Power outage area warning method, device, electronic device and computer-readable medium

Abstract

The embodiments of the present disclosure disclose a power outage area alarm method, device, electronic device and computer-readable medium. A specific implementation of the method includes: for each power equipment, executing a generation step: determining the target power data sequence corresponding to the power equipment; determining the first data interception time period, the second data interception time period, the third data interception time period and the fourth data interception time period sequence; generating the first power data subsequence, the second power data subsequence, the third power data subsequence and the fourth power data subsequence set; generating equipment abnormality detection information; determining the equipment abnormality cause information and the equipment impact range information; generating equipment operation summary information; performing power operation abnormality display, and performing alarm processing on the corresponding power outage area. This implementation can accurately and efficiently display the power operation abnormality corresponding to the target power area, and timely perform equipment maintenance and power outage alarm for abnormally operating power equipment.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technologies, and particularly to a power outage area warning method, apparatus, electronic device, and computer-readable medium. Background Art

[0002] Currently, with the continuous development of power, the abnormal detection of power is also one of the directions that need to be focused on in the power field. For the abnormal detection of power equipment, the commonly used method is to receive the abnormal detection information obtained by manual detection corresponding to each power equipment in the power area to obtain the abnormal operation conditions of each power equipment.

[0003] However, when using the above method to determine the abnormal operation conditions of power equipment in the power area, the following technical problems often exist:

[0004] There are a large number of power equipment in the power area. The efficiency of abnormal detection by manual detection is low, and the accuracy cannot be effectively guaranteed. In addition, the results of manual detection need to be summarized and sent, which wastes a lot of time, resulting in the inability to maintain power equipment in a timely manner when facing abnormal operating power equipment, and wasting power resources.

[0005] The above information disclosed in this background art section is only used to enhance the understanding of the background of the inventive concept, and thus, it may include information that does not form the prior art known to those of ordinary skill in the art in this country. Summary of the Invention

[0006] This summary of the disclosure is used to introduce concepts in a brief form, which will be described in detail in the following detailed implementation section. This summary of the disclosure is not intended to identify the key features or essential features of the claimed technical solution, nor is it intended to be used to limit the scope of the claimed technical solution.

[0007] Some embodiments of the present disclosure propose a power outage area warning method, apparatus, electronic device, and computer-readable medium to solve one or more of the technical problems mentioned in the above background art section.

[0008] In a first aspect, some embodiments of the present disclosure provide a power outage area warning method, including: obtaining a set of power data sequences corresponding to each power device in a target power area, where each power device has a corresponding power data sequence; for each power device among the above-mentioned power devices, perform the following generation steps: determining the power data sequence corresponding to the power device as the target power data sequence; determining the first data truncation time period, the second data truncation time period, the third data truncation time period, and the fourth data truncation time period sequence for the current time corresponding to the power device, where the first data truncation time period includes the second data truncation time period, the corresponding duration of the first data truncation time period is greater than the corresponding duration of the second data truncation time period, the fourth data truncation time period sequence includes the third data truncation time period, and the central time corresponding to the third data truncation time period has the same date relationship with the current time; generating a first power data subsequence corresponding to the first data truncation time period, a second power data subsequence corresponding to the second data truncation time period, a third power data subsequence corresponding to the third data truncation time period, and a set of fourth power data subsequences corresponding to the fourth data truncation time period according to the target power data sequence; generating device anomaly detection information for the power device by using a pre-trained device anomaly detection model according to the first power data subsequence, the second power data subsequence, the third power data subsequence, and the set of fourth power data subsequences; in response to determining that the device anomaly detection information indicates that the power device is operating abnormally, determining the device anomaly cause information and the device impact range information corresponding to the power device; generating device operation summary information for the power device according to the device anomaly cause information, the target power data sequence, and the device impact range information; performing power operation anomaly display for each power device according to the obtained device operation summary information for each power device, and performing warning processing on the power outage areas corresponding to each power device.

[0009] In a second aspect, some embodiments of the present disclosure provide a power outage area warning device, including: an acquisition unit configured to acquire a set of power data sequences corresponding to each power device in a target power area, where each power device has a corresponding power data sequence; a generation unit configured to, for each of the above-mentioned power devices, perform the following generation steps: determine the power data sequence corresponding to the above-mentioned power device as a target power data sequence; determine a first data truncation time period, a second data truncation time period, a third data truncation time period, and a fourth data truncation time period sequence for the current time corresponding to the above-mentioned power device, where the above-mentioned first data truncation time period includes the above-mentioned second data truncation time period, the corresponding duration of the above-mentioned first data truncation time period is greater than the corresponding duration of the above-mentioned second data truncation time period, the above-mentioned fourth data truncation time period sequence includes the above-mentioned third data truncation time period, and the central time corresponding to the above-mentioned third data truncation time period has the same date relationship with the above-mentioned current time; generate a first power data subsequence corresponding to the above-mentioned first data truncation time period, a second power data subsequence corresponding to the above-mentioned second data truncation time period, a third power data subsequence corresponding to the above-mentioned third data truncation time period, and a set of fourth power data subsequences corresponding to the above-mentioned fourth data truncation time period according to the above-mentioned target power data sequence; generate device anomaly detection information for the above-mentioned power device by using a pre-trained device anomaly detection model according to the above-mentioned first power data subsequence, the above-mentioned second power data subsequence, the above-mentioned third power data subsequence, and the set of above-mentioned fourth power data subsequences; in response to determining that the above-mentioned device anomaly detection information indicates that the above-mentioned power device is operating abnormally, determine the device anomaly cause information and the device influence range information corresponding to the above-mentioned power device; generate device operation summary information for the above-mentioned power device according to the above-mentioned device anomaly cause information, the above-mentioned target power data sequence, and the above-mentioned device influence range information; an execution unit configured to perform power operation anomaly display for the above-mentioned power devices according to the obtained device operation summary information for each device, and perform warning processing on the power outage areas corresponding to the above-mentioned power devices.

[0010] In a third aspect, some embodiments of the present disclosure provide an electronic device, including: one or more processors; a storage device having one or more programs stored thereon, and when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method described in any implementation manner of the first aspect.

[0011] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, where the program, when executed by a processor, implements the method described in any implementation manner of the first aspect.

[0012] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: Through the power outage area warning method of some embodiments of the present disclosure, the abnormal power operation conditions corresponding to the target power area can be accurately and efficiently displayed, so as to timely perform equipment maintenance on the abnormally operating power equipment. Specifically, the reasons for the lack of accuracy in the relevant abnormal power operation conditions are as follows: There are a large number of power equipment in the power area. The efficiency of abnormal detection by manual detection is low, and the accuracy rate cannot be effectively guaranteed. In addition, it is also necessary to summarize and send the manual detection results, which wastes a lot of time. As a result, in the face of abnormally operating power equipment, the power equipment cannot be maintained in time, resulting in waste of power resources.

[0013] Based on this, for the power outage area warning method of some embodiments of the present disclosure, first, obtain the power data sequence set corresponding to each power device in the target power area. Among them, each power device has a corresponding power data sequence. Here, the power data sequence set is used as the device basic data set to facilitate the subsequent accurate generation of device anomaly detection information corresponding to each device. Then, for each of the above power devices, the following generation steps are performed: The first step is to determine the power data sequence corresponding to the above power device as the target power data sequence to serve as the operation data set corresponding to the power device, so as to facilitate the subsequent generation of device anomaly detection information according to the operation conditions reflected by the operation data set. The second step is to determine the first data truncation time period, the second data truncation time period, the third data truncation time period, and the fourth data truncation time period sequence corresponding to the current time for the above power device. Among them, the above first data truncation time period includes the above second data truncation time period. The corresponding duration of the above first data truncation time period is greater than the corresponding duration of the above second data truncation time period. The above fourth data truncation time period sequence includes the above third data truncation time period. The central time corresponding to the above third data truncation time period has the same date relationship as the above current time. Here, different data truncation time periods are set for the current time to facilitate the subsequent power data subsequence sets under each data truncation time period. The third step is to generate the first power data subsequence corresponding to the above first data truncation time period, the second power data subsequence corresponding to the above second data truncation time period, the third power data subsequence corresponding to the above third data truncation time period, and the fourth power data subsequence set corresponding to the above fourth data truncation time period according to the above target power data sequence, so as to obtain the power data for each period corresponding to the current time, adding more power data features to make the subsequent device anomaly detection more accurate. The fourth step is to use the pre-trained device anomaly detection model according to the above first power data subsequence, the above second power data subsequence, the above third power data subsequence, and the above fourth power data subsequence set to accurately generate the device anomaly detection information for the above power device. The fifth step is to accurately determine the device anomaly cause information and the device influence range information corresponding to the above power device in response to determining that the above device anomaly detection information characterizes the abnormal operation of the above power device, so as to facilitate the subsequent determination of the comprehensive state during the device operation corresponding to the power device. The sixth step is to accurately generate the device operation summary information for the above power device according to the above device anomaly cause information, the above target power data sequence, and the above device influence range information. Finally, according to the obtained device operation summary information for each device, perform the abnormal display of power operation for the above power devices and perform warning processing on the power outage areas corresponding to the above power devices. Description of the Drawings

[0014] In conjunction with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the elements and elements are not necessarily drawn to scale.

[0015] Figure 1 is a flowchart of some embodiments of a power outage area warning method according to the present disclosure;

[0016] Figure 2 is a schematic structural diagram of some embodiments of a power outage area warning device according to the present disclosure;

[0017] Figure 3 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. Specific Embodiments

[0018] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for illustrative purposes and are not used to limit the protection scope of the present disclosure.

[0019] In addition, it should be noted that for the sake of convenience of description, only parts related to the relevant invention are shown in the drawings. Without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other.

[0020] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules, or units, and are not used to limit the order or interdependence relationship of the functions performed by these devices, modules, or units.

[0021] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0022] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0023] The present disclosure will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0024] Reference Figure 1, which shows the flow 100 of some embodiments of the power outage area warning method according to the present disclosure. The power outage area warning method includes the following steps:

[0025] Step 101, obtain the power data sequence set corresponding to each power device in the target power area.

[0026] In some embodiments, the execution subject (e.g., an electronic device) of the above power outage area warning method can obtain the power data sequence set corresponding to each power device in the target power area through a wired connection method or a wireless connection method. Among them, each power device has a corresponding power data sequence. Among them, the target power area can be a power area to be subjected to power device anomaly detection. For example, the target power area can be Haidian District, Beijing. Each power device can be various types of power devices in the target power area. In practice, each power device can include: transformers, generators, motors. There is a one-to-one correspondence between the power devices in each power device and the power data sequences in the power data sequence set. The power data sequence can characterize the power data of the power device at the current time and within a predetermined historical time period before the current time. That is, the time period corresponding to the power data sequence includes: the current time period and the predetermined historical time period. The power data can be the device operation data of the power device. For example, for a power device being a transformer, the corresponding power data can include: voltage change amount, rated voltage, number of phases, number of windings.

[0027] Step 102, for each power device in the above each power device, perform the following generation steps:

[0028] Step 1021, determine the power data sequence corresponding to the above power device as the target power data sequence.

[0029] In some embodiments, the above execution subject can determine the power data sequence corresponding to the above power device as the target power data sequence. Among them, the above target power data sequence is the power data sequence in the power data sequence set that characterizes the device operation condition corresponding to the above power device.

[0030] Step 1022, determine the first data truncation time period, the second data truncation time period, the third data truncation time period, and the fourth data truncation time period sequence corresponding to the above power device for the current time.

[0031] In some embodiments, the above-mentioned execution entity may determine a first data interception time period, a second data interception time period, a third data interception time period, and a fourth data interception time period sequence corresponding to the above-mentioned power equipment for the current time. Among them, the above-mentioned first data interception time period includes the above-mentioned second data interception time period. The corresponding duration of the above-mentioned first data interception time period is greater than the corresponding duration of the above-mentioned second data interception time period. The above-mentioned fourth data interception time period sequence includes the above-mentioned third data interception time period. The central time corresponding to the above-mentioned third data interception time period has the same date relationship with the above-mentioned current time. The first data interception time period may be the sum of the time periods of the historical time periods under the first duration before the current time and the current time. The second data interception time period may be the sum of the time periods of the historical time periods under the second duration before the current time and the current time. The duration corresponding to the first duration is multiple times the magnitude of the duration corresponding to the second duration. That is, the first data interception time period may be a historical time period representing a long term for the current time. The second data interception time period may be a historical time period representing a short term for the current time. For example, the current time is June 1, 2024. The corresponding second data interception time period may be the previous month before June 1, 2024. That is, the second data interception time period may be "May 1, 2024 - June 1, 2024". The corresponding first data interception time period may be the previous year before June 1, 2024. That is, the first data interception time period may be "June 1, 2023 - June 1, 2024". The central time point corresponding to the third data interception time period has the same date association relationship with the current time. The same date association relationship may be the same day relationship. For example, the current time is June 1, 2024. The corresponding month and day of the central time point corresponding to the third data interception time period may be June 1. The third data interception time period may be a historical time period set for the current time and a predetermined time period range. The year corresponding to the third data interception time period is the previous year of the year corresponding to the current time. For example, the current time is June 1, 2024. The third data interception time period may be "May 1, 2023 - July 1, 2023". The central time point corresponding to the third data interception time period may be June 1, 2023. Each fourth data interception time period in the fourth data interception time period sequence also has the same date association relationship with the current time. The corresponding year sequence of the fourth data interception time period sequence is a sequence of connected years. And, the year corresponding to the third data interception time period is the largest year among the years corresponding to each of the fourth data interception time period sequences. For example, the current time is June 1, 2024. The corresponding year sequence of the fourth data interception time period sequence may be {2019, 2020, 2021, 2022, 2023}.The fourth data truncation time period sequence can be {"May 1, 2019 - July 1, 2019", "May 1, 2020 - July 1, 2020", "May 1, 2021 - July 1, 2021", "May 1, 2022 - July 1, 2022", "May 1, 2023 - July 1, 2023"}.

[0032] In some optional implementation manners of some embodiments, the determining of the first data truncation time period, the second data truncation time period, the third data truncation time period, and the fourth data truncation time period sequence corresponding to the power device for the current time may include the following steps:

[0033] First step, determine the device type and the device location area information corresponding to the power device. Among them, the device category can represent the device category corresponding to the power device. In practice, the device type can be set according to the device function and relevant parameters of the power device. For example, the device type can be, but is not limited to, at least one of the following: a transformer of the first specification, a transformer of the second specification, a generator of the first specification, and a generator of the second specification. The device location area information can be the regional location of the power device within the target power area.

[0034] Second step, according to the device type and the device location area information, obtain the first data truncation duration, the second data truncation duration, the third data truncation duration, and the fourth data truncation duration sequence corresponding to the power device from the target association table. Among them, the target association table can represent the corresponding relationship between the device type, the device location area information, the first data truncation duration, the second data truncation duration, the third data truncation duration, and the fourth data truncation duration sequence. It can be obtained therefrom that the target association table can be a table pre-set for the target power area.

[0035] As an example, the execution subject can determine the first data truncation duration, the second data truncation duration, the third data truncation duration, and the fourth data truncation duration sequence corresponding to the device type and the device location area information by querying the target association table.

[0036] Third step, obtain the power fluctuation period corresponding to the power device. Among them, the power fluctuation period can represent the operation state change period of the power device during operation.

[0037] Fourth step, according to the power fluctuation period, adjust the first data truncation duration, the second data truncation duration, the third data truncation duration, and the fourth data truncation duration to generate the first adjusted duration, the second adjusted duration, the third adjusted duration, and the fourth adjusted duration sequence.

[0038] As an example, the above-mentioned execution entity may determine the maximum value between the first data truncation duration and the power fluctuation period as the first adjustment duration, determine the maximum value between the second data truncation duration and the power fluctuation period as the second adjustment duration, determine the maximum value between the third data truncation duration and the power fluctuation period as the third adjustment duration, and determine the maximum value between each fourth data truncation duration and the power fluctuation period as the fourth adjustment duration to obtain a fourth adjustment duration sequence.

[0039] Step 5, generate the first data truncation time period, the second data truncation time period, the third data truncation time period, and the fourth data truncation time period sequence according to the above-mentioned first adjustment duration, the second adjustment duration, the third adjustment duration, the fourth adjustment duration, and the above-mentioned current time.

[0040] As an example, the above-mentioned execution entity may perform time period truncation for the current time according to the correspondence between the current time and the first adjustment duration to generate the first data truncation time period. Similarly, for the generation of the second data truncation time period, the third data truncation time period, and the fourth data truncation time period sequence, reference may be made to the generation of the first data truncation time period.

[0041] Step 1023, generate a first power data subsequence corresponding to the first data truncation time period, a second power data subsequence corresponding to the second data truncation time period, a third power data subsequence corresponding to the third data truncation time period, and a fourth power data subsequence set corresponding to the fourth data truncation time period according to the above-mentioned target power data sequence.

[0042] In some embodiments, the above-mentioned execution entity may generate a first power data subsequence corresponding to the first data interception time period, a second power data subsequence corresponding to the second data interception time period, a third power data subsequence corresponding to the third data interception time period, and a fourth power data subsequence set corresponding to the fourth data interception time period according to the above-mentioned target power data sequence. Among them, there is a one-to-one correspondence between the time in the first data interception time period and the first power data in the first power data subsequence. The first power data subsequence may characterize the operation of the power equipment during the first data interception time period. There is a one-to-one correspondence between the time in the second data interception time period and the second power data in the second power data subsequence. The second power data subsequence may characterize the operation of the power equipment during the second data interception time period. There is a one-to-one correspondence between the time in the third data interception time period and the third power data in the third power data subsequence. The third power data subsequence may characterize the operation of the power equipment during the third data interception time period. There is a one-to-one correspondence between the time in the fourth data interception time period sequence and the fourth power data in the fourth power data subsequence set. The fourth power data subsequence set may characterize the operation of the power equipment during the fourth data interception time period sequence.

[0043] As an example, the above-mentioned execution entity may extract the data sets under the first data interception time period, the second data interception time period, the third data interception time period, and the fourth data interception time period sequence from the above-mentioned target power data sequence, and use them as the first power data subsequence, the second power data subsequence, the third power data subsequence, and the fourth power data subsequence set respectively.

[0044] Step 1024, generate device anomaly detection information for the above-mentioned power equipment by using the pre-trained device anomaly detection model according to the above-mentioned first power data subsequence, the above-mentioned second power data subsequence, the above-mentioned third power data subsequence, and the above-mentioned fourth power data subsequence set.

[0045] In some embodiments, the above-mentioned execution entity may generate device anomaly detection information for the above-mentioned power device according to the above-mentioned first power data subsequence, the above-mentioned second power data subsequence, the above-mentioned third power data subsequence, and the above-mentioned fourth power data subsequence set by using a pre-trained device anomaly detection model. Among them, the device anomaly detection model may be a neural network model for generating device anomaly detection information. In practice, the device anomaly detection model may be trained by the conventional backpropagation method. The device anomaly detection information may be information indicating whether the power device has an abnormal operation condition. In practice, the device anomaly detection information may be in the form of a score. The higher the value, the higher the probability that the power device has an abnormal problem. For example, the device anomaly detection model includes: multiple encoding layers, a feature splicing layer, a convolutional layer, and an output layer based on a time series neural network model.

[0046] As an example, first, the above-mentioned execution entity may respectively perform data vectorization processing on the above-mentioned first power data subsequence, the above-mentioned second power data subsequence, the above-mentioned third power data subsequence, and the above-mentioned fourth power data subsequence set to generate a first power vector subsequence, the above-mentioned second power vector subsequence, the above-mentioned third power vector subsequence, and the above-mentioned fourth power vector subsequence set. Then, the first power vector subsequence, the above-mentioned second power vector subsequence, the above-mentioned third power vector subsequence, and the above-mentioned fourth power vector subsequence set are spliced to generate a power splicing vector. Finally, the power splicing vector is input into the device anomaly detection model to generate device anomaly detection information.

[0047] In some optional implementation manners of some embodiments, the generating device anomaly detection information for the above-mentioned power device according to the above-mentioned first power data subsequence, the above-mentioned second power data subsequence, the above-mentioned third power data subsequence, and the above-mentioned fourth power data subsequence set by using a pre-trained device anomaly detection model may include the following steps:

[0048] In the first step, the above-mentioned second power data subsequence is removed from the above-mentioned first power data subsequence to obtain a power data subsequence after removal.

[0049] In the second step, the above-mentioned power data subsequence after removal is input into the first time series feature extraction model included in the above-mentioned device anomaly detection model to generate time series feature information corresponding to the above-mentioned power data subsequence after removal as the first time series feature information. Among them, the first time series feature extraction model may be a neural network model for extracting time series feature information. For example, the first time series feature extraction model may be a first number layer recurrent neural network model.

[0050] In the third step, input the above first temporal feature information into the second temporal feature extraction model included in the above device anomaly detection model to generate the temporal feature information corresponding to the above first power data subsequence as the second temporal feature information. Among them, the second temporal feature extraction model can be a neural network model for extracting temporal feature information. For example, the first temporal feature extraction model can be a second-number-layer recurrent neural network model.

[0051] In the fourth step, input the above second power data subsequence into the above second temporal feature extraction model to generate the temporal feature information corresponding to the above second power data subsequence as the third temporal feature information.

[0052] In the fifth step, splice the above first temporal feature information and the above second temporal feature information to generate the first splicing information.

[0053] In the sixth step, splice the above first temporal feature information and the above third temporal feature information to generate the second splicing information.

[0054] In the seventh step, splice the above first splicing information and the above second splicing information in the depth direction to generate the third splicing information. Among them, the depth direction can be the depth direction of a matrix or an image.

[0055] In the eighth step, input the above third splicing information into the attention mechanism model included in the above device anomaly detection model to generate the future power data subsequence corresponding to the target future time period. For example, the attention mechanism model can be a multi-head attention mechanism model. Among them, the future power data subsequence can be the future power data corresponding to each future time point within the target future time period.

[0056] In the ninth step, splice the above future power data subsequence and the above second power data subsequence to generate the first future power data sequence.

[0057] In the tenth step, generate at least one data sequence index information corresponding to the above third power data subsequence as at least one first data sequence index information. Among them, the data sequence index information can represent the index content of the third power data subsequence under the corresponding sequence index. The sequence index can represent the feature performance of the third power data subsequence in a certain aspect. For example, the data sequence index information can include: increase rate, increase amount, decrease rate, decrease amount, fluctuation amount, average amount.

[0058] In the eleventh step, generate at least one data sequence index information corresponding to the above first future power data sequence as at least one second data sequence index information. The specific implementation method can refer to the generation of the first data sequence index information.

[0059] In the twelfth step, in response to determining that the index information difference between the at least one first data sequence index information and the at least one second data sequence index information satisfies a first preset index condition, determine the index information between the data subsequences corresponding to the fourth power data subsequence set as the index information between the first data subsequences. The first preset index condition may be that the index difference corresponding to each sequence index is greater than the corresponding preset difference.

[0060] In the thirteenth step, add the first future power data sequence to the fourth power data subsequence set to generate a first added power data subsequence set.

[0061] In the fourteenth step, determine the index information between the data subsequences corresponding to the first added power data subsequence set as the index information between the second data subsequences.

[0062] In the fifteenth step, in response to determining that the index information difference between the index information of the first data subsequences and the index information of the second data subsequences satisfies a second preset index condition, input the first future power data sequence into the first device anomaly detection information generation model included in the device anomaly detection model to generate first device anomaly detection information. The second preset index condition may be that the index difference corresponding to each sequence index is less than or equal to the corresponding preset difference. The first device anomaly detection information generation model may be a neural network model for generating device anomaly detection information. For example, the first device anomaly detection information generation model may be an LSTM model. And the first device anomaly detection information generation model may be trained together with the second device anomaly detection information generation model. The second device anomaly detection information generation model may be a neural network model for generating device anomaly detection information. The network structure between the first device anomaly detection information generation model and the second device anomaly detection information generation model may be the same or different, and is specifically customized according to the scenario.

[0063] In the sixteenth step, splice the future power data subsequence and the first power data subsequence to generate a second future power data sequence.

[0064] In the seventeenth step, input the second future power data sequence into the second device anomaly detection information generation model included in the device anomaly detection model to generate second device anomaly detection information.

[0065] In the eighteenth step, obtain the model output weights corresponding to the first device anomaly detection information generation model and the model output weights corresponding to the second device anomaly detection information generation model, and use them as the first model output weight and the second model output weight respectively.

[0066] The nineteenth step is to generate the device anomaly detection information based on the output weights of the first model, the output weights of the second model, the first device anomaly detection information, and the second device anomaly detection information mentioned above.

[0067] As an example, the execution entity can perform a weighted sum processing on the output weights of the first model, the output weights of the second model, the first device anomaly detection information, and the second device anomaly detection information to generate the device anomaly detection information.

[0068] Optionally, the steps further include:

[0069] The first step is to, in response to determining that the index information difference between the at least one first data sequence index information and the at least one second data sequence index information does not meet the first preset index condition, determine a candidate power data subsequence corresponding to the first historical time period from the third power data subsequence as the first candidate power data subsequence. Among them, the first historical time period has a corresponding same-date relationship with the target future time period.

[0070] The second step is to, for each fourth power data subsequence in the fourth power data subsequence set, determine a candidate power data subsequence corresponding to the second historical time period from the fourth power data subsequence as the second candidate power data subsequence. Among them, the second historical time period has a corresponding same-date relationship with the target future time period.

[0071] The third step is to generate at least one data sequence index information corresponding to the first candidate power data subsequence as at least one third data sequence index information.

[0072] The fourth step is to generate at least one data sequence index information corresponding to the future power data subsequence as at least one fourth data sequence index information.

[0073] The fifth step is to, in response to determining that the index information difference between the at least one third data sequence index information and the at least one fourth data sequence index information meets the first preset index condition, determine the index information between the data subsequences corresponding to the fourth power data subsequence set as the first index information between data subsequences.

[0074] The sixth step is to add the first future power data sequence to the fourth power data subsequence set to generate an added power data subsequence set.

[0075] The seventh step is to determine the index information between the data subsequences corresponding to the added power data subsequence set as the second index information between data subsequences.

[0076] In the eighth step, in response to determining that the index information difference between the above-mentioned first inter-data-subsequence index information and the above-mentioned second inter-data-subsequence index information does not meet the second preset index condition, add the above-mentioned future power data subsequence to the obtained second candidate power data subsequence set to generate a third added power data subsequence set.

[0077] In the ninth step, determine the inter-data-subsequence index information corresponding to the above-mentioned second candidate power data subsequence set as the third inter-data-subsequence index information.

[0078] In the tenth step, determine the inter-data-subsequence index information corresponding to the above-mentioned third added power data subsequence set as the fourth inter-data-subsequence index information.

[0079] In the eleventh step, in response to determining that the index information difference between the above-mentioned third inter-data-subsequence index information and the above-mentioned fourth inter-data-subsequence index information meets the second preset index condition, input the above-mentioned first future power data sequence into the first device anomaly detection information generation model included in the above-mentioned device anomaly detection model to generate first device anomaly detection information.

[0080] In the twelfth step, splice the above-mentioned future power data subsequence and the above-mentioned first power data subsequence to generate a second future power data sequence.

[0081] In the thirteenth step, input the above-mentioned second future power data sequence into the second device anomaly detection information generation model included in the above-mentioned device anomaly detection model to generate second device anomaly detection information.

[0082] In the fourteenth step, obtain the model output weight corresponding to the above-mentioned first device anomaly detection information generation model and the model output weight corresponding to the above-mentioned second device anomaly detection information generation model, and use them as the first model output weight and the second model output weight respectively.

[0083] In the fifteenth step, generate the above-mentioned device anomaly detection information according to the above-mentioned first model output weight, the above-mentioned second model output weight, the above-mentioned first device anomaly detection information, and the above-mentioned second device anomaly detection information.

[0084] As an example, the above-mentioned execution subject may perform a weighted summation process on the above-mentioned first model output weight, the above-mentioned second model output weight, the above-mentioned first device anomaly detection information, and the above-mentioned second device anomaly detection information to generate device anomaly detection information.

[0085] In step 1025, in response to determining that the above-mentioned device anomaly detection information indicates that the above-mentioned power equipment is operating abnormally, determine the device anomaly cause information and the device impact range information corresponding to the above-mentioned power equipment.

[0086] In some embodiments, in response to determining that the above device anomaly detection information characterizes an anomaly in the operation of the above power device, the above execution entity may determine the device anomaly cause information and the device impact scope information corresponding to the above power device. In practice, when the score corresponding to the device anomaly detection information is greater than 70 points, it characterizes an anomaly in the operation of the power device. The device anomaly cause information may be the reason for the anomaly in the power device. The device impact scope information may be the regional scope where the power transmission is affected due to the anomaly of the device.

[0087] As an example, the above execution entity may generate the above device anomaly cause information according to the target power data sequence by using a power device operation anomaly cause generation model. In practice, the power device operation anomaly cause generation model may be a classification model for generating device anomaly cause information. For example, the power device operation anomaly cause generation model may be a support vector machine. The above execution entity may obtain a query power device association graph. Then, according to the device anomaly cause information, determine the associated electronic devices affecting the operation. Next, by traversing the associated electronic devices in the power device association graph, determine the set of affected power devices. Finally, generate the device impact scope information according to the set of affected power devices.

[0088] Step 1026, generate device operation summary information for the above power device according to the above device anomaly cause information, the above target power data sequence, and the above device impact scope information.

[0089] In some embodiments, the above execution entity may generate device operation summary information for the above power device according to the above device anomaly cause information, the above target power data sequence, and the above device impact scope information. Among them, the device operation summary information may be the information obtained by summarizing various data during the operation of the power device.

[0090] As an example, the above execution entity may generate device operation summary information with the device identifier corresponding to the power device as the key and the corresponding contents of the above device anomaly cause information, the above target power data sequence, and the above device impact scope information as the values.

[0091] In some alternative implementation manners of some embodiments, the generating device operation summary information for the above power device according to the above device anomaly cause information, the above target power data sequence, and the above device impact scope information may include the following steps:

[0092] First step, determine the power data trend graph corresponding to the above target power data sequence. Among them, the power data trend graph may be a graph characterizing the change trend of the target power data sequence in at least one power feature.

[0093] Step 2: Obtain the abnormal maintenance status, abnormal maintenance time, and corresponding real-time maintenance video of the above-mentioned power equipment. Among them, the abnormal maintenance status can be information indicating whether the current power equipment is in a maintenance state. That is, the abnormal maintenance status can be one of the following: in a maintenance state, not in a maintenance state. The abnormal maintenance time can be the time required for the successful maintenance of the current power equipment. The real-time maintenance video can be a video of the real-time maintenance process of the power equipment.

[0094] Step 3: Generate a video link corresponding to the above real-time maintenance video. Among them, the video link can be the opening link corresponding to the real-time maintenance video.

[0095] Step 4: Concatenate the above device abnormal cause information, the above target power data sequence, the above device influence range information, the above abnormal maintenance status, and the above video link according to a predetermined format to obtain the above device operation summary information.

[0096] Step 103: According to the obtained device operation summary information of each device, perform power operation anomaly display for each of the above power equipment, and perform alarm processing on the power outage areas corresponding to each of the above power equipment.

[0097] In some embodiments, the above execution entity can perform power operation anomaly display for each of the above power equipment according to the obtained device operation summary information of each device, and perform alarm processing on the power outage areas corresponding to each of the above power equipment.

[0098] As an example, the above execution entity can use the device operation summary information of each device as the device operation data of each power equipment and display the operation status of each power equipment on the target interface.

[0099] In some optional implementation manners of some embodiments, the above performing power operation anomaly display for each of the above power equipment according to the obtained device operation summary information of each device may include the following steps:

[0100] Step 1: According to the above device operation summary information of each device, determine the power operation impact information corresponding to each sub-region in the above target power region to obtain each power operation impact information. Among them, the power operation impact information can be information indicating the power operation status in the sub-region. The power operation impact information can be numerical information. The higher the corresponding value of the power operation impact information, the better the operation status in the corresponding sub-region.

[0101] As an example, for each sub-region, first, based on the summary information of the operation of each device, determine the power devices with abnormal characteristics in the sub-region to obtain a set of abnormal power devices. Then, determine the influence coefficient corresponding to each power device in the set of abnormal power devices to obtain a set of influence coefficients. Among them, the influence coefficient can represent the importance of the normal operation of the power device. Finally, add up the various influence coefficients in the set of influence coefficients to generate a summed value as the power operation influence information.

[0102] In the second step, based on the above-mentioned various power operation influence information and the above-mentioned summary information of the operation of each device, determine the rendering method corresponding to each power device and the rendering method corresponding to each sub-region. Among them, the rendering methods include: a transparent rendering method and a color rendering method. Among them, the transparent rendering method can be a method of performing semi-transparent rendering processing on a power device or a sub-region on the digital twin model corresponding to the target power region. The color rendering method can be a method of performing color rendering processing on a power device or a sub-region on the digital twin model corresponding to the target power region.

[0103] As an example, the above-mentioned execution entity can obtain a first association table representing the correspondence between the device abnormal cause information and the rendering method, and determine the rendering method corresponding to each power device according to the summary information of the operation of each device. The above-mentioned execution entity can obtain a second association table representing the correspondence between the power operation influence information and the rendering method, and determine the rendering method corresponding to each sub-region according to the various power operation influence information.

[0104] In the third step, perform corresponding rendering processing on each power device and each sub-region in the digital twin model corresponding to the above-mentioned target power region according to the rendering method corresponding to each power device and the rendering method corresponding to each sub-region.

[0105] In some optional implementation manners of some embodiments, after step 103, the steps further include:

[0106] In the first step, in response to receiving device display information for a target power device in the above-mentioned digital twin model, pop up a device information category selection interface for the above-mentioned target power device. Among them, the target power device can be a device for which relevant device information is to be displayed. The device display information can be device information related to the target power device. The device information category selection interface can be an interface for selecting device information categories. The device information category selection interface displays multiple device information categories. The multiple device information categories can include: device cause category, device influence range category, abnormal repair status category, abnormal repair time category, and real-time repair video category.

[0107] Second step, in response to receiving device information category selection information for the above-mentioned device information category selection interface, determine the device information category corresponding to the above-mentioned device information category selection information as the target device information category. Among them, the device information category selection information may be information for selecting the target device information category.

[0108] Third step, obtain the category information corresponding to the above-mentioned target device information category from the device operation summary information corresponding to the above-mentioned target power device.

[0109] Fourth step, display the above-mentioned category information on the interface at the target position in the above-mentioned digital twin model. Among them, the target position may be a preset position.

[0110] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: Through the power outage area warning method of some embodiments of the present disclosure, the abnormal power operation conditions corresponding to the target power area can be accurately and efficiently displayed, so as to timely perform equipment maintenance on the abnormally operating power equipment. Specifically, the reason for the inaccuracy of the relevant power operation abnormal conditions is that there are a large number of power equipment in the power area. The efficiency of abnormal detection by manual detection is low, and the accuracy rate cannot be effectively guaranteed. In addition, it is also necessary to summarize and send the results of manual detection, wasting a lot of time, resulting in the inability to timely maintain the power equipment in the face of abnormally operating power equipment, and wasting power resources. Based on this, in the power outage area warning method of some embodiments of the present disclosure, first, obtain the power data sequence set corresponding to each power equipment in the target power area. Among them, each power equipment has a corresponding power data sequence. Here, the power data sequence set is used as the equipment basic data set to facilitate the subsequent accurate generation of equipment anomaly detection information corresponding to each equipment. Then, for each of the above-mentioned power equipment, the following generation steps are performed: The first step is to determine the power data sequence corresponding to the above-mentioned power equipment as the target power data sequence to serve as the operation data set corresponding to the power equipment, so as to facilitate the subsequent generation of equipment anomaly detection information according to the operation conditions reflected by the operation data set. The second step is to determine the first data truncation time period, the second data truncation time period, the third data truncation time period, and the fourth data truncation time period sequence corresponding to the above-mentioned power equipment for the current time. Among them, the above-mentioned first data truncation time period includes the above-mentioned second data truncation time period. The corresponding duration of the above-mentioned first data truncation time period is greater than the corresponding duration of the above-mentioned second data truncation time period. The above-mentioned fourth data truncation time period sequence includes the above-mentioned third data truncation time period. The central time corresponding to the above-mentioned third data truncation time period has the same date relationship as the above-mentioned current time. Here, different data truncation time periods are set for the current time to facilitate the subsequent power data subsequence sets under each data truncation time period. The third step is to generate the first power data subsequence corresponding to the above-mentioned first data truncation time period, the second power data subsequence corresponding to the above-mentioned second data truncation time period, the third power data subsequence corresponding to the above-mentioned third data truncation time period, and the fourth power data subsequence set corresponding to the above-mentioned fourth data truncation time period according to the above-mentioned target power data sequence, so as to obtain the power data of each period for the current time, adding more power data features to make the subsequent equipment anomaly detection more accurate. The fourth step is to accurately generate the equipment anomaly detection information for the above-mentioned power equipment by using the pre-trained equipment anomaly detection model according to the above-mentioned first power data subsequence, the above-mentioned second power data subsequence, the above-mentioned third power data subsequence, and the above-mentioned fourth power data subsequence set.In the fifth step, in response to determining that the above device anomaly detection information indicates an abnormal operation of the above power device, the device anomaly cause information and the device impact range information corresponding to the above power device can be accurately determined, so as to facilitate the subsequent determination of the comprehensive state during the operation process of the device corresponding to the power device. In the sixth step, according to the above device anomaly cause information, the above target power data sequence, and the above device impact range information, the device operation summary information for the above power device can be accurately generated. Finally, according to the obtained device operation summary information for each device, perform the display of power operation anomalies for the above power devices, and perform an alarm process on the power outage areas corresponding to the above power devices.

[0111] Further referring to Figure 2 , as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a power outage area alarm device, and these device embodiments correspond to Figure 1 the method embodiments shown, and the power outage area alarm device can be specifically applied to various electronic devices.

[0112] As Figure 2As shown in the figure, a power outage area warning device 200 includes: an acquisition unit 201, a generation unit 202, and an execution unit 203. Among them, the acquisition unit 201 is configured to acquire a set of power data sequences corresponding to each power device in a target power area, where each power device has a corresponding power data sequence; the generation unit 202 is configured to perform the following generation steps for each power device among the above-mentioned various power devices: determine the power data sequence corresponding to the power device as the target power data sequence; determine the first data truncation time period, the second data truncation time period, the third data truncation time period, and the fourth data truncation time period sequence for the current time corresponding to the power device, where the first data truncation time period includes the second data truncation time period, the corresponding duration of the first data truncation time period is greater than the corresponding duration of the second data truncation time period, the fourth data truncation time period sequence includes the third data truncation time period, and the central time corresponding to the third data truncation time period has the same date relationship as the current time; generate a first power data subsequence corresponding to the first data truncation time period, a second power data subsequence corresponding to the second data truncation time period, a third power data subsequence corresponding to the third data truncation time period, and a set of fourth power data subsequences corresponding to the fourth data truncation time period according to the target power data sequence; generate device anomaly detection information for the power device by using a pre-trained device anomaly detection model according to the first power data subsequence, the second power data subsequence, the third power data subsequence, and the set of fourth power data subsequences; in response to determining that the device anomaly detection information indicates that the power device is operating abnormally, determine the device anomaly cause information and the device impact range information corresponding to the power device; generate device operation summary information for the power device according to the device anomaly cause information, the target power data sequence, and the device impact range information; the execution unit 203 is configured to perform power operation anomaly display for each power device according to the obtained device operation summary information, and perform warning processing on the power outage areas corresponding to each power device.

[0113] It can be understood that the various units described in the power outage area warning device 200 correspond to the respective steps in the method described in the reference Figure 1 Therefore, the operations, features, and beneficial effects described above for the method also apply to the power outage area warning device 200 and the units included therein, and will not be repeated here.

[0114] Next, refer to Figure 3 , which shows a schematic structural diagram of an electronic device (e.g., an electronic device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3The electronic device shown is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present disclosure.

[0115] As Figure 3 shown, the electronic device 300 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 301, which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0116] Generally, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or wirelessly to exchange data. Although Figure 3 the electronic device 300 with various devices is shown, it should be understood that it is not required to implement or include all the shown devices. Instead, more or fewer devices may be implemented or included. Figure 3 Each block shown in

[0117] particular, according to some embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for performing the methods shown in the flowcharts. In such some embodiments, the computer program may be downloaded and installed from a network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the methods of some embodiments of the present disclosure are executed.

[0118] It should be noted that, in some embodiments of the present disclosure, the above-mentioned computer-readable medium may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0119] In some embodiments, the client and the server can communicate using any currently known or future-developed network protocol such as HTTP (HyperText Transfer Protocol), and can be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed network.

[0120] The above computer-readable medium may be included in the above electronic device; or it may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device is caused to: obtain a set of power data sequences corresponding to each power device in the target power area, where each power device has a corresponding power data sequence; for each of the above power devices, perform the following generation steps: determine the power data sequence corresponding to the power device as the target power data sequence; determine the first data truncation time period, the second data truncation time period, the third data truncation time period, and the fourth data truncation time period sequence for the current time corresponding to the power device, where the first data truncation time period includes the second data truncation time period, the duration corresponding to the first data truncation time period is greater than the duration corresponding to the second data truncation time period, the fourth data truncation time period sequence includes the third data truncation time period, and the central time corresponding to the third data truncation time period has the same date relationship with the current time; generate a first power data subsequence corresponding to the first data truncation time period, a second power data subsequence corresponding to the second data truncation time period, a third power data subsequence corresponding to the third data truncation time period, and a set of fourth power data subsequences corresponding to the fourth data truncation time period according to the target power data sequence; generate device anomaly detection information for the power device by using a pre-trained device anomaly detection model according to the first power data subsequence, the second power data subsequence, the third power data subsequence, and the set of fourth power data subsequences; in response to determining that the device anomaly detection information indicates that the power device is operating abnormally, determine the device anomaly cause information and the device impact range information corresponding to the power device; generate device operation summary information for the power device according to the device anomaly cause information, the target power data sequence, and the device impact range information; perform abnormal power operation display for each of the above power devices and alarm processing for the power outage areas corresponding to each of the above power devices according to the obtained device operation summary information for each device.

[0121] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it may be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0122] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations 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 diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0123] The units described in some embodiments of the present disclosure may be implemented in software or in hardware. The described units may also be provided in a processor. For example, it may be described as: a processor includes an acquisition unit, a generation unit, and an execution unit. Among them, the names of these units do not constitute a limitation on the unit itself in some cases. For example, the acquisition unit may also be described as "the unit for acquiring the set of power data sequences corresponding to each power device in the target power area".

[0124] 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: field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system on a chip (SOC), complex programmable logic devices (CPLD), and so on.

[0125] The above description is only some preferred embodiments of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A power outage area alarm method, comprising: Acquire a power data sequence set corresponding to each power device in the target power area, wherein each power device has a corresponding power data sequence; For each of the various electrical devices, the following generation steps are performed: determining a power data sequence corresponding to the power equipment as a target power data sequence; Determine a first data interception time period, a second data interception time period, a third data interception time period and a fourth data interception time period sequence corresponding to the electric power equipment for the current time, wherein the first data interception time period includes the second data interception time period, the corresponding duration of the first data interception time period is greater than the corresponding duration of the second data interception time period, the fourth data interception time period sequence includes the third data interception time period, and the central time corresponding to the third data interception time period has the same date relationship with the current time; According to the target power data sequence, generating a first power data subsequence, a second power data subsequence, a third power data subsequence and a fourth power data subsequence set in each data interception time period; Removing the second power data subsequence from the first power data subsequence to obtain a post-removal power data subsequence; Inputting the removed power data subsequence into a first time series feature extraction model included in a device abnormality detection model to generate time series feature information corresponding to the removed power data subsequence as first time series feature information; Inputting the first time series feature information into a second time series feature extraction model included in the device abnormality detection model to generate time series feature information corresponding to the first power data subsequence as second time series feature information; Inputting the second power data subsequence into the second time series feature extraction model to generate time series feature information corresponding to the second power data subsequence as third time series feature information; splicing the first time series characteristic information and the second time series characteristic information to generate first splicing information; splicing the first time series characteristic information and the third time series characteristic information to generate second splicing information; Splicing the first splicing information and the second splicing information in a depth direction to generate third splicing information; Inputting the third splicing information into the attention mechanism model included in the device abnormality detection model to generate a future power data subsequence corresponding to the target future time period; Generate device abnormality detection information for the power device using a pre-trained device abnormality detection model according to the future power data subsequence, the second power data subsequence, the third power data subsequence, and the fourth power data subsequence set; In response to determining that the device abnormality detection information indicates that the power device is operating abnormally, determining device abnormality cause information and device impact range information corresponding to the power device; Generate equipment operation summary information for the power equipment according to the equipment abnormality cause information, the target power data sequence and the equipment impact range information; Based on the obtained summary information of the operation of each device, the abnormal power operation of each power device is displayed, and the alarm processing is performed on the power outage area corresponding to each power device.

2. The method according to claim 1, wherein: The performing of displaying power operation abnormality for each power device according to the obtained summary information of operation of each device includes: Determine the power operation impact information corresponding to each sub-area in the target power area according to the summary information of each device operation, and obtain each power operation impact information; Determine, according to the individual power operation impact information and the individual equipment operation summary information, a rendering mode corresponding to each power equipment and a rendering mode corresponding to each sub-area, wherein the rendering modes include: a transparent rendering mode and a color rendering mode; According to the rendering mode corresponding to each power device and the rendering mode corresponding to each sub-area, corresponding rendering processing is performed on each power device and each sub-area in the digital twin model corresponding to the target power area.

3. The method according to claim 1, wherein: The determining of a sequence of a first data interception time period, a second data interception time period, a third data interception time period and a fourth data interception time period corresponding to the electric power equipment for the current time includes: Determine the device type corresponding to the electric power device and the device location information; According to the device type and the area information of the device, obtaining a first data interception time, a second data interception time, a third data interception time and a fourth data interception time sequence corresponding to the power device from the target association table; Obtaining a power fluctuation period corresponding to the power equipment; According to the power fluctuation cycle, adjusting the first data interception duration, the second data interception duration, the third data interception duration, and the fourth data interception duration to generate a first adjustment duration, a second adjustment duration, a third adjustment duration, and a fourth adjustment duration sequence; A sequence of the first data interception time period, the second data interception time period, the third data interception time period and the fourth data interception time period is generated according to the first adjustment time period, the second adjustment time period, the third adjustment time period, the fourth adjustment time period and the current time.

4. The method according to claim 2, wherein: The generating of equipment operation summary information for the power equipment according to the equipment abnormality cause information, the target power data sequence and the equipment impact range information includes: Determine a power data trend graph corresponding to the target power data sequence; Obtaining the abnormal maintenance status, abnormal maintenance time and corresponding real-time maintenance video corresponding to the electric power equipment; Generate a video link corresponding to the real-time maintenance video; The equipment abnormality cause information, the target power data sequence, the equipment impact range information, the abnormal maintenance status and the video link are spliced ​​according to a predetermined format to obtain the equipment operation summary information.

5. The method according to claim 4, wherein: The method further comprises: In response to receiving device display information for a target power device in the digital twin model, popping up a device information category selection interface for the target power device; In response to receiving device information category selection information for the device information category selection interface, determining a device information category corresponding to the device information category selection information as a target device information category; Acquire category information corresponding to the target equipment information category from the equipment operation summary information corresponding to the target power equipment; The category information is displayed on an interface at a target location in the digital twin model.

6. The method according to claim 1, wherein: The generating of device abnormality detection information for the power device using a pre-trained device abnormality detection model according to the future power data subsequence, the second power data subsequence, the third power data subsequence, and the fourth power data subsequence set includes: splicing the future power data subsequence and the second power data subsequence to generate a first future power data sequence; generating at least one data sequence indicator information corresponding to the third power data subsequence as at least one first data sequence indicator information; generating at least one data sequence indicator information corresponding to the first future power data sequence as at least one second data sequence indicator information; In response to determining that the indicator information difference between the at least one first data sequence indicator information and the at least one second data sequence indicator information satisfies the first preset indicator condition, determining the inter-data subsequence indicator information corresponding to the fourth power data subsequence set as the first inter-data subsequence indicator information; adding the first future power data sequence to the fourth power data subsequence set to generate a first added power data subsequence set; Determine the inter-data subsequence indicator information corresponding to the first added power data subsequence set as the second inter-data subsequence indicator information; In response to determining that the indicator information difference between the indicator information between the first data subsequences and the indicator information between the second data subsequences satisfies a second preset indicator condition, inputting the first future power data sequence into a first device abnormality detection information generation model included in the device abnormality detection model to generate first device abnormality detection information; splicing the future power data subsequence and the first power data subsequence to generate a second future power data sequence; inputting the second future power data sequence into a second device abnormality detection information generation model included in the device abnormality detection model to generate second device abnormality detection information; Obtaining a model output weight corresponding to the first device abnormality detection information generation model and a model output weight corresponding to the second device abnormality detection information generation model, as the first model output weight and the second model output weight, respectively; The device abnormality detection information is generated according to the first model output weight, the second model output weight, the first device abnormality detection information and the second device abnormality detection information.

7. The method according to claim 6, wherein: The method further comprises: In response to determining that the indicator information difference between the at least one first data sequence indicator information and the at least one second data sequence indicator information does not meet the first preset indicator condition, determining a candidate power data subsequence corresponding to a first historical time period from the third power data subsequence as a first candidate power data subsequence, wherein the first historical time period has a same date correspondence relationship with the target future time period; For each fourth power data subsequence in the fourth power data subsequence set, determining a candidate power data subsequence corresponding to a second historical time period from the fourth power data subsequence as a second candidate power data subsequence, wherein the second historical time period has a same date correspondence relationship with the target future time period; generating at least one data sequence indicator information corresponding to the first candidate power data subsequence as at least one third data sequence indicator information; generating at least one data sequence indicator information corresponding to the future power data subsequence as at least one fourth data sequence indicator information; In response to determining that the indicator information difference between the at least one third data sequence indicator information and the at least one fourth data sequence indicator information satisfies the first preset indicator condition, determining the inter-data subsequence indicator information corresponding to the fourth power data subsequence set as the first inter-data subsequence indicator information; adding the first future power data sequence to the fourth power data subsequence set to generate an added power data subsequence set; Determine the data subsequence index information corresponding to the added power data subsequence set as the second data subsequence index information; In response to determining that the indicator information difference between the indicator information between the first data subsequences and the indicator information between the second data subsequences does not meet a second preset indicator condition, adding the future power data subsequence to the obtained second candidate power data subsequence set to generate a third added power data subsequence set; Determine the inter-data subsequence indicator information corresponding to the second candidate power data subsequence set as the third inter-data subsequence indicator information; Determine the inter-data subsequence indicator information corresponding to the third added power data subsequence set as the fourth inter-data subsequence indicator information; In response to determining that the indicator information difference between the indicator information between the third data subsequences and the indicator information between the fourth data subsequences satisfies a second preset indicator condition, inputting the first future power data sequence into a first device abnormality detection information generation model included in the device abnormality detection model to generate first device abnormality detection information; splicing the future power data subsequence and the first power data subsequence to generate a second future power data sequence; inputting the second future power data sequence into a second device abnormality detection information generation model included in the device abnormality detection model to generate second device abnormality detection information; Obtaining a model output weight corresponding to the first device abnormality detection information generation model and a model output weight corresponding to the second device abnormality detection information generation model, as the first model output weight and the second model output weight, respectively; The device abnormality detection information is generated according to the first model output weight, the second model output weight, the first device abnormality detection information and the second device abnormality detection information.

8. A power outage area alarm device, comprising: An acquisition unit is configured to acquire a power data sequence set corresponding to each power device in a target power area, wherein each power device has a corresponding power data sequence; A generating unit is configured to perform the following generating steps for each of the power devices: determining a power data sequence corresponding to the power device as a target power data sequence; determining a first data interception time period, a second data interception time period, a third data interception time period and a fourth data interception time period sequence corresponding to the power device for the current time, wherein the first data interception time period includes the second data interception time period, the corresponding duration of the first data interception time period is greater than the corresponding duration of the second data interception time period, the fourth data interception time period sequence includes the third data interception time period, and the central time corresponding to the third data interception time period is having the same date relationship as the current time; generating a first power data subsequence, a second power data subsequence, a third power data subsequence and a fourth power data subsequence set under each data interception time period according to the target power data sequence; removing the second power data subsequence from the first power data subsequence to obtain a removed power data subsequence; inputting the removed power data subsequence into a first time series feature extraction model included in a device abnormality detection model to generate time series feature information corresponding to the removed power data subsequence as the first time series feature information; inputting the first time series feature information into a second time series feature extraction model included in the device abnormality detection model , to generate the timing feature information corresponding to the first power data subsequence as the second timing feature information; input the second power data subsequence into the second timing feature extraction model to generate the timing feature information corresponding to the second power data subsequence as the third timing feature information; splice the first timing feature information and the second timing feature information to generate the first splicing information; splice the first timing feature information and the third timing feature information to generate the second splicing information; splice the first splicing information and the second splicing information in the depth direction to generate the third splicing information; input the third splicing information into the device abnormality detection model The attention mechanism model included in the model is used to generate a future power data subsequence corresponding to a target future time period; based on the future power data subsequence, the second power data subsequence, the third power data subsequence and the fourth power data subsequence set, using a pre-trained device abnormality detection model, generate device abnormality detection information for the power device; in response to determining that the device abnormality detection information represents abnormal operation of the power device, determine the device abnormality cause information and device impact range information corresponding to the power device; based on the device abnormality cause information, the target power data sequence and the device impact range information, generate device operation summary information for the power device; The execution unit is configured to perform power operation abnormality display for each power device according to the obtained summary information of the operation of each device, and to perform alarm processing on the power outage area corresponding to each power device.

9. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images