CN116388112A

CN116388112A - Abnormal supply end power-off method, device, electronic equipment and computer readable medium

Info

Publication number: CN116388112A
Application number: CN202310605958.2A
Authority: CN
Inventors: 孙兴达; 卢彩霞; 何嘉; 唐志涛; 刘明明; 赵园园; 高天; 郑凤柱; 杜晔; 李泽盼
Original assignee: State Grid Information and Telecommunication Co Ltd; Beijing Guodiantong Network Technology Co Ltd
Current assignee: State Grid Information and Telecommunication Co Ltd; Beijing Guodiantong Network Technology Co Ltd
Priority date: 2023-05-26
Filing date: 2023-05-26
Publication date: 2023-07-04
Anticipated expiration: 2043-05-26
Also published as: CN116388112B

Abstract

The embodiment of the disclosure discloses an abnormal supply end power-off method, an abnormal supply end power-off device, electronic equipment and a computer readable medium. One embodiment of the method comprises the following steps: determining an average value of each power capacity in the power capacity sequence as a power capacity average value; determining an average value of all the first electric quantities in the first electric quantity sequence as an average value of the electric quantities; determining an average value of all the first electric quantities larger than the average value of the electric quantities in the first electric quantity sequence as an upper average value of the electric quantities; adding the power capacity average value and the power consumption upper average value into power initial information; performing data cleaning processing on the power initial information to generate power information; inputting the power information into a pre-trained target power information generation model to obtain target power information; inputting the target power information into a pre-trained power result information generation model to obtain power result information; and carrying out power-off treatment on the supply end. The implementation mode can timely power off part of abnormal supply ends.

Description

Abnormal supply end power-off method, device, electronic equipment and computer readable medium

Technical Field

Embodiments of the present disclosure relate to the field of computer technology, and in particular, to an abnormal supply end power outage method, an apparatus, an electronic device, and a computer readable medium.

Background

The power of the abnormal supply end is cut off, so that the waste of the power of the abnormal supply end can be reduced. At present, the abnormal supply end is powered off in the following manner: and identifying whether the supply end is an abnormal supply end according to the basic power information provided by the supply end and a preset rule, and then powering off the abnormal supply end.

However, the following technical problems generally exist in the above manner:

firstly, the accuracy and timeliness of the basic information of the electric power provided by the supply end cannot be guaranteed, so that the accuracy of the abnormal supply end identified by the basic information of the electric power provided by the supply end is low, and the power failure of part of the abnormal supply ends is difficult to be performed in time;

second, since the electricity attribute value in the electricity attribute value sequence included in the electricity basic information may have an abnormality (for example, a deficiency, an excessively large value, an excessively small value, etc.), the accuracy of the abnormal supply terminal identified by the electricity basic information having the abnormality is low, resulting in difficulty in powering off a part of the abnormal supply terminals;

Thirdly, because the basic power information comprises a large amount of information irrelevant to a preset rule, when an abnormal supply end is identified, the information relevant to the preset rule needs to be screened out from the large amount of irrelevant information, so that the calculation resource is wasted;

fourth, the preset rule considers that the abnormal supply ends are less corresponding, the accuracy of the identified abnormal supply ends is lower, and it is difficult to power off part of the abnormal supply ends.

The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, may contain information that does not form the prior art that is already known to those of ordinary skill in the art in this country.

Disclosure of Invention

The disclosure is in part intended to introduce concepts in a simplified form that are further described below in the detailed description. The disclosure is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure propose an abnormal supply outage method, apparatus, electronic device, and computer readable medium to solve one or more of the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide an abnormal supply end power-off method, the method including: acquiring basic power information of a supply end, wherein the basic power information comprises the following steps: the power capacity sequence corresponds to a time granularity in a first preset time period, and the first electric quantity in the first electric quantity sequence corresponds to a time granularity in the first preset time period; determining an average value of each power capacity in the power capacity sequence as a power capacity average value; determining an average value of all the first electric quantities in the first electric quantity sequence as an average value of the electric quantities; determining an average value of all the first electric quantities larger than the average value of the electric quantities in the first electric quantity sequence as an upper average value of the electric quantities; adding the power capacity average value and the power consumption upper average value to power initial information, wherein the power initial information is initially empty; performing data cleaning processing on the electric power initial information to generate electric power information; inputting the power information into a pre-trained target power information generation model to obtain target power information; inputting the target power information into a pre-trained power result information generation model to obtain power result information; and responding to the fact that the power result information meets a preset abnormal condition, and performing power-off processing on the supply end.

In a second aspect, some embodiments of the present disclosure provide an abnormal supply side outage apparatus, the apparatus comprising: an acquisition unit configured to acquire power basic information of a supply terminal, wherein the power basic information includes: the power capacity sequence corresponds to a time granularity in a first preset time period, and the first electric quantity in the first electric quantity sequence corresponds to a time granularity in the first preset time period; a first determination unit configured to determine an average value of the respective electric power capacities in the electric power capacity sequence as an electric power capacity average value; a second determining unit configured to determine an average value of each first electric quantity in the first electric quantity sequence as an average value of electric quantities; a third determining unit configured to determine an average value of each of the first electric quantities greater than the average value of the electric quantities in the first electric quantity sequence as an upper average value of the electric quantities; an adding unit configured to add the electric power capacity average value and the electric power consumption upper average value to electric power initial information, wherein the electric power initial information is initially empty; a data cleansing unit configured to perform data cleansing processing on the electric power initial information to generate electric power information; a first input unit configured to input the power information into a pre-trained target power information generation model to obtain target power information; a second input unit configured to input the target power information into a pre-trained power result information generation model to obtain power result information; and the power-off unit is configured to perform power-off processing on the supply end in response to determining that the power result information meets a preset abnormal condition.

In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors causes the one or more processors to implement the method described in any of the implementations of the first aspect above.

In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

The above embodiments of the present disclosure have the following advantageous effects: by the abnormal supply end power-off method of some embodiments of the present disclosure, a part of abnormal supply ends can be powered off in time. Specifically, the reason why it is difficult to power off a part of abnormal supply terminals in time is that: the accuracy and timeliness of the power basic information provided by the supply end cannot be guaranteed, so that the accuracy of the abnormal supply end identified by the power basic information provided by the supply end is low. Based on this, the abnormal supply side power-off method of some embodiments of the present disclosure first obtains the power basic information of the supply side. Wherein, the electric power basic information includes: the power capacity sequence corresponds to a time granularity in a first preset time period, and the first electric quantity in the first electric quantity sequence corresponds to a time granularity in the first preset time period. Therefore, the power grid terminal can directly acquire the electric power basic information with smaller time granularity (one day, half month, one month and the like) and higher accuracy. Next, an average value of each power capacity in the power capacity sequence is determined as a power capacity average value. And then, determining the average value of each first electric quantity in the first electric quantity sequence as an average value of the electric quantity. And then, determining the average value of each first electric quantity larger than the average value of the electric quantity in the first electric quantity sequence as the average value of the electric quantity. Then, the above-described power capacity average value and the above-described power consumption upper average value are added to the power initial information. Wherein, the power initial information is initially empty. Therefore, the power initial information with high timeliness and accuracy can be obtained according to the power basic information with small time granularity and high accuracy, so that the abnormal supply end can be identified according to the power initial information later. Then, the data cleansing process is performed on the above-described power initial information to generate power information. Therefore, the power information after data cleaning can be obtained, so that the complexity of a subsequent target power information generation model is reduced. Then, the power information is input into a pre-trained target power information generation model to obtain target power information. Thus, the target power information can be obtained, so that the subsequent power result information generation model takes the target power information instead of the power information as input, and the complexity of the power result information generation model can be reduced. And then, inputting the target power information into a pre-trained power result information generation model to obtain power result information. Thus, the power result information can be obtained so that the abnormal supply end can be identified by the power result information later. And finally, in response to determining that the power result information meets a preset abnormal condition, carrying out power-off processing on the supply end. Thus, the power-off process can be performed on the abnormal supply terminal. Therefore, the power initial information with higher timeliness can be obtained according to the power basic information with smaller time granularity. Therefore, the more accurate abnormal supply end can be identified, and the power of part of the abnormal supply ends can be timely cut off.

Drawings

The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.

FIG. 1 is a flow chart of some embodiments of an abnormal supply side outage method according to the present disclosure;

FIG. 2 is a schematic diagram of some embodiments of an abnormal supply side power outage apparatus according to the present disclosure;

fig. 3 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.

It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Referring to fig. 1, a flow 100 of some embodiments of an abnormal supply side outage method according to the present disclosure is shown. The abnormal supply end power-off method comprises the following steps:

Step 101, obtaining basic power information of a supply end.

In some embodiments, the executing body (for example, the power grid terminal) of the abnormal supply end power outage method may acquire the power basic information of the supply end from the terminal device through a wired connection or a wireless connection. Wherein, the above-mentioned electric power basic information may include, but is not limited to, at least one of: the power capacity sequence, the first power consumption sequence, the second power consumption sequence, the first power attribute value sequence, the capacity reduction capacity sequence, the target power capacity, the second power attribute value sequence, the regional power consumption sequence and the regional power attribute value sequence. Here, the grid terminal may be a terminal that supplies power to the supply terminal. The supply side may be a terminal that operates the powered device. The power capacity in the power capacity sequence corresponds to a time granularity within a first preset time period. The first electric quantity in the first electric quantity sequence corresponds to a time granularity in a first preset time period. The power capacity in the power capacity sequence may be an operation capacity when the power receiving device is operated by the supply side. The operation capacity may be a capacity in which the powered device actually operates. The first power in the first power sequence may be a power required by the supply end to operate the powered device. The second power consumption in the second power consumption sequence may be the power required by the supply end corresponding to the time granularity in the second preset time period when the powered device operates. The first electricity attribute value in the first electricity attribute value sequence may be an electricity attribute value (electricity fee) required when the supply end corresponding to a time granularity in the first preset time period operates the powered device. The volume reduction capacity in the volume reduction capacity sequence may be an operation capacity reduced when the power receiving device is operated by the supply end corresponding to a time granularity in the first preset time period. The target power capacity may be an operation capacity when the current supply side operates the powered device. The second electricity attribute value in the second electricity attribute value sequence may be an electricity attribute value (electricity fee) required when the supply end corresponding to a time granularity in the second preset time period operates the powered device. The regional power consumption in the regional power consumption sequence may be the power consumption required by the power supply running on the powered device, where the power supply is of the same type as the power supply and corresponds to a time granularity in the first preset time period. The region electricity attribute value in the region electricity attribute value sequence may be an electricity attribute value (electricity fee) required when the power receiving device is operated by a supply terminal of the same type as the supply terminal, corresponding to a time granularity in the first preset time period. For example, the above-described temporal granularity may be, but is not limited to: one day, one week, half month. The first predetermined period of time may be 2022.5.1-2022.6.1. The first predetermined period of time may also be 2022.7.1-2023.1.1. The first predetermined period of time may be 2022.1.1-22023.1.1. The second predetermined period of time may be 2022.4.1-2022.5.1. The second predetermined period of time may also be 2022.1.1-2022.7.1. The second time period may also be 2021.1.1-2022.1.1. The powered device may include, but is not limited to, at least one of: mobile phones, tablet computers, mobile internet devices (Mobile Internet Device, MID), fans, etc.

Step 102, determining an average value of each power capacity in the power capacity sequence as a power capacity average value.

In some embodiments, the executing entity may determine an average value of each power capacity in the power capacity sequence as a power capacity average value.

And 103, determining the average value of each first electric quantity in the first electric quantity sequence as an average value of the electric quantity.

In some embodiments, the executing body may determine an average value of each first power in the first power sequence as a power consumption average value.

And 104, determining the average value of each first electric quantity larger than the average value of the electric quantity in the first electric quantity sequence as the average value of the electric quantity.

In some embodiments, the executing body may determine an average value of each first power amount greater than the average value of the power amounts in the first power amount sequence as the average value of the power amounts.

And step 105, adding the power capacity average value and the upper power consumption average value to the power initial information.

In some embodiments, the executing entity may add the power capacity average value and the power consumption upper average value to the power initial information. Wherein, the power initial information is initially empty. The power initial information may be information after the power basic information is subjected to data preprocessing.

Optionally, before step 106, the method further includes:

and a first step of updating the first electrical attribute value sequence to generate a first updated electrical attribute value sequence.

In some embodiments, the execution body may perform an update process on the first electrical attribute value sequence to generate a first updated electrical attribute value sequence.

In practice, the execution body may perform an update process on the first electrical property value sequence to generate a first updated electrical property value sequence by:

a first sub-step of, for each first electrical property value in the sequence of first electrical property values, performing the following determination step:

and a first determining step of determining the first electric property value sequence from which the first electric property value is removed as a first target electric property value sequence.

And a second determining step of determining, for each first target electricity attribute value in the first target electricity attribute value sequence, a difference between the first target electricity attribute value and the first electricity attribute value as a first electricity attribute difference.

And a third determining step of determining the first electric attribute value as a first center electric attribute value in response to determining that the number of the first electric attribute differences satisfying the preset difference condition is greater than the preset difference number. The preset difference condition may be that the first electrical property difference is smaller than a preset difference. For example, the preset difference may be 20. The predetermined number of differences may be 10.

A second sub-step of determining each of the determined first center electricity usage attribute values as a first set of center electricity usage attribute values.

A third sub-step of, for each first electrical property value in the sequence of first electrical property values, performing the following processing steps:

and a first processing step of determining, for each first center electricity attribute value in the first center electricity attribute value group, a difference between the first center electricity attribute value and the first electricity attribute value as a first center attribute difference.

And a second processing step of determining the first electric attribute value as a first abnormal electric attribute value in response to determining that the determined respective first center attribute differences satisfy a preset distance condition. The predetermined distance condition may be that the determined differences of the first center attributes are all greater than a predetermined maximum difference. For example, the preset maximum difference may be 100.

And a fourth sub-step of removing each determined first abnormal electrical property value from the first electrical property value sequence to obtain a first updated electrical property value sequence.

The related art content in step 105 is an invention point of the embodiment of the present disclosure, and solves the second technical problem mentioned in the background art, which "causes that it is difficult to power off a part of the abnormal supply terminals". Factors that cause difficulty in powering down a portion of the abnormal supply tend to be as follows: since the electricity attribute value in the electricity attribute value sequence included in the electricity basic information may have an abnormality (for example, a deficiency, an excessive value, or the like), the accuracy of the abnormal supply end identified by the electricity basic information having the abnormality is low. If the above factors are solved, the effect of power-off of part of abnormal supply ends can be achieved. To achieve this, first, individual first center-use electrical property values in the first sequence of electrical property values may be determined so as to classify the first electrical property values in the first sequence of electrical property values, a center of each class of first center-use electrical property values in the first set of center-use electrical property values. Then, according to the fact that the distance from the first electric attribute value to each central electric attribute value in the first electric attribute value sequence is larger than the preset maximum difference value, the abnormal first electric attribute value in the first electric attribute value sequence can be determined. Finally, the first electrical property value of each anomaly may be removed from the first sequence of electrical property values to remove anomaly data in the first sequence of electrical property values. Therefore, the more accurate first electric attribute value sequence can be obtained, so that the more accurate abnormal supply end can be identified later according to the electric power basic information comprising the more accurate first electric attribute value sequence. Thus, a portion of the abnormal supply terminals can be powered off.

And a second step of determining the sum of the first electric quantity in the first electric quantity sequence as a first total electric quantity.

In some embodiments, the executing entity may determine a sum of the respective first electric powers in the first electric power sequence as a first total electric power consumption.

And thirdly, determining the sum of the second power consumption in the second power consumption sequence as a second total power consumption.

In some embodiments, the executing entity may determine a sum of the second power consumption amounts in the second power consumption amount sequence as a second total power consumption amount.

And step four, determining the ratio of the first total power consumption to the second total power consumption as the same ratio of the total power consumption.

In some embodiments, the executing entity may determine a ratio of the first total power consumption and the second total power consumption as a total power consumption to be the same.

And fifthly, determining the average value of the first updated electricity attribute values in the first updated electricity attribute value sequence as an electricity attribute average value.

In some embodiments, the executing entity may determine an average value of each first updated electricity attribute value in the first updated electricity attribute value sequence as an electricity attribute average value.

And sixthly, determining the average value of the first updated electricity attribute values larger than the average value of the electricity attribute in the first updated electricity attribute value sequence as the average value of the electricity attribute.

In some embodiments, the executing entity may determine an average value of each first updated power attribute value in the first updated power attribute value sequence that is greater than the average value of the power attribute as the average value of the power attribute.

And seventh, determining the ratio of the largest first updating electricity consumption attribute value in the first updating electricity consumption attribute value sequence to the smallest first updating electricity consumption attribute value in the first updating electricity consumption attribute value sequence as an electricity consumption attribute ratio.

In some embodiments, the executing entity may determine a ratio of a largest first updated electrical property value in the first sequence of updated electrical property values to a smallest first updated electrical property value in the first sequence of updated electrical property values as the electrical property ratio.

And eighth step, adding the total electricity consumption with the same ratio, the average value of the electricity consumption attributes and the electricity consumption attribute ratio to the electric power initial information.

In some embodiments, the executing entity may add the total power consumption to the initial power information, the average value of the power consumption attribute, and the power consumption attribute ratio.

Optionally, the method further comprises:

and a first step of updating the second power utilization attribute value sequence to generate a second updated power utilization attribute value sequence.

In some embodiments, the executing entity may update the second sequence of electrical attribute values to generate a second sequence of updated electrical attribute values. In practice, the specific implementation manner of the update process for the second electrical attribute value sequence and the technical effects thereof may refer to step 105 in the foregoing embodiment, which is not described herein again.

And secondly, determining the number of volume reduction capacities in the volume reduction capacity sequence as the volume reduction times.

In some embodiments, the execution body may determine the number of volume reductions in the volume reduction sequence as the number of volume reductions.

And thirdly, determining the sum of the volume reduction capacities in the volume reduction capacity sequence as the total volume reduction capacity.

In some embodiments, the executing entity may determine a sum of the individual volume reduction capacities in the volume reduction capacity sequence as a volume reduction total capacity.

And step four, determining the ratio of the volume-reducing total capacity to the target power capacity as a volume-reducing ratio.

In some embodiments, the executing body may determine a ratio of the total capacity of the reduction volume to the target power capacity as a reduction volume ratio.

And fifthly, determining the sum of the first updated electricity attribute values in the first updated electricity attribute value sequence as a first total electricity attribute value.

In some embodiments, the execution body may determine a sum of the respective first updated electrical property values in the first updated electrical property value sequence as a first total electrical property value.

And a sixth step of determining the sum of the second updated electricity attribute values in the second updated electricity attribute value sequence as a second total electricity attribute value.

In some embodiments, the execution body may determine a sum of the respective second updated electrical property values in the sequence of second updated electrical property values as a second total electrical property value.

And seventh, determining the ratio of the first total electricity utilization attribute value to the second total electricity utilization attribute value as the same ratio of the total electricity utilization attributes.

In some embodiments, the executing entity may determine a ratio of the first total power attribute value and the second total power attribute value as a total power attribute to total power attribute.

Eighth, for each first electric quantity in the first electric quantity sequence, determining a ratio of the first electric quantity to a last first electric quantity of the first electric quantity as a first electric quantity ratio.

In some embodiments, the executing entity may determine, for each first power in the first power sequence, a ratio of the first power to a last first power of the first power as a first power ratio.

And a ninth step of determining an average value of the determined respective first electric quantity ratios as an electric quantity change rate.

In some embodiments, the executing body may determine an average value of the determined respective first power consumption ratios as the power consumption change rate.

And a tenth step of adding the volume reduction times, the volume reduction ratio, the total electricity utilization attribute same ratio and the electricity consumption change rate to the electric power initial information.

In some embodiments, the executing entity may add the number of volume reductions, the volume reduction ratio, the total power consumption attribute homoratio, and the power consumption rate to the power initial information.

Optionally, the method further comprises:

And determining the average value of the power consumption of each area in the power consumption sequence of the area as the average value of the power consumption of the area.

In some embodiments, the executing body may determine an average value of the area power consumption amounts in the area power consumption amount sequence as an area power consumption amount average value.

And secondly, determining the square of the power consumption of each area in the area power consumption sequence as an area power consumption square value, and obtaining an area power consumption square value sequence.

In some embodiments, the executing body may determine a square of each area power consumption in the area power consumption sequence as an area power consumption square value, to obtain an area power consumption square value sequence.

And thirdly, determining the sum of the square values of the power consumption of each area in the square value sequence of the power consumption of the area as the square sum of the power consumption of the area.

In some embodiments, the executing body may determine a sum of the area power consumption square values of each of the area power consumption square value sequences as an area power consumption square sum value.

And step four, determining the sum of the power consumption of each area in the power consumption sequence of the area as the sum of the power consumption of the area.

In some embodiments, the executing body may determine a sum of the area power consumption amounts in the area power consumption amount sequence as an area power consumption amount sum value.

And fifthly, determining the square of the regional power consumption sum as the regional power consumption sum square value.

In some embodiments, the executing body may determine the square of the area power consumption amount and the value as the area power consumption amount and the square value.

And sixthly, determining the ratio of the square sum value of the regional power consumption to the square sum value of the regional power consumption as the regional power consumption concentration degree.

In some embodiments, the executing body may determine a ratio of the area power consumption sum value to the area power consumption sum value as the area power consumption concentration.

And seventh, determining the average value of the regional power consumption attribute values in the regional power consumption attribute value sequence as the regional power consumption attribute average value.

In some embodiments, the executing entity may determine an average value of the region electricity attribute values in the sequence of region electricity attribute values as a region electricity attribute average value.

And eighth, generating the regional electricity attribute value concentration degree based on the regional electricity attribute value sequence.

In some embodiments, the executing entity may generate the regional power usage attribute value concentration based on the regional power usage attribute value sequence. In practice, first, the execution body may determine, as the region electricity attribute square value, the square of each region electricity attribute value in the region electricity attribute value sequence, and obtain the region electricity attribute square value sequence. Next, the execution body may determine a sum of the area electricity attribute square values of each of the area electricity attribute square value sequences as an area electricity attribute sum square value. Then, the execution body may determine a sum of the region electricity attribute values in the region electricity attribute value sequence as a region electricity attribute sum value. Then, the execution body may determine the square of the region electricity usage attribute and the value as a region electricity usage attribute and a square value. Finally, the execution body may determine a ratio of the area electricity attribute sum square value to the area electricity attribute sum square value as the area electricity attribute value concentration.

And a ninth step of adding the regional power consumption average value, the regional power consumption concentration, the regional power consumption attribute average value and the regional power consumption attribute value concentration to the electric power initial information.

In some embodiments, the execution subject may add the region electricity consumption amount average value, the region electricity consumption amount concentration ratio, the region electricity consumption attribute average value, and the region electricity consumption attribute value concentration ratio to the power initial information. Wherein, the above-mentioned electric power initial information may further include, but is not limited to, at least one of the following: the first user duty ratio, the first electricity number and the second electricity number. Here, the first user ratio may be a ratio of the total number of first users (total number of users of the supply end) to the second number of users (total number of users of the current supply end) within the above-mentioned first preset period. The first electricity number may be the number of times of first electricity (theft of electricity) within a third preset period of time. The second electricity usage number may be the number of times of second electricity usage (default electricity usage) within a third preset period of time. The third preset time period may be a sum of the first preset time period and the second preset time period.

And 106, performing data cleaning processing on the power initial information to generate power information.

In some embodiments, the executing body may perform a data cleansing process on the power initial information to generate power information. In practice, first, the execution subject may remove the total electricity usage attribute homoratio and the electricity usage amount change rate from the electricity initial information to generate electricity update information. Then, the execution subject may remove the information that is empty in the power update information to generate power information. Therefore, the information of the same total electricity utilization property, the electricity utilization change rate and the null can be removed, so that the complexity of the target electricity information generation model is reduced.

Step 107, inputting the power information into a pre-trained target power information generation model to obtain target power information.

In some embodiments, the executing body may input the power information into a pre-trained target power information generation model to obtain target power information. The target power information generation model may be a neural network model that takes power information as input and target power information as output. The target power information may include: the power information includes information satisfying a preset number of conditions. The preset number of conditions may be each information corresponding to a preset number of weights in the weight sequence corresponding to the power information. The weights in the weight sequence may characterize the importance of the information included in the power information. The above-mentioned weight sequence may be a sequence in which the respective pieces of information included in the power information are ordered from large to small according to weights. For example, the preset number may be 15.

Alternatively, the pre-trained target power information generation model may be trained by:

first, a training sample set is obtained.

In some embodiments, the executing entity may obtain the training sample set from the terminal device through a wired connection or a wireless connection. Wherein, the training samples in the training sample set include: sample power information and sample target power information. Here, the sample target power information may be a sample tag corresponding to the sample power information.

And secondly, determining an initial target power information generation model.

In some embodiments, the execution subject may determine an initial target power information generation model. The initial target power information generation model may be a neural network model that takes sample power information as input and initial target power information as output. The initial target power information generation model may include: the initial weight generates a model and initially selects a model.

The initial weight generation model may be a first custom model that takes sample power information as input and initial weight information as output. Here, the initial weight information may characterize respective weights corresponding to respective information included in the sample power information. The first custom model can be divided into three layers:

A first layer: an input layer for receiving the sample power information and inputting the sample power information to the second layer.

A second layer: a handle layer comprising: a first sub-model and a second sub-model. The first sub-model may be a gradient lifting model with sample power information as input and first weight information as output. The second sub-model may be a classifier model with sample power information as input and second weight information as output. Wherein the first weight information may include, but is not limited to: a first set of weights. The first weight in the first weight set may be a weight of information included in the generated corresponding sample power information through the first sub-model. The second weight information may include, but is not limited to: and a second set of weights. The second weight in the second weight set may be a weight of information included in the generated corresponding sample power information through the second sub-model. Here, the first weight included in the first weight information may correspond to the second weight included in the second weight information. The first weight included in the first weight information may correspond to information included in the sample power information. For example, the first sub-model may be an XGBoost (eXtreme Gradient Boosting, extreme gradient lifting) model. The second sub-model may be an RF (Random Forest) model.

A third layer, an output layer, for: first, first weight information and second weight information output by a second layer are received. Then, for each first weight included in the first weight information, an average value of the first weight and a second weight corresponding to the first weight is determined as an average weight. Then, each of the determined average weights is determined as initial weight information. And finally, taking the initial weight information as the output of the whole first custom model.

The initial selection model may be a model in which initial weight information and sample power information are input and initial target power information is output. The initial selection model described above may be used to: firstly, all weights included in the initial weight information are sequenced according to the sequence from big to small, and a transit weight sequence is obtained. And then, determining each weight of the preset number in the transit weight sequence as a transit weight group. Then, for each relay weight in the relay weight group, information corresponding to the relay weight included in the sample power information is determined as target information. Finally, each of the determined target information is determined as initial target power information.

And thirdly, selecting training samples from the training sample set.

In some embodiments, the executing entity may select a training sample from the training sample set. In practice, the executing entity may randomly select training samples from the training sample set.

And step four, inputting the sample power information included in the training sample into the initial weight information generation model to obtain initial weight information.

In some embodiments, the execution subject may input the sample power information included in the training sample into the initial weight information generation model to obtain initial weight information.

And fifthly, inputting the initial weight information and the sample power information included in the training sample into the initial selection model to obtain initial target power information.

In some embodiments, the execution body may input the initial weight information and the sample power information included in the training sample into the initial selection model to obtain initial target power information.

And a sixth step of determining a first difference value between the initial target power information and the sample target power information included in the training sample based on a preset first loss function.

In some embodiments, the executing body may determine a first difference value between the initial target power information and sample target power information included in the training sample based on a preset first loss function. The preset first loss function may be, but is not limited to: mean square error loss function (MSE), hinge loss function (SVM), cross entropy loss function (CrossEntropy), 0-1 loss function, absolute value loss function, log loss function, square loss function, exponential loss function, etc.

And seventh, in response to determining that the first difference value meets a first preset condition, adjusting network parameters of the initial target power information generation model.

In some embodiments, the executing entity may adjust the network parameters of the initial target power information generation model in response to determining that the first difference value satisfies a first preset condition. The first preset condition may be that the first difference value is greater than a first preset difference value. For example, the first difference value and the first preset difference value may be differentiated. On the basis, the network parameters of the initial target power information generation model are adjusted by using methods such as back propagation, gradient descent and the like. It should be noted that the back propagation algorithm and the gradient descent method are well known techniques widely studied and applied at present, and will not be described herein. The setting of the first preset difference value is not limited, and for example, the first preset difference value may be 0.1.

The optional technical content in step 107 is taken as an invention point of the embodiment of the present disclosure, and solves the third "technical problem mentioned in the background art, which causes waste of computing resources". Factors that lead to wasted computing resources are often as follows: since the power basic information includes a large amount of information irrelevant to a preset rule, when identifying an abnormal supply end, the information relevant to the preset rule needs to be screened out from the large amount of irrelevant information. If the above factors are solved, an effect that the waste of the computing resources can be reduced can be achieved. To achieve this effect, first, weights corresponding to respective pieces of information included in the power information may be obtained by a first sub-model and a second sub-model included in the first predefined model, respectively. Then, the weight output by the first sub-model and the second sub-model can be considered through the third layer output of the first predefined model, so that more accurate initial weight information can be obtained. Thereafter, the target power information may be selected from among the respective information included in the power information by the initial selection model. Finally, the target power information generation model can be obtained by training an initial weight generation model and an initial selection model included in the initial target power information generation model. Therefore, the method and the device can obtain each information with higher importance degree in the power information through the trained target power information generation model. Therefore, only important power information is considered, and the waste of calculation resources can be reduced.

Optionally, in response to determining that the first difference value does not meet the first preset condition, the initial target power information generation model is determined as a trained target power information generation model.

In some embodiments, the executing body may determine the initial target power information generation model as the trained target power information generation model in response to determining that the first difference value does not satisfy the first preset condition.

And step 108, inputting the target power information into a pre-trained power result information generation model to obtain power result information.

In some embodiments, the executing body may input the target power information into a power result information generation model trained in advance, to obtain power result information. The power result information generation model may be a neural network model that takes target power information as input and power result information as output. The power result information may be, but is not limited to: first result information and second result information. Here, the first result information may characterize that the supply terminal is an abnormal supply terminal. The second result information may indicate that the supply is not an abnormal supply. The abnormal supply terminal may be a supply terminal of abnormal electricity consumption.

Alternatively, the pre-trained power result information generation model may be trained by:

first, a training sample set is obtained.

In some embodiments, the executing entity may obtain the training sample set from the terminal device through a wired connection or a wireless connection. Wherein, the training samples in the training sample set include: sample target power information and sample power result information.

And secondly, determining an initial power result information generation model.

In some embodiments, the execution subject may determine an initial power result information generation model. The initial power result information generation model may be a neural network model that takes sample target power information as input and initial power result information as output. The initial power result information generation model may include: an initial target weight generation model, an initial fusion model and an initial marking model.

The initial target weight generation model may be a second custom model that takes sample target power information as input and initial target weight information as output. Here, the initial target weight information may characterize respective weights corresponding to respective information included in the sample target power information. The second custom model may be divided into three layers:

A first layer: an input layer for receiving the sample target power information and inputting the sample target power information to the second layer.

A second layer: a handle layer comprising: a first target sub-model and a second target sub-model. The first target sub-model may be a multi-layer feedforward neural network model with sample target power information as input and first target weight information as output. The second target sub-model may be a gradient lifting model with the sample target power information as output and the second target weight information as output. The first target weight information may include, but is not limited to: a first set of target weights. The first target weight in the first target weight set may be a weight of information included in the generated corresponding sample target power information through the first target sub-model. The second target weight information may include, but is not limited to: a second set of target weights. The second target weight in the second target weight set may be a weight of information included in the generated corresponding sample target power information through the second target sub-model. Here, the first target weight included in the first target weight information may correspond to the second target weight included in the second target weight information. The first target weight included in the first target weight information may correspond to information included in the sample target power information. For example, the first target sub-model may be a BP (back propagation) model. The second target sub-model may be an XGBoost (eXtreme Gradient Boosting, extreme gradient lifting) model.

A third layer, an output layer, for: first, first target weight information and second target weight information output by a second layer are received. Then, for each first target weight included in the first target weight information, an average value of the first target weight and a second target weight corresponding to the first target weight is determined as an average target weight. Then, each of the determined target weights is determined as initial target weight information. And finally, taking the initial target weight information as the output of the whole second custom model.

The initial fusion model may be a model in which sample target power information and initial target weight information are input and initial fusion information is output. Here, the above initial fusion model is used for: first, for each piece of information included in the sample target power information, a product of the information and an average target weight corresponding to the information included in the initial target weight information is determined as a power weight value. Then, the sum of the determined individual power weight values is determined as initial fusion information.

The initial marking model may be a model in which initial fusion information is input and initial power result information is output. Here, the above initial marking model is used for: first, in response to determining that the initial fusion information satisfies a preset marking condition, the first result information is determined as initial power result information. Then, in response to determining that the initial fusion information does not satisfy the preset marking condition, the second result information is determined as initial power result information. The preset marking condition may be that the initial fusion information is smaller than a preset marking value. For example, the preset flag value may be 0.5.

And thirdly, selecting training samples from the training sample set.

Fourth, inputting the sample target power information included in the training sample into the initial target weight generation model to obtain initial target weight information.

In some embodiments, the execution subject may input sample target power information included in the training sample into the initial target weight generation model to obtain initial target weight information.

And fifthly, inputting sample target power information and initial target weight information included in the training sample into the initial fusion model to obtain initial fusion information.

In some embodiments, the execution subject may input the sample target power information and the initial target weight information included in the training sample into the initial fusion model to obtain initial fusion information.

And sixthly, inputting the initial fusion information into the initial marking model to obtain initial power result information.

In some embodiments, the execution body may input the initial fusion information into the initial tag model to obtain initial power result information.

And seventh, determining a second difference value between the initial power result information and sample power result information included in the training sample based on a preset second loss function.

In some embodiments, the executing body may determine a second difference value between the initial power result information and sample power result information included in the training sample based on a preset second loss function. The preset second loss function may be, but is not limited to: mean square error loss function (MSE), hinge loss function (SVM), cross entropy loss function (CrossEntropy), 0-1 loss function, absolute value loss function, log loss function, square loss function, exponential loss function, etc.

And eighth step, in response to determining that the second difference value meets a second preset condition, adjusting network parameters of the initial power result information generation model.

In some embodiments, the executing entity may adjust the network parameters of the initial power result information generation model in response to determining that the second difference value satisfies a second preset condition. The second preset condition may be that the second difference value is greater than a second preset difference value. For example, the second difference value and the second preset difference value may be differentiated. On the basis, the network parameters of the initial power result information generation model are adjusted by using methods such as back propagation, gradient descent and the like. It should be noted that the back propagation algorithm and the gradient descent method are well known techniques widely studied and applied at present, and will not be described herein. The setting of the second preset difference value is not limited, and for example, the second preset difference value may be 0.1.

The optional technical content in step 108 is taken as an invention point of the embodiment of the present disclosure, and solves the fourth technical problem mentioned in the background art, namely that it is difficult to power off a part of the abnormal supply terminals. Factors that make it difficult to power down a portion of the abnormal supply are often as follows: the preset rule considers that the abnormal supply end is less in corresponding condition, and the accuracy of the identified abnormal supply end is lower. If the above factors are solved, the effect of power-off of part of abnormal supply ends can be achieved. To achieve this effect, first, weights corresponding to respective pieces of information included in the target power information may be obtained by a first target sub-model and a second target sub-model included in the second predefined model, respectively. Then, the weight output by the first target sub-model and the second target sub-model can be considered through the third layer output of the second predefined model, and more accurate initial target weight information can be obtained. And then, obtaining initial fusion information representing the abnormal condition of the supply end through an initial fusion model. Then, the abnormal supply end can be marked by the initial marking model. Finally, the power result information generation model can be obtained by training an initial target weight generation model, an initial fusion model and an initial marking model which are included in the initial power result information generation model. Therefore, the abnormal supply end can be identified through the trained power result information generation model, and compared with the abnormal supply end identified through a preset rule, the abnormal supply end is more accurate. Therefore, a part of the abnormal supply terminal can be powered off.

Optionally, in response to determining that the second difference value meets a second preset condition, the initial power result information generation model is determined as a trained power result information generation model.

In some embodiments, the executing body may determine the initial power result information generation model as a trained power result information generation model in response to determining that the second difference value satisfies a second preset condition.

And step 109, in response to determining that the power result information meets a preset abnormal condition, performing power-off processing on the supply end.

In some embodiments, the executing body may perform a power-off process on the supply terminal in response to determining that the power result information satisfies a preset abnormal condition. The preset abnormal condition may be that the power result information is first result information.

With further reference to fig. 2, as an implementation of the method shown in the above figures, the present disclosure provides some embodiments of an abnormal supply side outage apparatus, which correspond to those method embodiments shown in fig. 1, and which are particularly applicable to various electronic devices.

As shown in fig. 2, the abnormal supply side power outage apparatus 200 of some embodiments includes: an acquisition unit 201, a first determination unit 202, a second determination unit 203, a third determination unit 204, an addition unit 205, a data cleansing unit 206, a first input unit 207, a second input unit 208, and a power-off unit 209. Wherein, the obtaining unit 201 is configured to obtain the power basic information of the supply end, wherein the power basic information includes: the power capacity sequence corresponds to a time granularity in a first preset time period, and the first electric quantity in the first electric quantity sequence corresponds to a time granularity in the first preset time period; a first determining unit 202 configured to determine an average value of the respective electric power capacities in the above-described electric power capacity sequence as an electric power capacity average value; a second determining unit 203 configured to determine an average value of the respective first electric powers in the first electric power sequence as an average value of the electric powers; a third determining unit 204 configured to determine an average value of each first electric quantity larger than the average value of the electric quantities in the first electric quantity sequence as an upper average value of the electric quantities; an adding unit 205 configured to add the above-described power capacity average value and the above-described power consumption upper average value to power initial information, wherein the above-described power initial information is initially empty; a data cleansing unit 206 configured to perform data cleansing processing on the above-described power initial information to generate power information; a first input unit 207 configured to input the above-described power information into a target power information generation model trained in advance, resulting in target power information; a second input unit 208 configured to input the target power information into a pre-trained power result information generation model, to obtain power result information; and a power-off unit 209 configured to perform power-off processing on the supply terminal in response to determining that the power result information satisfies a preset abnormal condition.

It will be appreciated that the elements described in the abnormal supply side power cut-off 200 correspond to the steps of the method described with reference to fig. 1. Thus, the operations, features and advantages described above for the method are equally applicable to the abnormal supply side power cut-off device 200 and the units contained therein, and are not described herein.

Referring now to fig. 3, a schematic diagram of an electronic device (e.g., a grid terminal) 300 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), car terminals (e.g., car navigation terminals), and the like, as well as stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 3 is merely an example and should not impose any limitations on the functionality and scope of use of embodiments of the present disclosure.

As shown in fig. 3, the electronic device 300 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 301 that may perform various suitable actions and processes in accordance with a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM303, various programs and data required for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM302, and the RAM303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.

In general, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 308 including, for example, magnetic tape, hard disk, etc.; and communication means 309. The communication means 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. While fig. 3 shows an electronic device 300 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 3 may represent one device or a plurality of devices as needed.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications device 309, or from storage device 308, or from ROM 302. The above-described functions defined in the methods of some embodiments of the present disclosure are performed when the computer program is executed by the processing means 301.

It should be noted that, the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

In some implementations, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring basic power information of a supply end, wherein the basic power information comprises the following steps: the power capacity sequence corresponds to a time granularity in a first preset time period, and the first electric quantity in the first electric quantity sequence corresponds to a time granularity in the first preset time period; determining an average value of each power capacity in the power capacity sequence as a power capacity average value; determining an average value of all the first electric quantities in the first electric quantity sequence as an average value of the electric quantities; determining an average value of all the first electric quantities larger than the average value of the electric quantities in the first electric quantity sequence as an upper average value of the electric quantities; adding the power capacity average value and the power consumption upper average value to power initial information, wherein the power initial information is initially empty; performing data cleaning processing on the electric power initial information to generate electric power information; inputting the power information into a pre-trained target power information generation model to obtain target power information; inputting the target power information into a pre-trained power result information generation model to obtain power result information; and responding to the fact that the power result information meets a preset abnormal condition, and performing power-off processing on the supply end.

Computer program code for carrying out operations for some embodiments of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in some embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The described units may also be provided in a processor, for example, described as: a processor includes an acquisition unit, a first determination unit, a second determination unit, a third determination unit, an addition unit, a data cleansing unit, a first input unit, a second input unit, and a power-off unit. The names of these units do not constitute a limitation of the unit itself in some cases, and the acquisition unit may also be described as "acquiring the power basic information of the supply side", for example.

The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.

Claims

1. An abnormal supply end power-off method comprises the following steps:

acquiring basic power information of a supply end, wherein the basic power information comprises: the power capacity in the power capacity sequence corresponds to a time granularity in a first preset time period, and the first power in the first power sequence corresponds to a time granularity in the first preset time period;

determining an average value of each power capacity in the power capacity sequence as a power capacity average value;

determining an average value of all the first electric quantities in the first electric quantity sequence as an average value of the electric quantities;

determining an average value of all the first electric quantities larger than the average value of the electric quantities in the first electric quantity sequence as an upper average value of the electric quantities;

adding the power capacity average value and the power consumption upper average value into power initial information, wherein the power initial information is initially empty;

performing data cleaning processing on the electric power initial information to generate electric power information;

inputting the power information into a pre-trained target power information generation model to obtain target power information;

inputting the target power information into a pre-trained power result information generation model to obtain power result information;

And responding to the fact that the power result information meets a preset abnormal condition, and performing power-off processing on the supply end.

2. The method of claim 1, wherein the power base information further comprises: the second electricity consumption sequence and the first electricity attribute value sequence; and

before the data cleansing process is performed on the power initial information to generate power information, the method further includes:

updating the first electrical attribute value sequence to generate a first updated electrical attribute value sequence;

determining the sum of all the first electric quantities in the first electric quantity sequence as a first total electric quantity;

determining the sum of the second power consumption in the second power consumption sequence as a second total power consumption;

determining the ratio of the first total power consumption to the second total power consumption as the same ratio of the total power consumption;

determining an average value of each first updated electricity attribute value in the first updated electricity attribute value sequence as an electricity attribute average value;

determining the average value of each first updated electricity attribute value larger than the average value of the electricity attribute in the first updated electricity attribute value sequence as the average value of the electricity attribute;

Determining the ratio of the largest first updated electricity utilization attribute value in the first updated electricity utilization attribute value sequence to the smallest first updated electricity utilization attribute value in the first updated electricity utilization attribute value sequence as an electricity utilization attribute ratio;

and adding the total electricity consumption homonymy, the electricity consumption attribute upper average value and the electricity consumption attribute ratio to the electric power initial information.

3. The method of claim 2, wherein the power base information further comprises: a sequence of volume reduction capacities, a target power capacity, and a sequence of second power usage attribute values; and

the method further comprises the steps of:

updating the second power utilization attribute value sequence to generate a second updated power utilization attribute value sequence;

determining the number of volume reduction capacities in the volume reduction capacity sequence as volume reduction times;

determining the sum of the volume-reducing capacities in the volume-reducing capacity sequence as the volume-reducing total capacity;

determining a ratio of the reduced-volume total capacity to the target power capacity as a reduced-volume duty cycle;

determining a sum of the first updated electrical attribute values in the sequence of first updated electrical attribute values as a first total electrical attribute value;

determining a sum of the second updated electrical attribute values in the sequence of second updated electrical attribute values as a second total electrical attribute value;

Determining the ratio of the first total electricity utilization attribute value and the second total electricity utilization attribute value as the total electricity utilization attribute same ratio;

for each first electric quantity in the first electric quantity sequence, determining the ratio of the first electric quantity to the last first electric quantity of the first electric quantity as a first electric quantity ratio;

determining an average value of the determined first electric quantity ratios as an electric quantity change rate;

and adding the volume reduction times, the volume reduction ratio, the total electricity utilization attribute homoratio and the electricity utilization change rate to the electric power initial information.

4. A method according to claim 3, wherein the power base information further comprises: a region electricity consumption sequence and a region electricity consumption attribute value sequence; and

the method further comprises the steps of:

determining an average value of the power consumption of each area in the area power consumption sequence as an average value of the power consumption of the area;

determining the square of the power consumption of each area in the area power consumption sequence as an area power consumption square value, and obtaining an area power consumption square value sequence;

determining the sum of the square values of the power consumption of each area in the square value sequence of the power consumption of the area as the square sum of the power consumption of the area;

Determining the sum of the regional power consumption in the regional power consumption sequence as the regional power consumption sum value;

determining the square of the regional power consumption sum as a regional power consumption sum square value;

determining the ratio of the square sum value of the regional power consumption to the square sum value of the regional power consumption as regional power consumption concentration;

determining the average value of all the regional power utilization attribute values in the regional power utilization attribute value sequence as the regional power utilization attribute average value;

generating regional electricity attribute value concentration based on the regional electricity attribute value sequence;

and adding the regional power consumption average value, the regional power consumption concentration, the regional power consumption attribute average value and the regional power consumption attribute value concentration to the electric power initial information.

5. An abnormal supply end power-off device, comprising:

an acquisition unit configured to acquire power basic information of a supply terminal, wherein the power basic information includes: the power capacity in the power capacity sequence corresponds to a time granularity in a first preset time period, and the first power in the first power sequence corresponds to a time granularity in the first preset time period;

A first determination unit configured to determine an average value of the individual power capacities in the power capacity sequence as a power capacity average value;

a second determining unit configured to determine an average value of each first electric quantity in the first electric quantity sequence as an electric quantity average value;

a third determining unit configured to determine an average value of each first electric quantity larger than the average value of the electric quantities in the first electric quantity sequence as an upper average value of the electric quantities;

an adding unit configured to add the power capacity average value and the power consumption upper average value to power initial information, wherein the power initial information is initially empty;

a data cleansing unit configured to perform data cleansing processing on the power initial information to generate power information;

a first input unit configured to input the power information into a pre-trained target power information generation model to obtain target power information;

a second input unit configured to input the target power information into a pre-trained power result information generation model to obtain power result information;

and the power-off unit is configured to perform power-off processing on the supply end in response to determining that the power result information meets a preset abnormal condition.

6. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon;

when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-4.

7. A computer readable medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method of any of claims 1-4.