Abnormal supply-side alarm method, device, electronic device and computer-readable medium

Abstract

The embodiments of the present disclosure disclose an abnormal supply-side alarm method, device, electronic device and computer-readable medium. A specific implementation of the method includes: obtaining power business data of each power business; inputting power index information into a pre-trained target power index data generation model to obtain a target power index data set; sending the target power index data set to a monitoring terminal; receiving a target power verification index data set sent by the monitoring terminal; collecting the initial power data set of the supply side; classifying and processing the initial power data set to generate a basic power data set; identifying and processing the basic power data set and the target power verification index data set to generate an abnormal power data set; for each abnormal power data set in the abnormal power data set, performing an alarm process on the supply side corresponding to the abnormal power data set. This implementation can alarm some supply sides.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to an abnormal supply-side alarm method, device, electronic device, and computer-readable medium. Background Art

[0002] By giving an alarm to an abnormal supply end, an alarm can be given for abnormal behavior that occurs when the supply end generates power equipment (for example, the no-load current value of the power equipment is too high, the temperature for drying the power equipment is too high, etc.), so that the supply end can produce power equipment that meets user needs. At present, the usual method for giving an alarm to an abnormal supply end is: first, the supply end fills in the power index information list to obtain the power index information, and then compares the power data when the supply end produces the power equipment with the power index information by manual comparison, and the supply end corresponding to the power data that is less than the power index information is given an alarm.

[0003] However, the above method usually has the following technical problems:

[0004] First, the accuracy of the comparison results obtained through manual comparison is low, making it difficult to accurately issue alarms to the supply side, resulting in difficulty in issuing alarms to some supply sides;

[0005] Second, since there are too many items in the list of power index information to be filled in, the supplier may make mistakes when filling in the list of power index information, resulting in low accuracy of the power index information, which causes the supplier to spend time repeatedly checking the power index information;

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0007] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0008] Some embodiments of the present disclosure propose abnormal supply-side alarm methods, devices, electronic devices, and computer-readable media to solve one or more of the technical problems mentioned in the above background technology section.

[0009] In a first aspect, some embodiments of the present disclosure provide an abnormal supply-side alarm method, the method comprising: acquiring power business data of each power business to obtain a power business data set; in response to receiving power indicator information sent by the supply side, inputting the above power indicator information into a pre-trained target power indicator data generation model to obtain a target power indicator data set, wherein the target power indicator data set in the above target power indicator data set corresponds to the power business data in the above power business data set; sending the above target power indicator data set to a monitoring terminal to verify and update the above target power indicator data set to obtain a target power verification indicator data set; receiving the target power verification indicator data set sent by the above monitoring terminal Indicator data set; collecting the initial power data set from the supply end; based on the power business data set, classifying and processing the initial power data set to generate a basic power data set, wherein the basic power data set in the basic power data set corresponds to the power business data in the power business data set, and the basic power data in the basic power data set corresponds to the target power verification indicator data in the target power verification indicator data set; identifying and processing the basic power data set and the target power verification indicator data set to generate an abnormal power data set; for each abnormal power data set in the abnormal power data set, performing alarm processing on the supply end corresponding to the abnormal power data set.

[0010] In a second aspect, some embodiments of the present disclosure provide an abnormal supply-side alarm device, the device comprising: an acquisition unit, configured to acquire power business data of each power business, and obtain a power business data set; an input unit, configured to, in response to receiving power indicator information sent by the supply side, input the above power indicator information into a pre-trained target power indicator data generation model, and obtain a target power indicator data set, wherein the target power indicator data set in the above target power indicator data set corresponds to the power business data in the above power business data set; a sending unit, configured to send the above target power indicator data set to a monitoring terminal, so as to perform verification and update processing on the above target power indicator data set, and obtain a target power verification indicator data set; a receiving unit, configured to receive the target power verification data set sent by the above monitoring terminal. An indicator data set; a collection unit configured to collect the initial power data set of the above-mentioned supply end; a classification unit configured to classify the above-mentioned initial power data set based on the above-mentioned power business data set to generate a basic power data set, wherein the basic power data sets in the above-mentioned basic power data set correspond to the power business data in the above-mentioned power business data set, and the basic power data in the above-mentioned basic power data set correspond to the target power verification indicator data in the above-mentioned target power verification indicator data set; an identification unit configured to identify the above-mentioned basic power data set and the above-mentioned target power verification indicator data set to generate an abnormal power data set; an alarm unit configured to perform alarm processing on the supply end corresponding to the above-mentioned abnormal power data set for each abnormal power data set in the above-mentioned abnormal power data set.

[0011] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0012] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0013] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the abnormal supply-side alarm method of some embodiments of the present disclosure, an alarm can be given to some supply ends. Specifically, the reason why it is difficult to alarm some supply ends is that the accuracy of the comparison results obtained by manual comparison is low, and it is difficult to accurately alarm the supply end. Based on this, the abnormal supply-side alarm method of some embodiments of the present disclosure first obtains the power business data of each power business to obtain a power business data set. Secondly, in response to receiving the power indicator information sent by the supply end, the above-mentioned power indicator information is input into the pre-trained target power indicator data generation model to obtain a target power indicator data set. Thus, a relatively accurate target power indicator data set can be obtained through the target power indicator data generation model. Then, the above-mentioned target power indicator data set is sent to the monitoring terminal to verify and update the above-mentioned target power indicator data set to obtain a target power verification indicator data set. Thus, the target power indicator data set can be verified by the monitoring terminal to obtain a relatively accurate target power indicator data set. Then, the target power verification indicator data set sent by the above-mentioned monitoring terminal is received. Then, the initial power data set of the above-mentioned supply end is collected. Thus, a relatively accurate initial power data set can be directly collected. Afterwards, based on the above-mentioned power business data set, the above-mentioned initial power data set is classified and processed to generate a basic power data set. Thus, a basic power data set corresponding to the power business data set can be obtained, so as to subsequently compare the basic power data set with the target power verification index data set corresponding to the power business data set. Subsequently, the above-mentioned basic power data set and the above-mentioned target power verification index data set are identified and processed to generate an abnormal power data set. Thus, a relatively accurate abnormal power data set can be obtained. Finally, for each abnormal power data set in the above-mentioned abnormal power data set, an alarm is processed for the supply end corresponding to the above-mentioned abnormal power data set. Thus, through a relatively accurate abnormal power data set, an alarm can be processed for the supply end more accurately. Thus, an alarm can be issued to some supply ends. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0015] Figure 1 is a flow chart of some embodiments of the abnormal supply-side alarm method according to the present disclosure;

[0016] Figure 2is a schematic diagram of the structure of some embodiments of the abnormal supply end alarm device according to the present disclosure;

[0017] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0019] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure 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 of the functions performed by these devices, modules or units.

[0021] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and 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 used 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 accompanying drawings and in conjunction with embodiments.

[0024] refer to Figure 1 , shows a process 100 of some embodiments of the abnormal supply end alarm method according to the present disclosure. The abnormal supply end alarm method comprises the following steps:

[0025] Step 101: Acquire power business data of each power business to obtain a power business data set.

[0026] In some embodiments, the execution subject (e.g., a computing device) of the abnormal supply-side alarm method can obtain the power business data of each power business from the terminal device through a wired connection or a wireless connection to obtain a power business data set. Among them, the power business data in the above-mentioned power business data set may include but is not limited to at least one of the following: power business identification, supply-side identification, power equipment identification, and the number of power equipment. The power business identification can uniquely identify an electric business. The electric business can be, but is not limited to: obtaining electric equipment (obtaining electric equipment from the supply side), transporting electric equipment (sending electric equipment to the user terminal), etc. The electric equipment can be, but is not limited to: transformers, cables, current transformers, voltage transformers, reactors, etc. The supply-side identification can uniquely identify a supply side. The supply side can be a terminal that produces electric equipment. The power equipment identification can uniquely identify an electric equipment. The number of electric equipment can be the number of electric equipment. The user terminal can be a terminal that uses electric equipment.

[0027] Optionally, before step 102, the method further includes:

[0028] The first step is to send the access application information sent by the supply end to the monitoring terminal in response to receiving the access application information sent by the supply end.

[0029] In some embodiments, the above-mentioned execution entity may send the above-mentioned access application information to the monitoring terminal in response to receiving the access application information sent by the supply end. Among them, the access application information may indicate that the supply end wants to communicate with the above-mentioned execution entity. The monitoring terminal may be a terminal for monitoring the supply end. The access application information may include but is not limited to at least one of the following: supply end identification, historical proof information, camera information. The supply end identification can uniquely identify a supply end. The historical proof information may characterize the communication status between the supply end and the above-mentioned execution entity within a preset time period (the communication status may include: communication time, number of communications). For example, the preset time period may be the time period from three years before the current time to the current time. The camera information may indicate whether the supply end has installed a camera.

[0030] The second step is to receive the access status identifier sent by the monitoring terminal.

[0031] In some embodiments, the execution entity may receive the access status identifier sent by the monitoring terminal. Here, the monitoring terminal may generate the access status identifier by the following steps: First, receive the access application information sent by the execution entity. Secondly, in response to determining that the access application information satisfies the first access application condition, the abnormal access identifier is determined as the access status identifier. Among them, the first access application condition may be that the historical proof information or the power equipment quality information included in the access application information is empty, or the camera information indicates that the camera is not installed on the supply side. The abnormal access identifier may indicate that the monitoring terminal does not agree with the supply side to communicate with the execution entity. Next, in response to determining that the access application information satisfies the second access application condition, the normal access identifier is determined as the access status identifier. Among them, the second access application condition may be that the historical proof information and the power equipment quality information included in the access application information are not empty, and the camera information indicates that the camera is installed on the supply side. The normal access identifier may indicate that the monitoring terminal agrees with the supply side to communicate with the execution entity.

[0032] In a third step, in response to determining that the access status identifier satisfies a preset abnormal access condition, an alarm is performed on the supply end corresponding to the access status identifier.

[0033] In some embodiments, the execution subject may, in response to determining that the access status identifier satisfies a preset abnormal access condition, perform an alarm process on the supply end corresponding to the access status identifier. The preset abnormal access condition may be that the access status identifier is an abnormal access identifier. Here, the alarm process may be displaying a warning text or controlling a speaker to emit a prompt sound.

[0034] In the fourth step, in response to determining that the access status identifier satisfies a preset access consent condition, an access consent identifier is sent to a supply end corresponding to the access status identifier.

[0035] In some embodiments, the execution subject may send an access consent identifier to the supply end corresponding to the access state identifier in response to determining that the access state identifier satisfies a preset access consent condition. The preset access consent condition may be that the access state identifier is a normal access identifier. The access consent identifier may indicate that the monitoring terminal agrees to the supply end to communicate with the execution subject.

[0036] Step 102, in response to receiving the power indicator information sent by the supply end, input the power indicator information into a pre-trained target power indicator data generation model to obtain a target power indicator data set.

[0037] In some embodiments, the above-mentioned execution subject may, in response to receiving the power index information sent by the supply end, input the above-mentioned power index information into the pre-trained target power index data generation model to obtain the target power index data set. Among them, the target power index data set in the above-mentioned target power index data set may correspond to the power business data in the above-mentioned power business data set. Here, the above-mentioned power index information is sent to the above-mentioned execution subject after the supply end receives the access consent identifier sent by the above-mentioned monitoring terminal. The power index information can represent the power data expected when the supply end produces power equipment. The power index information may include but is not limited to at least one of the following: supply end identification, power equipment identification, target no-load current value of power equipment, and target drying temperature of power equipment. Among them, the target power index data in the above-mentioned target power index data set may be but is not limited to: supply end identification, power equipment identification, target no-load current value of power equipment (the current value expected when the power equipment is no-load), and target drying temperature of power equipment (the temperature expected when the power equipment is dried). For example, the power equipment identification can represent a transformer, the target no-load current value of the power equipment can be 50A (ampere), and the target drying temperature of the power equipment can be 100 degrees Celsius. The power indicator information may represent a picture or a document. The target power indicator data set may represent text power indicator information. The target power indicator data generation model may be a neural network model that takes power indicator information as input and takes the target power indicator data set as output.

[0038] Optionally, the pre-trained target power index data generation model may be trained through the following steps:

[0039] The first step is to obtain the training sample set.

[0040] In some embodiments, the execution subject may obtain the training sample set from the terminal device through a wired connection or a wireless connection. The training samples in the training sample set include: sample power indicator information and a sample target power indicator data set.

[0041] The second step is to determine the initial target power index data generation model.

[0042] In some embodiments, the execution subject may determine an initial target power index data generation model, wherein the initial target power index data generation model may include: an initial recognition model, an initial generation model, an initial attention model, and an initial classification model.

[0043] Here, the above-mentioned initial recognition model can be a model that takes sample power indicator information as input and takes initial recognition results as output. The above-mentioned initial recognition result can characterize the sample power indicator information as a picture or a document. The above-mentioned initial recognition model is used to: identify the initial recognition result according to the file suffix corresponding to the sample power identification information. For example, when the file suffix corresponding to the sample power identification information is a picture format such as PNG (Portable Network Graphics), JPEG (Joint Photographic Experts Group), etc., the initial recognition result can characterize the sample power indicator information as a picture. When the suffix corresponding to the sample power identification information is a file format such as word (document), excel (table), etc., the initial recognition result can characterize the sample power indicator information as a document.

[0044] The above-mentioned initial generation model can be a custom model that takes the sample power index information and the initial recognition result as input and takes the initial generation data set as output. The initial generation data in the initial generation data set may include but is not limited to at least one of the following: supply end identification, power equipment identification, power equipment target no-load current value, power equipment target drying temperature. The custom model can be divided into three layers:

[0045] The first layer may be an input layer for passing sample power indicator information and initial recognition results to the second layer.

[0046] The second layer may include: a judgment model, a first sub-model, and a second sub-model. The judgment model is used to: input the sample power indicator information into the first sub-model or the second sub-model according to the initial recognition result. For example, when the initial recognition result characterizes the sample power indicator information as a picture, the judgment model may input the sample power indicator information into the first sub-model. When the initial recognition result characterizes the sample power indicator information as a document, the judgment model may input the sample power indicator information into the second sub-model. The first sub-model may be a text recognition model that takes the sample power indicator information as input and the initial generated data set as output. The second sub-model may be a text recognition model that takes the sample power indicator information as input and the initial generated data set as output. For example, the first sub-model may include: a YOLO (You Only Look Once) model and a CRNN (Convolutional Recurrent Neural Network) model. For example, the second sub-model may include: a Faster-RCNN (Faster Regions with CNN features, a target detection network that uses CNN to extract features faster) model, and an RNN (Recurrent neural network) model.

[0047] The third layer may be an output layer, which is used to receive the output of the second layer as the output of the entire custom model.

[0048] The initial attention model may be an attention model that takes the initial generated data set as input and the initial power indicator data set as output. For example, the initial attention model may be a Self-Attention model.

[0049] The above-mentioned initial classification model can be a model that takes the initial power index data set as input and the initial target power index data set as output. The initial classification model is used to: determine each initial power index data corresponding to the same power business in the initial power index data set as the initial target power index data set, and obtain the initial target power index data set.

[0050] The third step is to select training samples from the above training sample set.

[0051] In some embodiments, the execution entity may select training samples from the training sample set. In practice, the execution entity may randomly select training samples from the training sample set.

[0052] The fourth step is to input the sample power index information included in the selected training samples into the above-mentioned initial recognition model to obtain the initial recognition result.

[0053] In some embodiments, the execution entity may input the sample power indicator information included in the selected training sample into the initial recognition model to obtain an initial recognition result.

[0054] In the fifth step, the sample power index information included in the selected training samples and the above initial recognition results are input into the above initial generation model to obtain an initial generation data set.

[0055] In some embodiments, the execution entity may input the sample power indicator information included in the selected training sample and the initial recognition result into the initial generation model to obtain an initial generation data set.

[0056] In the sixth step, the above-mentioned initial generated data set is input into the above-mentioned initial attention model to obtain an initial power indicator data set.

[0057] In some embodiments, the execution entity may input the initial generated data set into the initial attention model to obtain an initial power indicator data set.

[0058] The seventh step is to input the above initial power index data set into the above initial classification model to obtain an initial target power index data set.

[0059] In some embodiments, the execution entity may input the initial power indicator data set into the initial classification model to obtain an initial target power indicator data set.

[0060] In the eighth step, based on a preset loss function, a difference value between the initial target power index data set and the sample target power index data set included in the selected training samples is determined.

[0061] In some embodiments, based on a preset loss function, the execution subject may determine the difference between the initial target power index data set and the sample target power index data set included in the selected training sample. The preset loss function may be, but is not limited to, mean square error loss function (MSE), hinge loss function, cross entropy loss function (CrossEntropy), 0-1 loss function, absolute value loss function, log loss function, square loss function, exponential loss function, etc.

[0062] In a ninth step, in response to determining that the difference value is greater than or equal to a preset difference value, adjusting the network parameters of the initial target power index data generation model.

[0063] In some embodiments, in response to determining that the above difference value is greater than or equal to the preset difference value, the network parameters of the above initial target power index data generation model are adjusted. For example, the difference between the above difference value and the preset difference value can be calculated. On this basis, the error value is passed forward from the last layer of the model using back propagation, stochastic gradient descent and other methods to adjust the parameters of each layer. Of course, as needed, the network freezing (dropout) method can also be used to keep the network parameters of some layers unchanged and not adjust them. There is no limitation on this. Among them, there is no limitation on the setting of the preset difference value. For example, the preset difference value can be 0.1.

[0064] The optional technical content in step 102, as an inventive point of an embodiment of the present disclosure, solves the second technical problem mentioned in the background technology, "causing the supply side to spend time to check the power indicator information repeatedly". The factors that cause the supply side to spend time to check the power indicator information repeatedly are often as follows: due to the excessive content of the power indicator information list to be filled in, the supply side may make mistakes when filling in the power indicator information list, resulting in low accuracy of the obtained power indicator information. If the above factors are solved, the effect of reducing the waste of the supply side's checking time can be achieved. In order to achieve this effect, first, the format of the power indicator information uploaded by the supply side can be identified through the initial recognition model. Secondly, through the first sub-model included in the initial generation model, the power indicator information representing the picture can be identified and processed to generate an initial recognition result. Then, through the second sub-model included in the initial generation model, the power indicator information representing the document can be identified and processed to generate an initial recognition result. Therefore, through the initial generation model including the first sub-model and the second sub-model, the power indicator information of different formats can be identified and processed to generate a more accurate initial recognition result. Afterwards, the initial attention model can be used to more accurately identify the initial power indicator data set corresponding to the power business data set in the initial recognition result. Then, the initial power indicator data set can be classified by the initial classification model to obtain the initial target power indicator data set. As a result, the supply side can obtain more accurate power indicator data through the target power indicator data generation model by uploading power indicator information representing pictures or documents instead of filling in the power indicator information list. Thus, the situation where the supply side repeatedly checks the power indicator information can be reduced. Therefore, the waste of verification time on the supply side can be reduced.

[0065] Optionally, in response to determining that the difference value is less than the preset difference value, the initial target power indicator data generation model is determined as the trained target power indicator data generation model.

[0066] In some embodiments, the execution entity may determine the initial target power indicator data generation model as the trained target power indicator data generation model in response to determining that the difference value is less than the preset difference value.

[0067] Step 103: Send the target power indicator data set to the monitoring terminal to perform verification and update processing on the target power indicator data set to obtain a target power verification indicator data set.

[0068] In some embodiments, the execution subject may send the target power index data set to the monitoring terminal to perform verification and update processing on the target power index data set to obtain the target power verification index data set. The monitoring terminal may perform verification and update processing on the target power index data set to obtain the target power verification index data set through the following steps: First, the target power index data set is verified to generate a verification result. In practice, first, in response to determining that the target power index data set is the same as the preset specification data, the monitoring terminal may determine the information representing "verification success" as the verification result. Here, the preset specification data may be the same as the power index information. Second, in response to determining that the target power index data set is not the same as the preset specification data, the monitoring terminal may determine the information representing "verification failure" as the verification result. Then, in response to determining that the verification result represents verification failure, the target power index data set is updated. In practice, the monitoring terminal may update the target power index data set so that the target power index data set is the same as the preset specification data. Afterwards, the updated target power indicator data set is determined as the target power indicator data set to perform the verification process again. Finally, in response to determining that the verification result indicates that the verification is successful, the target power indicator data set is determined as the target power verification indicator data set.

[0069] Step 104: Receive a target power verification index data set sent by the monitoring terminal.

[0070] In some embodiments, the execution entity may receive a target power verification index data set sent by the monitoring terminal.

[0071] Step 105 , collecting the initial power data set from the supply side.

[0072] In some embodiments, the execution entity may collect the initial power data set of the supply side from the supply side database. The supply side database may be used to store the initial power data of the supply side. The initial power data in the initial power data set may include but is not limited to at least one of the following: supply side identification, power equipment identification, no-load current value of the power equipment, and drying temperature of the power equipment. The no-load current value of the power equipment may be the actual current value of the power equipment when it is no-loaded. The drying temperature of the power equipment may be the actual temperature when the power equipment is dried.

[0073] Step 106: Based on the power business data set, the initial power data set is classified to generate a power basic data set.

[0074] In some embodiments, the execution subject may classify the initial power data set based on the power business data set to generate a power basic data set. The power basic data set in the power basic data set may correspond to the power business data in the power business data set. The power basic data in the power basic data set may correspond to the target power verification index data in the target power verification index data set. In practice, the execution subject may determine the initial power data corresponding to the same power business in the initial power data set as a power basic data set to obtain a power basic data set.

[0075] Step 107 , identifying and processing the basic power data set and the target power verification index data set to generate an abnormal power data set.

[0076] In some embodiments, the execution entity may identify and process the basic power data set and the target power verification index data set to generate an abnormal power data set.

[0077] In practice, the execution subject may identify and process the basic power data set and the target power verification index data set through the following steps to generate an abnormal power data set:

[0078] In the first step, for each basic power data group in the above basic power data group set, the following comparison sub-steps are performed:

[0079] In the first comparison sub-step, the above-mentioned basic power data group and the target indicator data group are subjected to similarity comparison processing to generate a first data comparison result. Among them, the above-mentioned target indicator data group may be a target power verification indicator data group corresponding to the above-mentioned basic power data group in the above-mentioned target power verification indicator data group set. In practice, first, the above-mentioned execution subject may perform similarity comparison processing on the above-mentioned basic power data group and the above-mentioned target indicator data group through a first preset similarity algorithm to generate a first similarity. Then, the above-mentioned execution subject may perform similarity comparison processing on the above-mentioned basic power data group and the above-mentioned target indicator data group through a second preset similarity algorithm to generate a second similarity. Finally, the above-mentioned execution subject may determine the average value of the above-mentioned first similarity and the above-mentioned second similarity as the first data comparison result. For example, the above-mentioned first preset similarity algorithm may be a cosine similarity algorithm. The above-mentioned second preset similarity algorithm may be a Pearson similarity coefficient algorithm.

[0080] Therefore, a relatively accurate similarity between the basic power data group and the target power verification index data group can be obtained through two similarity algorithms.

[0081] The second comparison sub-step is to compare each basic power data in the above-mentioned basic power data group with the corresponding target indicator data in the above-mentioned target indicator data group to generate a second data comparison result and obtain a second data comparison result set. In practice, first, for each basic power data in the above-mentioned basic power data group, the above-mentioned execution subject can perform the following steps: First, in response to determining that the above-mentioned basic power data is less than the target indicator data corresponding to the above-mentioned basic power data in the above-mentioned target indicator data group, the information characterizing "normal data" is determined as the second data comparison result. Second, in response to determining that the above-mentioned basic power data is greater than or equal to the target indicator data corresponding to the above-mentioned basic power data in the above-mentioned target indicator data group, the information characterizing "abnormal data" is determined as the second data comparison result. Then, the above-mentioned execution subject can determine the determined respective second data comparison results as the second data comparison result set.

[0082] The third comparison sub-step is to determine the abnormal power data group based on the first data comparison result, the second data comparison result set and the basic power data group. In practice, first, in response to determining that the first data comparison result is less than the preset similarity, the execution subject may determine the basic power data group as an abnormal power data group. Then, in response to determining that the first data comparison result is greater than or equal to the preset similarity, the execution subject may determine each basic power data group in the basic power data group that meets the preset comparison condition as an abnormal power data group. Among them, the preset comparison condition may be that the second data comparison result corresponding to the basic power data characterizes the data abnormality. For example, the preset similarity may be 0.6.

[0083] Therefore, in addition to considering the relationship between the basic power data and the target power verification index data, the similarity between the basic power data group and the target power verification index data group is also considered, so that a more accurate abnormal power data group can be obtained.

[0084] In the second step, each of the obtained abnormal power data groups is determined as an abnormal power data group set.

[0085] Step 108 : for each abnormal power data group in the abnormal power data group set, performing alarm processing on the supply end corresponding to the abnormal power data group.

[0086] In some embodiments, the execution subject may perform an alarm process on the supply end corresponding to each abnormal power data group in the abnormal power data group set. The alarm process may be displaying warning text or controlling a speaker to emit a prompt sound. Here, the warning text may be the abnormal power data group.

[0087] Optionally, the above execution entity may further perform the following steps:

[0088] In the first step, for each basic power data group in the above basic power data group set, the following processing sub-steps are performed:

[0089] In the first sub-step, a target power verification indicator data group corresponding to the above-mentioned power basic data group is selected from the above-mentioned target power verification indicator data group set as the power verification indicator basic data group.

[0090] The second sub-step is, for each basic power data in the above-mentioned basic power data group, comparing the above-mentioned basic power data with the basic power verification index basic data corresponding to the above-mentioned basic power data in the above-mentioned basic power verification index basic data group to generate a comparison result. Among them, the above-mentioned comparison result can be a first comparison result, a second comparison result, a third comparison result or a fourth comparison result. The above-mentioned first comparison result can characterize that the basic power data is less than the product of the basic power verification index basic data and the first preset value. The above-mentioned second comparison result can characterize that the basic power data is greater than the product of the basic power verification index basic data and the first preset value, and is less than the product of the basic power verification index basic data and the second preset value. The above-mentioned third comparison result can characterize that the basic power data is greater than the product of the basic power verification index basic data and the second preset value, and is less than the basic power verification index basic data. The above-mentioned fourth comparison result can characterize that the basic power data is greater than the basic power verification index basic data. For example, the first preset value can be 0.5. The second preset value can be 0.7.

[0091] The third sub-step is to determine each initial power score corresponding to each generated comparison result. In practice, the above-mentioned execution subject can determine the initial power score through the following steps: First, in response to determining that the comparison result is the first comparison result, the first preset score is determined as the initial power score. Secondly, in response to determining that the comparison result is the second comparison result, the second preset score is determined as the initial power score. Then, in response to determining that the comparison result is the third comparison result, the third preset score is determined as the initial power score. Finally, in response to determining that the comparison result is the fourth comparison result, the fourth preset score is determined as the initial power score. For example, the first preset score may be 10. The second preset score may be 8. The third preset score may be 7. The fourth preset score may be 6.

[0092] In the fourth sub-step, the sum of the determined initial power scores is determined as the power score.

[0093] In the second step, the determined power scores are determined as a power score set.

[0094] The third step is to send the above power score set to the supply end corresponding to the above power score set.

[0095] In the fourth step, in response to receiving the power service score viewing request sent by the monitoring terminal, the power score set and the power score corresponding to the power service score viewing request are sent to the monitoring terminal. The power service score viewing request may indicate that the monitoring terminal wants to view the power score corresponding to the specified power service.

[0096] Optionally, the above execution entity may further perform the following steps:

[0097] The first step is to obtain the electricity video collection.

[0098] In some embodiments, the execution subject may obtain the power video set from a camera installed at the supply end through a wired connection or a wireless connection, wherein the power video in the power video set corresponds to the power basic data in the power basic data set.

[0099] In the second step, in response to receiving the power business video viewing request sent by the monitoring terminal, the power video set corresponding to the power business video viewing request is sent to the monitoring terminal. The power business video viewing request may indicate that the monitoring terminal wants to view the power video of the supply end corresponding to the specified power business.

[0100] The third step is to, in response to receiving the power service viewing request sent by the monitoring terminal, send the power service data corresponding to the power service viewing request in the power service data set to the monitoring terminal. The power service viewing request may indicate that the monitoring terminal wants to view the power service data of the specified power service.

[0101] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the abnormal supply-side alarm method of some embodiments of the present disclosure, an alarm can be given to some supply ends. Specifically, the reason why it is difficult to alarm some supply ends is that the accuracy of the comparison results obtained by manual comparison is low, and it is difficult to accurately alarm the supply end. Based on this, the abnormal supply-side alarm method of some embodiments of the present disclosure first obtains the power business data of each power business to obtain a power business data set. Secondly, in response to receiving the power indicator information sent by the supply end, the above-mentioned power indicator information is input into the pre-trained target power indicator data generation model to obtain a target power indicator data set. Thus, a relatively accurate target power indicator data set can be obtained through the target power indicator data generation model. Then, the above-mentioned target power indicator data set is sent to the monitoring terminal to verify and update the above-mentioned target power indicator data set to obtain a target power verification indicator data set. Thus, the target power indicator data set can be verified by the monitoring terminal to obtain a relatively accurate target power indicator data set. Then, the target power verification indicator data set sent by the above-mentioned monitoring terminal is received. Then, the initial power data set of the above-mentioned supply end is collected. Thus, a relatively accurate initial power data set can be directly collected. Afterwards, based on the above-mentioned power business data set, the above-mentioned initial power data set is classified and processed to generate a basic power data set. Thus, a basic power data set corresponding to the power business data set can be obtained, so as to subsequently compare the basic power data set with the target power verification index data set corresponding to the power business data set. Subsequently, the above-mentioned basic power data set and the above-mentioned target power verification index data set are identified and processed to generate an abnormal power data set. Thus, a relatively accurate abnormal power data set can be obtained. Finally, for each abnormal power data set in the above-mentioned abnormal power data set, an alarm is processed for the supply end corresponding to the above-mentioned abnormal power data set. Thus, through a relatively accurate abnormal power data set, an alarm can be processed for the supply end more accurately. Thus, an alarm can be issued to some supply ends.

[0102] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of an abnormal supply-side alarm device. These abnormal supply-side alarm device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the abnormal supply end alarm device can be specifically applied to various electronic devices.

[0103] like Figure 2As shown, the abnormal supply-side alarm device 200 of some embodiments includes: an acquisition unit 201, an input unit 202, a sending unit 203, a receiving unit 204, a collection unit 205, a classification unit 206, an identification unit 207 and an alarm unit 208. Among them, the acquisition unit 201 is configured to acquire the power business data of each power business and obtain a power business data set; the input unit 202 is configured to, in response to receiving the power indicator information sent by the supply end, input the above power indicator information into a pre-trained target power indicator data generation model to obtain a target power indicator data set, wherein the target power indicator data set in the above target power indicator data set corresponds to the power business data in the above power business data set; the sending unit 203 is configured to send the above target power indicator data set to the monitoring terminal to verify and update the above target power indicator data set to obtain a target power verification indicator data set; the receiving unit 204 is configured to receive the target power verification indicator data set sent by the above monitoring terminal; the collection unit 205 is Configured to collect the initial power data set of the above-mentioned supply end; the classification unit 206 is configured to classify the above-mentioned initial power data set based on the above-mentioned power business data set to generate a basic power data set, wherein the basic power data groups in the above-mentioned basic power data set correspond to the power business data in the above-mentioned power business data set, and the basic power data in the above-mentioned basic power data set corresponds to the target power verification index data in the above-mentioned target power verification index data set; the identification unit 207 is configured to identify and process the above-mentioned basic power data set and the above-mentioned target power verification index data set to generate an abnormal power data set; the alarm unit 208 is configured to perform alarm processing on the supply end corresponding to the above-mentioned abnormal power data set for each abnormal power data group in the above-mentioned abnormal power data set.

[0104] It is understandable that the various units recorded in the abnormal supply end alarm device 200 are similar to those in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the abnormal supply end alarm device 200 and the units contained therein, and will not be described in detail here.

[0105] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device (e.g., a computing device) 300 suitable for implementing some embodiments of the present disclosure. The electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (e.g., vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0106] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can 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 via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0107] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0108] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. 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 a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the 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 method of some embodiments of the present disclosure are executed.

[0109] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media 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, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device 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 a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0110] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0111] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently without being assembled into the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains the power business data of each power business to obtain a power business data set; in response to receiving the power indicator information sent by the supply end, inputs the above-mentioned power indicator information into a pre-trained target power indicator data generation model to obtain a target power indicator data set, wherein the target power indicator data set in the above-mentioned target power indicator data set corresponds to the power business data in the above-mentioned power business data set; sends the above-mentioned target power indicator data set to the monitoring terminal to verify and update the above-mentioned target power indicator data set to obtain a target power verification indicator data set; receives the power indicator information sent by the above-mentioned monitoring terminal; The target power verification index data set sent by the supply end; the initial power data set of the supply end is collected; based on the power business data set, the initial power data set is classified and processed to generate a basic power data set, wherein the basic power data set in the basic power data set corresponds to the power business data in the power business data set, and the basic power data in the basic power data set corresponds to the target power verification index data in the target power verification index data set; the basic power data set and the target power verification index data set are identified and processed to generate an abnormal power data set; for each abnormal power data set in the abnormal power data set, an alarm is processed for the supply end corresponding to the abnormal power data set.

[0112] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0113] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0114] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including an acquisition unit, an input unit, a sending unit, a receiving unit, a collection unit, a classification unit, an identification unit and an alarm unit. The names of these units do not constitute limitations on the units themselves in certain circumstances, for example, the acquisition unit may also be described as a "unit for acquiring power business data of each power business and obtaining a power business data set".

[0115] 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 (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0116] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. 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 a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. An abnormal supply-side alarm method, comprising: Acquire power business data of each power business to obtain a power business data set; In response to receiving the power indicator information sent by the supply end, the power indicator information is input into a pre-trained target power indicator data generation model to obtain a target power indicator data set, wherein the target power indicator data set in the target power indicator data set corresponds to the power business data in the power business data set; Sending the target power index data set to the monitoring terminal to perform verification and update processing on the target power index data set to obtain a target power verification index data set; Receiving a target power verification index data set sent by the monitoring terminal; Collecting an initial power data set from the supply end; Based on the power business data set, the initial power data set is classified and processed to generate a power basic data set, wherein the power basic data set in the power basic data set corresponds to the power business data in the power business data set, and the power basic data in the power basic data set corresponds to the target power verification index data in the target power verification index data set; Performing identification processing on the basic power data set and the target power verification index data set to generate an abnormal power data set; For each abnormal power data group in the abnormal power data group set, performing alarm processing on the supply end corresponding to the abnormal power data group; The identifying and processing the basic power data set and the target power verification index data set to generate an abnormal power data set includes: For each basic power data group in the basic power data group set, the following comparison steps are performed: Performing a similarity comparison process on the basic power data group and the target indicator data group to generate a first data comparison result, wherein the target indicator data group is a target power verification indicator data group corresponding to the basic power data group in the target power verification indicator data group set, including: performing a similarity comparison process on the basic power data group and the target indicator data group through a first preset similarity algorithm to generate a first similarity, performing a similarity comparison process on the basic power data group and the target indicator data group through a second preset similarity algorithm to generate a second similarity, and determining an average value of the first similarity and the second similarity as the first data comparison result; Performing a comparison process on each basic power data in the basic power data group and the corresponding target indicator data in the target indicator data group to generate a second data comparison result and obtain a second data comparison result set, including: for each basic power data in the basic power data group, performing the following steps: first, in response to determining that the basic power data is less than the target indicator data corresponding to the basic power data in the target indicator data group, determining information characterizing "normal data" as the second data comparison result; second, in response to determining that the basic power data is greater than or equal to the target indicator data corresponding to the basic power data in the target indicator data group, determining information characterizing "abnormal data" as the second data comparison result; and determining each determined second data comparison result as a second data comparison result set; Determining an abnormal power data group based on the first data comparison result, the second data comparison result set and the basic power data group, including: in response to determining that the first data comparison result is less than a preset similarity, determining the basic power data group as an abnormal power data group; in response to determining that the first data comparison result is greater than or equal to the preset similarity, determining each basic power data group in the basic power data group that meets a preset comparison condition as an abnormal power data group, wherein the preset comparison condition is that the second data comparison result corresponding to the basic power data characterizes that the data is abnormal; Determining each obtained abnormal power data group as an abnormal power data group set; The pre-trained target power index data generation model is trained through the following steps: Obtain a training sample set; Determine the initial target power index data generation model. The initial generation model is a custom model that takes sample power index information and initial recognition results as input and takes initial generation data set as output. The custom model is divided into three layers: the first layer is the input layer, which is used to pass the sample power index information and initial recognition results to the second layer. The second layer includes: a judgment model, a first sub-model and a second sub-model; the third layer is the output layer, which is used to receive the output of the second layer as the output of the entire custom model; Selecting training samples from the training sample set; Inputting the sample power index information included in the selected training sample into the initial recognition model to obtain an initial recognition result; Inputting the sample power index information included in the selected training sample and the initial recognition result into the initial generation model to obtain an initial generation data set; Inputting the initial generated data set into an initial attention model to obtain an initial power indicator data set; Inputting the initial power index data set into an initial classification model to obtain an initial target power index data set; Based on a preset loss function, determining a difference value between the initial target power index data set and the sample target power index data set included in the selected training sample; In response to determining that the difference value is greater than or equal to a preset difference value, a network parameter of the initial target power indicator data generation model is adjusted.

2. The method according to claim 1, wherein: Before, in response to receiving the power indicator information sent by the supply end, inputting the power indicator information into a pre-trained target power indicator data generation model to obtain a target power indicator data set, the method further includes: In response to receiving the access application information sent by the supply end, sending the access application information to the monitoring terminal; Receiving an access status identifier sent by the monitoring terminal; In response to determining that the access status identifier satisfies a preset abnormal access condition, performing an alarm process on a supply end corresponding to the access status identifier; In response to determining that the access status identifier satisfies a preset access consent condition, an access consent identifier is sent to a supply end corresponding to the access status identifier.

3. The method according to claim 1, wherein: The method further comprises: For each basic power data group in the basic power data group set, the following processing steps are performed: Selecting a target power verification index data group corresponding to the power basic data group from the target power verification index data group set as a power verification index basic data group; For each power basic data in the power basic data group, performing a comparison process on the power basic data and the power verification index basic data corresponding to the power basic data in the power verification index basic data group to generate a comparison result; Determine each initial power score corresponding to each generated comparison result; Determine the sum of the determined initial power scores as the power score; Determining the determined power scores as a power score set; Sending the power score set to a supply end corresponding to the power score set; In response to receiving the power service score viewing request sent by the monitoring terminal, the power score set and the power score corresponding to the power service score viewing request are sent to the monitoring terminal.

4. The method according to claim 1, wherein: The method further comprises: Acquire a power video set, wherein the power videos in the power video set correspond to the power basic data in the power basic data set; In response to receiving a power business video viewing request sent by the monitoring terminal, sending the power video in the power video set corresponding to the power business video viewing request to the monitoring terminal; In response to receiving the electric power service viewing request sent by the monitoring terminal, the electric power service data corresponding to the electric power service viewing request in the electric power service data set is sent to the monitoring terminal.

5. An abnormal supply-side alarm device, comprising: An acquisition unit is configured to acquire power service data of each power service to obtain a power service data set; An input unit is configured to, in response to receiving the power indicator information sent by the supply end, input the power indicator information into a pre-trained target power indicator data generation model to obtain a target power indicator data set, wherein the target power indicator data set in the target power indicator data set corresponds to the power business data in the power business data set; A sending unit, configured to send the target power indicator data set to a monitoring terminal, so as to perform verification and update processing on the target power indicator data set to obtain a target power verification indicator data set; A receiving unit, configured to receive a target power verification index data set sent by the monitoring terminal; A collection unit configured to collect an initial power data set of the supply end; a classification unit configured to classify the initial power data set based on the power business data set to generate a power basic data set, wherein the power basic data set in the power basic data set corresponds to the power business data in the power business data set, and the power basic data in the power basic data set corresponds to the target power verification index data in the target power verification index data set; an identification unit configured to perform identification processing on the basic power data set and the target power verification index data set to generate an abnormal power data set; An alarm unit is configured to perform an alarm process on a supply end corresponding to each abnormal power data group in the abnormal power data group set; Wherein, the identification unit is further configured to: For each basic power data group in the basic power data group set, the following comparison steps are performed: Performing a similarity comparison process on the basic power data group and the target indicator data group to generate a first data comparison result, wherein the target indicator data group is a target power verification indicator data group corresponding to the basic power data group in the target power verification indicator data group set, including: performing a similarity comparison process on the basic power data group and the target indicator data group through a first preset similarity algorithm to generate a first similarity, performing a similarity comparison process on the basic power data group and the target indicator data group through a second preset similarity algorithm to generate a second similarity, and determining an average value of the first similarity and the second similarity as the first data comparison result; Performing a comparison process on each basic power data in the basic power data group and the corresponding target indicator data in the target indicator data group to generate a second data comparison result and obtain a second data comparison result set, including: for each basic power data in the basic power data group, performing the following steps: first, in response to determining that the basic power data is less than the target indicator data corresponding to the basic power data in the target indicator data group, determining information characterizing "normal data" as the second data comparison result; second, in response to determining that the basic power data is greater than or equal to the target indicator data corresponding to the basic power data in the target indicator data group, determining information characterizing "abnormal data" as the second data comparison result; and determining each determined second data comparison result as a second data comparison result set; Determining an abnormal power data group based on the first data comparison result, the second data comparison result set and the basic power data group, including: in response to determining that the first data comparison result is less than a preset similarity, determining the basic power data group as an abnormal power data group; in response to determining that the first data comparison result is greater than or equal to the preset similarity, determining each basic power data group in the basic power data group that meets a preset comparison condition as an abnormal power data group, wherein the preset comparison condition is that the second data comparison result corresponding to the basic power data characterizes that the data is abnormal; Determining each obtained abnormal power data group as an abnormal power data group set; The pre-trained target power index data generation model is trained through the following steps: Obtain a training sample set; Determine the initial target power index data generation model. The initial generation model is a custom model that takes sample power index information and initial recognition results as input and takes initial generation data set as output. The custom model is divided into three layers: the first layer is the input layer, which is used to pass the sample power index information and initial recognition results to the second layer. The second layer includes: a judgment model, a first sub-model and a second sub-model; the third layer is the output layer, which is used to receive the output of the second layer as the output of the entire custom model; Selecting training samples from the training sample set; Inputting the sample power index information included in the selected training sample into the initial recognition model to obtain an initial recognition result; Inputting the sample power index information included in the selected training sample and the initial recognition result into the initial generation model to obtain an initial generation data set; Inputting the initial generated data set into an initial attention model to obtain an initial power indicator data set; Inputting the initial power index data set into an initial classification model to obtain an initial target power index data set; Based on a preset loss function, determining a difference value between the initial target power index data set and the sample target power index data set included in the selected training sample; In response to determining that the difference value is greater than or equal to a preset difference value, a network parameter of the initial target power indicator data generation model is adjusted.

6. 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 as claimed in any one of claims 1 to 4.

7. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images