determination module 702, a screening module 703, a second determination module 704, and a push module 705, wherein:

[0156] A first acquisition module 701 is configured to acquire historical electricity usage information of multiple users collected by multiple smart meters;

[0157] A first determining module 702 is configured to determine an electricity cost performance index corresponding to each user's electricity usage behavior information based on historical electricity usage information of multiple users;

[0158] A screening module 703 is configured to screen out a plurality of target electricity usage behavior information from the electricity usage behavior information of a plurality of users based on various electricity cost performance indicators;

[0159] A second determining module 704 is configured to determine the pushed electricity usage behavior information of each user based on the plurality of target electricity usage behavior information;

[0160] The push module 705 is used to push the power usage behavior information of each user to each user.

[0161] In an optional embodiment, historical electricity usage information includes the user's total electricity costs, total electricity consumption, and usage time periods of various electrical appliances. The electricity usage behavior information includes the user's frequent usage time periods of various electrical appliances. The electricity cost-effectiveness index is the ratio of total electricity costs to total electricity consumption.

[0162] In an optional embodiment, determining the pushed electricity usage behavior information of each user based on multiple target electricity usage behavior information includes:

[0163] Clustering multiple users based on their electricity usage behavior information to obtain multiple user clusters;

[0164] Determine a preset number of electricity usage behavior information items ranked top in descending order of electricity cost performance in the user cluster as a preset number of target electricity usage behavior information items, and obtain multiple target electricity usage behavior information items corresponding to the user cluster clusters;

[0165] The method of determining the pushed electricity usage behavior information of each user based on the plurality of target electricity usage behavior information includes:

[0166] A target electricity usage behavior information is selected from a plurality of target electricity usage behavior information corresponding to the user cluster to which the user belongs as the pushed electricity usage behavior information of the user.

[0167] In an optional embodiment, selecting a target electricity usage behavior information from a plurality of target electricity usage behavior information corresponding to the user cluster to which the user belongs as the pushed electricity usage behavior information of the user includes:

[0168] Allocating target electricity usage behavior information to each user multiple times to obtain multiple electricity usage behavior allocation information after multiple allocations, wherein the electricity usage behavior allocation information includes a target electricity usage behavior information allocated to each user in a single allocation, and each electricity usage behavior allocation information is different.

[0169] Determine a regional power average value of power consumption in a power consumption area over multiple preset periods based on the power consumption behavior distribution information and the power consumption area to which each user belongs;

[0170] Calculating the power capacity ratio of the regional power average value of the power consumption area and the transformer capacity of the power consumption area, and obtaining the ratio variance of the power capacity ratios of multiple power consumption areas;

[0171] determining an allocation evaluation parameter for the electricity consumption behavior allocation information based on the ratio variance, wherein the larger the ratio variance, the smaller the allocation evaluation parameter;

[0172] Determine the electricity consumption behavior allocation information with the largest allocation evaluation parameter as the target allocation information;

[0173] The target electricity usage behavior information corresponding to each user in the target allocation information is used as the user's pushed electricity usage behavior information.

[0174] In an optional embodiment, determining the distribution evaluation parameter of the electricity usage behavior distribution information based on the ratio variance includes:

[0175] Determine the regional power variation coefficient of the power consumption of the power consumption area in multiple preset periods based on the power consumption behavior distribution information and the power consumption area to which each user belongs;

[0176] Performing a weighted average of the regional power variation coefficients of the multiple power consumption areas based on the number of users in the multiple power consumption areas to obtain a weighted average of the variation coefficients;

[0177] The distribution evaluation parameter of the electricity consumption behavior distribution information is determined based on the ratio variance and the weighted average value of the variation coefficient, wherein the larger the ratio variance, the smaller the distribution evaluation parameter, and the larger the weighted average value of the variation coefficient, the smaller the distribution evaluation parameter.

[0178] In an optional embodiment, obtaining electricity usage behavior information of multiple users collected by multiple smart meters includes:

[0179] The usage time of various electrical appliances is collected through the built-in electricity meters of various electrical appliances or the smart sockets of various electrical appliances.

[0180] The specific implementation of each of the above modules can be found in the previous embodiments and will not be described again here.

[0181] Compared to related technologies, this application obtains historical electricity usage information of multiple users collected by multiple smart meters; determines the electricity cost-effectiveness index corresponding to each user's electricity usage behavior information based on the historical electricity usage information of the multiple users; filters multiple target electricity usage behavior information from the multiple users' electricity usage behavior information based on the respective electricity cost-effectiveness indexes; determines the pushed electricity usage behavior information of each user based on the multiple target electricity usage behavior information; and pushes the pushed electricity usage behavior information of each user to each user. This application can improve the accuracy of multi-source data operation status diagnosis and early warning for power terminals.

[0182] Please refer to Figure 4 , Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0183] The electronic device may include components such as a processor 101 with one or more processing cores, a memory 102 with one or more computer-readable storage media, a power supply 103, and an input unit 104. Those skilled in the art will appreciate that the electronic device structure shown in the figure does not limit the electronic device and may include more or fewer components than shown, or combine certain components, or arrange the components differently. Among them:

[0184] Processor 101 is the control center of the electronic device. It connects all parts of the electronic device using various interfaces and circuits. It executes software programs and / or modules stored in memory 102 and accesses data stored in memory 102 to perform various functions of the electronic device and process data. Optionally, processor 101 may include one or more processing cores. Alternatively, processor 101 may integrate an application processor and a modem processor. The application processor primarily handles the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 101.

[0185] Memory 102 can be used to store software programs and modules. Processor 101 executes various functional applications and data processing by running the software programs and modules stored in memory 102. Memory 102 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as sound playback or image playback); the data storage area may store data generated based on the use of the electronic device. Furthermore, memory 102 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, memory 102 may also include a memory controller to provide processor 101 with access to memory 102.

[0186] The electronic device also includes a power supply 103 for supplying power to various components. Optionally, the power supply 103 can be logically connected to the processor 101 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 103 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0187] The electronic device may further include an input unit 104, which may be configured to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0188] Although not shown, the electronic device may also include a display unit, an image acquisition element, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 101 in the electronic device will load the executable code corresponding to one or more computer programs into the memory 102 according to the following instructions, and the processor 101 will execute the steps of the multi-source data operation status diagnosis and early warning method for power terminals provided in this application, such as:

[0189] Obtain historical electricity usage information of multiple users collected by multiple smart meters; determine the electricity cost-effectiveness index corresponding to the electricity usage behavior information of each user based on the historical electricity usage information of multiple users; filter out multiple target electricity usage behavior information from the electricity usage behavior information of multiple users based on the multiple electricity cost-effectiveness indexes; determine the pushed electricity usage behavior information of each user based on the multiple target electricity usage behavior information; and push the pushed electricity usage behavior information of each user to each user.

[0190] It should be noted that the electronic device provided in the embodiment of the present application belongs to the same concept as the multi-source data operation status diagnosis and early warning method for power terminals in the above embodiment. Its specific implementation process is detailed in the above related embodiments and will not be repeated here.

[0191] This application also provides a computer-readable storage medium having a computer program stored thereon. When the stored computer program is executed on a processor of an electronic device provided in an embodiment of this application, the processor of the electronic device executes the steps of the multi-source data operating status diagnosis and early warning method for power terminals provided in this application. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0192] The present application also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to execute various optional implementations of the multi-source data operating status diagnosis and early warning method for power terminals.

[0193] The above is a detailed introduction to the multi-source data operation status diagnosis and early warning method and device for power terminals provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0194] It should be noted that when the above embodiments of this application are applied to specific products or technologies, the relevant user data is involved, and the user's permission or consent must be obtained, and the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

Claims

1. A multi-source data operation status diagnosis and early warning method for power terminals, characterized by: include: Obtain historical electricity usage information of multiple users collected by multiple smart meters; Determine the electricity cost performance index corresponding to each user's electricity usage behavior information based on the historical electricity usage information of multiple users; Based on each electricity cost performance index, multiple target electricity consumption behavior information is screened out from the electricity consumption behavior information of multiple users, multiple users are clustered based on the electricity consumption behavior information of multiple users to obtain multiple user clustering clusters, and it is determined whether the user's smart meter is an old meter, and the electricity cost performance index of the electricity consumption behavior information of users whose smart meters are not old meters in the user clustering clusters is sorted from large to small, and a preset number of electricity consumption behavior information with the highest sorting order is determined as multiple target electricity consumption behavior information, wherein, the electricity consumption reading sequence of the total meter device in the electricity consumption area where the smart meter is located and the electricity consumption reading sequence of each smart meter in the electricity consumption area are obtained; when the independent electricity consumption time period of the smart meter is not obtained, the other smart meters except the smart meter for which the independent electricity consumption time period is not obtained are respectively determined as target devices, and the sum of the electricity consumption readings of the other smart meters in the electricity consumption area excluding the target device within the independent electricity consumption time period of the target device is obtained; the difference between the electricity consumption reading of the total meter device and the sum of the electricity consumption readings is determined as The actual power consumption of the target device, the difference between the power consumption reading of the target device and the actual power consumption of the target device is determined as the error difference, and the ratio of the error difference to the power consumption reading is determined as the reading error parameter of the target device; the power consumption readings of the total meter device and each target device in the target time period are obtained, the actual power consumption of each target device in the target time period is determined according to the reading error parameters of each target device, and the total actual power consumption is added together, and the difference between the power consumption reading of the total meter device in the target time period and the total actual power consumption is determined as the actual power consumption of the smart meter that has not obtained the independent power consumption time period, the difference between the power consumption reading and the actual power consumption of the smart meter that has not obtained the independent power consumption time period is determined as the error difference of the smart meter that has not obtained the independent power consumption time period, and the ratio of the error difference to the power consumption reading of the smart meter that has not obtained the independent power consumption time period is determined as the reading error parameter of the smart meter that has not obtained the independent power consumption time period; the smart meter whose reading error parameter is higher than the target error upper limit is determined as an old device; Determining the pushed electricity usage behavior information of each user based on multiple target electricity usage behavior information, wherein one target electricity usage behavior information is selected from multiple target electricity usage behavior information corresponding to the user cluster to which the user belongs as the pushed electricity usage behavior information of the user; Push each user's electricity usage behavior information to each user.

2. The method according to claim 1, wherein Historical electricity usage information includes the user's total electricity costs, total electricity consumption, and the usage time periods of various electrical appliances. Electricity usage behavior information includes the user's frequent usage time periods of various electrical appliances. The electricity cost-effectiveness index is the ratio of total electricity costs to total electricity consumption.

3. The method according to claim 2, wherein The step of selecting a target electricity usage behavior information from a plurality of target electricity usage behavior information corresponding to the user cluster to which the user belongs as the pushed electricity usage behavior information of the user includes: Allocating target electricity usage behavior information to each user multiple times to obtain multiple electricity usage behavior allocation information after multiple allocations, wherein the electricity usage behavior allocation information includes a target electricity usage behavior information allocated to each user in a single allocation, and each electricity usage behavior allocation information is different. Determine a regional power average of power consumption in a power consumption area over multiple preset periods based on the power consumption behavior distribution information and the power consumption area to which each user belongs; Calculating the power capacity ratio of the regional power average value of the power consumption area and the transformer capacity of the power consumption area, and obtaining the ratio variance of the power capacity ratios of multiple power consumption areas; determining an allocation evaluation parameter for the electricity consumption behavior allocation information based on the ratio variance, wherein the larger the ratio variance, the smaller the allocation evaluation parameter; Determine the electricity consumption behavior allocation information with the largest allocation evaluation parameter as the target allocation information; The target electricity usage behavior information corresponding to each user in the target allocation information is used as the user's pushed electricity usage behavior information.

4. The method according to claim 3, wherein The method of determining the distribution evaluation parameter of the electricity consumption behavior distribution information based on the ratio variance includes: Determine the regional power variation coefficient of the power consumption of the power consumption area in multiple preset periods based on the power consumption behavior distribution information and the power consumption area to which each user belongs; Performing a weighted average of the regional power variation coefficients of the multiple power consumption areas based on the number of users in the multiple power consumption areas to obtain a weighted average of the variation coefficients; The distribution evaluation parameter of the electricity consumption behavior distribution information is determined based on the ratio variance and the weighted average value of the variation coefficient, wherein the larger the ratio variance, the smaller the distribution evaluation parameter, and the larger the weighted average value of the variation coefficient, the smaller the distribution evaluation parameter.

5. The method according to claim 1, wherein The obtaining of electricity usage behavior information of multiple users collected by multiple smart meters includes: The usage time of various electrical appliances is collected through the built-in electricity meters of various electrical appliances or the smart sockets of various electrical appliances.

6. A multi-source data operation status diagnosis and early warning device for power terminals, characterized in that: The multi-source data operation status diagnosis and early warning device for power terminals includes: A first acquisition module is used to acquire historical electricity usage information of multiple users collected by multiple smart meters; A first determining module is configured to determine an electricity cost performance index corresponding to each user's electricity usage behavior information based on historical electricity usage information of multiple users; A screening module is used to screen out multiple target electricity usage behavior information from the electricity usage behavior information of multiple users based on each electricity usage cost performance index, cluster the multiple users based on the electricity usage behavior information of the multiple users to obtain multiple user clustering clusters, determine whether the user's smart meter is an old meter, sort the electricity usage cost performance index of the electricity usage behavior information of the users whose smart meters are not old meters in the user clustering cluster from large to small, and determine a preset number of electricity usage behavior information with the highest sorting as multiple target electricity usage behavior information, wherein, the electricity consumption reading sequence of the total meter device in the electricity consumption area where the smart meter is located and the electricity consumption reading sequence of each smart meter in the electricity consumption area are obtained; when the independent electricity consumption time period of the smart meter is not obtained, the other smart meters except the smart meter for which the independent electricity consumption time period is not obtained are respectively determined as target devices, and the sum of the electricity consumption readings of the other smart meters in the electricity consumption area excluding the target device within the independent electricity consumption time period of the target device is obtained; the difference between the electricity consumption reading of the total meter device and the sum of the electricity consumption readings is calculated. The value is determined as the actual power consumption of the target device, the difference between the power consumption reading of the target device and the actual power consumption of the target device is determined as the error difference, and the ratio of the error difference to the power consumption reading is determined as the reading error parameter of the target device; the power consumption readings of the total meter device and each target device in the target time period are obtained, the actual power consumption of each target device in the target time period is determined according to the reading error parameters of each target device, and the total actual power consumption is added together, and the difference between the power consumption reading of the total meter device in the target time period and the total actual power consumption is determined as the actual power consumption of the smart meter that has not obtained the independent power consumption time period, the difference between the power consumption reading and the actual power consumption of the smart meter that has not obtained the independent power consumption time period is determined as the error difference of the smart meter that has not obtained the independent power consumption time period, and the ratio of the error difference to the power consumption reading of the smart meter that has not obtained the independent power consumption time period is determined as the reading error parameter of the smart meter that has not obtained the independent power consumption time period; the smart meter whose reading error parameter is higher than the target error upper limit is determined as an old device; A second determination module is configured to determine the pushed electricity usage behavior information of each user based on the plurality of target electricity usage behavior information, wherein one target electricity usage behavior information is selected from the plurality of target electricity usage behavior information corresponding to the user cluster to which the user belongs as the pushed electricity usage behavior information of the user; The push module is used to push the power usage behavior information of each user to each user.

7. An electronic device, characterized in that: It includes a memory and a processor, the memory stores a computer program, and the processor is used to run the computer program in the memory to execute the steps in the multi-source data operation status diagnosis and early warning method for power terminals as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a plurality of instructions, which are suitable for loading by a processor to execute the steps in the multi-source data operating status diagnosis and early warning method for power terminals as described in any one of claims 1 to 5.

9. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the multi-source data operation status diagnosis and early warning method for power terminals as described in any one of claims 1 to 5 are implemented.

Images