Intelligent prompting method and system based on high-protection intelligent electric energy meter

Abstract

The invention discloses an intelligent prompting method and system based on a high-protection intelligent electric energy meter, and the method comprises the steps: obtaining a current detection time interval corresponding to an intelligent prompting instruction, and obtaining a temperature sequence, a humidity sequence and a corrosion degree value sequence corresponding to the current detection time interval, so as to form a current electric energy meter environment parameter sequence; after sequence feature analysis is carried out in combination with a current electric meter environment parameter sequence collected by the high-protection intelligent electric energy meter, intelligent analysis is carried out on a current electricity utilization data set collected in a current detection time interval and the current electric meter environment parameter sequence in the high-protection intelligent electric energy meter, an edge server or a cloud server; therefore, the remote automatic detection of the fault of the high-protection intelligent electric energy meter and the timely intelligent fault prompt can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of smart electric energy meters, and in particular to an intelligent prompting method and system based on a high-protection smart electric energy meter. Background Art

[0002] High-protection smart energy meters are a new generation of power equipment that integrates advanced protection technologies and intelligent metering functions. Designed specifically for extreme environments, they feature IP67 / IP68 dust and water resistance, corrosion resistance, and wide operating temperature range. They also integrate intelligent capabilities such as remote communication, data encryption, and power quality monitoring. High-protection smart energy meters are commonly deployed in coastal residential areas, cold winter climates, and desert regions. While these meters offer excellent dust and water resistance, corrosion resistance, and wide operating temperature range, long-term operation in extreme environments can still expose them to water ingress, corrosion of core components, and freezing of internal components. If these conditions damage the meter's core electricity metering components (such as current transformers, sampling resistors, and voltage transformers), this can lead to inaccurate metering data.

[0003] Currently, the method of checking whether high-protection smart electricity meters deployed in extreme environments have faults is to conduct regular manual inspections on site, which makes it impossible to perform remote smart meter fault detection. Once a meter fault occurs, it cannot be discovered in time and can only be discovered during the next manual inspection, making it impossible to detect and prompt the meter fault in time. Summary of the Invention

[0004] The embodiments of the present invention provide an intelligent prompt method and system based on a high-protection smart electricity meter, aiming to solve the problem in the prior art that high-protection smart electricity meters deployed in extreme environments are checked on-site by manual regular inspections, resulting in the inability to perform remote smart meter fault detection and timely detection and prompt of meter faults.

[0005] In a first aspect, an embodiment of the present invention provides an intelligent prompt method based on a high-protection smart energy meter, which is applied to a high-protection smart energy meter in a smart meter system, wherein the smart meter system further includes an edge server and a cloud server; the high-protection smart energy meter is communicatively connected to both the edge server and the cloud server; the high-protection smart energy meter includes a temperature sensor, a humidity sensor, and a resistive corrosion sensor; the intelligent prompt method based on the high-protection smart energy meter includes: In response to the intelligent prompt instruction, obtaining a current detection time interval corresponding to the intelligent prompt instruction, and obtaining a temperature sequence, a humidity sequence, and a corrosion degree value sequence corresponding to the current detection time interval to form a current electric meter environmental parameter sequence; If it is determined that the current electricity meter environmental parameter sequence meets the first sequence characteristic analysis condition, generating a smart meter fault analysis result based on the current electricity consumption data set collected in the current detection time interval and the current electricity meter environmental parameter sequence; If it is determined that the current electricity meter environment parameter sequence meets the second sequence feature analysis condition, the current electricity consumption data set collected in the current detection time interval and the current electricity meter environment parameter sequence are sent to the edge server, so that the edge server performs an electricity meter fault analysis on the current electricity consumption data set and the current electricity meter environment parameter sequence through the first classification model to obtain the smart meter fault analysis result; If it is determined that the current electricity meter environmental parameter sequence meets the third sequence characteristic analysis condition, the current electricity consumption data set collected during the current detection time interval, the current electricity meter environmental parameter sequence, and the location information of the high-protection smart energy meter are sent to the cloud server, so that the cloud server performs an electricity meter fault analysis on the current electricity consumption data set, the current electricity meter environmental parameter sequence, and the location information using a second classification model to obtain the smart meter fault analysis result; According to the smart meter fault analysis result, corresponding intelligent prompt information is generated and sent to the corresponding receiving terminal.

[0006] In a second aspect, an embodiment of the present invention further provides an intelligent prompt system based on a high-protection smart energy meter, wherein the high-protection smart energy meter is configured in a smart meter system, wherein the smart meter system further includes an edge server and a cloud server; the high-protection smart energy meter is communicatively connected to both the edge server and the cloud server; the high-protection smart energy meter includes a temperature sensor, a humidity sensor, and a resistive corrosion sensor; the intelligent prompt system based on the high-protection smart energy meter includes: an environmental parameter sequence acquisition unit, configured to, in response to an intelligent prompt instruction, acquire a current detection time interval corresponding to the intelligent prompt instruction, and acquire a temperature sequence, a humidity sequence, and a corrosion degree value sequence corresponding to the current detection time interval to form a current electric meter environmental parameter sequence; a first electric meter fault analysis unit, configured to generate a smart meter fault analysis result based on a current electricity consumption dataset collected during the current detection time interval and the current electric meter environmental parameter sequence if it is determined that the current electric meter environmental parameter sequence meets a first sequence characteristic analysis condition; a second electric meter fault analysis unit, configured to, if it is determined that the current electric meter environment parameter sequence satisfies a second sequence characteristic analysis condition, send the current electricity consumption dataset and the current electric meter environment parameter sequence collected during the current detection time interval to the edge server, so that the edge server performs an electric meter fault analysis on the current electricity consumption dataset and the current electric meter environment parameter sequence using a first classification model to obtain the smart meter fault analysis result; a third electric meter fault analysis unit, configured to, if it is determined that the current electric meter environmental parameter sequence satisfies a third sequence characteristic analysis condition, send the current electricity consumption dataset collected during the current detection time interval, the current electric meter environmental parameter sequence, and the location information of the high-protection smart electric energy meter to the cloud server, so that the cloud server performs an electric meter fault analysis on the current electricity consumption dataset, the current electric meter environmental parameter sequence, and the location information using a second classification model to obtain a smart meter fault analysis result; The intelligent prompt unit is used to generate intelligent prompt information according to the fault analysis result of the smart meter and send it to the corresponding receiving terminal.

[0007] In a third aspect, an embodiment of the present invention further provides a computer device comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0008] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the method described in the first aspect can be implemented.

[0009] An embodiment of the present invention provides an intelligent prompt method and system based on a high-protection smart energy meter, the method comprising: in response to an intelligent prompt instruction, obtaining a current detection time interval corresponding to the intelligent prompt instruction, and obtaining a temperature sequence, a humidity sequence, and a corrosion degree value sequence corresponding to the current detection time interval to form a current meter environmental parameter sequence; if it is determined that the current meter environmental parameter sequence meets the first sequence feature analysis condition, then according to the current power consumption data set collected in the current detection time interval and the current meter environmental parameter sequence, a smart meter fault analysis result is generated; if it is determined that the current meter environmental parameter sequence meets the second sequence feature analysis condition, then the current power consumption data set and the current meter environmental parameter sequence collected in the current detection time interval are collected. The sequence is sent to the edge server, so that the edge server performs a meter fault analysis on the current electricity consumption data set and the current meter environmental parameter sequence through the first classification model to obtain the smart meter fault analysis result; if it is determined that the current meter environmental parameter sequence meets the third sequence feature analysis condition, the current electricity consumption data set, the current meter environmental parameter sequence and the location information of the high-protection smart energy meter collected in the current detection time interval are sent to the cloud server, so that the cloud server performs a meter fault analysis on the current electricity consumption data set, the current meter environmental parameter sequence and the location information through the second classification model to obtain the smart meter fault analysis result; and intelligent prompt information is generated according to the smart meter fault analysis result and sent to the corresponding receiving terminal. The embodiment of the present invention can combine the current meter environmental parameter sequence including the temperature sequence, humidity sequence and corrosion degree value sequence collected by the high-protection smart energy meter to perform sequence feature analysis, and then perform intelligent analysis on the current electricity consumption data set collected in the current detection time interval and the current meter environmental parameter sequence in the high-protection smart energy meter, edge server or cloud server, so as to obtain the smart meter fault analysis results in time, realize remote automatic detection of high-protection smart energy meter faults and timely intelligent fault prompts. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0011] Figure 1 A schematic diagram of an application scenario of the intelligent prompt method based on a high-protection smart energy meter provided by an embodiment of the present invention; Figure 2 A flow chart of an intelligent prompt method based on a high-protection smart energy meter provided by an embodiment of the present invention; Figure 3A schematic diagram of a first sub-process of an intelligent prompt method based on a high-protection intelligent electric energy meter provided in an embodiment of the present invention; Figure 4 A schematic diagram of a second sub-process of the intelligent prompt method based on a high-protection intelligent electric energy meter provided in an embodiment of the present invention; Figure 5 A schematic diagram of a third sub-process of the intelligent prompt method based on a high-protection intelligent electric energy meter provided in an embodiment of the present invention; Figure 6 A schematic block diagram of an intelligent prompt system based on a high-protection intelligent electricity meter provided by an embodiment of the present invention; Figure 7 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0012] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0013] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0014] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the present invention. As used in the specification and appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0015] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0016] Please also refer to Figure 1 and Figure 2 ,in Figure 1 1 is a schematic diagram of a scenario of an intelligent prompt method based on a high-protection intelligent electric energy meter according to an embodiment of the present invention. Figure 2 This is a flow chart of an intelligent prompt method based on a high-protection intelligent energy meter provided by an embodiment of the present invention. Figure 1As shown, the intelligent prompt method based on the high-protection smart energy meter provided by the embodiment of the present invention is applied to the high-protection smart energy meter 10 in the smart energy meter system, and the smart energy meter system also includes an edge server 20 and a cloud server 30; the high-protection smart energy meter 10 is communicatively connected with the edge server 20 and the cloud server 30; the high-protection smart energy meter includes a temperature sensor 11, a humidity sensor 12 and a resistive corrosion sensor 13. Figure 2 As shown, the method includes the following steps S110-S150.

[0017] S110. In response to the intelligent prompt instruction, obtain a current detection time interval corresponding to the intelligent prompt instruction, and obtain a temperature sequence, a humidity sequence, and a corrosion degree value sequence corresponding to the current detection time interval to form a current electric meter environmental parameter sequence.

[0018] In this embodiment, the technical solution is described using a high-protection smart meter in a smart meter system as the main implementation. These high-protection smart meters are deployed in scenarios such as coastal residences, low-temperature winter areas, and desert regions. A self-test cycle can be preset within the high-protection smart meter (e.g., 30 minutes, 1 hour, 2 hours, 6 hours, 12 hours, 24 hours, or 7 days, or other durations can be set based on actual user needs). Furthermore, the processor within the high-protection smart meter automatically generates intelligent prompt instructions based on this self-test cycle. Once the intelligent prompt instruction is generated and detected by the processor within the smart meter system, the processor first retrieves the current detection time interval corresponding to the intelligent prompt instruction. It then retrieves the temperature, humidity, and corrosion severity value sequences corresponding to the current detection time interval from the meter's historical data set stored in a memory within the high-protection smart meter (connected to the processor) to form the current meter environmental parameter sequence.

[0019] The temperature sequence is obtained by collecting multiple internal ambient temperatures of a high-protection smart energy meter by a temperature sensor according to a preset temperature collection cycle and arranging them in a collection time sequence. The humidity sequence is obtained by collecting multiple internal ambient humidity values ​​of a high-protection smart energy meter by a humidity sensor according to a preset humidity collection cycle and arranging them in a collection time sequence. The corrosion degree value sequence is obtained by collecting multiple internal corrosion degrees of a high-protection smart energy meter by a resistance corrosion sensor according to a preset corrosion degree collection cycle (for example, a resistance corrosion sensor reflects the internal corrosion degree of a high-protection smart energy meter by measuring the resistance change of nickel-chromium alloy) and arranging them in a collection time sequence. After the acquisition of the above three sequences is completed, the temperature sequence, humidity sequence, and corrosion degree value sequence can be combined in the order of the temperature sequence, humidity sequence, and corrosion degree value sequence to form a current meter environmental parameter sequence. Moreover, it should be noted that the reason why the above three parameters of the high-protection smart electricity meter are collected in this application is because abnormal changes in the above three parameters are the main factors that cause failure or damage to the electricity metering components of the high-protection smart electricity meter (such as current transformers, sampling resistors, voltage transformers, etc.), and are also the main factors affecting the accuracy of the electricity metering data of the high-protection smart electricity meter.

[0020] In one embodiment, the step S110 of obtaining the current detection time interval corresponding to the smart prompt instruction includes: Obtaining the instruction generation time corresponding to the intelligent prompt instruction and obtaining a preset data collection period; The current detection time interval is determined according to the instruction generation time and the data collection cycle; wherein the current detection time interval is [instruction generation time-data collection cycle, instruction generation time].

[0021] In this embodiment, each time a smart prompt command is generated, the command generation time and the preset data collection period (e.g., 30 minutes, 1 hour, 2 hours, 1 day, 7 days, 15 days, 30 days, etc.) in the high-protection smart energy meter are also obtained. The current detection time interval is then determined as [command generation time - data collection period, command generation time]. Once the current detection time interval is determined, various data within the current detection time interval can be filtered from the historical data stored in the memory of the high-protection smart energy meter for subsequent data processing and analysis.

[0022] S120: If it is determined that the current electricity meter environment parameter sequence meets the first sequence characteristic analysis condition, generate a smart meter fault analysis result based on the current electricity consumption data set collected in the current detection time interval and the current electricity meter environment parameter sequence.

[0023] In this embodiment, multiple sequence feature analysis conditions can be pre-set in the high-protection smart electricity meter, such as a first sequence feature analysis condition (specifically, there is no abnormal jump sequence in the current meter environment parameter sequence), a second sequence feature analysis condition (specifically, there is an abnormal jump sequence in the current meter environment parameter sequence and the total number of abnormal jump sequences is less than 3), and a third sequence feature analysis condition (specifically, there is an abnormal jump sequence in the current meter environment parameter sequence and the total number of abnormal jump sequences is equal to 3), etc. When the current meter environment parameter sequence meets different sequence feature analysis conditions, the corresponding data analysis method is used to perform meter fault analysis.

[0024] If the current meter environmental parameter sequence satisfies the first sequence characteristic analysis condition, local analysis can be performed on the high-protection smart meter (i.e., without uploading to an edge server or cloud server). A smart meter fault analysis result is generated based on the current electricity usage dataset collected during the current detection time interval and the current meter environmental parameter sequence. The smart meter fault analysis result can be used to determine whether the high-protection smart meter has failed.

[0025] In one embodiment, the first sequence feature analysis condition is that there is no abnormal jump sequence in the current electricity meter environment parameter sequence, such as Figure 3 As shown, step S120 includes: S121. Acquire the current power consumption data set; wherein the current power consumption data set is any combination of a historical power consumption sequence, a historical power consumption factor sequence, a historical power consumption current sequence, or a historical power consumption voltage sequence within the current detection time interval; S122: If it is determined that an abnormal jump sequence exists in the current electricity consumption data set, a fault in the electric meter is regarded as a fault analysis result of the smart electric meter; S123: If it is determined that there is no abnormal jump sequence in the current electricity consumption data set, the normal state of the electric meter is taken as the fault analysis result of the smart electric meter.

[0026] In this embodiment, the first sequence feature analysis condition is that there is no abnormal jump sequence in the current electric meter environmental parameter sequence, that is, there is no abnormal jump in the three sequences of temperature sequence, humidity sequence and corrosion degree value sequence. Among them, whether there is an abnormal jump in the sequence can be judged specifically by an adjacent difference comparison method. For example, when determining whether there is an abnormal jump in the temperature sequence, it can be determined whether the difference between two adjacent data points in the temperature sequence (that is, the latter value - the former value) exceeds a preset temperature difference range to determine whether there is an abnormal jump in the temperature sequence. Specifically, when the difference between two adjacent data points in the temperature sequence does not exceed the preset temperature difference range, it is determined that there is no abnormal jump; when the difference between two adjacent data points in the temperature sequence exceeds the preset temperature difference range, it is determined that there is an abnormal jump.

[0027] When performing a local smart meter fault analysis on a high-protection smart energy meter, the adjacent difference comparison method is also used to determine whether there are abnormal jump sequences in the historical power sequence, historical power factor sequence, historical current sequence, or historical voltage sequence included in the current power consumption data set. If it is determined that there are abnormal jump sequences in the sequences included in the current power consumption data set, the meter fault is considered as the smart meter fault analysis result; if it is determined that there are no abnormal jump sequences in the sequences included in the current power consumption data set, the meter is considered normal as the smart meter fault analysis result. It can be seen that when the equipment environment of the high-protection smart energy meter is normal, it can itself serve as a processing terminal to perform meter fault detection.

[0028] S130. If it is determined that the current electricity meter environment parameter sequence meets the second sequence feature analysis condition, the current electricity consumption data set and the current electricity meter environment parameter sequence collected in the current detection time interval are sent to the edge server, so that the edge server performs an electricity meter fault analysis on the current electricity consumption data set and the current electricity meter environment parameter sequence through the first classification model to obtain the smart meter fault analysis result.

[0029] In this embodiment, if it is determined that the current meter environmental parameter sequence meets the second sequence characteristic analysis condition, it means that it is better to perform meter fault analysis in an edge server that is closer to the communication distance corresponding to the high-protection smart energy meter. At this time, the high-protection smart energy meter sends the current electricity consumption data set and the current meter environmental parameter sequence collected in the current detection time interval to the edge server, so that the edge server performs meter fault analysis on the current electricity consumption data set and the current meter environmental parameter sequence through the first classification model to obtain the smart meter fault analysis result.

[0030] In one embodiment, the second sequence feature analysis condition is that there are abnormal jump sequences in the current meter environment parameter sequence and the total number of abnormal jump sequences is less than 3, such as Figure 4 As shown, step S130 includes: S131. Acquire the current power consumption data set; wherein the current power consumption data set is any combination of a historical power consumption sequence, a historical power consumption factor sequence, a historical power consumption current sequence, or a historical power consumption voltage sequence within the current detection time interval; S132: normalize each sequence included in the current electricity consumption dataset to obtain a corresponding number of normalized electricity consumption sequences; S133, normalizing each sequence included in the current electricity meter environment parameter sequence to obtain a corresponding number of electricity meter environment normalized sequences; S134. Obtain multiple normalized sequences corresponding to the current electricity consumption dataset and multiple normalized electricity meter environment sequences corresponding to the current electricity meter environment parameter sequence, and perform weighted processing based on the first multi-head attention mechanism in the first classification model to obtain a first current weighted feature; S135. Input the first current weighted feature into the first convolutional neural network in the first classification model to obtain a first current classification value; S136. Based on the first target classification value interval to which the first current classification value belongs in multiple preset classification value intervals, obtain a first preset meter fault analysis result corresponding to the first target classification value interval as the smart meter fault analysis result.

[0031] In this embodiment, the second sequence feature analysis condition is that there are abnormal jump sequences in the current electricity meter environmental parameter sequence and the total number of abnormal jump sequences is less than 3, that is, one or two of the three sequences of temperature sequence, humidity sequence, and corrosion degree value sequence have abnormal jumps (the method for determining whether a sequence is an abnormal jump sequence can refer to the above example).

[0032] When analyzing smart meter fault results in the edge server, abnormal sequence transitions are no longer used as a detection method. Instead, judgment is made based on a pre-deployed first classification model in the edge server. Because the historical power, power factor, current, or voltage sequences in the current power consumption dataset are in different units or dimensions, direct feature fusion is not possible. Instead, each sequence in the current power consumption dataset can be normalized (e.g., using min-max normalization or standard deviation normalization). The sequences in the current meter environment parameter sequence can also be normalized. The multiple normalized sequences corresponding to the current power consumption dataset and the multiple normalized meter environment sequences corresponding to the current meter environment parameter sequence are then weighted using a first multi-head attention mechanism in the first classification model to obtain a first current weighted feature. Finally, the first current weighted feature is input into the classifier in the first classification model to obtain a first current classification value.

[0033] Finally, because multiple preset classification value intervals and preset meter fault analysis results corresponding to each of these preset classification value intervals (e.g., meter fault presence or meter non-fault presence) are preset in the edge server or obtained from the cloud server, after determining the first target classification value interval to which the first current classification value belongs among the multiple preset classification value intervals, the first preset meter fault analysis result corresponding to the first target classification value interval is directly used as the smart meter fault analysis result. After the smart meter fault analysis result is obtained by the edge server, it is sent back to the high-protection smart energy meter for subsequent intelligent prompt processing.

[0034] S140. If it is determined that the current electricity meter environmental parameter sequence meets the third sequence characteristic analysis condition, the current electricity consumption data set collected in the current detection time interval, the current electricity meter environmental parameter sequence and the location information of the high-protection smart electricity meter are sent to the cloud server, so that the cloud server performs an electricity meter fault analysis on the current electricity consumption data set, the current electricity meter environmental parameter sequence and the location information through the second classification model to obtain the smart meter fault analysis result.

[0035] In this embodiment, if it is determined that the current meter environmental parameter sequence meets the third sequence characteristic analysis condition, it means that it is better to perform meter fault analysis in a cloud server corresponding to the high-protection smart energy meter and having higher data processing performance. At this time, the high-protection smart energy meter will send the current electricity consumption data set collected in the current detection time interval, the current meter environmental parameter sequence and the location information of the high-protection smart energy meter to the cloud server, so that the cloud server performs meter fault analysis on the current electricity consumption data set, the current meter environmental parameter sequence and the location information through the second classification model to obtain the smart meter fault analysis result.

[0036] In one embodiment, the third sequence characteristic analysis condition is that there is an abnormal jump sequence in the current meter environment parameter sequence and the total number of abnormal jump sequences is equal to 3, such as Figure 5 As shown, step S140 includes: S141. Obtaining a model version of the second classification model and a matching result between an applicable area of ​​the second classification model and location information of the high-protection smart energy meter; S142. If it is determined that the model version of the second classification model meets a preset version condition and the applicable area of ​​the second classification model matches the location information, obtaining the current electricity consumption dataset and the current electricity meter environmental parameter sequence; wherein the current electricity consumption dataset is any combination of a historical electricity power sequence, a historical electricity power factor sequence, a historical electricity current sequence, or a historical electricity voltage sequence within the current detection time interval; S143, normalizing each sequence included in the current electricity consumption dataset to obtain a corresponding number of normalized electricity consumption sequences; S144, normalizing each sequence included in the current electricity meter environment parameter sequence to obtain a corresponding number of electricity meter environment normalized sequences; S145. Obtain multiple normalized sequences corresponding to the current electricity consumption dataset and multiple normalized electricity meter environment sequences corresponding to the current electricity meter environment parameter sequence, and perform weighted processing based on a second multi-head attention mechanism in the second classification model to obtain a second current weighted feature; S146. Input the second current weighted feature into the second convolutional neural network in the second classification model to obtain a second current classification value; S147. Based on the second target classification value interval to which the second current classification value belongs in multiple preset classification value intervals, obtain a second preset meter fault analysis result corresponding to the second target classification value interval as the smart meter fault analysis result.

[0037] In this embodiment, the third sequence characteristic analysis condition is that there are abnormal jump sequences in the current meter environmental parameter sequence and the total number of abnormal jump sequences is equal to 3, that is, abnormal jumps exist in the temperature sequence, humidity sequence, and corrosion degree value sequence (the method for determining whether a sequence is an abnormal jump sequence can refer to the above example).

[0038] When analyzing smart meter faults in the cloud server, the detection method is not based on abnormal sequence jumps. Instead, the judgment is made in conjunction with the second classification model pre-deployed in the cloud server. Of course, the location information of the high-protection smart energy meter determines its specific deployment scenario, such as a coastal residence, a low-temperature winter area, or a desert area. The cloud server uses a more refined method to select a classification model that is more suitable for the current scenario from multiple classification models to determine whether the high-protection smart energy meter in different deployment scenarios has a fault. That is, if it is determined that the model version of the second classification model meets the preset version condition (such as the preset version condition that the difference between the model version of the second classification model and the latest model version does not exceed one version) and the applicable area of ​​the second classification model (such as a coastal residence) matches the location information (based on the latitude and longitude data of the specific deployment location of the high-protection smart energy meter as positioning data, and its positioning area can be specifically determined based on this positioning data), then this indicates that the second classification model in the cloud server can be specifically applied.

[0039] Similarly, because the historical power series, historical power factor series, historical current series, or historical voltage series in the current power consumption dataset belong to different units or dimensions, direct feature fusion cannot be performed. In this case, each series included in the current power consumption dataset can be normalized (for example, a minimum-maximum normalization method or a standard deviation normalization method can be used when normalizing a series), and each series included in the current meter environment parameter series can also be normalized. Then, the multiple normalized series corresponding to the current power consumption dataset and the multiple normalized meter environment series corresponding to the current meter environment parameter series are weighted together with the second multi-head attention mechanism in the second classification model to obtain a second current weighted feature. Finally, the second current weighted feature is input into the classifier in the second classification model to obtain a second current classification value.

[0040] Finally, because the cloud server has preset multiple classification value intervals and preset meter fault analysis results corresponding to each of these preset classification value intervals (e.g., meter fault presence or non-fault presence), after determining the second target classification value interval to which the second current classification value belongs within the multiple preset classification value intervals, the second preset meter fault analysis result corresponding to the second target classification value interval is directly used as the smart meter fault analysis result. After the cloud server obtains the smart meter fault analysis result, it is sent back to the high-protection smart energy meter for subsequent intelligent prompt processing.

[0041] Among them, it should be noted that the first classification model deployed in the edge server and the second classification model deployed in the cloud server in this application can both adopt a convolutional neural network that integrates a multi-head attention mechanism, but the difference between the above two classification models is that the second classification model has a shorter model version update cycle. Moreover, when training multiple second classification models for different applicable areas in the cloud server, the training sets used are all obtained after normalization, splicing and labeling of the sequences in the electricity consumption data set and the meter environment parameter sequence collected in the corresponding geographical area. The training set used by the first classification model deployed in the edge server is obtained after normalization, splicing and labeling of the sequences in the electricity consumption data set and the meter environment parameter sequence collected from multiple high-protection smart electricity meters with a relatively close communication distance (such as a communication distance of no more than 50km).

[0042] In one embodiment, after step S141, the method further includes: If it is determined that the model version of the second classification model does not meet the preset version conditions or the applicable area of ​​the second classification model does not match the location information, then obtain a second classification model that meets the preset version conditions and matches the applicable area and the location information, and return to execute the step of obtaining the current electricity consumption data set and the current electricity meter environment parameter sequence.

[0043] In this embodiment, if it is determined that the model version of the second classification model does not meet the preset version conditions or the applicable region of the second classification model does not match the location information, this indicates that the current second classification model in the cloud server is not suitable for analyzing the relevant data uploaded by the high-protection smart energy meter. Instead, it is necessary to obtain a second classification model from the cloud server that meets the preset version conditions and matches the applicable region and location information. The process then returns to the step of obtaining the current electricity usage dataset and the current meter environmental parameter sequence (i.e., step S142 described above). In this way, the high system performance of the cloud server can be fully utilized to select the most suitable second classification model, thereby performing more accurate meter fault detection.

[0044] S150: Generate intelligent prompt information according to the smart meter fault analysis result and send it to the corresponding receiving terminal.

[0045] In this embodiment, after the high-protection smart electricity meter obtains the smart meter fault analysis results, it can automatically generate intelligent prompt information locally and send it to the receiving terminal (such as a smart phone used by maintenance personnel) with which the high-protection smart electricity meter has a pre-bound communication relationship, so as to prompt relevant personnel to check and handle it in time.

[0046] In one embodiment, step S150 includes: If it is determined that the fault analysis result of the smart meter is that the meter is faulty, obtaining preset alarm prompt information as the smart prompt information; If it is determined that the fault analysis result of the smart meter is that the meter has no fault, preset normal operation prompt information is obtained as the smart prompt information.

[0047] In this embodiment, if the fault analysis result for a high-protection smart meter indicates a fault, prompting maintenance personnel to perform on-site maintenance is necessary. In this case, the device ID and deployment location of the high-protection smart meter are entered into a preset alarm prompt information template to generate an alarm prompt message, which serves as the smart prompt message. Upon receiving this smart prompt message, the receiving terminal can promptly conduct on-site fault verification and troubleshooting.

[0048] In a high-protection smart energy meter, if it is determined that the fault analysis result of the smart energy meter is that there is no fault in the meter, normal operation prompt information can also be generated regularly as the smart prompt information and sent to the receiving terminal regularly to indicate that the high-protection smart energy meter is continuing to operate normally.

[0049] It can be seen that the embodiment of the method can combine the current meter environmental parameter sequence including the temperature sequence, humidity sequence and corrosion degree value sequence collected by the high-protection smart energy meter to perform sequence feature analysis, and then perform intelligent analysis on the current electricity consumption data set collected in the current detection time interval and the current meter environmental parameter sequence in the high-protection smart energy meter, edge server or cloud server, so as to obtain the smart meter fault analysis results in time, realize remote automatic detection of high-protection smart energy meter faults and timely intelligent fault prompts.

[0050] Figure 6 This is a schematic block diagram of an intelligent prompt system based on a high-protection intelligent energy meter provided by an embodiment of the present invention. Figure 6As shown, corresponding to the above intelligent prompt method based on high-protection smart energy meter, the present invention also provides an intelligent prompt system 100 based on high-protection smart energy meter. The intelligent prompt system 100 based on high-protection smart energy meter includes a unit for executing the above intelligent prompt method based on high-protection smart energy meter. Figure 1 and Figure 6 As shown, the intelligent prompt system 100 based on the high-protection smart energy meter is configured in the high-protection smart energy meter 10 of the smart meter system, and the smart meter system also includes an edge server 20 and a cloud server 30; the high-protection smart energy meter 10 is communicatively connected with the edge server 20 and the cloud server 30; the high-protection smart energy meter includes a temperature sensor 11, a humidity sensor 12 and a resistive corrosion sensor 13. Figure 6 The intelligent prompt system 100 based on the high-protection smart electric energy meter includes: an environmental parameter sequence acquisition unit 110, a first electric meter fault analysis unit 120, a second electric meter fault analysis unit 130, a third electric meter fault analysis unit 140 and an intelligent prompt unit 150.

[0051] The environmental parameter sequence acquisition unit 110 is configured to, in response to the intelligent prompt instruction, acquire a current detection time interval corresponding to the intelligent prompt instruction, and acquire a temperature sequence, a humidity sequence, and a corrosion degree value sequence corresponding to the current detection time interval to form a current electric meter environmental parameter sequence; A first electric meter fault analysis unit 120 is configured to generate a smart meter fault analysis result based on a current electricity consumption dataset collected during the current detection time interval and the current electric meter environment parameter sequence if it is determined that the current electric meter environment parameter sequence meets a first sequence characteristic analysis condition; The second electric meter fault analysis unit 130 is configured to, if it is determined that the current electric meter environment parameter sequence meets the second sequence characteristic analysis condition, send the current electricity consumption dataset and the current electric meter environment parameter sequence collected during the current detection time interval to the edge server, so that the edge server performs an electric meter fault analysis on the current electricity consumption dataset and the current electric meter environment parameter sequence using the first classification model to obtain the smart meter fault analysis result; a third electric meter fault analysis unit 140 configured to, if it is determined that the current electric meter environmental parameter sequence satisfies a third sequence characteristic analysis condition, send the current electric meter environmental parameter sequence, the current electric meter environmental parameter sequence, and the location information of the high-protection smart electric energy meter collected during the current detection time interval to the cloud server, so that the cloud server performs an electric meter fault analysis on the current electric meter environmental parameter sequence, the current electric meter environmental parameter sequence, and the location information using a second classification model to obtain a smart meter fault analysis result; The intelligent prompt unit 150 is used to generate intelligent prompt information according to the fault analysis result of the smart meter and send it to the corresponding receiving terminal.

[0052] In one embodiment, the first sequence feature analysis condition is that there is no abnormal jump sequence in the current electricity meter environmental parameter sequence; and the first electricity meter fault analysis unit is specifically configured to: Acquire the current power consumption data set; wherein the current power consumption data set is any combination of a historical power consumption sequence, a historical power consumption factor sequence, a historical power consumption current sequence, or a historical power consumption voltage sequence within the current detection time interval; If it is determined that an abnormal jump sequence exists in the current electricity consumption data set, the electric meter is deemed to be faulty as a fault analysis result of the smart electric meter; If it is determined that there is no abnormal jump sequence in the current electricity consumption data set, the normal state of the electric meter is regarded as the fault analysis result of the smart electric meter.

[0053] In one embodiment, the second sequence feature analysis condition is that there are abnormal jump sequences in the current electricity meter environmental parameter sequence and the total number of abnormal jump sequences is less than 3; the second electricity meter fault analysis unit is specifically configured to: Acquire the current power consumption data set; wherein the current power consumption data set is any combination of a historical power consumption sequence, a historical power consumption factor sequence, a historical power consumption current sequence, or a historical power consumption voltage sequence within the current detection time interval; Normalizing each sequence included in the current electricity consumption dataset to obtain a corresponding number of normalized electricity consumption sequences; Normalizing each sequence included in the current electricity meter environment parameter sequence to obtain a corresponding number of electricity meter environment normalized sequences; Obtaining multiple normalized sequences corresponding to the current electricity consumption dataset and multiple normalized sequences of electricity meter environments corresponding to the current electricity meter environment parameter sequence, and performing weighted processing based on a first multi-head attention mechanism in the first classification model to obtain a first current weighted feature; Inputting the first current weighted feature into a first convolutional neural network in the first classification model to obtain a first current classification value; Based on a first target classification value interval to which the first current classification value belongs among multiple preset classification value intervals, a first preset meter fault analysis result corresponding to the first target classification value interval is obtained as the smart meter fault analysis result.

[0054] In one embodiment, the third sequence feature analysis condition is that there is an abnormal jump sequence in the current electricity meter environment parameter sequence and the total number of abnormal jump sequences is equal to 3, and the third electricity meter fault analysis unit is specifically configured to: Obtaining a model version of the second classification model and a matching result between an applicable area of ​​the second classification model and location information of the high-protection smart electric energy meter; If it is determined that the model version of the second classification model meets the preset version condition and the applicable area of ​​the second classification model matches the location information, then obtaining the current electricity consumption data set and the current electricity meter environmental parameter sequence; wherein the current electricity consumption data set is any combination of a historical electricity power sequence, a historical electricity power factor sequence, a historical electricity current sequence, or a historical electricity voltage sequence within the current detection time interval; Normalizing each sequence included in the current electricity consumption dataset to obtain a corresponding number of normalized electricity consumption sequences; Normalizing each sequence included in the current electricity meter environment parameter sequence to obtain a corresponding number of electricity meter environment normalized sequences; Obtaining multiple normalized sequences corresponding to the current electricity consumption dataset and multiple normalized sequences of electricity meter environments corresponding to the current electricity meter environment parameter sequence, and performing weighted processing based on a second multi-head attention mechanism in the second classification model to obtain a second current weighted feature; Inputting the second current weighted feature into a second convolutional neural network in the second classification model to obtain a second current classification value; Based on the second target classification value interval to which the second current classification value belongs in multiple preset classification value intervals, a second preset meter fault analysis result corresponding to the second target classification value interval is obtained as the smart meter fault analysis result.

[0055] It should be noted that technical personnel in the relevant field can clearly understand that the specific implementation process of the above-mentioned intelligent prompt system based on high-protection smart electricity meter and each unit can refer to the corresponding description in the aforementioned method embodiment. For the convenience and conciseness of the description, it will not be repeated here.

[0056] It can be seen that the implementation embodiment of the system can combine the current meter environmental parameter sequence including temperature sequence, humidity sequence and corrosion degree value sequence collected by the high-protection smart energy meter to perform sequence feature analysis, and then perform intelligent analysis on the current electricity consumption data set collected in the current detection time interval and the current meter environmental parameter sequence in the high-protection smart energy meter, edge server or cloud server, so as to obtain the smart meter fault analysis results in time, realize remote automatic detection of high-protection smart energy meter faults and timely intelligent fault prompts.

[0057] The intelligent prompt system based on high protection intelligent energy meter can be realized in the form of a computer program. The computer program can be used in Figure 7 Runs on the computer equipment shown.

[0058] See also Figure 7 , Figure 7 This is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device integrates any intelligent prompt system based on a high-protection intelligent energy meter provided by an embodiment of the present invention.

[0059] See Figure 7 The computer device 400 includes a processor 402 , a memory, and a network interface 405 connected via a system bus 401 , wherein the memory may include a storage medium 403 and an internal memory 404 .

[0060] The storage medium 403 can store an operating system 4031 and a computer program 4032. The computer program 4032 includes program instructions, which, when executed, can enable the processor 402 to execute an intelligent prompt method based on a high-protection smart energy meter.

[0061] The processor 402 is used to provide computing and control capabilities to support the operation of the entire computer device.

[0062] The internal memory 404 provides an environment for the operation of the computer program 4032 in the storage medium 403. When the computer program 4032 is executed by the processor 402, the processor 402 can execute the above-mentioned intelligent prompt method based on the high-protection smart energy meter.

[0063] The network interface 405 is used to communicate with other devices through the network. Figure 7 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0064] The processor 402 is configured to run a computer program 4032 stored in a memory to implement the above-mentioned intelligent prompt method based on a high-protection smart energy meter.

[0065] It should be understood that in the embodiment of the present invention, the processor 402 may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0066] Those skilled in the art will appreciate that all or part of the steps in the method of the above-described embodiment can be implemented by instructing the relevant hardware through a computer program. The computer program includes program instructions, which can be stored in a storage medium that is computer-readable. The program instructions are executed by at least one processor in the computer system to implement the steps in the method of the above-described embodiment.

[0067] Therefore, the present invention further provides a computer-readable storage medium storing a computer program, wherein the computer program includes program instructions. When executed by a processor, the program instructions cause the processor to execute the above-mentioned intelligent prompt method based on a high-protection smart energy meter.

[0068] The storage medium may be any computer-readable storage medium that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk.

[0069] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0070] In the several embodiments provided herein, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the various units is merely a logical functional division, and actual implementation may employ other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0071] The steps in the methods of the embodiments of the present invention may be adjusted in order, combined, or deleted as needed. The units in the devices of the embodiments of the present invention may be combined, divided, or deleted as needed. Furthermore, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0072] If this integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (such as a personal computer, terminal, or network device) to execute all or part of the steps of the method described in various embodiments of the present invention.

[0073] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. An intelligent prompt method based on a high-protection smart energy meter, applied to a high-protection smart energy meter in a smart meter system, characterized in that: The smart meter system further includes an edge server and a cloud server; the high-protection smart energy meter is communicatively connected to both the edge server and the cloud server; the high-protection smart energy meter includes a temperature sensor, a humidity sensor, and a resistive corrosion sensor; the intelligent prompt method based on the high-protection smart energy meter includes: In response to the intelligent prompt instruction, obtaining a current detection time interval corresponding to the intelligent prompt instruction, and obtaining a temperature sequence, a humidity sequence, and a corrosion degree value sequence corresponding to the current detection time interval to form a current electric meter environmental parameter sequence; If it is determined that the current electricity meter environmental parameter sequence meets the first sequence characteristic analysis condition, generating a smart meter fault analysis result based on the current electricity consumption data set collected in the current detection time interval and the current electricity meter environmental parameter sequence; If it is determined that the current electricity meter environment parameter sequence meets the second sequence feature analysis condition, the current electricity consumption data set collected in the current detection time interval and the current electricity meter environment parameter sequence are sent to the edge server, so that the edge server performs an electricity meter fault analysis on the current electricity consumption data set and the current electricity meter environment parameter sequence through the first classification model to obtain the smart meter fault analysis result; If it is determined that the current electricity meter environmental parameter sequence meets the third sequence characteristic analysis condition, the current electricity consumption data set collected during the current detection time interval, the current electricity meter environmental parameter sequence, and the location information of the high-protection smart energy meter are sent to the cloud server, so that the cloud server performs an electricity meter fault analysis on the current electricity consumption data set, the current electricity meter environmental parameter sequence, and the location information using a second classification model to obtain the smart meter fault analysis result; According to the smart meter fault analysis result, corresponding intelligent prompt information is generated and sent to the corresponding receiving terminal.

2. The method according to claim 1, characterized in that The first sequence feature analysis condition is that there is no abnormal jump sequence in the current meter environment parameter sequence; generating the smart meter fault analysis result based on the current electricity consumption data set collected in the current detection time interval and the current meter environment parameter sequence includes: Acquire the current power consumption data set; wherein the current power consumption data set is any combination of a historical power consumption sequence, a historical power consumption factor sequence, a historical power consumption current sequence, or a historical power consumption voltage sequence within the current detection time interval; If it is determined that an abnormal jump sequence exists in the current electricity consumption data set, the electric meter is deemed to be faulty as a fault analysis result of the smart electric meter; If it is determined that there is no abnormal jump sequence in the current electricity consumption data set, the normal state of the electric meter is regarded as the fault analysis result of the smart electric meter.

3. The method according to claim 1, characterized in that The second sequence feature analysis condition is that there is an abnormal jump sequence in the current meter environment parameter sequence and the total number of abnormal jump sequences is less than 3; the edge server performs meter fault analysis on the current electricity consumption dataset and the current meter environment parameter sequence using the first classification model to obtain the smart meter fault analysis result, including: Acquire the current power consumption data set; wherein the current power consumption data set is any combination of a historical power consumption sequence, a historical power consumption factor sequence, a historical power consumption current sequence, or a historical power consumption voltage sequence within the current detection time interval; Normalizing each sequence included in the current electricity consumption dataset to obtain a corresponding number of normalized electricity consumption sequences; Normalizing each sequence included in the current electricity meter environment parameter sequence to obtain a corresponding number of electricity meter environment normalized sequences; Obtaining multiple normalized sequences corresponding to the current electricity consumption dataset and multiple normalized sequences of electricity meter environments corresponding to the current electricity meter environment parameter sequence, and performing weighted processing based on a first multi-head attention mechanism in the first classification model to obtain a first current weighted feature; Inputting the first current weighted feature into a first convolutional neural network in the first classification model to obtain a first current classification value; Based on a first target classification value interval to which the first current classification value belongs among multiple preset classification value intervals, a first preset meter fault analysis result corresponding to the first target classification value interval is obtained as the smart meter fault analysis result.

4. The method according to claim 1, wherein The third sequence feature analysis condition is that an abnormal jump sequence exists in the current meter environment parameter sequence and the total number of abnormal jump sequences is equal to 3; the cloud server performs meter fault analysis on the current electricity consumption dataset, the current meter environment parameter sequence, and the location information using a second classification model to obtain the smart meter fault analysis result, including: Obtaining a model version of the second classification model and a matching result between an applicable area of ​​the second classification model and location information of the high-protection smart electric energy meter; If it is determined that the model version of the second classification model meets the preset version condition and the applicable area of ​​the second classification model matches the location information, then obtaining the current electricity consumption data set and the current electricity meter environmental parameter sequence; wherein the current electricity consumption data set is any combination of a historical electricity power sequence, a historical electricity power factor sequence, a historical electricity current sequence, or a historical electricity voltage sequence within the current detection time interval; Normalizing each sequence included in the current electricity consumption dataset to obtain a corresponding number of normalized electricity consumption sequences; Normalizing each sequence included in the current electricity meter environment parameter sequence to obtain a corresponding number of electricity meter environment normalized sequences; Obtaining multiple normalized sequences corresponding to the current electricity consumption dataset and multiple normalized sequences of electricity meter environments corresponding to the current electricity meter environment parameter sequence, and performing weighted processing based on a second multi-head attention mechanism in the second classification model to obtain a second current weighted feature; Inputting the second current weighted feature into a second convolutional neural network in the second classification model to obtain a second current classification value; Based on the second target classification value interval to which the second current classification value belongs in multiple preset classification value intervals, a second preset meter fault analysis result corresponding to the second target classification value interval is obtained as the smart meter fault analysis result.

5. The method according to claim 4, characterized in that After obtaining the model version of the second classification model and the matching result between the applicable area of ​​the second classification model and the location information of the high-protection smart electric energy meter, the method further includes: If it is determined that the model version of the second classification model does not meet the preset version conditions or the applicable area of ​​the second classification model does not match the location information, then obtain a second classification model that meets the preset version conditions and matches the applicable area and the location information, and return to execute the step of obtaining the current electricity consumption data set and the current electricity meter environment parameter sequence.

6. The method according to claim 4, characterized in that Generating intelligent prompt information according to the smart meter fault analysis result includes: If it is determined that the fault analysis result of the smart meter is that the meter is faulty, obtaining preset alarm prompt information as the smart prompt information; If it is determined that the fault analysis result of the smart meter is that the meter has no fault, preset normal operation prompt information is obtained as the smart prompt information.

7. The method according to claim 1, characterized in that The obtaining of the current detection time interval corresponding to the intelligent prompt instruction includes: Obtaining the instruction generation time corresponding to the intelligent prompt instruction and obtaining a preset data collection period; The current detection time interval is determined according to the instruction generation time and the data collection cycle; wherein the current detection time interval is [instruction generation time-data collection cycle, instruction generation time].

8. An intelligent prompt system based on a high-protection smart energy meter, configured in a high-protection smart energy meter in a smart meter system, characterized in that: The smart meter system also includes an edge server and a cloud server; the high-protection smart energy meter is communicatively connected to both the edge server and the cloud server; the high-protection smart energy meter includes a temperature sensor, a humidity sensor, and a resistive corrosion sensor; the intelligent prompt system based on the high-protection smart energy meter includes: an environmental parameter sequence acquisition unit, configured to, in response to an intelligent prompt instruction, acquire a current detection time interval corresponding to the intelligent prompt instruction, and acquire a temperature sequence, a humidity sequence, and a corrosion degree value sequence corresponding to the current detection time interval to form a current electric meter environmental parameter sequence; a first electric meter fault analysis unit, configured to generate a smart meter fault analysis result based on a current electricity consumption dataset collected during the current detection time interval and the current electric meter environmental parameter sequence if it is determined that the current electric meter environmental parameter sequence meets a first sequence characteristic analysis condition; a second electric meter fault analysis unit, configured to, if it is determined that the current electric meter environment parameter sequence satisfies a second sequence characteristic analysis condition, send the current electricity consumption dataset and the current electric meter environment parameter sequence collected during the current detection time interval to the edge server, so that the edge server performs an electric meter fault analysis on the current electricity consumption dataset and the current electric meter environment parameter sequence using a first classification model to obtain the smart meter fault analysis result; a third electric meter fault analysis unit, configured to, if it is determined that the current electric meter environmental parameter sequence satisfies a third sequence characteristic analysis condition, send the current electricity consumption dataset collected during the current detection time interval, the current electric meter environmental parameter sequence, and the location information of the high-protection smart electric energy meter to the cloud server, so that the cloud server performs an electric meter fault analysis on the current electricity consumption dataset, the current electric meter environmental parameter sequence, and the location information using a second classification model to obtain a smart meter fault analysis result; The intelligent prompt unit is used to generate intelligent prompt information according to the fault analysis result of the smart meter and send it to the corresponding receiving terminal.

9. The intelligent prompt system based on the high-protection intelligent electric energy meter according to claim 8 is characterized in that: The first sequence feature analysis condition is that there is no abnormal jump sequence in the current electricity meter environmental parameter sequence; the first electricity meter fault analysis unit is specifically used to: Acquire the current power consumption data set; wherein the current power consumption data set is any combination of a historical power consumption sequence, a historical power consumption factor sequence, a historical power consumption current sequence, or a historical power consumption voltage sequence within the current detection time interval; If it is determined that an abnormal jump sequence exists in the current electricity consumption data set, the electric meter is deemed to be faulty as a fault analysis result of the smart electric meter; If it is determined that there is no abnormal jump sequence in the current electricity consumption data set, the normal state of the electric meter is regarded as the fault analysis result of the smart electric meter.

10. The intelligent prompt system based on high-protection intelligent electric energy meter according to claim 8, characterized in that: The second sequence feature analysis condition is that there is an abnormal jump sequence in the current meter environment parameter sequence and the total number of abnormal jump sequences is less than 3; the second meter fault analysis unit is specifically used to: Acquire the current power consumption data set; wherein the current power consumption data set is any combination of a historical power consumption sequence, a historical power consumption factor sequence, a historical power consumption current sequence, or a historical power consumption voltage sequence within the current detection time interval; Normalizing each sequence included in the current electricity consumption dataset to obtain a corresponding number of normalized electricity consumption sequences; Normalizing each sequence included in the current electricity meter environment parameter sequence to obtain a corresponding number of electricity meter environment normalized sequences; Obtaining multiple normalized sequences corresponding to the current electricity consumption dataset and multiple normalized sequences of electricity meter environments corresponding to the current electricity meter environment parameter sequence, and performing weighted processing based on a first multi-head attention mechanism in the first classification model to obtain a first current weighted feature; Inputting the first current weighted feature into a first convolutional neural network in the first classification model to obtain a first current classification value; Based on a first target classification value interval to which the first current classification value belongs among multiple preset classification value intervals, a first preset meter fault analysis result corresponding to the first target classification value interval is obtained as the smart meter fault analysis result.

Images