Electricity consumption metering prompt method based on energy distribution data of electric energy meter

Abstract

The present application relates to the technical field of smart electric meters, and in particular to an electricity metering prompt method based on the energy distribution data of electric energy meters. The method comprises: obtaining a graph data list P of a target electric meter within a target time window; obtaining a target feature vector X corresponding to the target electric meter according to P; and inputting X into a trained duration prediction model to predict the remaining usage duration corresponding to the target electric meter. The present application predicts the remaining usage duration corresponding to the target electric meter based on electricity usage data that can characterize the user's electricity usage habits and regularities, which can more effectively remind the user of the remaining usable duration of the electricity bill and urge the user to pay the bill in time.

Description

Background Art

[0002] Most existing electricity bill payment reminder systems are triggered based on a fixed remaining fee threshold. However, given the differences in electricity usage habits and daily electricity consumption of each user, even with the same remaining electricity fee, the duration of continuous use varies greatly. This one-size-fits-all reminder mechanism often ignores personalized needs. Therefore, it cannot effectively encourage users to complete electricity bill payments in a timely manner according to their actual situation, which may lead to inconvenience in electricity bill management and potential overdue risks. Summary of the invention

[0003] The technical problem to be solved by this application is: how to provide different users with the remaining electricity usage time so as to encourage users to complete the electricity bill payment in time according to their actual situation.

[0004] In view of the above technical problems, according to the first aspect of the present application, a method for electricity metering prompt based on energy distribution data of an electric energy meter is provided, and the method comprises:

[0005] S100, obtaining a graph data list P of a target electric meter within a target time window = (P1, P2, ..., P r , ..., P s ); r = 1, 2, ..., s; s is the number of consecutive and equal-length target time periods contained in the target time window; each target time period has a corresponding master node; P r is the graph data of the target meter in the rth target time period within the target time window; r Including a master node PZ r And the corresponding child node list PJ r =(PJ r1 , P.J. r2 , ..., P. J. rc , ..., P. J. rf(r) ); c = 1, 2, ..., f(r); f(r) is P r The number of child nodes included; PJ rc P r The cth child node is included; each child node has a corresponding target time segment; any target time segment belongs to the target time segment; PZ r With PJ rc The attribute value of the edge between is PJ rc The start and end time of the corresponding target time segment; PZ r Record the total electricity consumption of the target meter after homomorphic encryption in the rth target time period; PJ rc Record the PJ after homomorphic encryption rcThe average power calculated from the power corresponding to all recorded time points in the corresponding target time segment; no two target time segments overlap;

[0006] S200, according to P, obtain the target feature vector X corresponding to the target meter = (G1, G2, ..., G r , ..., G s );G r is the sub-vector corresponding to the rth target time period of the target meter within the target time window; G r =(G r1 , G r2 , ..., G rd , ..., G rf(r)-1 , G rf(r) ); d=1, 2,..., f(r)-1; G rd is the feature value list corresponding to the d-th child node in chronological order corresponding to the r-th target time period; G rd =(G rd1 , G rd2 , ..., G rdg , ..., G rdf(d) ), g = 1, 2, ..., f(d), where f(d) is the number of eigenvalues ​​corresponding to the dth child node in chronological order; T rd is the duration corresponding to the child node ranked at the dth position; ZT is the duration corresponding to the main node; W is the total number of eigenvalues ​​corresponding to the sub-vector; is the preset upper integer formula; G rd Each characteristic value in SG is the same, which is the average power corresponding to the dth child node in chronological order corresponding to the rth target time period of the target meter in the target time window; rf(r) =WW r0 SG rf(r) G rf(r) The number of eigenvalues ​​in W r0 is the sum of the number of characteristic values ​​of the other child nodes corresponding to the rth target time period of the target meter within the target time window, except for the child node ranked last in chronological order; G rf(r) Each characteristic value in is the same, which is the average power corresponding to the last child node in chronological order corresponding to the rth target time period of the target meter within the target time window;

[0007] S300: Input X into the trained duration prediction model to predict the remaining usage duration of the target electricity meter.

[0008] This application has at least the following beneficial effects:

[0009] The present application first obtains the graph data of each target time period in the target time window, and the graph data is in the form of a target main node corresponding to several target sub-nodes. And the target main node records the total power consumption in the target time period, and each target sub-node records the average power in the corresponding target time segment. The main node in the target time period can represent the total amount of electric energy consumed in the target time period, and each target sub-node represents the average energy consumption in the corresponding target time segment. And the total power consumption of the target main node is homomorphically encrypted, and each sub-node is homomorphically encrypted separately. The security of the power consumption data is guaranteed. Then, according to the graph data of each target time period mentioned above, the input vector is quickly constructed, and each target main node corresponds to a sub-vector, and the target feature vector is obtained after splicing multiple sub-vectors. The length of each sub-vector is pre-set, and the target sub-nodes corresponding to the target main node are arranged in chronological order, and the duration corresponding to each target sub-node is obtained. According to the ratio of the duration corresponding to each target sub-node to the duration of the sub-vector, the corresponding number of eigenvalues ​​is determined, and then the number of eigenvalues ​​corresponding to each target sub-node in the sub-vector is set to the average power value corresponding to the target sub-node. That is, the longer the duration of the target sub-node, the longer the length it occupies in the corresponding sub-vector, that is, the more average power values ​​corresponding to the target sub-node in the corresponding sub-vector. Thus, each sub-vector can present the energy consumption distribution of the target user in the corresponding target time period, and the user's electricity consumption in different target time periods can be known through the sub-vector, which can be used as a reference for the user's personalized electricity consumption rules, and then with the help of the trained duration prediction model, the available duration of the user's remaining electricity fee can be predicted. That is, for users with different sub-vectors, it means that their electricity consumption rules and habits are different, so under the same remaining electricity fee, the predicted available duration is also different. In addition, the input vector data is simpler to construct than the actual data, so it can be trained without relying on a large number of samples. In summary, the present application predicts the remaining usage time corresponding to the target meter based on the electricity consumption data that can characterize the user's electricity consumption habits and rules, which can more effectively remind the remaining electricity fee of the available duration, and can urge users to pay in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0011] Figure 1 A flowchart of an electricity metering prompt method based on energy distribution data of an electric energy meter provided in one embodiment of the present application. DETAILED DESCRIPTION

[0012] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0013] like Figure 1 As shown, a method for electricity metering prompting based on energy distribution data of an electric energy meter is provided according to an embodiment of the present application, and the method includes:

[0014] S100, obtaining a graph data list P of a target electric meter within a target time window = (P1, P2, ..., P r , ..., P s ); r = 1, 2, ..., s; s is the number of consecutive and equal-length target time periods contained in the target time window; each target time period has a corresponding master node; P r is the graph data of the target meter in the rth target time period within the target time window; r Including a master node PZ r And the corresponding child node list PJ r =(PJ r1 , P.J. r2 , ..., P. J. rc , ..., P. J. rf(r) ); c = 1, 2, ..., f(r); f(r) is P r The number of child nodes included; PJ rc P r The cth child node is included; each child node has a corresponding target time segment; any target time segment belongs to the target time segment; PZ r With PJ rc The attribute value of the edge between is PJ rc The start and end time of the corresponding target time segment; PZ r Record the total electricity consumption of the target meter after homomorphic encryption in the rth target time period; PJ rc Record the PJ after homomorphic encryption rc The average power calculated from the power corresponding to all recorded time points within the corresponding target time segment; no two target time segments overlap.

[0015] Specifically, in this embodiment, the data of the target meter is recorded once at each recording time point, and the power consumption data of the target meter is obtained once at each time interval corresponding to the target time period. The power consumption data of the target meter in this embodiment includes power consumption and power data. r Determine by following these steps:

[0016] S110, obtaining the target electric meter at P r The corresponding power consumption data D in the target time period is D = (D1, D2, ..., D i , ..., D n ), i = 1, 2, ..., n, wherein n is the number of electricity consumption data recorded by the target meter within the target time period; D i D is the electricity consumption data corresponding to the i-th recording time point of the target meter within the target time period; i =(DL i , D.G. i );DL i DG is the power consumption of the target meter at the i-th recording time point within the target time period; i It is the power corresponding to the i-th recording time point of the target meter within the target time period; the start time of the target time period is the time when the power consumption data of the target meter was last obtained, and the end time is the current time; the target meter has a unique corresponding target user node.

[0017] Here, the end time of the target time period is the current time, and the start time is the time when the target meter power consumption data was last obtained. In addition, each target meter has a unique corresponding target user node, that is, corresponds to one user.

[0018] S120, according to D and the first homomorphic encryption method, obtain the target meter at P r The corresponding target master node within the corresponding target time period; wherein the target master node records the total power consumption of the target meter after homomorphic encryption within the target time period.

[0019] In this embodiment, the first homomorphic encryption method uses a fully homomorphic encryption method to perform homomorphic encryption on the total power consumption data of the target meter within the target time period. Homomorphic encryption refers to performing specific operations on the obtained ciphertext after homomorphic encryption of the original data, such as addition and other operations. Then the plaintext obtained after the calculation result is homomorphically decrypted is equivalent to the data result obtained by directly performing the same calculation on the original plaintext data. Homomorphic encryption provides a function for processing encrypted data. That is to say, the encrypted data can be processed without leaking any original content in the process. After the data processing is completed, it is decrypted again, and the result obtained is the result of the same processing on the original data. In this embodiment, the total power consumption of the target meter within the target time period is homomorphically encrypted. Specifically, a fully homomorphic encryption method is used. Here, the fully homomorphic encryption method can perform any homomorphic operation on the ciphertext an unlimited number of times, that is, it can homomorphically calculate any function and can perform a variety of different calculation operations, including addition and multiplication.

[0020] S130, according to D and the second homomorphic encryption method, obtain the target meter at P r Several target sub-nodes within the corresponding target time period; wherein each target sub-node has a corresponding target time segment; each target time segment belongs to the range of the target time period; each target sub-node is individually homomorphically encrypted; each target sub-node records the average power obtained by calculating the power corresponding to all recorded time points of the target electric meter within the target time segment corresponding to the target sub-node and performing homomorphic encryption; the attribute value of the edge between each target sub-node and the target main node is the start time and end time of the target time segment corresponding to the target sub-node; the time of any two target time segments does not overlap; the first homomorphic encryption method and the second homomorphic encryption method both use fully homomorphic encryption.

[0021] In this embodiment, the target time period is segmented to obtain several target time segments; the time of any two target time segments does not overlap, and each target time segment belongs to the range of the target time period. Each target time segment corresponds to a target sub-node, and each target sub-node records the average power obtained by calculating the power corresponding to all recorded time points of the target meter in the target time segment corresponding to the target sub-node and performing homomorphic encryption. The power data can reflect the energy consumption of the corresponding target meter at a certain moment, and the average power of a target time segment can reflect the average energy consumption in the time period. The target time period is segmented to obtain several target time segments, and the corresponding target sub-nodes are generated in order to reduce the amount of data storage and facilitate data storage.

[0022] S140, generating P according to the target main node and several target sub-nodes r The graph data within the corresponding target time period.

[0023] Here, the graph data is composed of a target main node, a number of target sub-nodes, and edges between the target main node and each target sub-node, wherein the edges between the target main node and each target sub-node are plain text.

[0024] S200, according to P, obtain the target feature vector X corresponding to the target meter = (G1, G2, ..., G r , ..., G s );G r is the sub-vector corresponding to the rth target time period of the target meter within the target time window; G r =(G r1 , G r2 , ..., G rd , ..., G rf(r)-1 , G rf(r) ); d=1, 2,..., f(r)-1; G rd is the feature value list corresponding to the d-th child node in chronological order corresponding to the r-th target time period; G rd =(G rd1 , G rd2 , ..., G rdg , ..., G rdf(d) ), g = 1, 2, ..., f(d), where f(d) is the number of eigenvalues ​​corresponding to the dth child node in chronological order; T rd is the duration corresponding to the child node ranked at the dth position; ZT is the duration corresponding to the main node; W is the total number of eigenvalues ​​corresponding to the sub-vector; is the preset upper integer formula; G rd Each characteristic value in SG is the same, which is the average power corresponding to the dth child node in chronological order corresponding to the rth target time period of the target meter in the target time window; rf(r) =WW r0 SG rf(r) G rf(r) The number of eigenvalues ​​in W r0 is the sum of the number of characteristic values ​​of the other child nodes corresponding to the rth target time period of the target meter within the target time window, except for the child node ranked last in chronological order; G rf(r) Each characteristic value in is the same, which is the average power corresponding to the last child node in chronological order corresponding to the rth target time period of the target meter within the target time window.

[0025] Specifically, each target main node corresponds to a sub-vector, and multiple sub-vectors are concatenated to obtain the target feature vector. The length of each sub-vector is pre-set, and the target sub-nodes corresponding to the target main node are arranged in chronological order, and the duration corresponding to each target sub-node is obtained. According to the ratio of the duration corresponding to each target sub-node to the duration of the sub-vector, the corresponding number of eigenvalues ​​is determined, that is, the number of eigenvalues ​​corresponding to each target sub-node in the sub-vector is set to the average power value corresponding to the target sub-node, and because the previous data are rounded up, or the data is too large, the number of eigenvalues ​​corresponding to the last target sub-node is obtained by subtracting the length of the total sub-vector and the number of eigenvalues ​​corresponding to other target sub-nodes, so as to ensure that the length of the corresponding sub-vector is fixed.

[0026] S300: Input X into the trained duration prediction model to predict the remaining usage duration of the target electricity meter.

[0027] Specifically, the input vector is input into a trained duration prediction model (such as an LSTM model) to predict the remaining usage time corresponding to the target electricity meter.

[0028] The trained duration prediction model may be trained based on a training set consisting of a plurality of preset sub-vectors corresponding to different users in different target time windows and the corresponding actual remaining usage durations.

[0029] The duration prediction model mentioned above can be any model in the art that can realize the duration prediction function mentioned above, which will not be described in detail here.

[0030] In this embodiment, an input vector is quickly constructed based on the above data, and the input vector data is simpler than the actual data, so that training can be performed without relying on a large number of samples. And because the existing electricity bill payment reminders are simply based on a threshold of the remaining charges. However, everyone's electricity usage habits are different, and the remaining time that can be used for the same electricity bill is different, which results in many payment reminders being unable to effectively prompt users to pay on time. This embodiment predicts the remaining usage time corresponding to the target meter based on electricity usage data that can characterize the user's electricity usage habits and regularities, which can more effectively remind the user of the remaining usable time of the electricity bill and urge the user to pay on time.

[0031] In an exemplary embodiment of the present application, after step S140, the method further includes:

[0032] S150, uploading the above graph data and the corresponding target user ID to a first database; wherein the first database contains graph data of a plurality of electricity meters; and the first database can be accessed by the electricity consumption analysis party.

[0033] Specifically, the above graph data and the corresponding target user ID are uploaded to the first database so that the electricity consumption analysis party can aggregate and analyze the electricity consumption data.

[0034] As an example: if the power consumption analysis party wants to obtain the power consumption data S of a certain cell in any sub-time period within the target time period, the edges of all sub-nodes corresponding to the cell in the first database are compared for overlap (comparison of whether the time periods overlap), and all overlapped ones are filtered out. The result after calculation is S = m1 + m2 + ... + m e +...+m k ;m e =t e *p e ; where k is the number of overlapping edges, p e is the average power recorded by the child nodes corresponding to the e-th overlapping edge, t e The length of the time period corresponding to the e-th overlapping edge and the overlapping sub-time period. e The corresponding user is in t e The amount of electricity consumed during the corresponding time period.

[0035] It should be noted that p e 、m e and S are both ciphertext data. f() is the preset fully homomorphic encryption algorithm / homomorphic public key, then p e =f(q e );q e The power consumption is in plain text. The power consumption analysis party needs to send S to the secure management end for decryption to obtain the data sent back by the management party. Only the management party has the homomorphic private key. This achieves the goal of being able to analyze data while protecting the security of user power consumption data.

[0036] In summary, in this embodiment, the power consumption data within the target time period is processed into a form of graph data in which a target main node corresponds to several target sub-nodes, and the target main node records the total power consumption within the target time period, and each target sub-node records the average power within the corresponding target time segment. The main node within the target time period can represent the total amount of electric energy consumed within the target time period, and each target sub-node represents the average energy consumption within the corresponding target time segment. And the total power consumption of the target main node is homomorphically encrypted, and each sub-node is homomorphically encrypted separately. Since full homomorphic encryption can perform a variety of different calculation operations at the same time, such as addition or multiplication, it is convenient for the power analysis party to analyze the encrypted power consumption data. For example: when obtaining the power consumption of any time period within the target time period, it is only necessary to determine the multiple target sub-nodes that overlap with the time period in time, and according to the duration of overlap with each target sub-node and the average power corresponding to each target sub-node, the power consumption of each target sub-node that overlaps in time is obtained, and then the total power consumption is obtained by adding them. That is, the power consumption information in any time period is obtained. And because the average power of the target sub-node corresponding to each target time segment and the duration of overlap with each target sub-node are all data after fully homomorphic encryption, not only can they be calculated, but also the user's power consumption data is not exposed. In this embodiment, the target time period is divided into multiple target time segments, which reduces the amount of data storage and also reduces the amount of data analysis calculations for the data processor.

[0037] In an exemplary embodiment of the present application, the attribute value of the edge between the target master node and the target user node is the start time and end time of the target time period.

[0038] In an exemplary embodiment of the present application, after step S110, the method further includes:

[0039] S160, encrypt the electricity consumption data in D as a whole using a preset encryption method, and then package and upload it to a second database; wherein the second database cannot be accessed by the electricity consumption analysis party.

[0040] Specifically, the second database is used to trace back when there is a problem with the data. The preset encryption method can be a non-homomorphic encryption method or a homomorphic encryption method.

[0041] In an exemplary embodiment of the present application, the first database also includes a cell node or an administrative district node, and the attribute of the edge between the user node and the cell node or the administrative district node is an affiliation relationship.

[0042] Specifically, each node in the first database, including the edge relationship between each node, together constitutes graph data of the corresponding target electricity meter, including a subgraph consisting of a target main node and a number of target sub-nodes.

[0043] In an exemplary embodiment of the present application, the edge between the target main node and the target user node and the edge between the target child node and the target main node are both plain text.

[0044] Specifically, edges define the functions or relationships between nodes, making the entire graph data easier to visualize.

[0045] In an exemplary embodiment of the present application, step S130 further includes:

[0046] S131, according to D and the preset clustering method, obtain a cluster list J=(J1, J2, . . . , J j , ..., J m );j=1,2,...,m;wherein, m is the number of clusters arranged in chronological order obtained by clustering all the powers in D according to the preset clustering method; J j is the jth cluster in chronological order obtained by clustering all the powers in D according to the preset clustering method; J j =(J j1 , J j2 , ..., J jx , ..., J jf(x) ); x = 1, 2, ..., f(x); f(x) is the number of electricity consumption data in the jth cluster arranged in chronological order; J jx The power corresponding to the xth power consumption data in chronological order contained in the jth cluster; the difference between the maximum power and the minimum power in each cluster is less than the preset power difference threshold; each cluster has a corresponding target time segment; and the corresponding recording time points in each cluster are continuous; each cluster has a corresponding average power; the preset clustering method is a clustering method that does not specify the number of clusters.

[0047] Specifically, a density-based clustering algorithm (such as DBSCAN) that does not require the specification of the number of clusters is used to cluster the power consumption data in D, so that in a cluster after clustering, all the recording time points corresponding to the power are adjacent (the corresponding recording time points in each cluster are continuous), and the power values ​​are similar (the difference between the maximum power and the minimum power in each cluster is less than the preset power difference threshold). In this way, the average power recorded by each target sub-node is representative for the target sub-node. If there is an excessively large or small power in a cluster, which causes the overall average power to increase or decrease, the average power obtained in this way cannot represent the energy consumption of the target time segment. Therefore, the above-mentioned excessively large or small instantaneous power data exists as discrete points.

[0048] S132, merge the clusters in J to obtain a fused cluster list R = (R1, R2, ..., R p , ..., R q ), p = 1, 2, ..., q, where R p is the pth fusion cluster; R p =(J a-1 , J a , J a+1 );J a is the clustering cluster ranked ath in chronological order obtained by clustering all the powers in D according to the preset clustering method; and J a The amount of electricity consumption data included in the data is less than the preset amount; a-1 The corresponding average power and J a+1 The difference between the corresponding average powers is smaller than a preset average power difference.

[0049] Specifically, after clustering, in order to further reduce the amount of data storage, the above-mentioned clusters are clustered. That is, traverse each cluster, if the number of values ​​in the cluster is small (less than the preset number, or it is a discrete point), then obtain its two adjacent clusters in time. If the average power of these two clusters is relatively close (the difference is less than the preset average power difference), it means that their corresponding energy conditions are similar, then the three of them are merged into one cluster. Otherwise, they are not merged. After the fusion of each cluster, if there are still discrete points, the start time and end time of the edge of the corresponding subnode of the discrete point are the same.

[0050] S133, according to R and the unfused discrete points, a number of target sub-nodes are obtained; each target sub-node corresponds to a fused cluster or an unfused discrete point; each target sub-node records the average power calculated from the power corresponding to all recorded time points of the target meter within the target time segment corresponding to the target sub-node.

[0051] Specifically, the average power corresponding to each fusion cluster in R and the power corresponding to each discrete point are homomorphically encrypted to obtain the corresponding target sub-node.

[0052] The segmentation method provided in this embodiment uses a density-based clustering algorithm (such as DBSCAN) that does not require the specification of the number of clusters to cluster the power consumption data in D, so that in a cluster after clustering, all the recording time points corresponding to the power are adjacent (the corresponding recording time points in each cluster are continuous), and the power values ​​are similar (the difference between the maximum power and the minimum power in each cluster is less than the preset power difference threshold). In this way, the average power recorded by each target sub-node is representative for the target sub-node. If there is an excessively large or small power in a cluster, which causes the overall average power to increase or decrease, the average power obtained in this way cannot represent the energy consumption of the target time segment. After clustering, in order to further reduce the amount of data storage, the above-mentioned several clusters are clustered. That is, traverse each cluster. If the number of values ​​in the cluster is small (less than the preset number, or it is a discrete point itself), then obtain two clusters that are adjacent to each other in time. If the average power of these two clusters is close (the difference is less than the preset average power difference), it means that their corresponding energy consumption is similar, and then merge the three of them into one cluster. Otherwise, do not merge. After each cluster is merged, if there are still discrete points, the start time and end time of the edge of the corresponding subnode of the discrete point are the same. Through the two steps of clustering and fusion, the data storage volume is fully reduced, and the power consumption data is reasonably segmented according to the instantaneous power consumption, which is convenient for data analysis.

[0053] An embodiment of the present application further provides a computer program product, which includes program code. When the program product is run on an electronic device, the program code is used to enable the electronic device to execute the steps of the method according to various exemplary embodiments of the present application described above in this specification.

[0054] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0055] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0056] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0057] Those skilled in the art will appreciate that various aspects of the present application may be implemented as a system, method or program product. Therefore, various aspects of the present application may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to as "circuit", "module" or "system" herein.

[0058] The electronic device according to this embodiment of the present application is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0059] The electronic device is presented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: the at least one processor mentioned above, the at least one storage device mentioned above, and a bus connecting different system components (including storage devices and processors).

[0060] The storage stores program codes, which can be executed by the processor, so that the processor executes the steps described in the above “Exemplary Method” section of this specification according to various exemplary embodiments of the present application.

[0061] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read only memory (ROM).

[0062] The storage may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0063] The bus may represent one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0064] The electronic device can also communicate with one or more external devices (such as keyboards, pointing devices, Bluetooth devices, etc.), and can also communicate with one or more devices that enable users to interact with the electronic device, and / or communicate with any device (such as routers, modems, etc.) that enables the electronic device to communicate with one or more other computing devices. This communication can be carried out through an input / output (I / O) interface. In addition, the electronic device can also communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs) and / or public networks, such as the Internet) through a network adapter. As shown in the figure, the network adapter communicates with other modules of the electronic device through a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0065] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0066] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present application can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present application described in the above "Exemplary Method" section of the present specification.

[0067] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0068] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0069] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0070] Program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0071] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present application, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0072] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0073] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for electricity metering prompt based on energy distribution data of an electric energy meter, characterized in that: The method comprises: S100, obtaining a graph data list P=(P1, P2, ..., P r , ..., P s ); r = 1, 2, ..., s; s is the number of consecutive and equal-length target time periods contained in the target time window; each target time period has a corresponding master node; P r is the graph data of the target meter in the rth target time period within the target time window; r Including a master node PZ r And the corresponding child node list PJ r =(PJ r1 , P.J. r2 , ..., P. J. rc , ..., P. J. rf(r) ), c = 1, 2, ..., f(r), f(r) is P r The number of child nodes included; PJ rc P r The cth child node is included; each child node has a corresponding target time segment; any target time segment belongs to the target time segment; PZ r With PJ rc The attribute value of the edge between is PJ rc The start and end time of the corresponding target time segment; PZ r Record the total electricity consumption of the target meter after homomorphic encryption in the rth target time period; PJ rc Record the PJ after homomorphic encryption rc The average power calculated from the power corresponding to all recorded time points in the corresponding target time segment; no two target time segments overlap; S200, according to P, obtain the target feature vector X=(G1, G2, ..., G r , ..., G s );G r is the sub-vector corresponding to the rth target time period of the target meter within the target time window; G r =(G r1 , G r2 , ..., G rd , ..., G rf(r)-1 , G rf(r) ); d=1, 2,..., f(r)-1; G rd is the feature value list corresponding to the d-th child node in chronological order corresponding to the r-th target time period; G rd =(G rd1 , G rd2 , ..., G rdg , ..., G rdf(d) ); g = 1, 2, ..., f(d); f(d) is the number of eigenvalues ​​corresponding to the d-th child node in chronological order; f(d) = ⌈T rd / ZT*W⌉”;T rd is the duration corresponding to the child node ranked at the dth position; ZT is the duration corresponding to the main node; W is the total number of eigenvalues ​​corresponding to the sub-vector; ⌈⌉ is the preset upper integer formula; G rd Each characteristic value in SG is the same, which is the average power corresponding to the dth child node in chronological order corresponding to the rth target time period of the target meter in the target time window; rf(r) =WW r0 SG rf(r) G rf(r) The number of eigenvalues ​​in W r0 is the sum of the number of characteristic values ​​of the other child nodes corresponding to the rth target time period of the target meter within the target time window, except for the child node ranked last in chronological order; G rf(r) Each characteristic value in is the same, which is the average power corresponding to the last child node in chronological order corresponding to the rth target time period of the target meter within the target time window; S300: Input X into the trained duration prediction model to predict the remaining usage duration of the target electricity meter.

2. The method for prompting electricity consumption measurement based on energy distribution data of an electric energy meter according to claim 1, It is characterized in that Each eigenvalue in the target eigenvector is homomorphically encrypted.

3. The method for electricity metering prompt based on energy distribution data of an electric energy meter according to any one of claims 1 or 2, characterized in that: All homomorphic encryption methods are fully homomorphic encryption.

4. The method for electricity metering prompt based on energy distribution data of electric energy meters according to claim 1, characterized in that: Each target electric meter has a corresponding user node; each graph data also includes a cell node or an administrative district node; the attribute of the edge between the cell node or the administrative district node and the user node is an affiliation relationship.

5. The method for electricity metering prompt based on energy distribution data of electric energy meters according to claim 4, characterized in that: The attribute values ​​of the edge between the master node and the user node are the start time and end time of the target time period.

6. The method for electricity metering prompt based on energy distribution data of electric energy meters according to claim 1, characterized in that: The edges between any two nodes are in plaintext.

Images