Power material alarm method and device based on visualized digital intelligent cockpit

Abstract

The embodiments of the present disclosure disclose an electric power material alarm method and device based on a visualized digital cockpit. A specific implementation of the method includes: generating an electric power material prediction information set; inputting the electric power material prediction information set into a pre-trained first electric power material abnormal information generation model to obtain a first electric power material abnormal information set; encrypting the first electric power material abnormal information set; inspecting the first electric power material encrypted abnormal information and the second electric power material encrypted abnormal information corresponding to the second electric power material encrypted abnormal information to generate inspection result information; encrypting the inspection result information to generate encrypted inspection result information; determining the encrypted inspection result information as the target encrypted inspection result information; and performing an alarm on the supply end corresponding to the electric power material corresponding to the target encrypted inspection result information. This implementation can reduce the waste of waiting time of user terminals.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to a method and device for warning electric power materials based on a visualized digital cockpit. Background Art

[0002] The visualized digital cockpit can warn of a small number of power materials and increase the inventory of power materials in time so that power materials can be transported to the user terminal in time. At present, the usual way to warn of power materials is to warn the supply side of insufficient power materials after the user terminal sends a request for power materials, or to warn the supply side based on the user terminal's historical request for power materials, or to warn the supply side when the amount of power materials is less than a preset threshold.

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

[0004] First, when the power supply is insufficient, the supply side is warned, which requires time to produce power supplies and dispatch transportation equipment to transport power supplies to the user terminal, resulting in a waste of waiting time for the user terminal;

[0005] Second, the historical power material application request is used as the current power material application request, resulting in low accuracy of the power material application request, resulting in low accuracy of the power material quantity generated by the power material application request. When the power material quantity is insufficient, it will waste the waiting time of the user terminal.

[0006] Third, when the preset threshold is too large, some electric power materials will not be used for a long time, resulting in a waste of electric power materials.

[0007] 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

[0008] 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.

[0009] Some embodiments of the present disclosure propose an electric power material alarm method, device, electronic device and computer-readable medium based on a visualized digital cockpit to solve one or more of the technical problems mentioned in the above background technology section.

[0010] In a first aspect, some embodiments of the present disclosure provide an electric power material alarm method based on a visualized digital cockpit, the method comprising: acquiring basic electric power material information of each electric power material to obtain an electric power material basic information set; generating an electric power material prediction information set based on the above-mentioned electric power material basic information set; inputting the above-mentioned electric power material prediction information set into a pre-trained first electric power material abnormal information generation model to obtain a first electric power material abnormal information set; encrypting the above-mentioned first electric power material abnormal information set to generate a first electric power material encrypted abnormal information set, and sending the above-mentioned first electric power material encrypted abnormal information set to an associated monitoring terminal; in response to receiving any corresponding one of the above-mentioned monitoring terminals the second electric material encrypted abnormal information of the electric material, inspecting the first electric material encrypted abnormal information and the second electric material encrypted abnormal information corresponding to the second electric material encrypted abnormal information to generate inspection result information; encrypting the inspection result information to generate encrypted inspection result information, and sending the encrypted inspection result information to the monitoring terminal to generate inspection result confirmation information; in response to receiving the inspection result confirmation information sent by the monitoring terminal, determining the encrypted inspection result information as the target encrypted inspection result information; based on the target encrypted inspection result information, performing alarm processing on the supply end corresponding to the electric material corresponding to the target encrypted inspection result information.

[0011] In a second aspect, some embodiments of the present disclosure provide an electric material alarm device based on a visualized digital cockpit, the device comprising: an acquisition unit, configured to acquire basic electric material information of each electric material, and obtain an electric material basic information set; a generation unit, configured to generate an electric material prediction information set based on the above-mentioned electric material basic information set; an input unit, configured to input the above-mentioned electric material prediction information set into a pre-trained first electric material abnormal information generation model, and obtain a first electric material abnormal information set; a first encryption unit, configured to encrypt the above-mentioned first electric material abnormal information set to generate a first electric material encrypted abnormal information set, and send the above-mentioned first electric material encrypted abnormal information set to an associated monitoring terminal; a verification unit, configured to respond to receiving the above-mentioned monitoring The terminal sends the second electric material encrypted abnormal information corresponding to any electric material, and verifies the first electric material encrypted abnormal information and the second electric material encrypted abnormal information corresponding to the second electric material encrypted abnormal information to generate verification result information; the second encryption unit is configured to encrypt the verification result information to generate encrypted verification result information, and send the encrypted verification result information to the monitoring terminal to generate verification result confirmation information; the determination unit is configured to determine the encrypted verification result information as the target encrypted verification result information in response to receiving the verification result confirmation information sent by the monitoring terminal; the alarm unit is configured to perform alarm processing on the supply end corresponding to the electric material corresponding to the target encrypted verification result information based on the target encrypted verification result information.

[0012] 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.

[0013] 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.

[0014] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the electric power material alarm method based on the visualized digital cockpit of some embodiments of the present disclosure, the waiting time of the user terminal can be reduced. Specifically, the reason for wasting the waiting time of the user terminal is that the alarm is only given to the supply side when the electric power material is insufficient, and the supply side needs to consume time to produce electric power materials and time to dispatch transportation equipment to transport electric power materials to the user terminal. Based on this, the electric power material alarm method based on the visualized digital cockpit of some embodiments of the present disclosure first obtains the basic information of electric power materials for each electric power material to obtain a basic information set of electric power materials. Secondly, based on the above basic information set of electric power materials, a prediction information set of electric power materials is generated. Thus, a prediction information set of electric power materials representing the application request of the user terminal for electric power materials can be predicted. Then, the above prediction information set of electric power materials is input into the pre-trained first abnormal information generation model of electric power materials to obtain the first abnormal information set of electric power materials. Thus, the first abnormal information of electric power materials representing the lack of electric power materials can be identified by the first abnormal information generation model of electric power materials. Next, the first power material abnormal information set is encrypted to generate the first power material encrypted abnormal information set, and the first power material encrypted abnormal information set is sent to the associated monitoring terminal. Thus, the first power material abnormal information set can be encrypted to avoid leakage of the first power material abnormal information set during transmission. Then, in response to receiving the second power material encrypted abnormal information corresponding to any power material sent by the monitoring terminal, the first power material encrypted abnormal information corresponding to the second power material encrypted abnormal information and the second power material encrypted abnormal information are inspected to generate inspection result information. Thus, the first power material encrypted abnormal information and the historical second power material encrypted abnormal information can be compared. Then, the inspection result information is encrypted to generate encrypted inspection result information, and the encrypted inspection result information is sent to the monitoring terminal to generate inspection result confirmation information. Thus, whether the first power material encrypted abnormal information is correct can be further determined by the monitoring terminal. Thereafter, in response to receiving the inspection result confirmation information sent by the monitoring terminal, the encrypted inspection result information is determined as the target encrypted inspection result information. Finally, based on the target encryption test result information, the supply end corresponding to the power material corresponding to the target encryption test result information is alarmed. Thus, the supply end corresponding to a small number of power materials can be alarmed. Therefore, the supply end can be alarmed by predicting the demand for power materials at the user terminal to produce power materials in advance. Thus, when the user terminal needs power materials, the transportation equipment can be dispatched in time to transport power materials to the user terminal. Furthermore, the waiting time of the user terminal can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] 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.

[0016] Figure 1 is a flowchart of some embodiments of the power material alarm method based on the visualized digital intelligent cockpit according to the present disclosure;

[0017] Figure 2 It is a structural schematic diagram of some embodiments of the electric power material warning device based on the visualized digital intelligent cockpit according to the present disclosure;

[0018] 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

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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".

[0023] 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.

[0024] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0025] refer to Figure 1 , shows a process 100 of some embodiments of the electric power material alarm method based on a visualized digital intelligent cockpit according to the present disclosure. The electric power material alarm method based on a visualized digital intelligent cockpit includes the following steps:

[0026] Step 101, acquiring basic information of each electric material to obtain a basic information set of electric materials.

[0027] In some embodiments, the execution subject of the electric material alarm method based on the visualized digital cockpit can obtain the basic information of each electric material from the terminal device through a wired connection or a wireless connection to obtain a basic information set of electric materials. Among them, the basic information of electric materials in the basic information set of electric materials may include but is not limited to at least one of the following: electric material identification, electric material name, supply end identification, electric material quantity, electric material related information, supply end related information. Here, the electric material identification can uniquely identify an electric material. The electric material can be but is not limited to: a transformer, a generator, a mutual inductor, etc. The supply end identification can uniquely identify a supply end. The supply end can be a terminal for producing electric materials. A supply end can correspond to at least one electric material. The number of electric materials can be the number of current electric materials. The information related to electric materials can include but is not limited to at least one of the following: the production time of electric materials, the rated power of electric materials, and the actual power of electric materials. The relevant information of the supply end can include but is not limited to at least one of the following: the address of the supply end, the production equipment of the supply end. Here, the production time of electric materials can be the time required for the supply end to produce an electric material once. The rated power of electric materials can be the maximum power of electric materials. The actual power of electric materials can be the power of electric materials when they are actually running. The supply side address may be the location of the supply side in the map coordinate system. The supply side production equipment may be equipment used by the supply side to produce power materials.

[0028] For example, the execution subject may be a visualized digital cockpit, so that the supply side can conveniently view the basic information of power materials through the visualized digital cockpit.

[0029] Step 102: Generate an electric power material prediction information set based on the electric power material basic information set.

[0030] In some embodiments, the execution entity may generate an electric power material prediction information set based on the electric power material basic information set.

[0031] In practice, based on the above basic information set of electric power materials, the above execution entity can generate the electric power material forecast information set through the following steps:

[0032] The first step is to identify and process each electric power material basic information in the above electric power material basic information set to generate electric power material identification information and obtain the electric power material identification information set.

[0033] In some embodiments, the above-mentioned execution subject may identify and process each electric material basic information in the above-mentioned electric material basic information set to generate electric material identification information and obtain an electric material identification information set. In practice, the above-mentioned execution subject may input each electric material basic information in the above-mentioned electric material basic information set into the attention model to generate electric material identification information and obtain an electric material identification information set. Among them, the above-mentioned attention model may be an attention model that takes the basic information of electric materials as input and the electric material identification information as output. For example, the attention model may be a self-attention model. The above-mentioned electric material identification information may include but is not limited to at least one of the following: electric material identification, electric material quantity, supply-side identification, supply-side production equipment, electric material production time, electric material rated power, and electric material actual power.

[0034] In some optional implementations of some embodiments, the execution subject may identify and process each electric material basic information in the electric material basic information set through the following sub-steps to generate electric material identification information:

[0035] The first sub-step is to perform capability analysis on the basic information of the above-mentioned power materials to generate a first analysis result. In practice, the above-mentioned execution entity may determine the corresponding basic information of the supply side in the basic information of the above-mentioned power materials as the first analysis result. The basic information of the supply side may include but is not limited to at least one of the following: power material identification, supply side identification, supply side address, and supply side production equipment.

[0036] The second sub-step is to perform production analysis on the basic information of the electric power materials to generate a second analysis result. In practice, the execution entity may determine the corresponding electric power material production information in the basic information of the electric power materials as the second analysis result. The electric power material production information may include but is not limited to at least one of the following: electric power material identification, electric power material production time, and electric power material quantity.

[0037] The third sub-step is to perform quality analysis on the basic information of the electric power materials to generate a third analysis result. In practice, the execution subject may determine the corresponding electric power material quality information in the basic information of the electric power materials as the third analysis result. The electric power material quality information may include but is not limited to at least one of the following: electric power material identification, electric power material rated power, and electric power material actual power.

[0038] The fourth sub-step is to determine the first analysis result, the second analysis result, and the third analysis result as electric power material identification information.

[0039] The second step is to perform data cleaning on the above-mentioned power material identification information set to generate a power material cleaning information set.

[0040] In some embodiments, the execution subject may perform data cleaning on the electric material identification information set to generate an electric material cleaning information set. In practice, the execution subject may remove empty information in the electric material identification information set to generate an electric material cleaning information set.

[0041] The third step is to encrypt each piece of electric power material cleaning information in the electric power material cleaning information set to generate encrypted electric power material cleaning information and obtain the encrypted electric power material cleaning information set.

[0042] In some embodiments, the execution subject may encrypt each electric material cleaning information in the electric material cleaning information set to generate electric material encrypted cleaning information and obtain an electric material encrypted cleaning information set. In practice, the execution subject may encrypt each electric material cleaning information in the electric material cleaning information set according to a pre-set encryption algorithm to generate electric material encrypted cleaning information and obtain an electric material encrypted cleaning information set. For example, the pre-set encryption algorithm may be, but is not limited to: AES (Advanced Encryption Standard) algorithm, ECC (Error Checking and Correcting) algorithm, MD5 (Message-Digest Algorithm 5) algorithm.

[0043] The fourth step is to respond to receiving a basic information viewing request sent by the associated supply end, and send the encrypted cleaning information of the above-mentioned power materials corresponding to each encrypted cleaning information of the above-mentioned power materials of the above-mentioned supply end to the above-mentioned supply end.

[0044] In some embodiments, the execution subject may respond to receiving a request for viewing basic information sent by an associated supply end, and send the encrypted cleaning information of the power materials corresponding to each encrypted cleaning information of the power materials of the supply end to the supply end. The request for viewing basic information may indicate that the supply end wants to view the basic information of the power materials. The associated supply end may be a terminal that produces power materials.

[0045] In the fifth step, for each piece of electric material cleaning information in the electric material cleaning information set, the electric material cleaning information is input into a pre-trained electric material prediction information generation model to obtain electric material prediction information.

[0046] In some embodiments, for each electric material cleaning information in the electric material cleaning information set, the execution subject may input the electric material cleaning information into a pre-trained electric material prediction information generation model to obtain the electric material prediction information. The electric material prediction information generation model may be a neural network model that takes the electric material cleaning information as input and the electric material prediction information as output. Here, the electric material prediction information may characterize the predicted situation of the electric material desired by the user terminal. The electric material prediction information may include but is not limited to at least one of the following: electric material identification, electric material prediction quantity.

[0047] In the sixth step, each generated electric power material forecast information is determined as an electric power material forecast information set.

[0048] In some embodiments, the execution entity may determine each generated electric power material forecast information as an electric power material forecast information set.

[0049] Optionally, the pre-trained electric power material forecast information generation model may be trained by the following steps:

[0050] The first step is to obtain the training sample set.

[0051] In some embodiments, the execution subject may obtain a training sample set from a terminal device via a wired connection or a wireless connection. The training samples in the training sample set may include: sample power material cleaning information and sample power material prediction information. Here, the sample power material prediction information may be a sample label corresponding to the sample power material cleaning information.

[0052] The second step is to determine the initial power material forecast information generation model.

[0053] In some embodiments, the execution subject may determine an initial power material forecast information generation model. The initial power material forecast information generation model may be an untrained neural network model that takes sample power material cleaning information as input and outputs initial power material forecast information. Here, the initial power material forecast information generation model may include but is not limited to at least one of the following: an initial attention model, an initial forecast model.

[0054] The above-mentioned initial attention model may be an attention model that takes sample power material cleaning information as input and initial power material attention information as output. For example, the initial attention model may be a self_attention model. The initial power material attention information may include high-weight cleaning information and low-weight cleaning information. For example, high-weight cleaning information may be first cleaning information with a weight greater than 0.8. Low-weight cleaning information may be second cleaning information with a weight less than 0.2. The first cleaning information may include, but is not limited to, at least one of the following: power material identification, power material quantity. The second cleaning information may be, but is not limited to, at least one of the following: supply end address.

[0055] The above-mentioned initial prediction model may be a first custom model that takes initial power material attention information as input and initial power material prediction information as output. The initial power material prediction information may be a situation of power materials that characterizes the user terminal's desired power materials predicted by the initial prediction model. The first custom model may include three layers:

[0056] The first layer, the input layer, is used to pass the above initial power material attention information to the second layer.

[0057] The second layer, the processing layer, includes: a first sub-model and a second sub-model. The first sub-model may be a model that takes the initial power material attention information as input and the first information as output. The second sub-model may be a model that takes the initial power material attention information as output and the second information as output. Here, the first information may be a situation that characterizes the power material desired by the user terminal predicted by the first sub-model. The second information may be a situation that characterizes the power material desired by the user terminal predicted by the second sub-model. For example, the first sub-model may be an ARIMA (Autoregressive Differential Moving Average) model. The second sub-model may be an LSTM (Long Short Term Memory) model.

[0058] The third layer, the output layer, is used to take the average of the outputs of the first sub-model and the second sub-model as the output of the entire first custom model.

[0059] The third step is to select training samples from the above training sample set.

[0060] 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.

[0061] The fourth step is to input the sample power material cleaning information included in the above training samples into the above initial attention model to obtain the initial power material attention information.

[0062] In some embodiments, the execution entity may input the sample power material cleaning information included in the training sample into the initial attention model to obtain the initial power material attention information.

[0063] The fifth step is to input the above initial power material attention information into the above initial prediction model to obtain initial power material prediction information.

[0064] In some embodiments, the execution entity may input the initial power material attention information into the initial prediction model to obtain initial power material prediction information.

[0065] In a sixth step, based on a preset first loss function, a first difference value between the initial electric power material forecast information and the sample electric power material forecast information included in the training sample is determined.

[0066] In some embodiments, based on a preset first loss function, the execution subject may determine a first difference value between the initial power material prediction information and the sample power material prediction information included in the training sample. The preset first loss function may be, but is not limited to, a mean square error loss function (MSE), a cross entropy loss function (CrossEntropy), a 0-1 loss function, an absolute value loss function, a logarithmic loss function, a square loss function, an exponential loss function, etc.

[0067] In a seventh step, in response to determining that the first difference value is greater than the first preset difference value, the network parameters of the initial electric power material forecast information generation model are adjusted.

[0068] In some embodiments, in response to determining that the first difference value is greater than the first preset difference value, the execution entity may adjust the network parameters of the initial electric power material forecast information generation model. Among them, the difference between the first difference value and the first preset difference value can be calculated. On this basis, the error value is passed forward from the last layer of the model by 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 first preset difference value. For example, the first preset difference value can be 0.1.

[0069] The optional technical content in step 102 is an inventive point of an embodiment of the present disclosure, which solves the second technical problem mentioned in the background technology, "When the quantity of electric power materials is insufficient, the waiting time of the user terminal will be wasted". The factors that lead to the waste of the waiting time of the user terminal are often as follows: taking the historical request for electric power materials as the current request for electric power materials, resulting in a low accuracy of the request for electric power materials, resulting in a low accuracy of the quantity of electric power materials generated by the request for electric power materials. If the above factors are solved, the effect of reducing the waste of recognition time of the monitoring terminal can be achieved. In order to achieve this effect, first, a training sample set is obtained. Among them, the training samples in the above training sample set include: sample electric power material cleaning information and sample electric power material prediction information. Secondly, the initial electric power material prediction information generation model is determined. Among them, the above initial electric power material prediction information generation model includes: an initial attention model and an initial prediction model. Next, a training sample is selected from the above training sample set. Then, the sample electric power material cleaning information included in the above training sample is input into the above initial attention model to obtain the initial electric power material attention information. Thus, the initial electric power material attention information including high-weighted key information can be obtained through the initial attention model. Then, the above-mentioned initial power material attention information is input into the above-mentioned initial prediction model to obtain the initial power material prediction information. Thus, the initial power material prediction information can be obtained through the initial prediction model, so as to subsequently calculate the first difference value. Afterwards, based on the preset first loss function, the first difference value between the above-mentioned initial power material prediction information and the sample power material prediction information included in the above-mentioned training sample is determined. Thus, the first difference value can be calculated according to the first loss function, so as to subsequently adjust the network parameters of the initial power material prediction information generation model. Finally, in response to determining that the above-mentioned first difference value is greater than the first preset difference value, the network parameters of the above-mentioned initial power material prediction information generation model are adjusted. Thus, based on the first difference value, the parameters of the initial power material prediction information generation model can be adjusted to output more accurate power material prediction information. Furthermore, the waiting time of the user terminal can be reduced.

[0070] Optionally, in response to determining that the first difference value is less than or equal to the first preset difference value, the initial electric power material forecast information generation model is determined as a trained electric power material forecast information generation model.

[0071] In some embodiments, the execution entity may determine the initial electric power material forecast information generation model as a trained electric power material forecast information generation model in response to determining that the first difference value is less than or equal to the first preset difference value.

[0072] Step 103: input the electric power material prediction information set into a pre-trained first electric power material abnormal information generation model to obtain a first electric power material abnormal information set.

[0073] In some embodiments, the execution subject may input the electric power material prediction information set into a pre-trained first electric power material abnormal information generation model to obtain a first electric power material abnormal information set. In practice, the execution subject may input each electric power material prediction information in the electric power material prediction information set into a pre-trained first electric power material abnormal information generation model to generate first electric power material abnormal information and obtain a first electric power material abnormal information set. The first electric power material abnormal information generation model may be a neural network model with electric power material prediction information as input and first electric power material abnormal information as output. The first electric power material abnormal information in the first electric power material abnormal information set may include but is not limited to at least one of the following: electric power material identification, supply-side identification, abnormal information. The abnormal information may characterize the quantity of missing electric power materials.

[0074] Optionally, the pre-trained first power material abnormal information generation model may be trained through the following steps:

[0075] The first step is to obtain the training sample set.

[0076] In some embodiments, the execution subject may obtain a training sample set from a terminal device via a wired connection or a wireless connection. The training samples in the training sample set may include: sample power material prediction information and sample first power material abnormality information. Here, the sample first power material abnormality information may be a sample label corresponding to the sample power material prediction information.

[0077] The second step is to determine the initial first power material abnormal information generation model.

[0078] In some embodiments, the above-mentioned execution entity may determine an initial first power material abnormal information generation model. Among them, the initial first power material abnormal information generation model may be a neural network model with sample power material prediction information as input and initial first power material abnormal information as output. Here, the initial first power material abnormal information generation model may include: an initial recognition model, an initial generation model. The initial first power material abnormal information may include but is not limited to at least one of the following: power material identification, supply-side identification, and abnormal number of power materials. The abnormal number of power materials can represent the number of power materials missing.

[0079] Thus, the abnormal quantity of electric power materials can be obtained by considering the current predicted quantity of electric power materials and the historical quantity of electric power materials. The abnormal quantity of electric power materials obtained is more accurate than the predicted quantity of electric power materials.

[0080] The initial identification model may be a model that takes sample power material forecast information as input and initial abnormal information as output. The initial identification model may be a model that determines the initial abnormal information as the product of the power material forecast quantity included in the sample power material forecast information and a preset forecast threshold. For example, the preset forecast threshold may be 120%.

[0081] The above-mentioned initial generation model can be a second self-defined model that takes the initial abnormal information as input and the initial first power material abnormal information as output. The second self-defined model can be divided into three layers:

[0082] The first layer, the input layer, is used to receive initial abnormality information and input the initial abnormality information to the second layer.

[0083] The second layer, the processing layer, includes: a third sub-model and a fourth sub-model. The third sub-model can be a model that takes the initial abnormal information as input and the third information as output. The fourth sub-model can be a multi-layer feedforward neural network model trained according to the error back propagation algorithm that takes the initial abnormal information as input and the fourth information as output. Here, the third information can be information characterizing the number of missing power materials output by the third sub-model. The fourth information can be information characterizing the number of missing power materials output by the fourth sub-model. For example, the third sub-model can be a One-Class SVM (One-Class Support Vector Machine) model. For example, the fourth sub-model can be a BP (backpropagation, multi-layer feedforward neural network) model.

[0084] The third layer, the output layer, is used to receive the outputs of the first sub-model and the second sub-model respectively, and to fuse the outputs of the first sub-model and the second sub-model to obtain the initial first power material abnormality information as the output of the entire predefined model.

[0085] The third step is to select training samples from the above training sample set.

[0086] 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.

[0087] The fourth step is to input the sample power material prediction information included in the above training samples into the above initial recognition model to obtain initial abnormal information.

[0088] In some embodiments, the execution entity may input the sample power material prediction information included in the training sample into the initial recognition model to obtain initial abnormal information.

[0089] The fifth step is to input the above initial abnormal information into the initial generation model to obtain the initial first power material abnormal information.

[0090] In some embodiments, the execution entity may input the initial abnormal information into an initial generation model to obtain initial first electric power material abnormal information.

[0091] In the sixth step, based on a preset second loss function, a second difference value between the initial first electric power material abnormality information and the sample first electric power material abnormality information included in the training sample is determined.

[0092] In some embodiments, based on a preset second loss function, the execution subject may determine a second difference value between the initial first power material abnormality information and the sample first power material abnormality information included in the training sample. The preset second loss function may be, but is not limited to, a mean square error loss function (MSE), a cross entropy loss function (CrossEntropy), a 0-1 loss function, an absolute value loss function, a logarithmic loss function, a square loss function, an exponential loss function, etc.

[0093] In a seventh step, in response to determining that the second difference value is greater than the second preset difference value, the network parameters of the initial first electric power material abnormal information generation model are adjusted.

[0094] In some embodiments, in response to determining that the second difference value is greater than the second preset difference value, the execution entity may adjust the network parameters of the initial first electric power material abnormal information generation model. Among them, the second difference value and the second preset difference value may be differentiated. On this basis, the error value is passed forward from the last layer of the model by back propagation, stochastic gradient descent and other methods to adjust the parameters of each layer. Of course, as needed, the network freezing (dropout) method may also be used to keep the network parameters of some layers unchanged and not adjust them, and no limitation is made to this. Among them, there is no limitation on the setting of the second preset difference value. For example, the second preset difference value may be 0.1.

[0095] The optional technical content in step 103, as an inventive point of an embodiment of the present disclosure, solves the technical problem three mentioned in the background technology, "causing waste of electric power materials". The factors that cause waste of electric power materials are often as follows: when the preset threshold value is too large, some electric power materials will not be used for a long time. If the above factors are solved, the effect of reducing the waste of electric power materials can be achieved. In order to achieve this effect, first, a training sample set is obtained. Among them, the training samples in the above training sample set include: sample electric power material prediction information and sample first electric power material abnormal information. Secondly, the initial first electric power material abnormal information generation model is determined. Among them, the above initial first electric power material abnormal information generation model includes: initial recognition model and initial generation model. Then, a training sample is selected from the above training sample set. Then, the sample electric power material prediction information included in the above training sample is input into the above initial recognition model to obtain the initial abnormal information. Therefore, the initial abnormal information can be obtained through the initial recognition model. After that, the above initial abnormal information is input into the above initial generation model to obtain the initial first electric power material abnormal information. Thus, a more accurate initial first power material abnormality information considering the third model and the fourth model can be obtained by the initial generation model including the third model and the fourth model. After that, based on the preset second loss function, the second difference value between the initial first power material abnormality information and the sample first power material abnormality information included in the training sample is determined. Thus, according to the preset second loss function, the second difference value can be obtained so as to subsequently adjust the network parameters of the initial first power material abnormality information generation model. Finally, in response to determining that the second difference value is greater than the second preset difference value, the network parameters of the initial first power material abnormality information generation model are adjusted. Thus, the network parameters of the initial first power material abnormality information generation model can be continuously adjusted according to the second difference value so as to obtain more accurate first power material abnormality information. Therefore, the preset threshold can be replaced by the first power material abnormality information output by the first power material abnormality information generation model, so that the quantity of power materials can be kept within the ideal range, and the situation where the power materials are not used for a long time can be reduced. Thus, the waste of power materials can be reduced.

[0096] Optionally, in response to determining that the second difference value is less than or equal to the second preset difference value, the initial first electric power material abnormality information generation model is determined as the trained first electric power material abnormality information generation model.

[0097] In some embodiments, the execution entity may determine the initial first electric power material abnormality information generation model as the trained first electric power material abnormality information generation model in response to determining that the second difference value is less than or equal to the second preset difference value.

[0098] Step 104: encrypt the first power material abnormality information set to generate a first power material encrypted abnormality information set, and send the first power material encrypted abnormality information set to an associated monitoring terminal.

[0099] In some embodiments, the execution subject may encrypt the first power material abnormal information set to generate the first power material encrypted abnormal information set, and may send the first power material encrypted abnormal information set to the associated monitoring terminal. In practice, first, the execution subject may encrypt each first power material abnormal information in the first power material abnormal information set based on the encryption algorithm to generate the first power material encrypted abnormal information and obtain the first power material encrypted abnormal information set. Then, the execution subject may send the first power material encrypted abnormal information set to the associated monitoring terminal. Among them, the associated monitoring terminal may be a terminal for monitoring power material abnormal information. Thus, the first power material abnormal information may be encrypted by the encryption algorithm, so as to avoid leakage of the first power material abnormal information during transmission.

[0100] Step 105, in response to receiving the second power material encrypted abnormality information corresponding to any power material sent by the monitoring terminal, the first power material encrypted abnormality information and the second power material encrypted abnormality information corresponding to the second power material encrypted abnormality information are inspected and processed to generate inspection result information.

[0101] In some embodiments, the execution subject may, in response to receiving the second power material encrypted abnormal information corresponding to any power material sent by the monitoring terminal, perform verification processing on the first power material encrypted abnormal information and the second power material encrypted abnormal information corresponding to the second power material encrypted abnormal information to generate verification result information. In practice, first, in response to receiving the second power material encrypted abnormal information corresponding to any power material sent by the monitoring terminal, the execution subject may perform verification processing on the first power material encrypted abnormal information and the second power material encrypted abnormal information corresponding to the second power material encrypted abnormal information by a similarity algorithm to generate verification result information. For example, the similarity algorithm may be, but is not limited to, a Jaccard similarity algorithm and a cosine similarity algorithm. Here, the second power material encrypted abnormal information may represent the historical power material encrypted abnormal information sent by the monitoring terminal and having the same power material identifier as the first power material encrypted abnormal information.

[0102] Step 106, encrypting the inspection result information to generate encrypted inspection result information, and sending the encrypted inspection result information to the monitoring terminal to generate inspection result confirmation information.

[0103] In some embodiments, the execution subject may encrypt the inspection result information to generate encrypted inspection result information, and may send the encrypted inspection result information to the monitoring terminal to generate inspection result confirmation information. In practice, first, the execution subject may encrypt each inspection result information in the inspection result information group based on the encryption algorithm to generate encrypted inspection result information and obtain an encrypted inspection result information group. Then, the execution subject may send the encrypted inspection result information group to the monitoring terminal to generate inspection result confirmation information. Thus, the inspection result information may be encrypted by the encryption algorithm, and leakage of the inspection result information during transmission may be avoided.

[0104] Optionally, the monitoring terminal may generate the inspection result confirmation information through the following steps:

[0105] The first step is to, in response to receiving the encrypted verification result information, decrypt the encrypted verification result information to generate decrypted verification result information. In practice, in response to receiving the encrypted verification result information, the monitoring terminal can decrypt the encrypted verification result information using the encryption algorithm to generate decrypted verification result information.

[0106] In the second step, in response to determining that the decryption test result information satisfies a preset normal condition, the preset confirmation information is determined as the test result confirmation information. The preset normal condition may indicate that the monitoring terminal confirms that the decryption test result information is correct. The preset confirmation information may indicate that the monitoring terminal has confirmed that the encryption test result information is correct.

[0107] The third step is to generate target encryption verification result information corresponding to the decryption verification result information in response to determining that the decryption verification result information meets a preset abnormal condition, wherein the preset abnormal condition may be that the monitoring terminal confirms that the decryption verification result information is incorrect.

[0108] In a fourth step, in response to determining that the target encryption verification result information is the same as the encryption verification result information, the preset confirmation information is determined as the verification result confirmation information.

[0109] Step 5: In response to determining that the target encryption verification result information is different from the encryption verification result information, an alarm is performed on the associated supply end. The alarm may be displayed as a warning text or a speaker is controlled to emit a prompt sound. The associated supply end may be the supply end of the power material corresponding to the encryption verification result information.

[0110] In practice, the monitoring terminal may generate target encryption verification result information corresponding to the decryption verification result information through the following steps:

[0111] The first step is to obtain the target power material basic information of the power material corresponding to the above decryption test result information. In practice, the above monitoring terminal can obtain the target power material basic information of the power material corresponding to the above decryption test result information from the terminal device through a wired connection or a wireless connection. The above target power material basic information can correspond to the power material basic information in the power material basic information set.

[0112] The second step is to generate target power material forecast information based on the target power material basic information. The specific implementation method of generating the target power material forecast information and the technical effect brought about can refer to step 102 in the above embodiment, which will not be repeated here.

[0113] The third step is to input the target power material forecast information into the first power material abnormal information generation model to obtain the first target power material abnormal information. The specific implementation method and technical effect of inputting the target power material forecast information into the first power material abnormal information generation model can refer to step 103 in the above embodiment, which will not be repeated here.

[0114] The fourth step is to perform inspection and processing on the second target power material abnormal information corresponding to the first target power material abnormal information and the first target power material abnormal information to generate target inspection result information. Among them, the specific implementation method and technical effect of the inspection and processing of the second target power material abnormal information corresponding to the first target power material abnormal information and the first target power material abnormal information can refer to step 105 in the above embodiment, and will not be repeated here. Here, the second target power material abnormal information can represent the historical target power material abnormal information with the same power material identifier as the first target power material abnormal information.

[0115] The fifth step is to encrypt the target inspection result information to generate encrypted target inspection result information. The specific implementation method of encrypting the target inspection result information and the technical effect brought about by it can refer to step 106 in the above embodiment, which will not be repeated here.

[0116] Step 107: in response to receiving the verification result confirmation information sent by the monitoring terminal, determine the encrypted verification result information as the target encrypted verification result information.

[0117] In some embodiments, the execution entity may determine the encrypted verification result information as target encrypted verification result information in response to receiving the verification result confirmation information sent by the monitoring terminal.

[0118] Step 108, based on the target encryption inspection result information, an alarm is processed on the supply end corresponding to the electric power material corresponding to the target encryption inspection result information.

[0119] In some embodiments, the execution subject may, based on the target encryption test result information, perform an alarm process on the supply end corresponding to the electric power material corresponding to the target encryption test result information. In practice, the execution subject may perform an alarm process on the supply end corresponding to the electric power material corresponding to the target encryption test result information. The alarm process may be to display a warning text or control a speaker to emit a prompt sound.

[0120] Optionally, in response to receiving the request for applying for electric power materials sent by the user terminal, dispatching the transportation equipment to transport the associated electric power materials to the user terminal:

[0121] In some embodiments, the execution subject may dispatch a transport device to transport the associated electric power materials to the user terminal in response to receiving a request for electric power materials sent by the user terminal. The user terminal may be a terminal that uses electric power materials. The request for electric power materials may indicate that the user terminal needs electric power materials. The transport device may be a vehicle for transporting electric power materials. The associated electric power materials may be electric power materials corresponding to the request for electric power materials.

[0122] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the electric power material alarm method based on the visualized digital cockpit of some embodiments of the present disclosure, the waiting time of the user terminal can be reduced. Specifically, the reason for wasting the waiting time of the user terminal is that the alarm is only given to the supply side when the electric power material is insufficient, and the supply side needs to consume time to produce electric power materials and time to dispatch transportation equipment to transport electric power materials to the user terminal. Based on this, the electric power material alarm method based on the visualized digital cockpit of some embodiments of the present disclosure first obtains the basic information of electric power materials for each electric power material to obtain a basic information set of electric power materials. Secondly, based on the above basic information set of electric power materials, a prediction information set of electric power materials is generated. Thus, a prediction information set of electric power materials representing the application request of the user terminal for electric power materials can be predicted. Then, the above prediction information set of electric power materials is input into the pre-trained first abnormal information generation model of electric power materials to obtain the first abnormal information set of electric power materials. Thus, the first abnormal information of electric power materials representing the lack of electric power materials can be identified by the first abnormal information generation model of electric power materials. Next, the first power material abnormal information set is encrypted to generate the first power material encrypted abnormal information set, and the first power material encrypted abnormal information set is sent to the associated monitoring terminal. Thus, the first power material abnormal information set can be encrypted to avoid leakage of the first power material abnormal information set during transmission. Then, in response to receiving the second power material encrypted abnormal information corresponding to any power material sent by the monitoring terminal, the first power material encrypted abnormal information corresponding to the second power material encrypted abnormal information and the second power material encrypted abnormal information are inspected to generate inspection result information. Thus, the first power material encrypted abnormal information and the historical second power material encrypted abnormal information can be compared. Then, the inspection result information is encrypted to generate encrypted inspection result information, and the encrypted inspection result information is sent to the monitoring terminal to generate inspection result confirmation information. Thus, whether the first power material encrypted abnormal information is correct can be further determined by the monitoring terminal. Thereafter, in response to receiving the inspection result confirmation information sent by the monitoring terminal, the encrypted inspection result information is determined as the target encrypted inspection result information. Finally, based on the target encryption test result information, the supply end corresponding to the power material corresponding to the target encryption test result information is alarmed. Thus, the supply end corresponding to a small number of power materials can be alarmed. Therefore, the supply end can be alarmed by predicting the demand for power materials at the user terminal to produce power materials in advance. Thus, when the user terminal needs power materials, the transportation equipment can be dispatched in time to transport power materials to the user terminal. Furthermore, the waiting time of the user terminal can be reduced.

[0123] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a power material alarm device based on a visualized digital intelligent cockpit. These embodiments of the power material alarm device based on a visualized digital intelligent cockpit are similar to Figure 1 Corresponding to the method embodiments shown, the power material alarm device based on the visualization digital cockpit can be specifically applied to various electronic devices.

[0124] like Figure 2 As shown, some embodiments of the electric material alarm device 200 based on the visualized digital cockpit include: an acquisition unit 201, a generation unit 202, an input unit 203, a first encryption unit 204, a verification unit 205, a second encryption unit 206, a determination unit 207 and an alarm unit 208. Among them, the acquisition unit 201 is configured to acquire the basic information of each electric material and obtain a basic information set of electric materials; the generation unit 202 is configured to generate a prediction information set of electric materials based on the basic information set of electric materials; the input unit 203 is configured to input the prediction information set of electric materials into a pre-trained first electric material abnormal information generation model to obtain a first electric material abnormal information set; the first encryption unit 204 is configured to encrypt the first electric material abnormal information set to generate a first electric material encrypted abnormal information set, and send the first electric material encrypted abnormal information set to the associated monitoring terminal; the verification unit 205 is configured to respond to the second electric material corresponding to any electric material sent by the monitoring terminal. The material encryption abnormal information is used to inspect the first power material encryption abnormal information and the second power material encryption abnormal information corresponding to the second power material encryption abnormal information to generate inspection result information; the second encryption unit 206 is configured to encrypt the inspection result information to generate encrypted inspection result information, and send the encrypted inspection result information to the monitoring terminal to generate inspection result confirmation information; the determination unit 207 is configured to determine the encrypted inspection result information as the target encryption inspection result information in response to receiving the inspection result confirmation information sent by the monitoring terminal; the alarm unit 208 is configured to perform alarm processing on the supply end corresponding to the power material corresponding to the target encryption inspection result information based on the target encryption inspection result information.

[0125] It can be understood that the units recorded in the power material alarm device 200 based on the visualized digital cockpit are similar to the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the electric power material alarm device 200 based on the visualized digital cockpit and the units contained therein, and will not be repeated here.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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 contains 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.

[0130] 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.

[0131] 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.

[0132] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently without being installed in 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 basic information of each electric material to obtain a basic information set of electric materials; generates a prediction information set of electric materials based on the basic information set of electric materials; inputs the prediction information set of electric materials into a pre-trained first electric material abnormal information generation model to obtain a first electric material abnormal information set; encrypts the first electric material abnormal information set to generate a first electric material encrypted abnormal information set, and sends the first electric material encrypted abnormal information set to an associated monitoring terminal; in response to receiving the corresponding information sent by the above-mentioned monitoring terminal, the second electric material encrypted abnormal information of any electric material, inspecting and processing the first electric material encrypted abnormal information and the second electric material encrypted abnormal information corresponding to the second electric material encrypted abnormal information to generate inspection result information; encrypting the inspection result information to generate encrypted inspection result information, and sending the encrypted inspection result information to the monitoring terminal to generate inspection result confirmation information; in response to receiving the inspection result confirmation information sent by the monitoring terminal, determining the encrypted inspection result information as the target encrypted inspection result information; based on the target encrypted inspection result information, performing alarm processing on the supply end corresponding to the electric material corresponding to the target encrypted inspection result information.

[0133] 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).

[0134] 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.

[0135] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The units described may also be provided in a processor, for example, may be described as: a processor including an acquisition unit, a generation unit, an input unit, a first encryption unit, a verification unit, a second encryption unit, a determination unit, and an alarm unit. The names of these units do not, in some cases, constitute limitations on the units themselves, for example, the acquisition unit may also be described as "obtaining basic information of each electric material, and obtaining a basic information set of electric materials".

[0136] 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.

[0137] 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. A power material alarm method based on a visualized digital cockpit, comprising: Obtaining basic information of each electric material to obtain a basic information set of electric materials; Based on the basic information set of electric power materials, generating an electric power material prediction information set; Inputting the electric power material prediction information set into a pre-trained first electric power material abnormal information generation model to obtain a first electric power material abnormal information set; encrypting the first power material abnormality information set to generate a first power material encrypted abnormality information set, and sending the first power material encrypted abnormality information set to an associated monitoring terminal; In response to receiving the second electric material encrypted abnormality information corresponding to any electric material sent by the monitoring terminal, verifying the first electric material encrypted abnormality information and the second electric material encrypted abnormality information corresponding to the second electric material encrypted abnormality information to generate verification result information; Encrypting the inspection result information to generate encrypted inspection result information, and sending the encrypted inspection result information to the monitoring terminal to generate inspection result confirmation information; In response to receiving the verification result confirmation information sent by the monitoring terminal, determining the encrypted verification result information as target encrypted verification result information; Based on the target encryption inspection result information, an alarm is processed on the supply end corresponding to the electric power material corresponding to the target encryption inspection result information; The pre-trained first power material abnormal information generation model is obtained by training through the following steps: Acquire a training sample set, wherein the training samples in the training sample set include: sample power material prediction information and sample first power material abnormality information; Determine an initial first electric power material abnormal information generation model, wherein the initial first electric power material abnormal information generation model includes: an initial recognition model and an initial generation model; The initial recognition model is a model that takes sample power material forecast information as input and initial abnormal information as output, wherein the initial recognition model determines the product of the power material forecast quantity included in the sample power material forecast information and a preset forecast threshold as the initial abnormal information; The initial generation model is a second custom model that takes the initial abnormal information as input and the initial first power material abnormal information as output, and the second custom model is divided into three layers: the first layer, the input layer, is used to receive the initial abnormal information and input the initial abnormal information to the second layer; the second layer, the processing layer, includes: a third sub-model and a fourth sub-model, the third sub-model is a model that takes the initial abnormal information as input and the third information as output, and the fourth sub-model is a multi-layer feedforward neural network model trained according to the error back propagation algorithm that takes the initial abnormal information as input and the fourth information as output; the third layer, the output layer, is used to receive the outputs of the third sub-model and the fourth sub-model respectively, and the initial first power material abnormal information obtained by fusing the outputs of the third sub-model and the fourth sub-model as the output of the entire predefined model; Selecting training samples from the training sample set; Inputting the sample power material prediction information included in the training sample into the initial recognition model to obtain initial abnormal information; Inputting the initial abnormal information into the initial generation model to obtain initial first power material abnormal information; Based on a preset second loss function, determining a second difference value between the initial first power material abnormality information and the sample first power material abnormality information included in the training sample; In response to determining that the second difference value is greater than a second preset difference value, adjusting a network parameter of the initial first power material abnormal information generation model; Wherein, generating the electric power material prediction information set based on the electric power material basic information set includes: Identify and process each electric material basic information in the electric material basic information set to generate electric material identification information, thereby obtaining an electric material identification information set; Performing data cleaning processing on the electric power material identification information set to generate an electric power material cleaning information set; Encrypting each piece of electric material cleaning information in the electric material cleaning information set to generate encrypted electric material cleaning information and obtain an encrypted electric material cleaning information set; In response to receiving a basic information viewing request sent by an associated supply end, sending the encrypted cleaning information of each power material corresponding to the supply end to the supply end; For each piece of electric material cleaning information in the electric material cleaning information set, inputting the electric material cleaning information into a pre-trained electric material prediction information generation model to obtain electric material prediction information; Determine the generated individual electric power material forecast information as an electric power material forecast information set; The pre-trained power material forecast information generation model is trained through the following steps: Acquire a training sample set, wherein the training samples in the training sample set include: sample power material cleaning information and sample power material prediction information; Determine an initial power material forecast information generation model, the initial power material forecast information generation model including at least one of the following: an initial attention model, an initial forecast model; The initial attention model is an attention model that takes sample power material cleaning information as input and takes initial power material attention information as output; The initial prediction model is a first custom model that takes the initial power material attention information as input and takes the initial power material prediction information as output. The first custom model includes three layers: the first layer, the input layer, is used to pass the initial power material attention information to the second layer; the second layer, the processing layer, includes: a first sub-model and a second sub-model, the first sub-model is a model that takes the initial power material attention information as input and takes the first information as output, and the second sub-model is a model that takes the initial power material attention information as input and takes the second information as output; the third layer, the output layer, is used to take the average value of the outputs of the first sub-model and the second sub-model as the output of the entire first custom model; Selecting training samples from the training sample set; Inputting the sample power material cleaning information included in the training sample into the initial attention model to obtain initial power material attention information; Inputting the initial power material attention information into the initial prediction model to obtain initial power material prediction information; Based on a preset first loss function, determining a first difference value between the initial power material prediction information and the sample power material prediction information included in the training sample; In response to determining that the first difference value is greater than a first preset difference value, a network parameter of the initial electric power material forecast information generation model is adjusted.

2. The method according to claim 1, wherein: The method further comprises: In response to receiving the request for applying for electric power materials sent by the user terminal, the transportation equipment is dispatched to transport the associated electric power materials to the user terminal.

3. The method according to claim 2, wherein: The identifying and processing each electric material basic information in the electric material basic information set to generate electric material identification information includes: Performing capacity analysis on the basic information of the electric power materials to generate a first analysis result; Performing production analysis on the basic information of the electric power materials to generate a second analysis result; Performing quality analysis on the basic information of the electric power materials to generate a third analysis result; The first analysis result, the second analysis result, and the third analysis result are determined as electric power material identification information.

4. The method according to claim 1, wherein: The test result confirmation information is generated by the following steps: In response to receiving the encrypted verification result information, decrypting the encrypted verification result information to generate decrypted verification result information; In response to determining that the decryption verification result information satisfies a preset normal condition, determining preset confirmation information as verification result confirmation information; In response to determining that the decryption verification result information satisfies a preset abnormal condition, generating target encryption verification result information corresponding to the decryption verification result information; In response to determining that the target encryption verification result information and the encryption verification result information are the same, determining the preset confirmation information as the verification result confirmation information; In response to determining that the target encryption verification result information and the encryption verification result information are different, an alarm process is performed on the associated supply end.

5. The method according to claim 4, wherein: The generating target encryption verification result information corresponding to the decryption verification result information includes: Obtaining target electric power material basic information of the electric power material corresponding to the decryption inspection result information; Based on the basic information of the target electric power material, generating target electric power material prediction information; Inputting the target electric power material prediction information into the first electric power material abnormal information generation model to obtain the first target electric power material abnormal information; Performing inspection processing on the second target electric material abnormality information corresponding to the first target electric material abnormality information and the first target electric material abnormality information to generate target inspection result information; The target verification result information is encrypted to generate target encrypted verification result information.

6. A power material warning device based on a visualized digital cockpit, comprising: An acquisition unit is configured to acquire basic information of each electric material to obtain a basic information set of electric materials; A generating unit configured to generate a power material prediction information set based on the power material basic information set; An input unit is configured to input the electric power material prediction information set into a pre-trained first electric power material abnormal information generation model to obtain a first electric power material abnormal information set; a first encryption unit configured to encrypt the first power material abnormality information set to generate a first power material encrypted abnormality information set, and send the first power material encrypted abnormality information set to an associated monitoring terminal; a verification unit configured to, in response to receiving the second electric material encrypted abnormality information corresponding to any electric material sent by the monitoring terminal, perform verification processing on the first electric material encrypted abnormality information and the second electric material encrypted abnormality information corresponding to the second electric material encrypted abnormality information to generate verification result information; a second encryption unit configured to encrypt the inspection result information to generate encrypted inspection result information, and send the encrypted inspection result information to the monitoring terminal to generate inspection result confirmation information; a determination unit, configured to determine the encrypted verification result information as target encrypted verification result information in response to receiving the verification result confirmation information sent by the monitoring terminal; An alarm unit is configured to perform an alarm process on a supply end corresponding to the electric power material corresponding to the target encryption inspection result information based on the target encryption inspection result information; The pre-trained first power material abnormal information generation model is obtained by training through the following steps: Acquire a training sample set, wherein the training samples in the training sample set include: sample power material prediction information and sample first power material abnormality information; Determine an initial first electric power material abnormal information generation model, wherein the initial first electric power material abnormal information generation model includes: an initial recognition model and an initial generation model; The initial recognition model is a model that takes sample power material forecast information as input and initial abnormal information as output, wherein the initial recognition model determines the product of the power material forecast quantity included in the sample power material forecast information and a preset forecast threshold as the initial abnormal information; The initial generation model is a second custom model that takes the initial abnormal information as input and the initial first power material abnormal information as output, and the second custom model is divided into three layers: the first layer, the input layer, is used to receive the initial abnormal information and input the initial abnormal information to the second layer; the second layer, the processing layer, includes: a third sub-model and a fourth sub-model, the third sub-model is a model that takes the initial abnormal information as input and the third information as output, and the fourth sub-model is a multi-layer feedforward neural network model trained according to the error back propagation algorithm that takes the initial abnormal information as input and the fourth information as output; the third layer, the output layer, is used to receive the outputs of the third sub-model and the fourth sub-model respectively, and the initial first power material abnormal information obtained by fusing the outputs of the third sub-model and the fourth sub-model as the output of the entire predefined model; Selecting training samples from the training sample set; Inputting the sample power material prediction information included in the training sample into the initial recognition model to obtain initial abnormal information; Inputting the initial abnormal information into the initial generation model to obtain initial first power material abnormal information; Based on a preset second loss function, determining a second difference value between the initial first power material abnormality information and the sample first power material abnormality information included in the training sample; In response to determining that the second difference value is greater than a second preset difference value, adjusting a network parameter of the initial first power material abnormal information generation model; Wherein, generating the electric power material prediction information set based on the electric power material basic information set includes: Identify and process each electric material basic information in the electric material basic information set to generate electric material identification information, thereby obtaining an electric material identification information set; Performing data cleaning processing on the electric power material identification information set to generate an electric power material cleaning information set; Encrypting each piece of electric material cleaning information in the electric material cleaning information set to generate encrypted electric material cleaning information and obtain an encrypted electric material cleaning information set; In response to receiving a basic information viewing request sent by an associated supply end, sending the encrypted cleaning information of each power material corresponding to the supply end to the supply end; For each piece of electric material cleaning information in the electric material cleaning information set, inputting the electric material cleaning information into a pre-trained electric material prediction information generation model to obtain electric material prediction information; Determine the generated individual electric power material forecast information as an electric power material forecast information set; The pre-trained power material forecast information generation model is trained through the following steps: Acquire a training sample set, wherein the training samples in the training sample set include: sample power material cleaning information and sample power material prediction information; Determine an initial power material forecast information generation model, the initial power material forecast information generation model including at least one of the following: an initial attention model, an initial forecast model; The initial attention model is an attention model that takes sample power material cleaning information as input and takes initial power material attention information as output; The initial prediction model is a first custom model that takes the initial power material attention information as input and takes the initial power material prediction information as output. The first custom model includes three layers: the first layer, the input layer, is used to pass the initial power material attention information to the second layer; the second layer, the processing layer, includes: a first sub-model and a second sub-model, the first sub-model is a model that takes the initial power material attention information as input and takes the first information as output, and the second sub-model is a model that takes the initial power material attention information as input and takes the second information as output; the third layer, the output layer, is used to take the average value of the outputs of the first sub-model and the second sub-model as the output of the entire first custom model; Selecting training samples from the training sample set; Inputting the sample power material cleaning information included in the training sample into the initial attention model to obtain initial power material attention information; Inputting the initial power material attention information into the initial prediction model to obtain initial power material prediction information; Based on a preset first loss function, determining a first difference value between the initial power material prediction information and the sample power material prediction information included in the training sample; In response to determining that the first difference value is greater than a first preset difference value, a network parameter of the initial electric power material forecast information generation model is adjusted.

7. 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 5.

8. 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 5 is implemented.

Images